diff options
29 files changed, 40 insertions, 21500 deletions
diff --git a/src/OS/Makefile-Base b/src/OS/Makefile-Base index 6740e733c..98f3ec3e1 100644 --- a/src/OS/Makefile-Base +++ b/src/OS/Makefile-Base @@ -1,4 +1,4 @@ -# $Cambridge: exim/src/OS/Makefile-Base,v 1.12 2007/11/12 13:02:19 nm4 Exp $ +# $Cambridge: exim/src/OS/Makefile-Base,v 1.13 2008/01/16 13:44:45 nm4 Exp $ # This file is the basis of the main makefile for Exim and friends. The # makefile at the top level arranges to build the main makefile by calling @@ -96,14 +96,14 @@ config.h: Makefile buildconfig ../src/config.h.defaults $(EDITME) # therefore always be run, even if the files exist. This shouldn't in fact be a # problem, but it does no harm. Other make programs will just ignore this. -.PHONY: all allexim buildauths buildlookups buildpcre buildrouters \ +.PHONY: all allexim buildauths buildlookups buildrouters \ buildtransports checklocalmake clean # This is the real default target for all the various exim binaries and # scripts, once the configuring stuff is done. -allexim: config.h buildpcre $(EXIM_MONITOR) exicyclog exinext exiwhat \ +allexim: config.h $(EXIM_MONITOR) exicyclog exinext exiwhat \ exigrep eximstats exipick exiqgrep exiqsumm \ transport-filter.pl convert4r3 convert4r4 \ exim_checkaccess \ @@ -314,7 +314,7 @@ OBJ_EXIM = acl.o child.o crypt16.o daemon.o dbfn.o debug.o deliver.o \ local_scan.o $(EXIM_PERL) $(OBJ_WITH_CONTENT_SCAN) \ $(OBJ_WITH_OLD_DEMIME) $(OBJ_EXPERIMENTAL) -exim: pcre/libpcre.a lookups/lookups.a auths/auths.a \ +exim: lookups/lookups.a auths/auths.a \ routers/routers.a transports/transports.a \ $(OBJ_EXIM) version.c @echo " " @@ -325,12 +325,11 @@ exim: pcre/libpcre.a lookups/lookups.a auths/auths.a \ rm -f exim @echo "$(LNCC) -o exim" $(FE)$(PURIFY) $(LNCC) -o exim $(LFLAGS) $(OBJ_EXIM) version.o \ - pcre/libpcre.a \ routers/routers.a transports/transports.a lookups/lookups.a \ auths/auths.a \ $(LIBRESOLV) $(LIBS) $(LIBS_EXIM) $(IPV6_LIBS) $(EXTRALIBS) \ $(EXTRALIBS_EXIM) $(DBMLIB) $(LOOKUP_LIBS) $(AUTH_LIBS) \ - $(PERL_LIBS) $(TLS_LIBS) $(LDFLAGS) + $(PERL_LIBS) $(TLS_LIBS) $(PCRE_LIBS) $(LDFLAGS) @if [ x"$(STRIP_COMMAND)" != x"" ]; then \ echo $(STRIP_COMMAND) exim; \ $(STRIP_COMMAND) exim; \ @@ -429,14 +428,14 @@ MONBIN = em_StripChart.o $(EXIMON_TEXTPOP) em_globals.o em_init.o \ OBJ_MONBIN = util-spool_in.o util-store.o util-string.o tod.o tree.o $(MONBIN) -eximon.bin: $(EXIMON_EDITME) eximon $(OBJ_MONBIN) pcre/libpcre.a \ +eximon.bin: $(EXIMON_EDITME) eximon $(OBJ_MONBIN) \ ../exim_monitor/em_version.c @echo "$(CC) exim_monitor/em_version.c" $(FE)$(CC) -o em_version.o -c \ $(CFLAGS) $(XINCLUDE) -I. ../exim_monitor/em_version.c @echo "$(LNCC) -o eximon.bin" $(FE)$(PURIFY) $(LNCC) -o eximon.bin em_version.o $(LFLAGS) $(XLFLAGS) \ - $(OBJ_MONBIN) -lXaw -lXmu -lXt -lXext -lX11 pcre/libpcre.a \ + $(OBJ_MONBIN) -lXaw -lXmu -lXt -lXext -lX11 $(PCRE_LIBS) \ $(LIBS) $(LIBS_EXIMON) $(EXTRALIBS) $(EXTRALIBS_EXIMON) -lc @if [ x"$(STRIP_COMMAND)" != x"" ]; then \ echo $(STRIP_COMMAND) eximon.bin; \ @@ -647,21 +646,6 @@ $(MONBIN): $(HDRS) # drtables.o when they rebuild.) To get round this, we forcibly remove the # binary when it needs to be rebuilt. -# The PCRE regex library. Move the pcretest program to the util directory. Some -# "clever" versions of make notice that there are two successive shell -# commands, and they run them in the same shell. This means that we have to -# take care to encapsulate change of directory in parentheses, so that it -# reverts when it should. - -buildpcre: - @(cd pcre; $(MAKE) SHELL=$(SHELL) AR="$(AR)" $(MFLAGS) CC="$(CC)" \ - FE="$(FE)" CFLAGS="$(CFLAGS) $(PCRE_CFLAGS) -DHAVE_CONFIG_H" \ - RANLIB="$(RANLIB)" RM_COMMAND="$(RM_COMMAND)" HDRS="$(PHDRS)" \ - INCLUDE="$(INCLUDE) $(IPV6_INCLUDE) $(TLS_INCLUDE)") - @if $(SHELL) $(SCRIPTS)/newer pcre/libpcre.a exim; then \ - rm -f exim eximon.bin; fi - @echo " " - # The lookups library. buildlookups: diff --git a/src/OS/Makefile-Default b/src/OS/Makefile-Default index 9f9ff2276..49052b3b3 100644 --- a/src/OS/Makefile-Default +++ b/src/OS/Makefile-Default @@ -1,4 +1,4 @@ -# $Cambridge: exim/src/OS/Makefile-Default,v 1.2 2006/02/10 14:33:26 ph10 Exp $ +# $Cambridge: exim/src/OS/Makefile-Default,v 1.3 2008/01/16 13:44:45 nm4 Exp $ ################################################## # The Exim mail transport agent # @@ -87,6 +87,11 @@ CC=gcc # LFLAGS= +# PCRE_LIBS contains the library to be linked for PCRE + +#PCRE_LIBS=-lpcre + + # LIBS and EXTRALIBS contain library settings that are used on linking # commands to build binaries. The OS-dependent Makefile may contain a default # setting for LIBS, leaving EXTRALIBS available for adding further libraries @@ -112,14 +117,6 @@ CC=gcc # EXTRALIBS_EXIMON= -# PCRE_CFLAGS contains flags to be passed to the CFLAGS parameter of the -# makefile for building the PCRE regular expression library, in addition -# to CFLAGS. Typical use is to set -DUSE_BCOPY on legacy systems that lack -# the memmove() function but do have bcopy(). - -# PCRE_CFLAGS= - - # The error name for quota exceeded varies among operating systems, and # even, unfortunately, in different versions of the same operating system. # EDQUOT was not in Sys V, but is in SPEC 1170, apparently. It was used diff --git a/src/exim_monitor/em_hdr.h b/src/exim_monitor/em_hdr.h index a6a642f62..c0621d9de 100644 --- a/src/exim_monitor/em_hdr.h +++ b/src/exim_monitor/em_hdr.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/exim_monitor/em_hdr.h,v 1.6 2007/01/08 10:50:17 ph10 Exp $ */ +/* $Cambridge: exim/src/exim_monitor/em_hdr.h,v 1.7 2008/01/16 13:44:45 nm4 Exp $ */ /************************************************* * Exim Monitor * @@ -87,7 +87,7 @@ anything. */ /* Regular expression include */ -#include "pcre/pcre.h" +#include <pcre.h> /* Includes from the main source of Exim. We need to have MAXPACKET defined for the benefit of structs.h. One of these days I should tidy up this interface so diff --git a/src/src/EDITME b/src/src/EDITME index 77b4f3686..7d3d069a6 100644 --- a/src/src/EDITME +++ b/src/src/EDITME @@ -1,4 +1,4 @@ -# $Cambridge: exim/src/src/EDITME,v 1.20 2007/01/22 16:29:54 ph10 Exp $ +# $Cambridge: exim/src/src/EDITME,v 1.21 2008/01/16 13:44:45 nm4 Exp $ ################################################## # The Exim mail transport agent # @@ -301,6 +301,19 @@ LOOKUP_LSEARCH=yes #------------------------------------------------------------------------------ +# The PCRE library is required for exim. There is no longer an embedded +# version of the PCRE library included with the source code, instead you +# must use a system library or build your own copy of PCRE. +# In either case you must specify the library link info here. If the +# PCRE header files are not in the standard search path you must also +# modify the INCLUDE path (above) +# The default setting of PCRE_LIBS should work on the vast majority of +# systems + +PCRE_LIBS=-lpcre + + +#------------------------------------------------------------------------------ # Additional libraries and include directories may be required for some # lookup styles (e.g. LDAP, MYSQL or PGSQL). LOOKUP_LIBS is included only on # the command for linking Exim itself, not on any auxiliary programs. You diff --git a/src/src/exim.h b/src/src/exim.h index 9118e4d89..a2f422c11 100644 --- a/src/src/exim.h +++ b/src/src/exim.h @@ -1,4 +1,4 @@ -/* $Cambridge: exim/src/src/exim.h,v 1.23 2007/09/28 12:21:57 tom Exp $ */ +/* $Cambridge: exim/src/src/exim.h,v 1.24 2008/01/16 13:44:45 nm4 Exp $ */ /************************************************* * Exim - an Internet mail transport agent * @@ -422,7 +422,7 @@ extern int ferror(FILE *); /* The header from the PCRE regex package */ -#include "pcre/pcre.h" +#include <pcre.h> /* Exim includes are in several files. Note that local_scan.h #includes config.h, mytypes.h, and store.h, so we don't need to mention them explicitly. diff --git a/src/src/pcre/ChangeLog b/src/src/pcre/ChangeLog deleted file mode 100644 index cff73670a..000000000 --- a/src/src/pcre/ChangeLog +++ /dev/null @@ -1,3015 +0,0 @@ -ChangeLog for PCRE ------------------- - -Version 7.4 21-Sep-07 ---------------------- - -1. Change 7.3/28 was implemented for classes by looking at the bitmap. This - means that a class such as [\s] counted as "explicit reference to CR or - LF". That isn't really right - the whole point of the change was to try to - help when there was an actual mention of one of the two characters. So now - the change happens only if \r or \n (or a literal CR or LF) character is - encountered. - -2. The 32-bit options word was also used for 6 internal flags, but the numbers - of both had grown to the point where there were only 3 bits left. - Fortunately, there was spare space in the data structure, and so I have - moved the internal flags into a new 16-bit field to free up more option - bits. - -3. The appearance of (?J) at the start of a pattern set the DUPNAMES option, - but did not set the internal JCHANGED flag - either of these is enough to - control the way the "get" function works - but the PCRE_INFO_JCHANGED - facility is supposed to tell if (?J) was ever used, so now (?J) at the - start sets both bits. - -4. Added options (at build time, compile time, exec time) to change \R from - matching any Unicode line ending sequence to just matching CR, LF, or CRLF. - -5. doc/pcresyntax.html was missing from the distribution. - -6. Put back the definition of PCRE_ERROR_NULLWSLIMIT, for backward - compatibility, even though it is no longer used. - -7. Added macro for snprintf to pcrecpp_unittest.cc and also for strtoll and - strtoull to pcrecpp.cc to select the available functions in WIN32 when the - windows.h file is present (where different names are used). [This was - reversed later after testing - see 16 below.] - -8. Changed all #include <config.h> to #include "config.h". There were also - some further <pcre.h> cases that I changed to "pcre.h". - -9. When pcregrep was used with the --colour option, it missed the line ending - sequence off the lines that it output. - -10. It was pointed out to me that arrays of string pointers cause lots of - relocations when a shared library is dynamically loaded. A technique of - using a single long string with a table of offsets can drastically reduce - these. I have refactored PCRE in four places to do this. The result is - dramatic: - - Originally: 290 - After changing UCP table: 187 - After changing error message table: 43 - After changing table of "verbs" 36 - After changing table of Posix names 22 - - Thanks to the folks working on Gregex for glib for this insight. - -11. --disable-stack-for-recursion caused compiling to fail unless -enable- - unicode-properties was also set. - -12. Updated the tests so that they work when \R is defaulted to ANYCRLF. - -13. Added checks for ANY and ANYCRLF to pcrecpp.cc where it previously - checked only for CRLF. - -14. Added casts to pcretest.c to avoid compiler warnings. - -15. Added Craig's patch to various pcrecpp modules to avoid compiler warnings. - -16. Added Craig's patch to remove the WINDOWS_H tests, that were not working, - and instead check for _strtoi64 explicitly, and avoid the use of snprintf() - entirely. This removes changes made in 7 above. - -17. The CMake files have been updated, and there is now more information about - building with CMake in the NON-UNIX-USE document. - - -Version 7.3 28-Aug-07 ---------------------- - - 1. In the rejigging of the build system that eventually resulted in 7.1, the - line "#include <pcre.h>" was included in pcre_internal.h. The use of angle - brackets there is not right, since it causes compilers to look for an - installed pcre.h, not the version that is in the source that is being - compiled (which of course may be different). I have changed it back to: - - #include "pcre.h" - - I have a vague recollection that the change was concerned with compiling in - different directories, but in the new build system, that is taken care of - by the VPATH setting the Makefile. - - 2. The pattern .*$ when run in not-DOTALL UTF-8 mode with newline=any failed - when the subject happened to end in the byte 0x85 (e.g. if the last - character was \x{1ec5}). *Character* 0x85 is one of the "any" newline - characters but of course it shouldn't be taken as a newline when it is part - of another character. The bug was that, for an unlimited repeat of . in - not-DOTALL UTF-8 mode, PCRE was advancing by bytes rather than by - characters when looking for a newline. - - 3. A small performance improvement in the DOTALL UTF-8 mode .* case. - - 4. Debugging: adjusted the names of opcodes for different kinds of parentheses - in debug output. - - 5. Arrange to use "%I64d" instead of "%lld" and "%I64u" instead of "%llu" for - long printing in the pcrecpp unittest when running under MinGW. - - 6. ESC_K was left out of the EBCDIC table. - - 7. Change 7.0/38 introduced a new limit on the number of nested non-capturing - parentheses; I made it 1000, which seemed large enough. Unfortunately, the - limit also applies to "virtual nesting" when a pattern is recursive, and in - this case 1000 isn't so big. I have been able to remove this limit at the - expense of backing off one optimization in certain circumstances. Normally, - when pcre_exec() would call its internal match() function recursively and - immediately return the result unconditionally, it uses a "tail recursion" - feature to save stack. However, when a subpattern that can match an empty - string has an unlimited repetition quantifier, it no longer makes this - optimization. That gives it a stack frame in which to save the data for - checking that an empty string has been matched. Previously this was taken - from the 1000-entry workspace that had been reserved. So now there is no - explicit limit, but more stack is used. - - 8. Applied Daniel's patches to solve problems with the import/export magic - syntax that is required for Windows, and which was going wrong for the - pcreposix and pcrecpp parts of the library. These were overlooked when this - problem was solved for the main library. - - 9. There were some crude static tests to avoid integer overflow when computing - the size of patterns that contain repeated groups with explicit upper - limits. As the maximum quantifier is 65535, the maximum group length was - set at 30,000 so that the product of these two numbers did not overflow a - 32-bit integer. However, it turns out that people want to use groups that - are longer than 30,000 bytes (though not repeat them that many times). - Change 7.0/17 (the refactoring of the way the pattern size is computed) has - made it possible to implement the integer overflow checks in a much more - dynamic way, which I have now done. The artificial limitation on group - length has been removed - we now have only the limit on the total length of - the compiled pattern, which depends on the LINK_SIZE setting. - -10. Fixed a bug in the documentation for get/copy named substring when - duplicate names are permitted. If none of the named substrings are set, the - functions return PCRE_ERROR_NOSUBSTRING (7); the doc said they returned an - empty string. - -11. Because Perl interprets \Q...\E at a high level, and ignores orphan \E - instances, patterns such as [\Q\E] or [\E] or even [^\E] cause an error, - because the ] is interpreted as the first data character and the - terminating ] is not found. PCRE has been made compatible with Perl in this - regard. Previously, it interpreted [\Q\E] as an empty class, and [\E] could - cause memory overwriting. - -10. Like Perl, PCRE automatically breaks an unlimited repeat after an empty - string has been matched (to stop an infinite loop). It was not recognizing - a conditional subpattern that could match an empty string if that - subpattern was within another subpattern. For example, it looped when - trying to match (((?(1)X|))*) but it was OK with ((?(1)X|)*) where the - condition was not nested. This bug has been fixed. - -12. A pattern like \X?\d or \P{L}?\d in non-UTF-8 mode could cause a backtrack - past the start of the subject in the presence of bytes with the top bit - set, for example "\x8aBCD". - -13. Added Perl 5.10 experimental backtracking controls (*FAIL), (*F), (*PRUNE), - (*SKIP), (*THEN), (*COMMIT), and (*ACCEPT). - -14. Optimized (?!) to (*FAIL). - -15. Updated the test for a valid UTF-8 string to conform to the later RFC 3629. - This restricts code points to be within the range 0 to 0x10FFFF, excluding - the "low surrogate" sequence 0xD800 to 0xDFFF. Previously, PCRE allowed the - full range 0 to 0x7FFFFFFF, as defined by RFC 2279. Internally, it still - does: it's just the validity check that is more restrictive. - -16. Inserted checks for integer overflows during escape sequence (backslash) - processing, and also fixed erroneous offset values for syntax errors during - backslash processing. - -17. Fixed another case of looking too far back in non-UTF-8 mode (cf 12 above) - for patterns like [\PPP\x8a]{1,}\x80 with the subject "A\x80". - -18. An unterminated class in a pattern like (?1)\c[ with a "forward reference" - caused an overrun. - -19. A pattern like (?:[\PPa*]*){8,} which had an "extended class" (one with - something other than just ASCII characters) inside a group that had an - unlimited repeat caused a loop at compile time (while checking to see - whether the group could match an empty string). - -20. Debugging a pattern containing \p or \P could cause a crash. For example, - [\P{Any}] did so. (Error in the code for printing property names.) - -21. An orphan \E inside a character class could cause a crash. - -22. A repeated capturing bracket such as (A)? could cause a wild memory - reference during compilation. - -23. There are several functions in pcre_compile() that scan along a compiled - expression for various reasons (e.g. to see if it's fixed length for look - behind). There were bugs in these functions when a repeated \p or \P was - present in the pattern. These operators have additional parameters compared - with \d, etc, and these were not being taken into account when moving along - the compiled data. Specifically: - - (a) A item such as \p{Yi}{3} in a lookbehind was not treated as fixed - length. - - (b) An item such as \pL+ within a repeated group could cause crashes or - loops. - - (c) A pattern such as \p{Yi}+(\P{Yi}+)(?1) could give an incorrect - "reference to non-existent subpattern" error. - - (d) A pattern like (\P{Yi}{2}\277)? could loop at compile time. - -24. A repeated \S or \W in UTF-8 mode could give wrong answers when multibyte - characters were involved (for example /\S{2}/8g with "A\x{a3}BC"). - -25. Using pcregrep in multiline, inverted mode (-Mv) caused it to loop. - -26. Patterns such as [\P{Yi}A] which include \p or \P and just one other - character were causing crashes (broken optimization). - -27. Patterns such as (\P{Yi}*\277)* (group with possible zero repeat containing - \p or \P) caused a compile-time loop. - -28. More problems have arisen in unanchored patterns when CRLF is a valid line - break. For example, the unstudied pattern [\r\n]A does not match the string - "\r\nA" because change 7.0/46 below moves the current point on by two - characters after failing to match at the start. However, the pattern \nA - *does* match, because it doesn't start till \n, and if [\r\n]A is studied, - the same is true. There doesn't seem any very clean way out of this, but - what I have chosen to do makes the common cases work: PCRE now takes note - of whether there can be an explicit match for \r or \n anywhere in the - pattern, and if so, 7.0/46 no longer applies. As part of this change, - there's a new PCRE_INFO_HASCRORLF option for finding out whether a compiled - pattern has explicit CR or LF references. - -29. Added (*CR) etc for changing newline setting at start of pattern. - - -Version 7.2 19-Jun-07 ---------------------- - - 1. If the fr_FR locale cannot be found for test 3, try the "french" locale, - which is apparently normally available under Windows. - - 2. Re-jig the pcregrep tests with different newline settings in an attempt - to make them independent of the local environment's newline setting. - - 3. Add code to configure.ac to remove -g from the CFLAGS default settings. - - 4. Some of the "internals" tests were previously cut out when the link size - was not 2, because the output contained actual offsets. The recent new - "Z" feature of pcretest means that these can be cut out, making the tests - usable with all link sizes. - - 5. Implemented Stan Switzer's goto replacement for longjmp() when not using - stack recursion. This gives a massive performance boost under BSD, but just - a small improvement under Linux. However, it saves one field in the frame - in all cases. - - 6. Added more features from the forthcoming Perl 5.10: - - (a) (?-n) (where n is a string of digits) is a relative subroutine or - recursion call. It refers to the nth most recently opened parentheses. - - (b) (?+n) is also a relative subroutine call; it refers to the nth next - to be opened parentheses. - - (c) Conditions that refer to capturing parentheses can be specified - relatively, for example, (?(-2)... or (?(+3)... - - (d) \K resets the start of the current match so that everything before - is not part of it. - - (e) \k{name} is synonymous with \k<name> and \k'name' (.NET compatible). - - (f) \g{name} is another synonym - part of Perl 5.10's unification of - reference syntax. - - (g) (?| introduces a group in which the numbering of parentheses in each - alternative starts with the same number. - - (h) \h, \H, \v, and \V match horizontal and vertical whitespace. - - 7. Added two new calls to pcre_fullinfo(): PCRE_INFO_OKPARTIAL and - PCRE_INFO_JCHANGED. - - 8. A pattern such as (.*(.)?)* caused pcre_exec() to fail by either not - terminating or by crashing. Diagnosed by Viktor Griph; it was in the code - for detecting groups that can match an empty string. - - 9. A pattern with a very large number of alternatives (more than several - hundred) was running out of internal workspace during the pre-compile - phase, where pcre_compile() figures out how much memory will be needed. A - bit of new cunning has reduced the workspace needed for groups with - alternatives. The 1000-alternative test pattern now uses 12 bytes of - workspace instead of running out of the 4096 that are available. - -10. Inserted some missing (unsigned int) casts to get rid of compiler warnings. - -11. Applied patch from Google to remove an optimization that didn't quite work. - The report of the bug said: - - pcrecpp::RE("a*").FullMatch("aaa") matches, while - pcrecpp::RE("a*?").FullMatch("aaa") does not, and - pcrecpp::RE("a*?\\z").FullMatch("aaa") does again. - -12. If \p or \P was used in non-UTF-8 mode on a character greater than 127 - it matched the wrong number of bytes. - - -Version 7.1 24-Apr-07 ---------------------- - - 1. Applied Bob Rossi and Daniel G's patches to convert the build system to one - that is more "standard", making use of automake and other Autotools. There - is some re-arrangement of the files and adjustment of comments consequent - on this. - - 2. Part of the patch fixed a problem with the pcregrep tests. The test of -r - for recursive directory scanning broke on some systems because the files - are not scanned in any specific order and on different systems the order - was different. A call to "sort" has been inserted into RunGrepTest for the - approprate test as a short-term fix. In the longer term there may be an - alternative. - - 3. I had an email from Eric Raymond about problems translating some of PCRE's - man pages to HTML (despite the fact that I distribute HTML pages, some - people do their own conversions for various reasons). The problems - concerned the use of low-level troff macros .br and .in. I have therefore - removed all such uses from the man pages (some were redundant, some could - be replaced by .nf/.fi pairs). The 132html script that I use to generate - HTML has been updated to handle .nf/.fi and to complain if it encounters - .br or .in. - - 4. Updated comments in configure.ac that get placed in config.h.in and also - arranged for config.h to be included in the distribution, with the name - config.h.generic, for the benefit of those who have to compile without - Autotools (compare pcre.h, which is now distributed as pcre.h.generic). - - 5. Updated the support (such as it is) for Virtual Pascal, thanks to Stefan - Weber: (1) pcre_internal.h was missing some function renames; (2) updated - makevp.bat for the current PCRE, using the additional files - makevp_c.txt, makevp_l.txt, and pcregexp.pas. - - 6. A Windows user reported a minor discrepancy with test 2, which turned out - to be caused by a trailing space on an input line that had got lost in his - copy. The trailing space was an accident, so I've just removed it. - - 7. Add -Wl,-R... flags in pcre-config.in for *BSD* systems, as I'm told - that is needed. - - 8. Mark ucp_table (in ucptable.h) and ucp_gentype (in pcre_ucp_searchfuncs.c) - as "const" (a) because they are and (b) because it helps the PHP - maintainers who have recently made a script to detect big data structures - in the php code that should be moved to the .rodata section. I remembered - to update Builducptable as well, so it won't revert if ucptable.h is ever - re-created. - - 9. Added some extra #ifdef SUPPORT_UTF8 conditionals into pcretest.c, - pcre_printint.src, pcre_compile.c, pcre_study.c, and pcre_tables.c, in - order to be able to cut out the UTF-8 tables in the latter when UTF-8 - support is not required. This saves 1.5-2K of code, which is important in - some applications. - - Later: more #ifdefs are needed in pcre_ord2utf8.c and pcre_valid_utf8.c - so as not to refer to the tables, even though these functions will never be - called when UTF-8 support is disabled. Otherwise there are problems with a - shared library. - -10. Fixed two bugs in the emulated memmove() function in pcre_internal.h: - - (a) It was defining its arguments as char * instead of void *. - - (b) It was assuming that all moves were upwards in memory; this was true - a long time ago when I wrote it, but is no longer the case. - - The emulated memove() is provided for those environments that have neither - memmove() nor bcopy(). I didn't think anyone used it these days, but that - is clearly not the case, as these two bugs were recently reported. - -11. The script PrepareRelease is now distributed: it calls 132html, CleanTxt, - and Detrail to create the HTML documentation, the .txt form of the man - pages, and it removes trailing spaces from listed files. It also creates - pcre.h.generic and config.h.generic from pcre.h and config.h. In the latter - case, it wraps all the #defines with #ifndefs. This script should be run - before "make dist". - -12. Fixed two fairly obscure bugs concerned with quantified caseless matching - with Unicode property support. - - (a) For a maximizing quantifier, if the two different cases of the - character were of different lengths in their UTF-8 codings (there are - some cases like this - I found 11), and the matching function had to - back up over a mixture of the two cases, it incorrectly assumed they - were both the same length. - - (b) When PCRE was configured to use the heap rather than the stack for - recursion during matching, it was not correctly preserving the data for - the other case of a UTF-8 character when checking ahead for a match - while processing a minimizing repeat. If the check also involved - matching a wide character, but failed, corruption could cause an - erroneous result when trying to check for a repeat of the original - character. - -13. Some tidying changes to the testing mechanism: - - (a) The RunTest script now detects the internal link size and whether there - is UTF-8 and UCP support by running ./pcretest -C instead of relying on - values substituted by "configure". (The RunGrepTest script already did - this for UTF-8.) The configure.ac script no longer substitutes the - relevant variables. - - (b) The debugging options /B and /D in pcretest show the compiled bytecode - with length and offset values. This means that the output is different - for different internal link sizes. Test 2 is skipped for link sizes - other than 2 because of this, bypassing the problem. Unfortunately, - there was also a test in test 3 (the locale tests) that used /B and - failed for link sizes other than 2. Rather than cut the whole test out, - I have added a new /Z option to pcretest that replaces the length and - offset values with spaces. This is now used to make test 3 independent - of link size. (Test 2 will be tidied up later.) - -14. If erroroffset was passed as NULL to pcre_compile, it provoked a - segmentation fault instead of returning the appropriate error message. - -15. In multiline mode when the newline sequence was set to "any", the pattern - ^$ would give a match between the \r and \n of a subject such as "A\r\nB". - This doesn't seem right; it now treats the CRLF combination as the line - ending, and so does not match in that case. It's only a pattern such as ^$ - that would hit this one: something like ^ABC$ would have failed after \r - and then tried again after \r\n. - -16. Changed the comparison command for RunGrepTest from "diff -u" to "diff -ub" - in an attempt to make files that differ only in their line terminators - compare equal. This works on Linux. - -17. Under certain error circumstances pcregrep might try to free random memory - as it exited. This is now fixed, thanks to valgrind. - -19. In pcretest, if the pattern /(?m)^$/g<any> was matched against the string - "abc\r\n\r\n", it found an unwanted second match after the second \r. This - was because its rules for how to advance for /g after matching an empty - string at the end of a line did not allow for this case. They now check for - it specially. - -20. pcretest is supposed to handle patterns and data of any length, by - extending its buffers when necessary. It was getting this wrong when the - buffer for a data line had to be extended. - -21. Added PCRE_NEWLINE_ANYCRLF which is like ANY, but matches only CR, LF, or - CRLF as a newline sequence. - -22. Code for handling Unicode properties in pcre_dfa_exec() wasn't being cut - out by #ifdef SUPPORT_UCP. This did no harm, as it could never be used, but - I have nevertheless tidied it up. - -23. Added some casts to kill warnings from HP-UX ia64 compiler. - -24. Added a man page for pcre-config. - - -Version 7.0 19-Dec-06 ---------------------- - - 1. Fixed a signed/unsigned compiler warning in pcre_compile.c, shown up by - moving to gcc 4.1.1. - - 2. The -S option for pcretest uses setrlimit(); I had omitted to #include - sys/time.h, which is documented as needed for this function. It doesn't - seem to matter on Linux, but it showed up on some releases of OS X. - - 3. It seems that there are systems where bytes whose values are greater than - 127 match isprint() in the "C" locale. The "C" locale should be the - default when a C program starts up. In most systems, only ASCII printing - characters match isprint(). This difference caused the output from pcretest - to vary, making some of the tests fail. I have changed pcretest so that: - - (a) When it is outputting text in the compiled version of a pattern, bytes - other than 32-126 are always shown as hex escapes. - - (b) When it is outputting text that is a matched part of a subject string, - it does the same, unless a different locale has been set for the match - (using the /L modifier). In this case, it uses isprint() to decide. - - 4. Fixed a major bug that caused incorrect computation of the amount of memory - required for a compiled pattern when options that changed within the - pattern affected the logic of the preliminary scan that determines the - length. The relevant options are -x, and -i in UTF-8 mode. The result was - that the computed length was too small. The symptoms of this bug were - either the PCRE error "internal error: code overflow" from pcre_compile(), - or a glibc crash with a message such as "pcretest: free(): invalid next - size (fast)". Examples of patterns that provoked this bug (shown in - pcretest format) are: - - /(?-x: )/x - /(?x)(?-x: \s*#\s*)/ - /((?i)[\x{c0}])/8 - /(?i:[\x{c0}])/8 - - HOWEVER: Change 17 below makes this fix obsolete as the memory computation - is now done differently. - - 5. Applied patches from Google to: (a) add a QuoteMeta function to the C++ - wrapper classes; (b) implement a new function in the C++ scanner that is - more efficient than the old way of doing things because it avoids levels of - recursion in the regex matching; (c) add a paragraph to the documentation - for the FullMatch() function. - - 6. The escape sequence \n was being treated as whatever was defined as - "newline". Not only was this contrary to the documentation, which states - that \n is character 10 (hex 0A), but it also went horribly wrong when - "newline" was defined as CRLF. This has been fixed. - - 7. In pcre_dfa_exec.c the value of an unsigned integer (the variable called c) - was being set to -1 for the "end of line" case (supposedly a value that no - character can have). Though this value is never used (the check for end of - line is "zero bytes in current character"), it caused compiler complaints. - I've changed it to 0xffffffff. - - 8. In pcre_version.c, the version string was being built by a sequence of - C macros that, in the event of PCRE_PRERELEASE being defined as an empty - string (as it is for production releases) called a macro with an empty - argument. The C standard says the result of this is undefined. The gcc - compiler treats it as an empty string (which was what was wanted) but it is - reported that Visual C gives an error. The source has been hacked around to - avoid this problem. - - 9. On the advice of a Windows user, included <io.h> and <fcntl.h> in Windows - builds of pcretest, and changed the call to _setmode() to use _O_BINARY - instead of 0x8000. Made all the #ifdefs test both _WIN32 and WIN32 (not all - of them did). - -10. Originally, pcretest opened its input and output without "b"; then I was - told that "b" was needed in some environments, so it was added for release - 5.0 to both the input and output. (It makes no difference on Unix-like - systems.) Later I was told that it is wrong for the input on Windows. I've - now abstracted the modes into two macros, to make it easier to fiddle with - them, and removed "b" from the input mode under Windows. - -11. Added pkgconfig support for the C++ wrapper library, libpcrecpp. - -12. Added -help and --help to pcretest as an official way of being reminded - of the options. - -13. Removed some redundant semicolons after macro calls in pcrecpparg.h.in - and pcrecpp.cc because they annoy compilers at high warning levels. - -14. A bit of tidying/refactoring in pcre_exec.c in the main bumpalong loop. - -15. Fixed an occurrence of == in configure.ac that should have been = (shell - scripts are not C programs :-) and which was not noticed because it works - on Linux. - -16. pcretest is supposed to handle any length of pattern and data line (as one - line or as a continued sequence of lines) by extending its input buffer if - necessary. This feature was broken for very long pattern lines, leading to - a string of junk being passed to pcre_compile() if the pattern was longer - than about 50K. - -17. I have done a major re-factoring of the way pcre_compile() computes the - amount of memory needed for a compiled pattern. Previously, there was code - that made a preliminary scan of the pattern in order to do this. That was - OK when PCRE was new, but as the facilities have expanded, it has become - harder and harder to keep it in step with the real compile phase, and there - have been a number of bugs (see for example, 4 above). I have now found a - cunning way of running the real compile function in a "fake" mode that - enables it to compute how much memory it would need, while actually only - ever using a few hundred bytes of working memory and without too many - tests of the mode. This should make future maintenance and development - easier. A side effect of this work is that the limit of 200 on the nesting - depth of parentheses has been removed (though this was never a serious - limitation, I suspect). However, there is a downside: pcre_compile() now - runs more slowly than before (30% or more, depending on the pattern). I - hope this isn't a big issue. There is no effect on runtime performance. - -18. Fixed a minor bug in pcretest: if a pattern line was not terminated by a - newline (only possible for the last line of a file) and it was a - pattern that set a locale (followed by /Lsomething), pcretest crashed. - -19. Added additional timing features to pcretest. (1) The -tm option now times - matching only, not compiling. (2) Both -t and -tm can be followed, as a - separate command line item, by a number that specifies the number of - repeats to use when timing. The default is 50000; this gives better - precision, but takes uncomfortably long for very large patterns. - -20. Extended pcre_study() to be more clever in cases where a branch of a - subpattern has no definite first character. For example, (a*|b*)[cd] would - previously give no result from pcre_study(). Now it recognizes that the - first character must be a, b, c, or d. - -21. There was an incorrect error "recursive call could loop indefinitely" if - a subpattern (or the entire pattern) that was being tested for matching an - empty string contained only one non-empty item after a nested subpattern. - For example, the pattern (?>\x{100}*)\d(?R) provoked this error - incorrectly, because the \d was being skipped in the check. - -22. The pcretest program now has a new pattern option /B and a command line - option -b, which is equivalent to adding /B to every pattern. This causes - it to show the compiled bytecode, without the additional information that - -d shows. The effect of -d is now the same as -b with -i (and similarly, /D - is the same as /B/I). - -23. A new optimization is now able automatically to treat some sequences such - as a*b as a*+b. More specifically, if something simple (such as a character - or a simple class like \d) has an unlimited quantifier, and is followed by - something that cannot possibly match the quantified thing, the quantifier - is automatically "possessified". - -24. A recursive reference to a subpattern whose number was greater than 39 - went wrong under certain circumstances in UTF-8 mode. This bug could also - have affected the operation of pcre_study(). - -25. Realized that a little bit of performance could be had by replacing - (c & 0xc0) == 0xc0 with c >= 0xc0 when processing UTF-8 characters. - -26. Timing data from pcretest is now shown to 4 decimal places instead of 3. - -27. Possessive quantifiers such as a++ were previously implemented by turning - them into atomic groups such as ($>a+). Now they have their own opcodes, - which improves performance. This includes the automatically created ones - from 23 above. - -28. A pattern such as (?=(\w+))\1: which simulates an atomic group using a - lookahead was broken if it was not anchored. PCRE was mistakenly expecting - the first matched character to be a colon. This applied both to named and - numbered groups. - -29. The ucpinternal.h header file was missing its idempotency #ifdef. - -30. I was sent a "project" file called libpcre.a.dev which I understand makes - building PCRE on Windows easier, so I have included it in the distribution. - -31. There is now a check in pcretest against a ridiculously large number being - returned by pcre_exec() or pcre_dfa_exec(). If this happens in a /g or /G - loop, the loop is abandoned. - -32. Forward references to subpatterns in conditions such as (?(2)...) where - subpattern 2 is defined later cause pcre_compile() to search forwards in - the pattern for the relevant set of parentheses. This search went wrong - when there were unescaped parentheses in a character class, parentheses - escaped with \Q...\E, or parentheses in a #-comment in /x mode. - -33. "Subroutine" calls and backreferences were previously restricted to - referencing subpatterns earlier in the regex. This restriction has now - been removed. - -34. Added a number of extra features that are going to be in Perl 5.10. On the - whole, these are just syntactic alternatives for features that PCRE had - previously implemented using the Python syntax or my own invention. The - other formats are all retained for compatibility. - - (a) Named groups can now be defined as (?<name>...) or (?'name'...) as well - as (?P<name>...). The new forms, as well as being in Perl 5.10, are - also .NET compatible. - - (b) A recursion or subroutine call to a named group can now be defined as - (?&name) as well as (?P>name). - - (c) A backreference to a named group can now be defined as \k<name> or - \k'name' as well as (?P=name). The new forms, as well as being in Perl - 5.10, are also .NET compatible. - - (d) A conditional reference to a named group can now use the syntax - (?(<name>) or (?('name') as well as (?(name). - - (e) A "conditional group" of the form (?(DEFINE)...) can be used to define - groups (named and numbered) that are never evaluated inline, but can be - called as "subroutines" from elsewhere. In effect, the DEFINE condition - is always false. There may be only one alternative in such a group. - - (f) A test for recursion can be given as (?(R1).. or (?(R&name)... as well - as the simple (?(R). The condition is true only if the most recent - recursion is that of the given number or name. It does not search out - through the entire recursion stack. - - (g) The escape \gN or \g{N} has been added, where N is a positive or - negative number, specifying an absolute or relative reference. - -35. Tidied to get rid of some further signed/unsigned compiler warnings and - some "unreachable code" warnings. - -36. Updated the Unicode property tables to Unicode version 5.0.0. Amongst other - things, this adds five new scripts. - -37. Perl ignores orphaned \E escapes completely. PCRE now does the same. - There were also incompatibilities regarding the handling of \Q..\E inside - character classes, for example with patterns like [\Qa\E-\Qz\E] where the - hyphen was adjacent to \Q or \E. I hope I've cleared all this up now. - -38. Like Perl, PCRE detects when an indefinitely repeated parenthesized group - matches an empty string, and forcibly breaks the loop. There were bugs in - this code in non-simple cases. For a pattern such as ^(a()*)* matched - against aaaa the result was just "a" rather than "aaaa", for example. Two - separate and independent bugs (that affected different cases) have been - fixed. - -39. Refactored the code to abolish the use of different opcodes for small - capturing bracket numbers. This is a tidy that I avoided doing when I - removed the limit on the number of capturing brackets for 3.5 back in 2001. - The new approach is not only tidier, it makes it possible to reduce the - memory needed to fix the previous bug (38). - -40. Implemented PCRE_NEWLINE_ANY to recognize any of the Unicode newline - sequences (http://unicode.org/unicode/reports/tr18/) as "newline" when - processing dot, circumflex, or dollar metacharacters, or #-comments in /x - mode. - -41. Add \R to match any Unicode newline sequence, as suggested in the Unicode - report. - -42. Applied patch, originally from Ari Pollak, modified by Google, to allow - copy construction and assignment in the C++ wrapper. - -43. Updated pcregrep to support "--newline=any". In the process, I fixed a - couple of bugs that could have given wrong results in the "--newline=crlf" - case. - -44. Added a number of casts and did some reorganization of signed/unsigned int - variables following suggestions from Dair Grant. Also renamed the variable - "this" as "item" because it is a C++ keyword. - -45. Arranged for dftables to add - - #include "pcre_internal.h" - - to pcre_chartables.c because without it, gcc 4.x may remove the array - definition from the final binary if PCRE is built into a static library and - dead code stripping is activated. - -46. For an unanchored pattern, if a match attempt fails at the start of a - newline sequence, and the newline setting is CRLF or ANY, and the next two - characters are CRLF, advance by two characters instead of one. - - -Version 6.7 04-Jul-06 ---------------------- - - 1. In order to handle tests when input lines are enormously long, pcretest has - been re-factored so that it automatically extends its buffers when - necessary. The code is crude, but this _is_ just a test program. The - default size has been increased from 32K to 50K. - - 2. The code in pcre_study() was using the value of the re argument before - testing it for NULL. (Of course, in any sensible call of the function, it - won't be NULL.) - - 3. The memmove() emulation function in pcre_internal.h, which is used on - systems that lack both memmove() and bcopy() - that is, hardly ever - - was missing a "static" storage class specifier. - - 4. When UTF-8 mode was not set, PCRE looped when compiling certain patterns - containing an extended class (one that cannot be represented by a bitmap - because it contains high-valued characters or Unicode property items, e.g. - [\pZ]). Almost always one would set UTF-8 mode when processing such a - pattern, but PCRE should not loop if you do not (it no longer does). - [Detail: two cases were found: (a) a repeated subpattern containing an - extended class; (b) a recursive reference to a subpattern that followed a - previous extended class. It wasn't skipping over the extended class - correctly when UTF-8 mode was not set.] - - 5. A negated single-character class was not being recognized as fixed-length - in lookbehind assertions such as (?<=[^f]), leading to an incorrect - compile error "lookbehind assertion is not fixed length". - - 6. The RunPerlTest auxiliary script was showing an unexpected difference - between PCRE and Perl for UTF-8 tests. It turns out that it is hard to - write a Perl script that can interpret lines of an input file either as - byte characters or as UTF-8, which is what "perltest" was being required to - do for the non-UTF-8 and UTF-8 tests, respectively. Essentially what you - can't do is switch easily at run time between having the "use utf8;" pragma - or not. In the end, I fudged it by using the RunPerlTest script to insert - "use utf8;" explicitly for the UTF-8 tests. - - 7. In multiline (/m) mode, PCRE was matching ^ after a terminating newline at - the end of the subject string, contrary to the documentation and to what - Perl does. This was true of both matching functions. Now it matches only at - the start of the subject and immediately after *internal* newlines. - - 8. A call of pcre_fullinfo() from pcretest to get the option bits was passing - a pointer to an int instead of a pointer to an unsigned long int. This - caused problems on 64-bit systems. - - 9. Applied a patch from the folks at Google to pcrecpp.cc, to fix "another - instance of the 'standard' template library not being so standard". - -10. There was no check on the number of named subpatterns nor the maximum - length of a subpattern name. The product of these values is used to compute - the size of the memory block for a compiled pattern. By supplying a very - long subpattern name and a large number of named subpatterns, the size - computation could be caused to overflow. This is now prevented by limiting - the length of names to 32 characters, and the number of named subpatterns - to 10,000. - -11. Subpatterns that are repeated with specific counts have to be replicated in - the compiled pattern. The size of memory for this was computed from the - length of the subpattern and the repeat count. The latter is limited to - 65535, but there was no limit on the former, meaning that integer overflow - could in principle occur. The compiled length of a repeated subpattern is - now limited to 30,000 bytes in order to prevent this. - -12. Added the optional facility to have named substrings with the same name. - -13. Added the ability to use a named substring as a condition, using the - Python syntax: (?(name)yes|no). This overloads (?(R)... and names that - are numbers (not recommended). Forward references are permitted. - -14. Added forward references in named backreferences (if you see what I mean). - -15. In UTF-8 mode, with the PCRE_DOTALL option set, a quantified dot in the - pattern could run off the end of the subject. For example, the pattern - "(?s)(.{1,5})"8 did this with the subject "ab". - -16. If PCRE_DOTALL or PCRE_MULTILINE were set, pcre_dfa_exec() behaved as if - PCRE_CASELESS was set when matching characters that were quantified with ? - or *. - -17. A character class other than a single negated character that had a minimum - but no maximum quantifier - for example [ab]{6,} - was not handled - correctly by pce_dfa_exec(). It would match only one character. - -18. A valid (though odd) pattern that looked like a POSIX character - class but used an invalid character after [ (for example [[,abc,]]) caused - pcre_compile() to give the error "Failed: internal error: code overflow" or - in some cases to crash with a glibc free() error. This could even happen if - the pattern terminated after [[ but there just happened to be a sequence of - letters, a binary zero, and a closing ] in the memory that followed. - -19. Perl's treatment of octal escapes in the range \400 to \777 has changed - over the years. Originally (before any Unicode support), just the bottom 8 - bits were taken. Thus, for example, \500 really meant \100. Nowadays the - output from "man perlunicode" includes this: - - The regular expression compiler produces polymorphic opcodes. That - is, the pattern adapts to the data and automatically switches to - the Unicode character scheme when presented with Unicode data--or - instead uses a traditional byte scheme when presented with byte - data. - - Sadly, a wide octal escape does not cause a switch, and in a string with - no other multibyte characters, these octal escapes are treated as before. - Thus, in Perl, the pattern /\500/ actually matches \100 but the pattern - /\500|\x{1ff}/ matches \500 or \777 because the whole thing is treated as a - Unicode string. - - I have not perpetrated such confusion in PCRE. Up till now, it took just - the bottom 8 bits, as in old Perl. I have now made octal escapes with - values greater than \377 illegal in non-UTF-8 mode. In UTF-8 mode they - translate to the appropriate multibyte character. - -29. Applied some refactoring to reduce the number of warnings from Microsoft - and Borland compilers. This has included removing the fudge introduced - seven years ago for the OS/2 compiler (see 2.02/2 below) because it caused - a warning about an unused variable. - -21. PCRE has not included VT (character 0x0b) in the set of whitespace - characters since release 4.0, because Perl (from release 5.004) does not. - [Or at least, is documented not to: some releases seem to be in conflict - with the documentation.] However, when a pattern was studied with - pcre_study() and all its branches started with \s, PCRE still included VT - as a possible starting character. Of course, this did no harm; it just - caused an unnecessary match attempt. - -22. Removed a now-redundant internal flag bit that recorded the fact that case - dependency changed within the pattern. This was once needed for "required - byte" processing, but is no longer used. This recovers a now-scarce options - bit. Also moved the least significant internal flag bit to the most- - significant bit of the word, which was not previously used (hangover from - the days when it was an int rather than a uint) to free up another bit for - the future. - -23. Added support for CRLF line endings as well as CR and LF. As well as the - default being selectable at build time, it can now be changed at runtime - via the PCRE_NEWLINE_xxx flags. There are now options for pcregrep to - specify that it is scanning data with non-default line endings. - -24. Changed the definition of CXXLINK to make it agree with the definition of - LINK in the Makefile, by replacing LDFLAGS to CXXFLAGS. - -25. Applied Ian Taylor's patches to avoid using another stack frame for tail - recursions. This makes a big different to stack usage for some patterns. - -26. If a subpattern containing a named recursion or subroutine reference such - as (?P>B) was quantified, for example (xxx(?P>B)){3}, the calculation of - the space required for the compiled pattern went wrong and gave too small a - value. Depending on the environment, this could lead to "Failed: internal - error: code overflow at offset 49" or "glibc detected double free or - corruption" errors. - -27. Applied patches from Google (a) to support the new newline modes and (b) to - advance over multibyte UTF-8 characters in GlobalReplace. - -28. Change free() to pcre_free() in pcredemo.c. Apparently this makes a - difference for some implementation of PCRE in some Windows version. - -29. Added some extra testing facilities to pcretest: - - \q<number> in a data line sets the "match limit" value - \Q<number> in a data line sets the "match recursion limt" value - -S <number> sets the stack size, where <number> is in megabytes - - The -S option isn't available for Windows. - - -Version 6.6 06-Feb-06 ---------------------- - - 1. Change 16(a) for 6.5 broke things, because PCRE_DATA_SCOPE was not defined - in pcreposix.h. I have copied the definition from pcre.h. - - 2. Change 25 for 6.5 broke compilation in a build directory out-of-tree - because pcre.h is no longer a built file. - - 3. Added Jeff Friedl's additional debugging patches to pcregrep. These are - not normally included in the compiled code. - - -Version 6.5 01-Feb-06 ---------------------- - - 1. When using the partial match feature with pcre_dfa_exec(), it was not - anchoring the second and subsequent partial matches at the new starting - point. This could lead to incorrect results. For example, with the pattern - /1234/, partially matching against "123" and then "a4" gave a match. - - 2. Changes to pcregrep: - - (a) All non-match returns from pcre_exec() were being treated as failures - to match the line. Now, unless the error is PCRE_ERROR_NOMATCH, an - error message is output. Some extra information is given for the - PCRE_ERROR_MATCHLIMIT and PCRE_ERROR_RECURSIONLIMIT errors, which are - probably the only errors that are likely to be caused by users (by - specifying a regex that has nested indefinite repeats, for instance). - If there are more than 20 of these errors, pcregrep is abandoned. - - (b) A binary zero was treated as data while matching, but terminated the - output line if it was written out. This has been fixed: binary zeroes - are now no different to any other data bytes. - - (c) Whichever of the LC_ALL or LC_CTYPE environment variables is set is - used to set a locale for matching. The --locale=xxxx long option has - been added (no short equivalent) to specify a locale explicitly on the - pcregrep command, overriding the environment variables. - - (d) When -B was used with -n, some line numbers in the output were one less - than they should have been. - - (e) Added the -o (--only-matching) option. - - (f) If -A or -C was used with -c (count only), some lines of context were - accidentally printed for the final match. - - (g) Added the -H (--with-filename) option. - - (h) The combination of options -rh failed to suppress file names for files - that were found from directory arguments. - - (i) Added the -D (--devices) and -d (--directories) options. - - (j) Added the -F (--fixed-strings) option. - - (k) Allow "-" to be used as a file name for -f as well as for a data file. - - (l) Added the --colo(u)r option. - - (m) Added Jeffrey Friedl's -S testing option, but within #ifdefs so that it - is not present by default. - - 3. A nasty bug was discovered in the handling of recursive patterns, that is, - items such as (?R) or (?1), when the recursion could match a number of - alternatives. If it matched one of the alternatives, but subsequently, - outside the recursion, there was a failure, the code tried to back up into - the recursion. However, because of the way PCRE is implemented, this is not - possible, and the result was an incorrect result from the match. - - In order to prevent this happening, the specification of recursion has - been changed so that all such subpatterns are automatically treated as - atomic groups. Thus, for example, (?R) is treated as if it were (?>(?R)). - - 4. I had overlooked the fact that, in some locales, there are characters for - which isalpha() is true but neither isupper() nor islower() are true. In - the fr_FR locale, for instance, the \xAA and \xBA characters (ordmasculine - and ordfeminine) are like this. This affected the treatment of \w and \W - when they appeared in character classes, but not when they appeared outside - a character class. The bit map for "word" characters is now created - separately from the results of isalnum() instead of just taking it from the - upper, lower, and digit maps. (Plus the underscore character, of course.) - - 5. The above bug also affected the handling of POSIX character classes such as - [[:alpha:]] and [[:alnum:]]. These do not have their own bit maps in PCRE's - permanent tables. Instead, the bit maps for such a class were previously - created as the appropriate unions of the upper, lower, and digit bitmaps. - Now they are created by subtraction from the [[:word:]] class, which has - its own bitmap. - - 6. The [[:blank:]] character class matches horizontal, but not vertical space. - It is created by subtracting the vertical space characters (\x09, \x0a, - \x0b, \x0c) from the [[:space:]] bitmap. Previously, however, the - subtraction was done in the overall bitmap for a character class, meaning - that a class such as [\x0c[:blank:]] was incorrect because \x0c would not - be recognized. This bug has been fixed. - - 7. Patches from the folks at Google: - - (a) pcrecpp.cc: "to handle a corner case that may or may not happen in - real life, but is still worth protecting against". - - (b) pcrecpp.cc: "corrects a bug when negative radixes are used with - regular expressions". - - (c) pcre_scanner.cc: avoid use of std::count() because not all systems - have it. - - (d) Split off pcrecpparg.h from pcrecpp.h and had the former built by - "configure" and the latter not, in order to fix a problem somebody had - with compiling the Arg class on HP-UX. - - (e) Improve the error-handling of the C++ wrapper a little bit. - - (f) New tests for checking recursion limiting. - - 8. The pcre_memmove() function, which is used only if the environment does not - have a standard memmove() function (and is therefore rarely compiled), - contained two bugs: (a) use of int instead of size_t, and (b) it was not - returning a result (though PCRE never actually uses the result). - - 9. In the POSIX regexec() interface, if nmatch is specified as a ridiculously - large number - greater than INT_MAX/(3*sizeof(int)) - REG_ESPACE is - returned instead of calling malloc() with an overflowing number that would - most likely cause subsequent chaos. - -10. The debugging option of pcretest was not showing the NO_AUTO_CAPTURE flag. - -11. The POSIX flag REG_NOSUB is now supported. When a pattern that was compiled - with this option is matched, the nmatch and pmatch options of regexec() are - ignored. - -12. Added REG_UTF8 to the POSIX interface. This is not defined by POSIX, but is - provided in case anyone wants to the the POSIX interface with UTF-8 - strings. - -13. Added CXXLDFLAGS to the Makefile parameters to provide settings only on the - C++ linking (needed for some HP-UX environments). - -14. Avoid compiler warnings in get_ucpname() when compiled without UCP support - (unused parameter) and in the pcre_printint() function (omitted "default" - switch label when the default is to do nothing). - -15. Added some code to make it possible, when PCRE is compiled as a C++ - library, to replace subject pointers for pcre_exec() with a smart pointer - class, thus making it possible to process discontinuous strings. - -16. The two macros PCRE_EXPORT and PCRE_DATA_SCOPE are confusing, and perform - much the same function. They were added by different people who were trying - to make PCRE easy to compile on non-Unix systems. It has been suggested - that PCRE_EXPORT be abolished now that there is more automatic apparatus - for compiling on Windows systems. I have therefore replaced it with - PCRE_DATA_SCOPE. This is set automatically for Windows; if not set it - defaults to "extern" for C or "extern C" for C++, which works fine on - Unix-like systems. It is now possible to override the value of PCRE_DATA_ - SCOPE with something explicit in config.h. In addition: - - (a) pcreposix.h still had just "extern" instead of either of these macros; - I have replaced it with PCRE_DATA_SCOPE. - - (b) Functions such as _pcre_xclass(), which are internal to the library, - but external in the C sense, all had PCRE_EXPORT in their definitions. - This is apparently wrong for the Windows case, so I have removed it. - (It makes no difference on Unix-like systems.) - -17. Added a new limit, MATCH_LIMIT_RECURSION, which limits the depth of nesting - of recursive calls to match(). This is different to MATCH_LIMIT because - that limits the total number of calls to match(), not all of which increase - the depth of recursion. Limiting the recursion depth limits the amount of - stack (or heap if NO_RECURSE is set) that is used. The default can be set - when PCRE is compiled, and changed at run time. A patch from Google adds - this functionality to the C++ interface. - -18. Changes to the handling of Unicode character properties: - - (a) Updated the table to Unicode 4.1.0. - - (b) Recognize characters that are not in the table as "Cn" (undefined). - - (c) I revised the way the table is implemented to a much improved format - which includes recognition of ranges. It now supports the ranges that - are defined in UnicodeData.txt, and it also amalgamates other - characters into ranges. This has reduced the number of entries in the - table from around 16,000 to around 3,000, thus reducing its size - considerably. I realized I did not need to use a tree structure after - all - a binary chop search is just as efficient. Having reduced the - number of entries, I extended their size from 6 bytes to 8 bytes to - allow for more data. - - (d) Added support for Unicode script names via properties such as \p{Han}. - -19. In UTF-8 mode, a backslash followed by a non-Ascii character was not - matching that character. - -20. When matching a repeated Unicode property with a minimum greater than zero, - (for example \pL{2,}), PCRE could look past the end of the subject if it - reached it while seeking the minimum number of characters. This could - happen only if some of the characters were more than one byte long, because - there is a check for at least the minimum number of bytes. - -21. Refactored the implementation of \p and \P so as to be more general, to - allow for more different types of property in future. This has changed the - compiled form incompatibly. Anybody with saved compiled patterns that use - \p or \P will have to recompile them. - -22. Added "Any" and "L&" to the supported property types. - -23. Recognize \x{...} as a code point specifier, even when not in UTF-8 mode, - but give a compile time error if the value is greater than 0xff. - -24. The man pages for pcrepartial, pcreprecompile, and pcre_compile2 were - accidentally not being installed or uninstalled. - -25. The pcre.h file was built from pcre.h.in, but the only changes that were - made were to insert the current release number. This seemed silly, because - it made things harder for people building PCRE on systems that don't run - "configure". I have turned pcre.h into a distributed file, no longer built - by "configure", with the version identification directly included. There is - no longer a pcre.h.in file. - - However, this change necessitated a change to the pcre-config script as - well. It is built from pcre-config.in, and one of the substitutions was the - release number. I have updated configure.ac so that ./configure now finds - the release number by grepping pcre.h. - -26. Added the ability to run the tests under valgrind. - - -Version 6.4 05-Sep-05 ---------------------- - - 1. Change 6.0/10/(l) to pcregrep introduced a bug that caused separator lines - "--" to be printed when multiple files were scanned, even when none of the - -A, -B, or -C options were used. This is not compatible with Gnu grep, so I - consider it to be a bug, and have restored the previous behaviour. - - 2. A couple of code tidies to get rid of compiler warnings. - - 3. The pcretest program used to cheat by referring to symbols in the library - whose names begin with _pcre_. These are internal symbols that are not - really supposed to be visible externally, and in some environments it is - possible to suppress them. The cheating is now confined to including - certain files from the library's source, which is a bit cleaner. - - 4. Renamed pcre.in as pcre.h.in to go with pcrecpp.h.in; it also makes the - file's purpose clearer. - - 5. Reorganized pcre_ucp_findchar(). - - -Version 6.3 15-Aug-05 ---------------------- - - 1. The file libpcre.pc.in did not have general read permission in the tarball. - - 2. There were some problems when building without C++ support: - - (a) If C++ support was not built, "make install" and "make test" still - tried to test it. - - (b) There were problems when the value of CXX was explicitly set. Some - changes have been made to try to fix these, and ... - - (c) --disable-cpp can now be used to explicitly disable C++ support. - - (d) The use of @CPP_OBJ@ directly caused a blank line preceded by a - backslash in a target when C++ was disabled. This confuses some - versions of "make", apparently. Using an intermediate variable solves - this. (Same for CPP_LOBJ.) - - 3. $(LINK_FOR_BUILD) now includes $(CFLAGS_FOR_BUILD) and $(LINK) - (non-Windows) now includes $(CFLAGS) because these flags are sometimes - necessary on certain architectures. - - 4. Added a setting of -export-symbols-regex to the link command to remove - those symbols that are exported in the C sense, but actually are local - within the library, and not documented. Their names all begin with - "_pcre_". This is not a perfect job, because (a) we have to except some - symbols that pcretest ("illegally") uses, and (b) the facility isn't always - available (and never for static libraries). I have made a note to try to - find a way round (a) in the future. - - -Version 6.2 01-Aug-05 ---------------------- - - 1. There was no test for integer overflow of quantifier values. A construction - such as {1111111111111111} would give undefined results. What is worse, if - a minimum quantifier for a parenthesized subpattern overflowed and became - negative, the calculation of the memory size went wrong. This could have - led to memory overwriting. - - 2. Building PCRE using VPATH was broken. Hopefully it is now fixed. - - 3. Added "b" to the 2nd argument of fopen() in dftables.c, for non-Unix-like - operating environments where this matters. - - 4. Applied Giuseppe Maxia's patch to add additional features for controlling - PCRE options from within the C++ wrapper. - - 5. Named capturing subpatterns were not being correctly counted when a pattern - was compiled. This caused two problems: (a) If there were more than 100 - such subpatterns, the calculation of the memory needed for the whole - compiled pattern went wrong, leading to an overflow error. (b) Numerical - back references of the form \12, where the number was greater than 9, were - not recognized as back references, even though there were sufficient - previous subpatterns. - - 6. Two minor patches to pcrecpp.cc in order to allow it to compile on older - versions of gcc, e.g. 2.95.4. - - -Version 6.1 21-Jun-05 ---------------------- - - 1. There was one reference to the variable "posix" in pcretest.c that was not - surrounded by "#if !defined NOPOSIX". - - 2. Make it possible to compile pcretest without DFA support, UTF8 support, or - the cross-check on the old pcre_info() function, for the benefit of the - cut-down version of PCRE that is currently imported into Exim. - - 3. A (silly) pattern starting with (?i)(?-i) caused an internal space - allocation error. I've done the easy fix, which wastes 2 bytes for sensible - patterns that start (?i) but I don't think that matters. The use of (?i) is - just an example; this all applies to the other options as well. - - 4. Since libtool seems to echo the compile commands it is issuing, the output - from "make" can be reduced a bit by putting "@" in front of each libtool - compile command. - - 5. Patch from the folks at Google for configure.in to be a bit more thorough - in checking for a suitable C++ installation before trying to compile the - C++ stuff. This should fix a reported problem when a compiler was present, - but no suitable headers. - - 6. The man pages all had just "PCRE" as their title. I have changed them to - be the relevant file name. I have also arranged that these names are - retained in the file doc/pcre.txt, which is a concatenation in text format - of all the man pages except the little individual ones for each function. - - 7. The NON-UNIX-USE file had not been updated for the different set of source - files that come with release 6. I also added a few comments about the C++ - wrapper. - - -Version 6.0 07-Jun-05 ---------------------- - - 1. Some minor internal re-organization to help with my DFA experiments. - - 2. Some missing #ifdef SUPPORT_UCP conditionals in pcretest and printint that - didn't matter for the library itself when fully configured, but did matter - when compiling without UCP support, or within Exim, where the ucp files are - not imported. - - 3. Refactoring of the library code to split up the various functions into - different source modules. The addition of the new DFA matching code (see - below) to a single monolithic source would have made it really too - unwieldy, quite apart from causing all the code to be include in a - statically linked application, when only some functions are used. This is - relevant even without the DFA addition now that patterns can be compiled in - one application and matched in another. - - The downside of splitting up is that there have to be some external - functions and data tables that are used internally in different modules of - the library but which are not part of the API. These have all had their - names changed to start with "_pcre_" so that they are unlikely to clash - with other external names. - - 4. Added an alternate matching function, pcre_dfa_exec(), which matches using - a different (DFA) algorithm. Although it is slower than the original - function, it does have some advantages for certain types of matching - problem. - - 5. Upgrades to pcretest in order to test the features of pcre_dfa_exec(), - including restarting after a partial match. - - 6. A patch for pcregrep that defines INVALID_FILE_ATTRIBUTES if it is not - defined when compiling for Windows was sent to me. I have put it into the - code, though I have no means of testing or verifying it. - - 7. Added the pcre_refcount() auxiliary function. - - 8. Added the PCRE_FIRSTLINE option. This constrains an unanchored pattern to - match before or at the first newline in the subject string. In pcretest, - the /f option on a pattern can be used to set this. - - 9. A repeated \w when used in UTF-8 mode with characters greater than 256 - would behave wrongly. This has been present in PCRE since release 4.0. - -10. A number of changes to the pcregrep command: - - (a) Refactored how -x works; insert ^(...)$ instead of setting - PCRE_ANCHORED and checking the length, in preparation for adding - something similar for -w. - - (b) Added the -w (match as a word) option. - - (c) Refactored the way lines are read and buffered so as to have more - than one at a time available. - - (d) Implemented a pcregrep test script. - - (e) Added the -M (multiline match) option. This allows patterns to match - over several lines of the subject. The buffering ensures that at least - 8K, or the rest of the document (whichever is the shorter) is available - for matching (and similarly the previous 8K for lookbehind assertions). - - (f) Changed the --help output so that it now says - - -w, --word-regex(p) - - instead of two lines, one with "regex" and the other with "regexp" - because that confused at least one person since the short forms are the - same. (This required a bit of code, as the output is generated - automatically from a table. It wasn't just a text change.) - - (g) -- can be used to terminate pcregrep options if the next thing isn't an - option but starts with a hyphen. Could be a pattern or a path name - starting with a hyphen, for instance. - - (h) "-" can be given as a file name to represent stdin. - - (i) When file names are being printed, "(standard input)" is used for - the standard input, for compatibility with GNU grep. Previously - "<stdin>" was used. - - (j) The option --label=xxx can be used to supply a name to be used for - stdin when file names are being printed. There is no short form. - - (k) Re-factored the options decoding logic because we are going to add - two more options that take data. Such options can now be given in four - different ways, e.g. "-fname", "-f name", "--file=name", "--file name". - - (l) Added the -A, -B, and -C options for requesting that lines of context - around matches be printed. - - (m) Added the -L option to print the names of files that do not contain - any matching lines, that is, the complement of -l. - - (n) The return code is 2 if any file cannot be opened, but pcregrep does - continue to scan other files. - - (o) The -s option was incorrectly implemented. For compatibility with other - greps, it now suppresses the error message for a non-existent or non- - accessible file (but not the return code). There is a new option called - -q that suppresses the output of matching lines, which was what -s was - previously doing. - - (p) Added --include and --exclude options to specify files for inclusion - and exclusion when recursing. - -11. The Makefile was not using the Autoconf-supported LDFLAGS macro properly. - Hopefully, it now does. - -12. Missing cast in pcre_study(). - -13. Added an "uninstall" target to the makefile. - -14. Replaced "extern" in the function prototypes in Makefile.in with - "PCRE_DATA_SCOPE", which defaults to 'extern' or 'extern "C"' in the Unix - world, but is set differently for Windows. - -15. Added a second compiling function called pcre_compile2(). The only - difference is that it has an extra argument, which is a pointer to an - integer error code. When there is a compile-time failure, this is set - non-zero, in addition to the error test pointer being set to point to an - error message. The new argument may be NULL if no error number is required - (but then you may as well call pcre_compile(), which is now just a - wrapper). This facility is provided because some applications need a - numeric error indication, but it has also enabled me to tidy up the way - compile-time errors are handled in the POSIX wrapper. - -16. Added VPATH=.libs to the makefile; this should help when building with one - prefix path and installing with another. (Or so I'm told by someone who - knows more about this stuff than I do.) - -17. Added a new option, REG_DOTALL, to the POSIX function regcomp(). This - passes PCRE_DOTALL to the pcre_compile() function, making the "." character - match everything, including newlines. This is not POSIX-compatible, but - somebody wanted the feature. From pcretest it can be activated by using - both the P and the s flags. - -18. AC_PROG_LIBTOOL appeared twice in Makefile.in. Removed one. - -19. libpcre.pc was being incorrectly installed as executable. - -20. A couple of places in pcretest check for end-of-line by looking for '\n'; - it now also looks for '\r' so that it will work unmodified on Windows. - -21. Added Google's contributed C++ wrapper to the distribution. - -22. Added some untidy missing memory free() calls in pcretest, to keep - Electric Fence happy when testing. - - - -Version 5.0 13-Sep-04 ---------------------- - - 1. Internal change: literal characters are no longer packed up into items - containing multiple characters in a single byte-string. Each character - is now matched using a separate opcode. However, there may be more than one - byte in the character in UTF-8 mode. - - 2. The pcre_callout_block structure has two new fields: pattern_position and - next_item_length. These contain the offset in the pattern to the next match - item, and its length, respectively. - - 3. The PCRE_AUTO_CALLOUT option for pcre_compile() requests the automatic - insertion of callouts before each pattern item. Added the /C option to - pcretest to make use of this. - - 4. On the advice of a Windows user, the lines - - #if defined(_WIN32) || defined(WIN32) - _setmode( _fileno( stdout ), 0x8000 ); - #endif /* defined(_WIN32) || defined(WIN32) */ - - have been added to the source of pcretest. This apparently does useful - magic in relation to line terminators. - - 5. Changed "r" and "w" in the calls to fopen() in pcretest to "rb" and "wb" - for the benefit of those environments where the "b" makes a difference. - - 6. The icc compiler has the same options as gcc, but "configure" doesn't seem - to know about it. I have put a hack into configure.in that adds in code - to set GCC=yes if CC=icc. This seems to end up at a point in the - generated configure script that is early enough to affect the setting of - compiler options, which is what is needed, but I have no means of testing - whether it really works. (The user who reported this had patched the - generated configure script, which of course I cannot do.) - - LATER: After change 22 below (new libtool files), the configure script - seems to know about icc (and also ecc). Therefore, I have commented out - this hack in configure.in. - - 7. Added support for pkg-config (2 patches were sent in). - - 8. Negated POSIX character classes that used a combination of internal tables - were completely broken. These were [[:^alpha:]], [[:^alnum:]], and - [[:^ascii]]. Typically, they would match almost any characters. The other - POSIX classes were not broken in this way. - - 9. Matching the pattern "\b.*?" against "ab cd", starting at offset 1, failed - to find the match, as PCRE was deluded into thinking that the match had to - start at the start point or following a newline. The same bug applied to - patterns with negative forward assertions or any backward assertions - preceding ".*" at the start, unless the pattern required a fixed first - character. This was a failing pattern: "(?!.bcd).*". The bug is now fixed. - -10. In UTF-8 mode, when moving forwards in the subject after a failed match - starting at the last subject character, bytes beyond the end of the subject - string were read. - -11. Renamed the variable "class" as "classbits" to make life easier for C++ - users. (Previously there was a macro definition, but it apparently wasn't - enough.) - -12. Added the new field "tables" to the extra data so that tables can be passed - in at exec time, or the internal tables can be re-selected. This allows - a compiled regex to be saved and re-used at a later time by a different - program that might have everything at different addresses. - -13. Modified the pcre-config script so that, when run on Solaris, it shows a - -R library as well as a -L library. - -14. The debugging options of pcretest (-d on the command line or D on a - pattern) showed incorrect output for anything following an extended class - that contained multibyte characters and which was followed by a quantifier. - -15. Added optional support for general category Unicode character properties - via the \p, \P, and \X escapes. Unicode property support implies UTF-8 - support. It adds about 90K to the size of the library. The meanings of the - inbuilt class escapes such as \d and \s have NOT been changed. - -16. Updated pcredemo.c to include calls to free() to release the memory for the - compiled pattern. - -17. The generated file chartables.c was being created in the source directory - instead of in the building directory. This caused the build to fail if the - source directory was different from the building directory, and was - read-only. - -18. Added some sample Win commands from Mark Tetrode into the NON-UNIX-USE - file. No doubt somebody will tell me if they don't make sense... Also added - Dan Mooney's comments about building on OpenVMS. - -19. Added support for partial matching via the PCRE_PARTIAL option for - pcre_exec() and the \P data escape in pcretest. - -20. Extended pcretest with 3 new pattern features: - - (i) A pattern option of the form ">rest-of-line" causes pcretest to - write the compiled pattern to the file whose name is "rest-of-line". - This is a straight binary dump of the data, with the saved pointer to - the character tables forced to be NULL. The study data, if any, is - written too. After writing, pcretest reads a new pattern. - - (ii) If, instead of a pattern, "<rest-of-line" is given, pcretest reads a - compiled pattern from the given file. There must not be any - occurrences of "<" in the file name (pretty unlikely); if there are, - pcretest will instead treat the initial "<" as a pattern delimiter. - After reading in the pattern, pcretest goes on to read data lines as - usual. - - (iii) The F pattern option causes pcretest to flip the bytes in the 32-bit - and 16-bit fields in a compiled pattern, to simulate a pattern that - was compiled on a host of opposite endianness. - -21. The pcre-exec() function can now cope with patterns that were compiled on - hosts of opposite endianness, with this restriction: - - As for any compiled expression that is saved and used later, the tables - pointer field cannot be preserved; the extra_data field in the arguments - to pcre_exec() should be used to pass in a tables address if a value - other than the default internal tables were used at compile time. - -22. Calling pcre_exec() with a negative value of the "ovecsize" parameter is - now diagnosed as an error. Previously, most of the time, a negative number - would have been treated as zero, but if in addition "ovector" was passed as - NULL, a crash could occur. - -23. Updated the files ltmain.sh, config.sub, config.guess, and aclocal.m4 with - new versions from the libtool 1.5 distribution (the last one is a copy of - a file called libtool.m4). This seems to have fixed the need to patch - "configure" to support Darwin 1.3 (which I used to do). However, I still - had to patch ltmain.sh to ensure that ${SED} is set (it isn't on my - workstation). - -24. Changed the PCRE licence to be the more standard "BSD" licence. - - -Version 4.5 01-Dec-03 ---------------------- - - 1. There has been some re-arrangement of the code for the match() function so - that it can be compiled in a version that does not call itself recursively. - Instead, it keeps those local variables that need separate instances for - each "recursion" in a frame on the heap, and gets/frees frames whenever it - needs to "recurse". Keeping track of where control must go is done by means - of setjmp/longjmp. The whole thing is implemented by a set of macros that - hide most of the details from the main code, and operates only if - NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the - "configure" mechanism, "--disable-stack-for-recursion" turns on this way of - operating. - - To make it easier for callers to provide specially tailored get/free - functions for this usage, two new functions, pcre_stack_malloc, and - pcre_stack_free, are used. They are always called in strict stacking order, - and the size of block requested is always the same. - - The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether - PCRE has been compiled to use the stack or the heap for recursion. The - -C option of pcretest uses this to show which version is compiled. - - A new data escape \S, is added to pcretest; it causes the amounts of store - obtained and freed by both kinds of malloc/free at match time to be added - to the output. - - 2. Changed the locale test to use "fr_FR" instead of "fr" because that's - what's available on my current Linux desktop machine. - - 3. When matching a UTF-8 string, the test for a valid string at the start has - been extended. If start_offset is not zero, PCRE now checks that it points - to a byte that is the start of a UTF-8 character. If not, it returns - PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked; - this is necessary because there may be backward assertions in the pattern. - When matching the same subject several times, it may save resources to use - PCRE_NO_UTF8_CHECK on all but the first call if the string is long. - - 4. The code for checking the validity of UTF-8 strings has been tightened so - that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings - containing "overlong sequences". - - 5. Fixed a bug (appearing twice) that I could not find any way of exploiting! - I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&" - should have been "&", but it just so happened that all the cases this let - through by mistake were picked up later in the function. - - 6. I had used a variable called "isblank" - this is a C99 function, causing - some compilers to warn. To avoid this, I renamed it (as "blankclass"). - - 7. Cosmetic: (a) only output another newline at the end of pcretest if it is - prompting; (b) run "./pcretest /dev/null" at the start of the test script - so the version is shown; (c) stop "make test" echoing "./RunTest". - - 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems. - - 9. The prototype for memmove() for systems that don't have it was using - size_t, but the inclusion of the header that defines size_t was later. I've - moved the #includes for the C headers earlier to avoid this. - -10. Added some adjustments to the code to make it easier to compiler on certain - special systems: - - (a) Some "const" qualifiers were missing. - (b) Added the macro EXPORT before all exported functions; by default this - is defined to be empty. - (c) Changed the dftables auxiliary program (that builds chartables.c) so - that it reads its output file name as an argument instead of writing - to the standard output and assuming this can be redirected. - -11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character - class containing characters with values greater than 255, PCRE compilation - went into a loop. - -12. A recursive reference to a subpattern that was within another subpattern - that had a minimum quantifier of zero caused PCRE to crash. For example, - (x(y(?2))z)? provoked this bug with a subject that got as far as the - recursion. If the recursively-called subpattern itself had a zero repeat, - that was OK. - -13. In pcretest, the buffer for reading a data line was set at 30K, but the - buffer into which it was copied (for escape processing) was still set at - 1024, so long lines caused crashes. - -14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error - "internal error: code overflow...". This applied to any character class - that was followed by a possessive quantifier. - -15. Modified the Makefile to add libpcre.la as a prerequisite for - libpcreposix.la because I was told this is needed for a parallel build to - work. - -16. If a pattern that contained .* following optional items at the start was - studied, the wrong optimizing data was generated, leading to matching - errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any - matching string must start with a or b or c. The correct conclusion for - this pattern is that a match can start with any character. - - -Version 4.4 13-Aug-03 ---------------------- - - 1. In UTF-8 mode, a character class containing characters with values between - 127 and 255 was not handled correctly if the compiled pattern was studied. - In fixing this, I have also improved the studying algorithm for such - classes (slightly). - - 2. Three internal functions had redundant arguments passed to them. Removal - might give a very teeny performance improvement. - - 3. Documentation bug: the value of the capture_top field in a callout is *one - more than* the number of the hightest numbered captured substring. - - 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result - in incorrectly linking with a previously installed version. They now link - explicitly with libpcre.la. - - 5. configure.in no longer needs to recognize Cygwin specially. - - 6. A problem in pcre.in for Windows platforms is fixed. - - 7. If a pattern was successfully studied, and the -d (or /D) flag was given to - pcretest, it used to include the size of the study block as part of its - output. Unfortunately, the structure contains a field that has a different - size on different hardware architectures. This meant that the tests that - showed this size failed. As the block is currently always of a fixed size, - this information isn't actually particularly useful in pcretest output, so - I have just removed it. - - 8. Three pre-processor statements accidentally did not start in column 1. - Sadly, there are *still* compilers around that complain, even though - standard C has not required this for well over a decade. Sigh. - - 9. In pcretest, the code for checking callouts passed small integers in the - callout_data field, which is a void * field. However, some picky compilers - complained about the casts involved for this on 64-bit systems. Now - pcretest passes the address of the small integer instead, which should get - rid of the warnings. - -10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at - both compile and run time, and gives an error if an invalid UTF-8 sequence - is found. There is a option for disabling this check in cases where the - string is known to be correct and/or the maximum performance is wanted. - -11. In response to a bug report, I changed one line in Makefile.in from - - -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \ - to - -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \ - - to look similar to other lines, but I have no way of telling whether this - is the right thing to do, as I do not use Windows. No doubt I'll get told - if it's wrong... - - -Version 4.3 21-May-03 ---------------------- - -1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the - Makefile. - -2. Some refactoring to improve the quality of the code: - - (i) The utf8_table... variables are now declared "const". - - (ii) The code for \cx, which used the "case flipping" table to upper case - lower case letters, now just substracts 32. This is ASCII-specific, - but the whole concept of \cx is ASCII-specific, so it seems - reasonable. - - (iii) PCRE was using its character types table to recognize decimal and - hexadecimal digits in the pattern. This is silly, because it handles - only 0-9, a-f, and A-F, but the character types table is locale- - specific, which means strange things might happen. A private - table is now used for this - though it costs 256 bytes, a table is - much faster than multiple explicit tests. Of course, the standard - character types table is still used for matching digits in subject - strings against \d. - - (iv) Strictly, the identifier ESC_t is reserved by POSIX (all identifiers - ending in _t are). So I've renamed it as ESC_tee. - -3. The first argument for regexec() in the POSIX wrapper should have been - defined as "const". - -4. Changed pcretest to use malloc() for its buffers so that they can be - Electric Fenced for debugging. - -5. There were several places in the code where, in UTF-8 mode, PCRE would try - to read one or more bytes before the start of the subject string. Often this - had no effect on PCRE's behaviour, but in some circumstances it could - provoke a segmentation fault. - -6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE - to try to read one or more bytes before the start of the subject string. - -7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with - UTF-8 support could misbehave in various ways if the subject string - contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind - area. (PCRE was not checking for the UTF-8 mode flag, and trying to move - back over UTF-8 characters.) - - -Version 4.2 14-Apr-03 ---------------------- - -1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed. - -2. Changes to the building process, supplied by Ronald Landheer-Cieslak - [ON_WINDOWS]: new variable, "#" on non-Windows platforms - [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms - [WIN_PREFIX]: new variable, "cyg" for Cygwin - * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT - and BUILD_EXEEXT - Note: automatic setting of the BUILD variables is not yet working - set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at - compile-time but not at link-time - [LINK]: use for linking executables only - make different versions for Windows and non-Windows - [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking - libraries - [LINK_FOR_BUILD]: new variable - [OBJEXT]: use throughout - [EXEEXT]: use throughout - <winshared>: new target - <wininstall>: new target - <dftables.o>: use native compiler - <dftables>: use native linker - <install>: handle Windows platform correctly - <clean>: ditto - <check>: ditto - copy DLL to top builddir before testing - - As part of these changes, -no-undefined was removed again. This was reported - to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea - in any case. - -3. Some tidies to get rid of compiler warnings: - - . In the match_data structure, match_limit was an unsigned long int, whereas - match_call_count was an int. I've made them both unsigned long ints. - - . In pcretest the fact that a const uschar * doesn't automatically cast to - a void * provoked a warning. - - . Turning on some more compiler warnings threw up some "shadow" variables - and a few more missing casts. - -4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained a single character with a value between 128 - and 255 (e.g. /[\xFF]/) caused PCRE to crash. - -5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained several characters, but with at least one - whose value was between 128 and 255 caused PCRE to crash. - - -Version 4.1 12-Mar-03 ---------------------- - -1. Compiling with gcc -pedantic found a couple of places where casts were -needed, and a string in dftables.c that was longer than standard compilers are -required to support. - -2. Compiling with Sun's compiler found a few more places where the code could -be tidied up in order to avoid warnings. - -3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the -first of these names is deprecated in the latest Autoconf in favour of the name -CC_FOR_BUILD, because "host" is typically used to mean the system on which the -compiled code will be run. I can't find a reference for HOST_CFLAGS, but by -analogy I have changed it to CFLAGS_FOR_BUILD. - -4. Added -no-undefined to the linking command in the Makefile, because this is -apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the -linking step for the pcreposix library. - -5. PCRE was failing to diagnose the case of two named groups with the same -name. - -6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a -literal character that is needed in the subject for a match, and scans along to -ensure that it is present before embarking on the full matching process. This -saves time in cases of nested unlimited repeats that are never going to match. -Problem: the scan can take a lot of time if the subject is very long (e.g. -megabytes), thus penalizing straightforward matches. It is now done only if the -amount of subject to be scanned is less than 1000 bytes. - -7. A lesser problem with the same optimization is that it was recording the -first character of an anchored pattern as "needed", thus provoking a search -right along the subject, even when the first match of the pattern was going to -fail. The "needed" character is now not set for anchored patterns, unless it -follows something in the pattern that is of non-fixed length. Thus, it still -fulfils its original purpose of finding quick non-matches in cases of nested -unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. - - -Version 4.0 17-Feb-03 ---------------------- - -1. If a comment in an extended regex that started immediately after a meta-item -extended to the end of string, PCRE compiled incorrect data. This could lead to -all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. - -2. Moved to autoconf 2.53 and libtool 1.4.2. - -3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, -the special perltest8 script is no longer needed - all the tests can be run -from a single perltest script. - -4. From 5.004, Perl has not included the VT character (0x0b) in the set defined -by \s. It has now been removed in PCRE. This means it isn't recognized as -whitespace in /x regexes too, which is the same as Perl. Note that the POSIX -class [:space:] *does* include VT, thereby creating a mess. - -5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only -space and tab. - -6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use -its new features into the main test script, reducing the number of scripts. - -7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions -were backward compatible, and made the (?i) apply to the whole pattern, as if -/i were given. Now it behaves more logically, and applies the option setting -only to what follows. PCRE has been changed to follow suit. However, if it -finds options settings right at the start of the pattern, it extracts them into -the global options, as before. Thus, they show up in the info data. - -8. Added support for the \Q...\E escape sequence. Characters in between are -treated as literals. This is slightly different from Perl in that $ and @ are -also handled as literals inside the quotes. In Perl, they will cause variable -interpolation. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - -For compatibility with Perl, \Q...\E sequences are recognized inside character -classes as well as outside them. - -9. Re-organized 3 code statements in pcretest to avoid "overflow in -floating-point constant arithmetic" warnings from a Microsoft compiler. Added a -(size_t) cast to one statement in pcretest and one in pcreposix to avoid -signed/unsigned warnings. - -10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o -option for pcretest, so I've replaced it by a simple function that does just -that job. - -11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or -"pcregrep -". - -12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's -Java package. This provides some syntactic sugar for simple cases of what my -documentation calls "once-only subpatterns". A pattern such as x*+ is the same -as (?>x*). In other words, if what is inside (?>...) is just a single repeated -item, you can use this simplified notation. Note that only makes sense with -greedy quantifiers. Consequently, the use of the possessive quantifier forces -greediness, whatever the setting of the PCRE_UNGREEDY option. - -13. A change of greediness default within a pattern was not taking effect at -the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized -subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option -was abstracted outside. - -14. PCRE now supports the \G assertion. It is true when the current matching -position is at the start point of the match. This differs from \A when the -starting offset is non-zero. Used with the /g option of pcretest (or similar -code), it works in the same way as it does for Perl's /g option. If all -alternatives of a regex begin with \G, the expression is anchored to the start -match position, and the "anchored" flag is set in the compiled expression. - -15. Some bugs concerning the handling of certain option changes within patterns -have been fixed. These applied to options other than (?ims). For example, -"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have -been the other way round. Some of this was related to change 7 above. - -16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX -features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ -and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports -POSIX classes only within a class (e.g. /[[:alpha:]]/). - -17. Added support for Perl's \C escape. This matches one byte, even in UTF8 -mode. Unlike ".", it always matches newline, whatever the setting of -PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind -assertions. Perl allows it, but it doesn't (in general) work because it can't -calculate the length of the lookbehind. At least, that's the case for Perl -5.8.0 - I've been told they are going to document that it doesn't work in -future. - -18. Added an error diagnosis for escapes that PCRE does not support: these are -\L, \l, \N, \P, \p, \U, \u, and \X. - -19. Although correctly diagnosing a missing ']' in a character class, PCRE was -reading past the end of the pattern in cases such as /[abcd/. - -20. PCRE was getting more memory than necessary for patterns with classes that -contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. - -21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for -compiling PCRE for use with Virtual Pascal. - -22. Small fix to the Makefile to make it work properly if the build is done -outside the source tree. - -23. Added a new extension: a condition to go with recursion. If a conditional -subpattern starts with (?(R) the "true" branch is used if recursion has -happened, whereas the "false" branch is used only at the top level. - -24. When there was a very long string of literal characters (over 255 bytes -without UTF support, over 250 bytes with UTF support), the computation of how -much memory was required could be incorrect, leading to segfaults or other -strange effects. - -25. PCRE was incorrectly assuming anchoring (either to start of subject or to -start of line for a non-DOTALL pattern) when a pattern started with (.*) and -there was a subsequent back reference to those brackets. This meant that, for -example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't -possible to check for precisely this case. All we can do is abandon the -optimization if .* occurs inside capturing brackets when there are any back -references whatsoever. (See below for a better fix that came later.) - -26. The handling of the optimization for finding the first character of a -non-anchored pattern, and for finding a character that is required later in the -match were failing in some cases. This didn't break the matching; it just -failed to optimize when it could. The way this is done has been re-implemented. - -27. Fixed typo in error message for invalid (?R item (it said "(?p"). - -28. Added a new feature that provides some of the functionality that Perl -provides with (?{...}). The facility is termed a "callout". The way it is done -in PCRE is for the caller to provide an optional function, by setting -pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a -global variable. By default it is unset, which disables all calling out. To get -the function called, the regex must include (?C) at appropriate points. This -is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). -This provides a means of identifying different callout points. When PCRE -reaches such a point in the regex, if pcre_callout has been set, the external -function is called. It is provided with data in a structure called -pcre_callout_block, which is defined in pcre.h. If the function returns 0, -matching continues; if it returns a non-zero value, the match at the current -point fails. However, backtracking will occur if possible. [This was changed -later and other features added - see item 49 below.] - -29. pcretest is upgraded to test the callout functionality. It provides a -callout function that displays information. By default, it shows the start of -the match and the current position in the text. There are some new data escapes -to vary what happens: - - \C+ in addition, show current contents of captured substrings - \C- do not supply a callout function - \C!n return 1 when callout number n is reached - \C!n!m return 1 when callout number n is reached for the mth time - -30. If pcregrep was called with the -l option and just a single file name, it -output "<stdin>" if a match was found, instead of the file name. - -31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing -slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to -pcre_exec(). This saves a malloc/free per call. The default value of -POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold -when configuring. - -32. The default maximum size of a compiled pattern is 64K. There have been a -few cases of people hitting this limit. The code now uses macros to handle the -storing of links as offsets within the compiled pattern. It defaults to 2-byte -links, but this can be changed to 3 or 4 bytes by --with-link-size when -configuring. Tests 2 and 5 work only with 2-byte links because they output -debugging information about compiled patterns. - -33. Internal code re-arrangements: - -(a) Moved the debugging function for printing out a compiled regex into - its own source file (printint.c) and used #include to pull it into - pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two - separate copies. - -(b) Defined the list of op-code names for debugging as a macro in - internal.h so that it is next to the definition of the opcodes. - -(c) Defined a table of op-code lengths for simpler skipping along compiled - code. This is again a macro in internal.h so that it is next to the - definition of the opcodes. - -34. Added support for recursive calls to individual subpatterns, along the -lines of Robin Houston's patch (but implemented somewhat differently). - -35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to -allow it to read and process whole directories in Win32. This code was -contributed by Lionel Fourquaux; it has not been tested by me. - -36. Added support for named subpatterns. The Python syntax (?P<name>...) is -used to name a group. Names consist of alphanumerics and underscores, and must -be unique. Back references use the syntax (?P=name) and recursive calls use -(?P>name) which is a PCRE extension to the Python extension. Groups still have -numbers. The function pcre_fullinfo() can be used after compilation to extract -a name/number map. There are three relevant calls: - - PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map - PCRE_INFO_NAMECOUNT yields the number of entries - PCRE_INFO_NAMETABLE yields a pointer to the map. - -The map is a vector of fixed-size entries. The size of each entry depends on -the length of the longest name used. The first two bytes of each entry are the -group number, most significant byte first. There follows the corresponding -name, zero terminated. The names are in alphabetical order. - -37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 -case instead of 255. Making it the same both with and without UTF-8 support -means that the same test output works with both. - -38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid -calling malloc() with a zero argument. - -39. Change 25 above had to resort to a heavy-handed test for the .* anchoring -optimization. I've improved things by keeping a bitmap of backreferences with -numbers 1-31 so that if .* occurs inside capturing brackets that are not in -fact referenced, the optimization can be applied. It is unlikely that a -relevant occurrence of .* (i.e. one which might indicate anchoring or forcing -the match to follow \n) will appear inside brackets with a number greater than -31, but if it does, any back reference > 31 suppresses the optimization. - -40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect -of disabling numbered capturing parentheses. Any opening parenthesis that is -not followed by ? behaves as if it were followed by ?: but named parentheses -can still be used for capturing (and they will acquire numbers in the usual -way). - -41. Redesigned the return codes from the match() function into yes/no/error so -that errors can be passed back from deep inside the nested calls. A malloc -failure while inside a recursive subpattern call now causes the -PCRE_ERROR_NOMEMORY return instead of quietly going wrong. - -42. It is now possible to set a limit on the number of times the match() -function is called in a call to pcre_exec(). This facility makes it possible to -limit the amount of recursion and backtracking, though not in a directly -obvious way, because the match() function is used in a number of different -circumstances. The count starts from zero for each position in the subject -string (for non-anchored patterns). The default limit is, for compatibility, a -large number, namely 10 000 000. You can change this in two ways: - -(a) When configuring PCRE before making, you can use --with-match-limit=n - to set a default value for the compiled library. - -(b) For each call to pcre_exec(), you can pass a pcre_extra block in which - a different value is set. See 45 below. - -If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - -43. Added a new function pcre_config(int, void *) to enable run-time extraction -of things that can be changed at compile time. The first argument specifies -what is wanted and the second points to where the information is to be placed. -The current list of available information is: - - PCRE_CONFIG_UTF8 - -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - -The output is an integer that it set to the value of the code that is used for -newline. It is either LF (10) or CR (13). - - PCRE_CONFIG_LINK_SIZE - -The output is an integer that contains the number of bytes used for internal -linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - -The output is an integer that contains the threshold above which the POSIX -interface uses malloc() for output vectors. See item 31 above. - - PCRE_CONFIG_MATCH_LIMIT - -The output is an unsigned integer that contains the default limit of the number -of match() calls in a pcre_exec() execution. See 42 above. - -44. pcretest has been upgraded by the addition of the -C option. This causes it -to extract all the available output from the new pcre_config() function, and to -output it. The program then exits immediately. - -45. A need has arisen to pass over additional data with calls to pcre_exec() in -order to support additional features. One way would have been to define -pcre_exec2() (for example) with extra arguments, but this would not have been -extensible, and would also have required all calls to the original function to -be mapped to the new one. Instead, I have chosen to extend the mechanism that -is used for passing in "extra" data from pcre_study(). - -The pcre_extra structure is now exposed and defined in pcre.h. It currently -contains the following fields: - - flags a bitmap indicating which of the following fields are set - study_data opaque data from pcre_study() - match_limit a way of specifying a limit on match() calls for a specific - call to pcre_exec() - callout_data data for callouts (see 49 below) - -The flag bits are also defined in pcre.h, and are - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - -The pcre_study() function now returns one of these new pcre_extra blocks, with -the actual study data pointed to by the study_data field, and the -PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as -before. That is, this change is entirely upwards-compatible and requires no -change to existing code. - -If you want to pass in additional data to pcre_exec(), you can either place it -in a pcre_extra block provided by pcre_study(), or create your own pcre_extra -block. - -46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a -data string contains the escape sequence \M, pcretest calls pcre_exec() several -times with different match limits, until it finds the minimum value needed for -pcre_exec() to complete. The value is then output. This can be instructive; for -most simple matches the number is quite small, but for pathological cases it -gets very large very quickly. - -47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It -returns the size of the data block pointed to by the study_data field in a -pcre_extra block, that is, the value that was passed as the argument to -pcre_malloc() when PCRE was getting memory in which to place the information -created by pcre_study(). The fourth argument should point to a size_t variable. -pcretest has been extended so that this information is shown after a successful -pcre_study() call when information about the compiled regex is being displayed. - -48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) -because what follows is always an absolute path. (Later: it turns out that this -is more than cosmetic for MinGW, because it doesn't like empty path -components.) - -49. Some changes have been made to the callout feature (see 28 above): - -(i) A callout function now has three choices for what it returns: - - 0 => success, carry on matching - > 0 => failure at this point, but backtrack if possible - < 0 => serious error, return this value from pcre_exec() - - Negative values should normally be chosen from the set of PCRE_ERROR_xxx - values. In particular, returning PCRE_ERROR_NOMATCH forces a standard - "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for - use by callout functions. It will never be used by PCRE itself. - -(ii) The pcre_extra structure (see 45 above) has a void * field called - callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The - pcre_callout_block structure has a field of the same name. The contents of - the field passed in the pcre_extra structure are passed to the callout - function in the corresponding field in the callout block. This makes it - easier to use the same callout-containing regex from multiple threads. For - testing, the pcretest program has a new data escape - - \C*n pass the number n (may be negative) as callout_data - - If the callout function in pcretest receives a non-zero value as - callout_data, it returns that value. - -50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, -there were some redundant $(CFLAGS) in commands that are now specified as -$(LINK), which already includes $(CFLAGS). - -51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE -has been compiled with UTF-8 support *and* pcre_compile() has been compiled -with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume -one-byte characters throughout. Note that case-insensitive matching applies -only to characters whose values are less than 256. PCRE doesn't support the -notion of cases for higher-valued characters. - -(i) A character class whose characters are all within 0-255 is handled as - a bit map, and the map is inverted for negative classes. Previously, a - character > 255 always failed to match such a class; however it should - match if the class was a negative one (e.g. [^ab]). This has been fixed. - -(ii) A negated character class with a single character < 255 is coded as - "not this character" (OP_NOT). This wasn't working properly when the test - character was multibyte, either singly or repeated. - -(iii) Repeats of multibyte characters are now handled correctly in UTF-8 - mode, for example: \x{100}{2,3}. - -(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either - singly or repeated) now correctly test multibyte characters. However, - PCRE doesn't recognize any characters with values greater than 255 as - digits, spaces, or word characters. Such characters always match \D, \S, - and \W, and never match \d, \s, or \w. - -(v) Classes may now contain characters and character ranges with values - greater than 255. For example: [ab\x{100}-\x{400}]. - -(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call - PCRE in UTF-8 mode. - -52. The info request value PCRE_INFO_FIRSTCHAR has been renamed -PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is -retained for backwards compatibility. (Note that LASTLITERAL is also a byte -value.) - -53. The single man page has become too large. I have therefore split it up into -a number of separate man pages. These also give rise to individual HTML pages; -these are now put in a separate directory, and there is an index.html page that -lists them all. Some hyperlinking between the pages has been installed. - -54. Added convenience functions for handling named capturing parentheses. - -55. Unknown escapes inside character classes (e.g. [\M]) and escapes that -aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also -true in PCRE, except when the PCRE_EXTENDED option is set, in which case they -are faulted. - -56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when -calling configure. These values are used when compiling the dftables.c program -which is run to generate the source of the default character tables. They -default to the values of CC and CFLAGS. If you are cross-compiling PCRE, -you will need to set these values. - -57. Updated the building process for Windows DLL, as provided by Fred Cox. - - -Version 3.9 02-Jan-02 ---------------------- - -1. A bit of extraneous text had somehow crept into the pcregrep documentation. - -2. If --disable-static was given, the building process failed when trying to -build pcretest and pcregrep. (For some reason it was using libtool to compile -them, which is not right, as they aren't part of the library.) - - -Version 3.8 18-Dec-01 ---------------------- - -1. The experimental UTF-8 code was completely screwed up. It was packing the -bytes in the wrong order. How dumb can you get? - - -Version 3.7 29-Oct-01 ---------------------- - -1. In updating pcretest to check change 1 of version 3.6, I screwed up. -This caused pcretest, when used on the test data, to segfault. Unfortunately, -this didn't happen under Solaris 8, where I normally test things. - -2. The Makefile had to be changed to make it work on BSD systems, where 'make' -doesn't seem to recognize that ./xxx and xxx are the same file. (This entry -isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made -this fix an hour or so after the initial 3.7 release.) - - -Version 3.6 23-Oct-01 ---------------------- - -1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if -offsets passed as NULL with zero offset count. - -2. The config.guess and config.sub files had not been updated when I moved to -the latest autoconf. - - -Version 3.5 15-Aug-01 ---------------------- - -1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that -had been forgotten. - -2. By using declared but undefined structures, we can avoid using "void" -definitions in pcre.h while keeping the internal definitions of the structures -private. - -3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a -user point of view, this means that both static and shared libraries are built -by default, but this can be individually controlled. More of the work of -handling this static/shared cases is now inside libtool instead of PCRE's make -file. - -4. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -5. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -6. pcre_exec() was referring to its "code" argument before testing that -argument for NULL (and giving an error if it was NULL). - -7. Upgraded Makefile.in to allow for compiling in a different directory from -the source directory. - -8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the -options bits, the pointer it was passed was to an int instead of to an unsigned -long int. This mattered only on 64-bit systems. - -9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is -generated) instead of pcre.in, which it its source. Also made the same change -in several of the .c files. - -10. A new release of gcc defines printf() as a macro, which broke pcretest -because it had an ifdef in the middle of a string argument for printf(). Fixed -by using separate calls to printf(). - -11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -13. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Version 3.4 22-Aug-00 ---------------------- - -1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. - -2. Diagnose condition (?(0) as an error instead of crashing on matching. - - -Version 3.3 01-Aug-00 ---------------------- - -1. If an octal character was given, but the value was greater than \377, it -was not getting masked to the least significant bits, as documented. This could -lead to crashes in some systems. - -2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats -the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. - -3. Added the functions pcre_free_substring() and pcre_free_substring_list(). -These just pass their arguments on to (pcre_free)(), but they are provided -because some uses of PCRE bind it to non-C systems that can call its functions, -but cannot call free() or pcre_free() directly. - -4. Add "make test" as a synonym for "make check". Corrected some comments in -the Makefile. - -5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the -Makefile. - -6. Changed the name of pgrep to pcregrep, because Solaris has introduced a -command called pgrep for grepping around the active processes. - -7. Added the beginnings of support for UTF-8 character strings. - -8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and -RANLIB to ./ltconfig so that they are used by libtool. I think these are all -the relevant ones. (AR is not passed because ./ltconfig does its own figuring -out for the ar command.) - - -Version 3.2 12-May-00 ---------------------- - -This is purely a bug fixing release. - -1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead -of ZA. This was just one example of several cases that could provoke this bug, -which was introduced by change 9 of version 2.00. The code for breaking -infinite loops after an iteration that matches an empty string was't working -correctly. - -2. The pcretest program was not imitating Perl correctly for the pattern /a*/g -when matched against abbab (for example). After matching an empty string, it -wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this -caused it to match further down the string than it should. - -3. The code contained an inclusion of sys/types.h. It isn't clear why this -was there because it doesn't seem to be needed, and it causes trouble on some -systems, as it is not a Standard C header. It has been removed. - -4. Made 4 silly changes to the source to avoid stupid compiler warnings that -were reported on the Macintosh. The changes were from - - while ((c = *(++ptr)) != 0 && c != '\n'); -to - while ((c = *(++ptr)) != 0 && c != '\n') ; - -Totally extraordinary, but if that's what it takes... - -5. PCRE is being used in one environment where neither memmove() nor bcopy() is -available. Added HAVE_BCOPY and an autoconf test for it; if neither -HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which -assumes the way PCRE uses memmove() (always moving upwards). - -6. PCRE is being used in one environment where strchr() is not available. There -was only one use in pcre.c, and writing it out to avoid strchr() probably gives -faster code anyway. - - -Version 3.1 09-Feb-00 ---------------------- - -The only change in this release is the fixing of some bugs in Makefile.in for -the "install" target: - -(1) It was failing to install pcreposix.h. - -(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. - - -Version 3.0 01-Feb-00 ---------------------- - -1. Add support for the /+ modifier to perltest (to output $` like it does in -pcretest). - -2. Add support for the /g modifier to perltest. - -3. Fix pcretest so that it behaves even more like Perl for /g when the pattern -matches null strings. - -4. Fix perltest so that it doesn't do unwanted things when fed an empty -pattern. Perl treats empty patterns specially - it reuses the most recent -pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this -effect. - -5. The POSIX interface was broken in that it was just handing over the POSIX -captured string vector to pcre_exec(), but (since release 2.00) PCRE has -required a bigger vector, with some working space on the end. This means that -the POSIX wrapper now has to get and free some memory, and copy the results. - -6. Added some simple autoconf support, placing the test data and the -documentation in separate directories, re-organizing some of the -information files, and making it build pcre-config (a GNU standard). Also added -libtool support for building PCRE as a shared library, which is now the -default. - -7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and -09 are not valid octal constants. Single digits will be used for minor values -less than 10. - -8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that -existing programs that set these in the POSIX interface can use PCRE without -modification. - -9. Added a new function, pcre_fullinfo() with an extensible interface. It can -return all that pcre_info() returns, plus additional data. The pcre_info() -function is retained for compatibility, but is considered to be obsolete. - -10. Added experimental recursion feature (?R) to handle one common case that -Perl 5.6 will be able to do with (?p{...}). - -11. Added support for POSIX character classes like [:alpha:], which Perl is -adopting. - - -Version 2.08 31-Aug-99 ----------------------- - -1. When startoffset was not zero and the pattern began with ".*", PCRE was not -trying to match at the startoffset position, but instead was moving forward to -the next newline as if a previous match had failed. - -2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, -and could get into a loop if a null string was matched other than at the start -of the subject. - -3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can -be distinguished at compile time, and for completeness also added PCRE_DATE. - -5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL -in GnuWin32 environments. - - -Version 2.07 29-Jul-99 ----------------------- - -1. The documentation is now supplied in plain text form and HTML as well as in -the form of man page sources. - -2. C++ compilers don't like assigning (void *) values to other pointer types. -In particular this affects malloc(). Although there is no problem in Standard -C, I've put in casts to keep C++ compilers happy. - -3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call -should be (const char *). - -4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may -be useful for non-Unix systems who don't want to bother with the POSIX stuff. -However, I haven't made this a standard facility. The documentation doesn't -mention it, and the Makefile doesn't support it. - -5. The Makefile now contains an "install" target, with editable destinations at -the top of the file. The pcretest program is not installed. - -6. pgrep -V now gives the PCRE version number and date. - -7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was -causing the entire string to be ignored, instead of just the last character. - -8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a -non-matching string, it can take a very, very long time, even for strings of -quite modest length, because of the nested recursion. PCRE now does better in -some of these cases. It does this by remembering the last required literal -character in the pattern, and pre-searching the subject to ensure it is present -before running the real match. In other words, it applies a heuristic to detect -some types of certain failure quickly, and in the above example, if presented -with a string that has no trailing " it gives "no match" very quickly. - -9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; -other alternatives are tried instead. - - -Version 2.06 09-Jun-99 ----------------------- - -1. Change pcretest's output for amount of store used to show just the code -space, because the remainder (the data block) varies in size between 32-bit and -64-bit systems. - -2. Added an extra argument to pcre_exec() to supply an offset in the subject to -start matching at. This allows lookbehinds to work when searching for multiple -occurrences in a string. - -3. Added additional options to pcretest for testing multiple occurrences: - - /+ outputs the rest of the string that follows a match - /g loops for multiple occurrences, using the new startoffset argument - /G loops for multiple occurrences by passing an incremented pointer - -4. PCRE wasn't doing the "first character" optimization for patterns starting -with \b or \B, though it was doing it for other lookbehind assertions. That is, -it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with -the letter 'x'. On long subject strings, this gives a significant speed-up. - - -Version 2.05 21-Apr-99 ----------------------- - -1. Changed the type of magic_number from int to long int so that it works -properly on 16-bit systems. - -2. Fixed a bug which caused patterns starting with .* not to work correctly -when the subject string contained newline characters. PCRE was assuming -anchoring for such patterns in all cases, which is not correct because .* will -not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if -DOTALL is set at top level; otherwise it knows that patterns starting with .* -must be retried after every newline in the subject. - - -Version 2.04 18-Feb-99 ----------------------- - -1. For parenthesized subpatterns with repeats whose minimum was zero, the -computation of the store needed to hold the pattern was incorrect (too large). -If such patterns were nested a few deep, this could multiply and become a real -problem. - -2. Added /M option to pcretest to show the memory requirement of a specific -pattern. Made -m a synonym of -s (which does this globally) for compatibility. - -3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being -compiled in such a way that the backtracking after subsequent failure was -pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of -((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. - - -Version 2.03 02-Feb-99 ----------------------- - -1. Fixed typo and small mistake in man page. - -2. Added 4th condition (GPL supersedes if conflict) and created separate -LICENCE file containing the conditions. - -3. Updated pcretest so that patterns such as /abc\/def/ work like they do in -Perl, that is the internal \ allows the delimiter to be included in the -pattern. Locked out the use of \ as a delimiter. If \ immediately follows -the final delimiter, add \ to the end of the pattern (to test the error). - -4. Added the convenience functions for extracting substrings after a successful -match. Updated pcretest to make it able to test these functions. - - -Version 2.02 14-Jan-99 ----------------------- - -1. Initialized the working variables associated with each extraction so that -their saving and restoring doesn't refer to uninitialized store. - -2. Put dummy code into study.c in order to trick the optimizer of the IBM C -compiler for OS/2 into generating correct code. Apparently IBM isn't going to -fix the problem. - -3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution -calls, and wasn't printing the correct value for compiling calls. Increased the -default value of LOOPREPEAT, and the number of significant figures in the -times. - -4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. - -5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid -a building problem on Windows NT with a FAT file system. - - -Version 2.01 21-Oct-98 ----------------------- - -1. Changed the API for pcre_compile() to allow for the provision of a pointer -to character tables built by pcre_maketables() in the current locale. If NULL -is passed, the default tables are used. - - -Version 2.00 24-Sep-98 ----------------------- - -1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable -it any more. - -2. Allow quantification of (?>) groups, and make it work correctly. - -3. The first character computation wasn't working for (?>) groups. - -4. Correct the implementation of \Z (it is permitted to match on the \n at the -end of the subject) and add 5.005's \z, which really does match only at the -very end of the subject. - -5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. - -6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and -DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 -localized options. All options to pcre_study() were also removed. - -7. Add other new features from 5.005: - - $(?<= positive lookbehind - $(?<! negative lookbehind - (?imsx-imsx) added the unsetting capability - such a setting is global if at outer level; local otherwise - (?imsx-imsx:) non-capturing groups with option setting - (?(cond)re|re) conditional pattern matching - - A backreference to itself in a repeated group matches the previous - captured string. - -8. General tidying up of studying (both automatic and via "study") -consequential on the addition of new assertions. - -9. As in 5.005, unlimited repeated groups that could match an empty substring -are no longer faulted at compile time. Instead, the loop is forcibly broken at -runtime if any iteration does actually match an empty substring. - -10. Include the RunTest script in the distribution. - -11. Added tests from the Perl 5.005_02 distribution. This showed up a few -discrepancies, some of which were old and were also with respect to 5.004. They -have now been fixed. - - -Version 1.09 28-Apr-98 ----------------------- - -1. A negated single character class followed by a quantifier with a minimum -value of one (e.g. [^x]{1,6} ) was not compiled correctly. This could lead to -program crashes, or just wrong answers. This did not apply to negated classes -containing more than one character, or to minima other than one. - - -Version 1.08 27-Mar-98 ----------------------- - -1. Add PCRE_UNGREEDY to invert the greediness of quantifiers. - -2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The -latter must appear before anything that relies on it in the pattern. - - -Version 1.07 16-Feb-98 ----------------------- - -1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited -repeat of a potentially empty string). - - -Version 1.06 23-Jan-98 ----------------------- - -1. Added Markus Oberhumer's little patches for C++. - -2. Literal strings longer than 255 characters were broken. - - -Version 1.05 23-Dec-97 ----------------------- - -1. Negated character classes containing more than one character were failing if -PCRE_CASELESS was set at run time. - - -Version 1.04 19-Dec-97 ----------------------- - -1. Corrected the man page, where some "const" qualifiers had been omitted. - -2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with -input syntax. - -3. Fixed memory leak which occurred when a regex with back references was -matched with an offsets vector that wasn't big enough. The temporary memory -that is used in this case wasn't being freed if the match failed. - -4. Tidied pcretest to ensure it frees memory that it gets. - -5. Temporary memory was being obtained in the case where the passed offsets -vector was exactly big enough. - -6. Corrected definition of offsetof() from change 5 below. - -7. I had screwed up change 6 below and broken the rules for the use of -setjmp(). Now fixed. - - -Version 1.03 18-Dec-97 ----------------------- - -1. A erroneous regex with a missing opening parenthesis was correctly -diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes -on some systems. - -2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because -it was reported that one broken compiler failed on the former because "code" is -also an independent variable. - -3. The erroneous regex a[]b caused an array overrun reference. - -4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not -fail on data ending with that character. (It was going on too far, and checking -the next character, typically a binary zero.) This was specific to the -optimized code for single-character negative classes. - -5. Added a contributed patch from the TIN world which does the following: - - + Add an undef for memmove, in case the the system defines a macro for it. - - + Add a definition of offsetof(), in case there isn't one. (I don't know - the reason behind this - offsetof() is part of the ANSI standard - but - it does no harm). - - + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating - most of the places where whitespace preceded '#'. I have given up and - allowed the remaining 2 cases to be at the margin. - - + Rename some variables in pcre to eliminate shadowing. This seems very - pedantic, but does no harm, of course. - -6. Moved the call to setjmp() into its own function, to get rid of warnings -from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used. - -7. Constructs such as \d{8,} were compiling into the equivalent of -\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the -outcome, but in this particular case used more store than had been allocated, -which caused the bug to be discovered because it threw up an internal error. - -8. The debugging code in both pcre and pcretest for outputting the compiled -form of a regex was going wrong in the case of back references followed by -curly-bracketed repeats. - - -Version 1.02 12-Dec-97 ----------------------- - -1. Typos in pcre.3 and comments in the source fixed. - -2. Applied a contributed patch to get rid of places where it used to remove -'const' from variables, and fixed some signed/unsigned and uninitialized -variable warnings. - -3. Added the "runtest" target to Makefile. - -4. Set default compiler flag to -O2 rather than just -O. - - -Version 1.01 19-Nov-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeat of empty string for patterns -like /([ab]*)*/, that is, for classes with more than one character in them. - -2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such -as /((?>a*))*/ (a PCRE_EXTRA facility). - - -Version 1.00 18-Nov-97 ----------------------- - -1. Added compile-time macros to support systems such as SunOS4 which don't have -memmove() or strerror() but have other things that can be used instead. - -2. Arranged that "make clean" removes the executables. - - -Version 0.99 27-Oct-97 ----------------------- - -1. Fixed bug in code for optimizing classes with only one character. It was -initializing a 32-byte map regardless, which could cause it to run off the end -of the memory it had got. - -2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. - - -Version 0.98 22-Oct-97 ----------------------- - -1. Fixed bug in code for handling temporary memory usage when there are more -back references than supplied space in the ovector. This could cause segfaults. - - -Version 0.97 21-Oct-97 ----------------------- - -1. Added the \X "cut" facility, conditional on PCRE_EXTRA. - -2. Optimized negated single characters not to use a bit map. - -3. Brought error texts together as macro definitions; clarified some of them; -fixed one that was wrong - it said "range out of order" when it meant "invalid -escape sequence". - -4. Changed some char * arguments to const char *. - -5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). - -6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in -pcretest. - - -Version 0.96 16-Oct-97 ----------------------- - -1. Added a simple "pgrep" utility to the distribution. - -2. Fixed an incompatibility with Perl: "{" is now treated as a normal character -unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" -where "ddd" means "one or more decimal digits". - -3. Fixed serious bug. If a pattern had a back reference, but the call to -pcre_exec() didn't supply a large enough ovector to record the related -identifying subpattern, the match always failed. PCRE now remembers the number -of the largest back reference, and gets some temporary memory in which to save -the offsets during matching if necessary, in order to ensure that -backreferences always work. - -4. Increased the compatibility with Perl in a number of ways: - - (a) . no longer matches \n by default; an option PCRE_DOTALL is provided - to request this handling. The option can be set at compile or exec time. - - (b) $ matches before a terminating newline by default; an option - PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline - mode). The option can be set at compile or exec time. - - (c) The handling of \ followed by a digit other than 0 is now supposed to be - the same as Perl's. If the decimal number it represents is less than 10 - or there aren't that many previous left capturing parentheses, an octal - escape is read. Inside a character class, it's always an octal escape, - even if it is a single digit. - - (d) An escaped but undefined alphabetic character is taken as a literal, - unless PCRE_EXTRA is set. Currently this just reserves the remaining - escapes. - - (e) {0} is now permitted. (The previous item is removed from the compiled - pattern). - -5. Changed all the names of code files so that the basic parts are no longer -than 10 characters, and abolished the teeny "globals.c" file. - -6. Changed the handling of character classes; they are now done with a 32-byte -bit map always. - -7. Added the -d and /D options to pcretest to make it possible to look at the -internals of compilation without having to recompile pcre. - - -Version 0.95 23-Sep-97 ----------------------- - -1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or -\x20 at the start of a run of normal characters. These were being treated as -real characters, instead of the source characters being re-checked. - - -Version 0.94 18-Sep-97 ----------------------- - -1. The functions are now thread-safe, with the caveat that the global variables -containing pointers to malloc() and free() or alternative functions are the -same for all threads. - -2. Get pcre_study() to generate a bitmap of initial characters for non- -anchored patterns when this is possible, and use it if passed to pcre_exec(). - - -Version 0.93 15-Sep-97 ----------------------- - -1. /(b)|(:+)/ was computing an incorrect first character. - -2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), -but not actually doing anything yet. - -3. Treat "-" characters in classes that cannot be part of ranges as literals, -as Perl does (e.g. [-az] or [az-]). - -4. Set the anchored flag if a branch starts with .* or .*? because that tests -all possible positions. - -5. Split up into different modules to avoid including unneeded functions in a -compiled binary. However, compile and exec are still in one module. The "study" -function is split off. - -6. The character tables are now in a separate module whose source is generated -by an auxiliary program - but can then be edited by hand if required. There are -now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or -toupper() in the code. - -7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and -make them global. Abolish the function for setting them, as the caller can now -set them directly. - - -Version 0.92 11-Sep-97 ----------------------- - -1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character -(e.g. /a{1,3}/) was broken (I mis-optimized it). - -2. Caseless matching was not working in character classes if the characters in -the pattern were in upper case. - -3. Make ranges like [W-c] work in the same way as Perl for caseless matching. - -4. Make PCRE_ANCHORED public and accept as a compile option. - -5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and -PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to -pass them. - -6. Give an error if bad option bits passed at compile or run time. - -7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to -pcretest to cause it to pass that flag. - -8. Add pcre_info(), to get the number of identifying subpatterns, the stored -options, and the first character, if set. - -9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. - - -Version 0.91 10-Sep-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeats of subpatterns that could -match the empty string as in /(a*)*/. It was looping and ultimately crashing. - -2. PCRE was looping on encountering an indefinitely repeated back reference to -a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what -Perl does - treats the match as successful. - -**** diff --git a/src/src/pcre/LICENCE b/src/src/pcre/LICENCE deleted file mode 100644 index 4baa7d83a..000000000 --- a/src/src/pcre/LICENCE +++ /dev/null @@ -1,68 +0,0 @@ -PCRE LICENCE ------------- - -PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - -Release 7 of PCRE is distributed under the terms of the "BSD" licence, as -specified below. The documentation for PCRE, supplied in the "doc" -directory, is distributed under the same terms as the software itself. - -The basic library functions are written in C and are freestanding. Also -included in the distribution is a set of C++ wrapper functions. - - -THE BASIC LIBRARY FUNCTIONS ---------------------------- - -Written by: Philip Hazel -Email local part: ph10 -Email domain: cam.ac.uk - -University of Cambridge Computing Service, -Cambridge, England. - -Copyright (c) 1997-2007 University of Cambridge -All rights reserved. - - -THE C++ WRAPPER FUNCTIONS -------------------------- - -Contributed by: Google Inc. - -Copyright (c) 2007, Google Inc. -All rights reserved. - - -THE "BSD" LICENCE ------------------ - -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the name of Google - Inc. nor the names of their contributors may be used to endorse or - promote products derived from this software without specific prior - written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. - -End diff --git a/src/src/pcre/Makefile b/src/src/pcre/Makefile deleted file mode 100644 index 3979a365c..000000000 --- a/src/src/pcre/Makefile +++ /dev/null @@ -1,88 +0,0 @@ -# $Cambridge: exim/src/src/pcre/Makefile,v 1.9 2007/06/29 08:49:17 ph10 Exp $ - -# Makefile for PCRE (Perl-Compatible Regular Expression) library for use by -# Exim. This is a tailored Makefile, not the normal one that comes with the -# PCRE distribution. - -# These variables are in practice overridden from the Exim Makefile. - -AR = ar cq -CC = gcc -O2 -Wall -CFLAGS = -RANLIB = @true - -############################################################################## - -OBJ = pcre_maketables.o pcre_chartables.o pcre_fullinfo.o pcre_get.o \ - pcre_globals.o pcre_compile.o pcre_config.o pcre_exec.o pcre_newline.o \ - pcre_study.o pcre_tables.o pcre_try_flipped.o pcre_version.o - -all: libpcre.a ../pcretest - -../pcretest: libpcre.a pcretest.o - @echo "$(CC) -o ../pcretest pcretest.o libpcre.a" - $(FE)$(CC) $(CFLAGS) -o ../pcretest pcretest.o libpcre.a - -libpcre.a: $(OBJ) - -rm -f libpcre.a - @echo "$(AR) libpcre.a" - $(FE)$(AR) libpcre.a $(OBJ) - $(RANLIB) libpcre.a - -pcre_chartables.o: pcre_chartables.c pcre_compile.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_chartables.c" - $(FE)$(CC) -c $(CFLAGS) pcre_chartables.c - -pcre_compile.o: pcre_compile.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_compile.c" - $(FE)$(CC) -c $(CFLAGS) pcre_compile.c - -pcre_config.o: pcre_config.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_config.c" - $(FE)$(CC) -c $(CFLAGS) pcre_config.c - -pcre_exec.o: pcre_chartables.c pcre_exec.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_exec.c" - $(FE)$(CC) -c $(CFLAGS) pcre_exec.c - -pcre_maketables.o: pcre_maketables.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_maketables.c" - $(FE)$(CC) -c $(CFLAGS) pcre_maketables.c - -pcre_fullinfo.o: pcre_fullinfo.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_fullinfo.c" - $(FE)$(CC) -c $(CFLAGS) pcre_fullinfo.c - -pcre_get.o: pcre_get.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_get.c" - $(FE)$(CC) -c $(CFLAGS) pcre_get.c - -pcre_globals.o: pcre_globals.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_globals.c" - $(FE)$(CC) -c $(CFLAGS) pcre_globals.c - -pcre_newline.o: pcre_newline.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_newline.c" - $(FE)$(CC) -c $(CFLAGS) pcre_newline.c - -pcre_study.o: pcre_study.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_study.c" - $(FE)$(CC) -c $(CFLAGS) pcre_study.c - -pcre_tables.o: pcre_tables.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_tables.c" - $(FE)$(CC) -c $(CFLAGS) pcre_tables.c - -pcre_try_flipped.o: pcre_try_flipped.c pcre.h config.h pcre_internal.h Makefile - @echo "$(CC) pcre_try_flipped.c" - $(FE)$(CC) -c $(CFLAGS) pcre_try_flipped.c - -pcre_version.o: pcre_version.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcre_version.c" - $(FE)$(CC) -c $(CFLAGS) pcre_version.c - -pcretest.o: pcretest.c config.h pcre.h pcre_internal.h Makefile - @echo "$(CC) pcretest.c" - $(FE)$(CC) -c -DNOPOSIX -DNODFA -DNOUTF8 -DNOINFOCHECK $(CFLAGS) pcretest.c - -# End diff --git a/src/src/pcre/README b/src/src/pcre/README index 07c2c5ad4..ffa40f038 100644 --- a/src/src/pcre/README +++ b/src/src/pcre/README @@ -1,20 +1,16 @@ -$Cambridge: exim/src/src/pcre/README,v 1.1 2004/10/07 13:04:13 ph10 Exp $ +$Cambridge: exim/src/src/pcre/README,v 1.2 2008/01/16 13:44:45 nm4 Exp $ PCRE for use in Exim -------------------- -This directory contains a subset of the files from the PCRE distribution, -enough to supply regular expression support for Exim, plus the pcretest test -program. Do not start from here if you want to install PCRE as a free-standing -library for use by other programs. Get the full PCRE distribution, which can be -obtained from +This directory used to contain a subset of the files from the PCRE distribution. -ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre/pcre-x.x.tar.gz +However carrying our own subset of PCRE, especially when the vast +majority of systems now have PCRE as a system library, has become a +liability, requiring exim to be manually updated whenever changes are +made in PCRE. -where x.x is the version number. This contains support for a POSIX interface to -PCRE, a "grep" program that uses PCRE, and the means to build PCRE as a shared -library. It is configured by autoconf, and has "make install" support in the -conventional way. +PCRE can be found at http://www.pcre.org/ -Philip Hazel <ph10@cam.ac.uk> -February 2000 +Nigel Metheringham +January 2008 diff --git a/src/src/pcre/config.h b/src/src/pcre/config.h deleted file mode 100644 index 1cd8fcfe3..000000000 --- a/src/src/pcre/config.h +++ /dev/null @@ -1,48 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/config.h,v 1.4 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* config.h for PCRE for Exim * -*************************************************/ - -/* The PCRE sources include config.h, which for a free-standing PCRE build gets -set up by autoconf. For the embedded version in Exim, this file, which is -manually maintained, is used. - -The only configuration thing that matters for the PCRE library itself is -whether the memmove() function exists or not. It should be present in all -Standard C libraries, but is missing in SunOS4. PCRE expects autoconf to set -HAVE_MEMMOVE to 1 in config.h when memmove() is present. If that is not set, it -defines memmove() as a macro for bcopy(). - -Exim works differently. It handles this case by defining memmove() as a macro -in its os.h-SunOS4 file. We interface this to PCRE by including the os.h file -here, and then defining HAVE_MEMOVE so that PCRE's code in internal.h leaves -things alone. */ - -#ifndef PCRE_CONFIG_H -#define PCRE_CONFIG_H - -#include "../os.h" -#define HAVE_MEMMOVE 1 - -/* We also set up directly a number of parameters that, in the freestanding -PCRE, can be adjusted by "configure". */ - -#define NEWLINE '\n' -#define LINK_SIZE 2 -#define MATCH_LIMIT 10000000 -#define MATCH_LIMIT_RECURSION 10000000 -#define POSIX_MALLOC_THRESHOLD 10 - -#define MAX_NAME_SIZE 32 -#define MAX_NAME_COUNT 10000 -#define MAX_DUPLENGTH 30000 - -/* There is some stuff in the PCRE sources for compilation on non-Unix systems -and non-ASCII systems. For Exim's purposes, just flatten it. */ - -#undef EBCDIC - -#endif // include once - -/* End */ diff --git a/src/src/pcre/dftables.c b/src/src/pcre/dftables.c deleted file mode 100644 index 33183496f..000000000 --- a/src/src/pcre/dftables.c +++ /dev/null @@ -1,201 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/dftables.c,v 1.7 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This is a freestanding support program to generate a file containing -character tables for PCRE. The tables are built according to the current -locale. Now that pcre_maketables is a function visible to the outside world, we -make use of its code from here in order to be consistent. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <ctype.h> -#include <stdio.h> -#include <string.h> -#include <locale.h> - -#include "pcre_internal.h" - -#define DFTABLES /* pcre_maketables.c notices this */ -#include "pcre_maketables.c" - - -int main(int argc, char **argv) -{ -FILE *f; -int i = 1; -const unsigned char *tables; -const unsigned char *base_of_tables; - -/* By default, the default C locale is used rather than what the building user -happens to have set. However, if the -L option is given, set the locale from -the LC_xxx environment variables. */ - -if (argc > 1 && strcmp(argv[1], "-L") == 0) - { - setlocale(LC_ALL, ""); /* Set from environment variables */ - i++; - } - -if (argc < i + 1) - { - fprintf(stderr, "dftables: one filename argument is required\n"); - return 1; - } - -tables = pcre_maketables(); -base_of_tables = tables; - -f = fopen(argv[i], "wb"); -if (f == NULL) - { - fprintf(stderr, "dftables: failed to open %s for writing\n", argv[1]); - return 1; - } - -/* There are several fprintf() calls here, because gcc in pedantic mode -complains about the very long string otherwise. */ - -fprintf(f, - "/*************************************************\n" - "* Perl-Compatible Regular Expressions *\n" - "*************************************************/\n\n" - "/* This file was automatically written by the dftables auxiliary\n" - "program. It contains character tables that are used when no external\n" - "tables are passed to PCRE by the application that calls it. The tables\n" - "are used only for characters whose code values are less than 256.\n\n"); -fprintf(f, - "The following #includes are present because without them gcc 4.x may remove\n" - "the array definition from the final binary if PCRE is built into a static\n" - "library and dead code stripping is activated. This leads to link errors.\n" - "Pulling in the header ensures that the array gets flagged as \"someone\n" - "outside this compilation unit might reference this\" and so it will always\n" - "be supplied to the linker. */\n\n" - "#ifdef HAVE_CONFIG_H\n" - "#include \"config.h\"\n" - "#endif\n\n" - "#include \"pcre_internal.h\"\n\n"); -fprintf(f, - "const unsigned char _pcre_default_tables[] = {\n\n" - "/* This table is a lower casing table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, "/* This table is a case flipping table. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) fprintf(f, "\n "); - fprintf(f, "%3d", *tables++); - if (i != 255) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table contains bit maps for various character classes.\n" - "Each map is 32 bytes long and the bits run from the least\n" - "significant end of each byte. The classes that have their own\n" - "maps are: space, xdigit, digit, upper, lower, word, graph\n" - "print, punct, and cntrl. Other classes are built from combinations. */\n\n"); - -fprintf(f, " "); -for (i = 0; i < cbit_length; i++) - { - if ((i & 7) == 0 && i != 0) - { - if ((i & 31) == 0) fprintf(f, "\n"); - fprintf(f, "\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != cbit_length - 1) fprintf(f, ","); - } -fprintf(f, ",\n\n"); - -fprintf(f, - "/* This table identifies various classes of character by individual bits:\n" - " 0x%02x white space character\n" - " 0x%02x letter\n" - " 0x%02x decimal digit\n" - " 0x%02x hexadecimal digit\n" - " 0x%02x alphanumeric or '_'\n" - " 0x%02x regular expression metacharacter or binary zero\n*/\n\n", - ctype_space, ctype_letter, ctype_digit, ctype_xdigit, ctype_word, - ctype_meta); - -fprintf(f, " "); -for (i = 0; i < 256; i++) - { - if ((i & 7) == 0 && i != 0) - { - fprintf(f, " /* "); - if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); - if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); - fprintf(f, " */\n "); - } - fprintf(f, "0x%02x", *tables++); - if (i != 255) fprintf(f, ","); - } - -fprintf(f, "};/* "); -if (isprint(i-8)) fprintf(f, " %c -", i-8); - else fprintf(f, "%3d-", i-8); -if (isprint(i-1)) fprintf(f, " %c ", i-1); - else fprintf(f, "%3d", i-1); -fprintf(f, " */\n\n/* End of pcre_chartables.c */\n"); - -fclose(f); -free((void *)base_of_tables); -return 0; -} - -/* End of dftables.c */ diff --git a/src/src/pcre/pcre.h b/src/src/pcre/pcre.h deleted file mode 100644 index 5e37c9270..000000000 --- a/src/src/pcre/pcre.h +++ /dev/null @@ -1,305 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre.h,v 1.7 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This is the public header file for the PCRE library, to be #included by -applications that call the PCRE functions. - - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The current PCRE version information. */ - -#define PCRE_MAJOR 7 -#define PCRE_MINOR 2 -#define PCRE_PRERELEASE -#define PCRE_DATE 2007-06-19 - -/* When an application links to a PCRE DLL in Windows, the symbols that are -imported have to be identified as such. When building PCRE, the appropriate -export setting is defined in pcre_internal.h, which includes this file. So we -don't change existing definitions of PCRE_EXP_DECL and PCRECPP_EXP_DECL. */ - -#if defined(_WIN32) && !defined(PCRE_STATIC) -# ifndef PCRE_EXP_DECL -# define PCRE_EXP_DECL extern __declspec(dllimport) -# endif -# ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern __declspec(dllimport) -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN __declspec(dllimport) -# endif -# endif -#endif - -/* By default, we use the standard "extern" declarations. */ - -#ifndef PCRE_EXP_DECL -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -#endif - -#ifdef __cplusplus -# ifndef PCRECPP_EXP_DECL -# define PCRECPP_EXP_DECL extern -# endif -# ifndef PCRECPP_EXP_DEFN -# define PCRECPP_EXP_DEFN -# endif -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options */ - -#define PCRE_CASELESS 0x00000001 -#define PCRE_MULTILINE 0x00000002 -#define PCRE_DOTALL 0x00000004 -#define PCRE_EXTENDED 0x00000008 -#define PCRE_ANCHORED 0x00000010 -#define PCRE_DOLLAR_ENDONLY 0x00000020 -#define PCRE_EXTRA 0x00000040 -#define PCRE_NOTBOL 0x00000080 -#define PCRE_NOTEOL 0x00000100 -#define PCRE_UNGREEDY 0x00000200 -#define PCRE_NOTEMPTY 0x00000400 -#define PCRE_UTF8 0x00000800 -#define PCRE_NO_AUTO_CAPTURE 0x00001000 -#define PCRE_NO_UTF8_CHECK 0x00002000 -#define PCRE_AUTO_CALLOUT 0x00004000 -#define PCRE_PARTIAL 0x00008000 -#define PCRE_DFA_SHORTEST 0x00010000 -#define PCRE_DFA_RESTART 0x00020000 -#define PCRE_FIRSTLINE 0x00040000 -#define PCRE_DUPNAMES 0x00080000 -#define PCRE_NEWLINE_CR 0x00100000 -#define PCRE_NEWLINE_LF 0x00200000 -#define PCRE_NEWLINE_CRLF 0x00300000 -#define PCRE_NEWLINE_ANY 0x00400000 -#define PCRE_NEWLINE_ANYCRLF 0x00500000 -#define PCRE_BSR_ANYCRLF 0x00800000 -#define PCRE_BSR_UNICODE 0x01000000 - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_OPCODE (-5) -#define PCRE_ERROR_UNKNOWN_NODE (-5) /* For backward compatibility */ -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) -#define PCRE_ERROR_PARTIAL (-12) -#define PCRE_ERROR_BADPARTIAL (-13) -#define PCRE_ERROR_INTERNAL (-14) -#define PCRE_ERROR_BADCOUNT (-15) -#define PCRE_ERROR_DFA_UITEM (-16) -#define PCRE_ERROR_DFA_UCOND (-17) -#define PCRE_ERROR_DFA_UMLIMIT (-18) -#define PCRE_ERROR_DFA_WSSIZE (-19) -#define PCRE_ERROR_DFA_RECURSE (-20) -#define PCRE_ERROR_RECURSIONLIMIT (-21) -#define PCRE_ERROR_NULLWSLIMIT (-22) /* No longer actually used */ -#define PCRE_ERROR_BADNEWLINE (-23) - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 -#define PCRE_INFO_DEFAULT_TABLES 11 -#define PCRE_INFO_OKPARTIAL 12 -#define PCRE_INFO_JCHANGED 13 -#define PCRE_INFO_HASCRORLF 14 - -/* Request types for pcre_config(). Do not re-arrange, in order to remain -compatible. */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 -#define PCRE_CONFIG_UNICODE_PROPERTIES 6 -#define PCRE_CONFIG_MATCH_LIMIT_RECURSION 7 -#define PCRE_CONFIG_BSR 8 - -/* Bit flags for the pcre_extra structure. Do not re-arrange or redefine -these bits, just add new ones on the end, in order to remain compatible. */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 -#define PCRE_EXTRA_TABLES 0x0008 -#define PCRE_EXTRA_MATCH_LIMIT_RECURSION 0x0010 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* When PCRE is compiled as a C++ library, the subject pointer type can be -replaced with a custom type. For conventional use, the public interface is a -const char *. */ - -#ifndef PCRE_SPTR -#define PCRE_SPTR const char * -#endif - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. Always add new fields at the end, in order to -remain compatible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ - const unsigned char *tables; /* Pointer to character tables */ - unsigned long int match_limit_recursion; /* Max recursive calls to match() */ -} pcre_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - PCRE_SPTR subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are in the subject */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------- Added for Version 1 -------------------------- */ - int pattern_position; /* Offset to next item in the pattern */ - int next_item_length; /* Length of next item in the pattern */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. For Virtual Pascal, these definitions -have to take another form. */ - -#ifndef VPCOMPAT -PCRE_EXP_DECL void *(*pcre_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_free)(void *); -PCRE_EXP_DECL void *(*pcre_stack_malloc)(size_t); -PCRE_EXP_DECL void (*pcre_stack_free)(void *); -PCRE_EXP_DECL int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -PCRE_EXP_DECL void *pcre_malloc(size_t); -PCRE_EXP_DECL void pcre_free(void *); -PCRE_EXP_DECL void *pcre_stack_malloc(size_t); -PCRE_EXP_DECL void pcre_stack_free(void *); -PCRE_EXP_DECL int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -PCRE_EXP_DECL pcre *pcre_compile(const char *, int, const char **, int *, - const unsigned char *); -PCRE_EXP_DECL pcre *pcre_compile2(const char *, int, int *, const char **, - int *, const unsigned char *); -PCRE_EXP_DECL int pcre_config(int, void *); -PCRE_EXP_DECL int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -PCRE_EXP_DECL int pcre_copy_substring(const char *, int *, int, int, char *, - int); -PCRE_EXP_DECL int pcre_dfa_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int , int *, int); -PCRE_EXP_DECL int pcre_exec(const pcre *, const pcre_extra *, PCRE_SPTR, - int, int, int, int *, int); -PCRE_EXP_DECL void pcre_free_substring(const char *); -PCRE_EXP_DECL void pcre_free_substring_list(const char **); -PCRE_EXP_DECL int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -PCRE_EXP_DECL int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -PCRE_EXP_DECL int pcre_get_stringnumber(const pcre *, const char *); -PCRE_EXP_DECL int pcre_get_stringtable_entries(const pcre *, const char *, - char **, char **); -PCRE_EXP_DECL int pcre_get_substring(const char *, int *, int, int, - const char **); -PCRE_EXP_DECL int pcre_get_substring_list(const char *, int *, int, - const char ***); -PCRE_EXP_DECL int pcre_info(const pcre *, int *, int *); -PCRE_EXP_DECL const unsigned char *pcre_maketables(void); -PCRE_EXP_DECL int pcre_refcount(pcre *, int); -PCRE_EXP_DECL pcre_extra *pcre_study(const pcre *, int, const char **); -PCRE_EXP_DECL const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/src/src/pcre/pcre_chartables.c b/src/src/pcre/pcre_chartables.c deleted file mode 100644 index 84ae8c91b..000000000 --- a/src/src/pcre/pcre_chartables.c +++ /dev/null @@ -1,200 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_chartables.c,v 1.2 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* This file contains character tables that are used when no external tables -are passed to PCRE by the application that calls it. The tables are used only -for characters whose code values are less than 256. - -This is a default version of the tables that assumes ASCII encoding. A program -called dftables (which is distributed with PCRE) can be used to build -alternative versions of this file. This is necessary if you are running in an -EBCDIC environment, or if you want to default to a different encoding, for -example ISO-8859-1. When dftables is run, it creates these tables in the -current locale. If PCRE is configured with --enable-rebuild-chartables, this -happens automatically. - -The following #includes are present because without the gcc 4.x may remove the -array definition from the final binary if PCRE is built into a static library -and dead code stripping is activated. This leads to link errors. Pulling in the -header ensures that the array gets flagged as "someone outside this compilation -unit might reference this" and so it will always be supplied to the linker. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -const unsigned char _pcre_default_tables[] = { - -/* This table is a lower casing table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table is a case flipping table. */ - - 0, 1, 2, 3, 4, 5, 6, 7, - 8, 9, 10, 11, 12, 13, 14, 15, - 16, 17, 18, 19, 20, 21, 22, 23, - 24, 25, 26, 27, 28, 29, 30, 31, - 32, 33, 34, 35, 36, 37, 38, 39, - 40, 41, 42, 43, 44, 45, 46, 47, - 48, 49, 50, 51, 52, 53, 54, 55, - 56, 57, 58, 59, 60, 61, 62, 63, - 64, 97, 98, 99,100,101,102,103, - 104,105,106,107,108,109,110,111, - 112,113,114,115,116,117,118,119, - 120,121,122, 91, 92, 93, 94, 95, - 96, 65, 66, 67, 68, 69, 70, 71, - 72, 73, 74, 75, 76, 77, 78, 79, - 80, 81, 82, 83, 84, 85, 86, 87, - 88, 89, 90,123,124,125,126,127, - 128,129,130,131,132,133,134,135, - 136,137,138,139,140,141,142,143, - 144,145,146,147,148,149,150,151, - 152,153,154,155,156,157,158,159, - 160,161,162,163,164,165,166,167, - 168,169,170,171,172,173,174,175, - 176,177,178,179,180,181,182,183, - 184,185,186,187,188,189,190,191, - 192,193,194,195,196,197,198,199, - 200,201,202,203,204,205,206,207, - 208,209,210,211,212,213,214,215, - 216,217,218,219,220,221,222,223, - 224,225,226,227,228,229,230,231, - 232,233,234,235,236,237,238,239, - 240,241,242,243,244,245,246,247, - 248,249,250,251,252,253,254,255, - -/* This table contains bit maps for various character classes. Each map is 32 -bytes long and the bits run from the least significant end of each byte. The -classes that have their own maps are: space, xdigit, digit, upper, lower, word, -graph, print, punct, and cntrl. Other classes are built from combinations. */ - - 0x00,0x3e,0x00,0x00,0x01,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x7e,0x00,0x00,0x00,0x7e,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0xfe,0xff,0xff,0x07,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0x00,0x00,0xff,0x03, - 0xfe,0xff,0xff,0x87,0xfe,0xff,0xff,0x07, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xff,0xff,0xff,0xff, - 0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0x00,0x00,0x00,0x00,0xfe,0xff,0x00,0xfc, - 0x01,0x00,0x00,0xf8,0x01,0x00,0x00,0x78, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - - 0xff,0xff,0xff,0xff,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, - -/* This table identifies various classes of character by individual bits: - 0x01 white space character - 0x02 letter - 0x04 decimal digit - 0x08 hexadecimal digit - 0x10 alphanumeric or '_' - 0x80 regular expression metacharacter or binary zero -*/ - - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x01,0x01,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x01,0x00,0x00,0x00,0x80,0x00,0x00,0x00, /* - ' */ - 0x80,0x80,0x80,0x80,0x00,0x00,0x80,0x00, /* ( - / */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x80, /* 8 - ? */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* @ - G */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* H - O */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* P - W */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x80,0x10, /* X - _ */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* ` - g */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* h - o */ - 0x12,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* p - w */ - 0x12,0x12,0x12,0x80,0x80,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -/* End of pcre_chartables.c */ diff --git a/src/src/pcre/pcre_compile.c b/src/src/pcre/pcre_compile.c deleted file mode 100644 index 98c307947..000000000 --- a/src/src/pcre/pcre_compile.c +++ /dev/null @@ -1,6147 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_compile.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_compile(), along with -supporting internal functions that are not used by other modules. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK cd /* Block containing newline information */ -#define PSSTART start_pattern /* Field containing processed string start */ -#define PSEND end_pattern /* Field containing processed string end */ - -#include "pcre_internal.h" - - -/* When DEBUG is defined, we need the pcre_printint() function, which is also -used by pcretest. DEBUG is not defined when building a production library. */ - -#ifdef DEBUG -#include "pcre_printint.src" -#endif - - -/* Macro for setting individual bits in class bitmaps. */ - -#define SETBIT(a,b) a[b/8] |= (1 << (b%8)) - -/* Maximum length value to check against when making sure that the integer that -holds the compiled pattern length does not overflow. We make it a bit less than -INT_MAX to allow for adding in group terminating bytes, so that we don't have -to check them every time. */ - -#define OFLOW_MAX (INT_MAX - 20) - - -/************************************************* -* Code parameters and static tables * -*************************************************/ - -/* This value specifies the size of stack workspace that is used during the -first pre-compile phase that determines how much memory is required. The regex -is partly compiled into this space, but the compiled parts are discarded as -soon as they can be, so that hopefully there will never be an overrun. The code -does, however, check for an overrun. The largest amount I've seen used is 218, -so this number is very generous. - -The same workspace is used during the second, actual compile phase for -remembering forward references to groups so that they can be filled in at the -end. Each entry in this list occupies LINK_SIZE bytes, so even when LINK_SIZE -is 4 there is plenty of room. */ - -#define COMPILE_WORK_SIZE (4096) - - -/* Table for handling escaped characters in the range '0'-'z'. Positive returns -are simple data values; negative values are for special things like \d and so -on. Zero means further processing is needed (for things like \x), or the escape -is invalid. */ - -#ifndef EBCDIC /* This is the "normal" table for ASCII systems */ -static const short int escapes[] = { - 0, 0, 0, 0, 0, 0, 0, 0, /* 0 - 7 */ - 0, 0, ':', ';', '<', '=', '>', '?', /* 8 - ? */ - '@', -ESC_A, -ESC_B, -ESC_C, -ESC_D, -ESC_E, 0, -ESC_G, /* @ - G */ --ESC_H, 0, 0, -ESC_K, 0, 0, 0, 0, /* H - O */ --ESC_P, -ESC_Q, -ESC_R, -ESC_S, 0, 0, -ESC_V, -ESC_W, /* P - W */ --ESC_X, 0, -ESC_Z, '[', '\\', ']', '^', '_', /* X - _ */ - '`', 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, /* ` - g */ --ESC_h, 0, 0, -ESC_k, 0, 0, ESC_n, 0, /* h - o */ --ESC_p, 0, ESC_r, -ESC_s, ESC_tee, 0, -ESC_v, -ESC_w, /* p - w */ - 0, 0, -ESC_z /* x - z */ -}; - -#else /* This is the "abnormal" table for EBCDIC systems */ -static const short int escapes[] = { -/* 48 */ 0, 0, 0, '.', '<', '(', '+', '|', -/* 50 */ '&', 0, 0, 0, 0, 0, 0, 0, -/* 58 */ 0, 0, '!', '$', '*', ')', ';', '~', -/* 60 */ '-', '/', 0, 0, 0, 0, 0, 0, -/* 68 */ 0, 0, '|', ',', '%', '_', '>', '?', -/* 70 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* 78 */ 0, '`', ':', '#', '@', '\'', '=', '"', -/* 80 */ 0, 7, -ESC_b, 0, -ESC_d, ESC_e, ESC_f, 0, -/* 88 */-ESC_h, 0, 0, '{', 0, 0, 0, 0, -/* 90 */ 0, 0, -ESC_k, 'l', 0, ESC_n, 0, -ESC_p, -/* 98 */ 0, ESC_r, 0, '}', 0, 0, 0, 0, -/* A0 */ 0, '~', -ESC_s, ESC_tee, 0,-ESC_v, -ESC_w, 0, -/* A8 */ 0,-ESC_z, 0, 0, 0, '[', 0, 0, -/* B0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* B8 */ 0, 0, 0, 0, 0, ']', '=', '-', -/* C0 */ '{',-ESC_A, -ESC_B, -ESC_C, -ESC_D,-ESC_E, 0, -ESC_G, -/* C8 */-ESC_H, 0, 0, 0, 0, 0, 0, 0, -/* D0 */ '}', 0, -ESC_K, 0, 0, 0, 0, -ESC_P, -/* D8 */-ESC_Q,-ESC_R, 0, 0, 0, 0, 0, 0, -/* E0 */ '\\', 0, -ESC_S, 0, 0,-ESC_V, -ESC_W, -ESC_X, -/* E8 */ 0,-ESC_Z, 0, 0, 0, 0, 0, 0, -/* F0 */ 0, 0, 0, 0, 0, 0, 0, 0, -/* F8 */ 0, 0, 0, 0, 0, 0, 0, 0 -}; -#endif - - -/* Table of special "verbs" like (*PRUNE). This is a short table, so it is -searched linearly. Put all the names into a single string, in order to reduce -the number of relocations when a shared library is dynamically linked. */ - -typedef struct verbitem { - int len; - int op; -} verbitem; - -static const char verbnames[] = - "ACCEPT\0" - "COMMIT\0" - "F\0" - "FAIL\0" - "PRUNE\0" - "SKIP\0" - "THEN"; - -static verbitem verbs[] = { - { 6, OP_ACCEPT }, - { 6, OP_COMMIT }, - { 1, OP_FAIL }, - { 4, OP_FAIL }, - { 5, OP_PRUNE }, - { 4, OP_SKIP }, - { 4, OP_THEN } -}; - -static int verbcount = sizeof(verbs)/sizeof(verbitem); - - -/* Tables of names of POSIX character classes and their lengths. The names are -now all in a single string, to reduce the number of relocations when a shared -library is dynamically loaded. The list of lengths is terminated by a zero -length entry. The first three must be alpha, lower, upper, as this is assumed -for handling case independence. */ - -static const char posix_names[] = - "alpha\0" "lower\0" "upper\0" "alnum\0" "ascii\0" "blank\0" - "cntrl\0" "digit\0" "graph\0" "print\0" "punct\0" "space\0" - "word\0" "xdigit"; - -static const uschar posix_name_lengths[] = { - 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 4, 6, 0 }; - -/* Table of class bit maps for each POSIX class. Each class is formed from a -base map, with an optional addition or removal of another map. Then, for some -classes, there is some additional tweaking: for [:blank:] the vertical space -characters are removed, and for [:alpha:] and [:alnum:] the underscore -character is removed. The triples in the table consist of the base map offset, -second map offset or -1 if no second map, and a non-negative value for map -addition or a negative value for map subtraction (if there are two maps). The -absolute value of the third field has these meanings: 0 => no tweaking, 1 => -remove vertical space characters, 2 => remove underscore. */ - -static const int posix_class_maps[] = { - cbit_word, cbit_digit, -2, /* alpha */ - cbit_lower, -1, 0, /* lower */ - cbit_upper, -1, 0, /* upper */ - cbit_word, -1, 2, /* alnum - word without underscore */ - cbit_print, cbit_cntrl, 0, /* ascii */ - cbit_space, -1, 1, /* blank - a GNU extension */ - cbit_cntrl, -1, 0, /* cntrl */ - cbit_digit, -1, 0, /* digit */ - cbit_graph, -1, 0, /* graph */ - cbit_print, -1, 0, /* print */ - cbit_punct, -1, 0, /* punct */ - cbit_space, -1, 0, /* space */ - cbit_word, -1, 0, /* word - a Perl extension */ - cbit_xdigit,-1, 0 /* xdigit */ -}; - - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* The texts of compile-time error messages. These are "char *" because they -are passed to the outside world. Do not ever re-use any error number, because -they are documented. Always add a new error instead. Messages marked DEAD below -are no longer used. This used to be a table of strings, but in order to reduce -the number of relocations needed when a shared library is loaded dynamically, -it is now one long string. We cannot use a table of offsets, because the -lengths of inserts such as XSTRING(MAX_NAME_SIZE) are not known. Instead, we -simply count through to the one we want - this isn't a performance issue -because these strings are used only when there is a compilation error. */ - -static const char error_texts[] = - "no error\0" - "\\ at end of pattern\0" - "\\c at end of pattern\0" - "unrecognized character follows \\\0" - "numbers out of order in {} quantifier\0" - /* 5 */ - "number too big in {} quantifier\0" - "missing terminating ] for character class\0" - "invalid escape sequence in character class\0" - "range out of order in character class\0" - "nothing to repeat\0" - /* 10 */ - "operand of unlimited repeat could match the empty string\0" /** DEAD **/ - "internal error: unexpected repeat\0" - "unrecognized character after (?\0" - "POSIX named classes are supported only within a class\0" - "missing )\0" - /* 15 */ - "reference to non-existent subpattern\0" - "erroffset passed as NULL\0" - "unknown option bit(s) set\0" - "missing ) after comment\0" - "parentheses nested too deeply\0" /** DEAD **/ - /* 20 */ - "regular expression is too large\0" - "failed to get memory\0" - "unmatched parentheses\0" - "internal error: code overflow\0" - "unrecognized character after (?<\0" - /* 25 */ - "lookbehind assertion is not fixed length\0" - "malformed number or name after (?(\0" - "conditional group contains more than two branches\0" - "assertion expected after (?(\0" - "(?R or (?[+-]digits must be followed by )\0" - /* 30 */ - "unknown POSIX class name\0" - "POSIX collating elements are not supported\0" - "this version of PCRE is not compiled with PCRE_UTF8 support\0" - "spare error\0" /** DEAD **/ - "character value in \\x{...} sequence is too large\0" - /* 35 */ - "invalid condition (?(0)\0" - "\\C not allowed in lookbehind assertion\0" - "PCRE does not support \\L, \\l, \\N, \\U, or \\u\0" - "number after (?C is > 255\0" - "closing ) for (?C expected\0" - /* 40 */ - "recursive call could loop indefinitely\0" - "unrecognized character after (?P\0" - "syntax error in subpattern name (missing terminator)\0" - "two named subpatterns have the same name\0" - "invalid UTF-8 string\0" - /* 45 */ - "support for \\P, \\p, and \\X has not been compiled\0" - "malformed \\P or \\p sequence\0" - "unknown property name after \\P or \\p\0" - "subpattern name is too long (maximum " XSTRING(MAX_NAME_SIZE) " characters)\0" - "too many named subpatterns (maximum " XSTRING(MAX_NAME_COUNT) ")\0" - /* 50 */ - "repeated subpattern is too long\0" /** DEAD **/ - "octal value is greater than \\377 (not in UTF-8 mode)\0" - "internal error: overran compiling workspace\0" - "internal error: previously-checked referenced subpattern not found\0" - "DEFINE group contains more than one branch\0" - /* 55 */ - "repeating a DEFINE group is not allowed\0" - "inconsistent NEWLINE options\0" - "\\g is not followed by a braced name or an optionally braced non-zero number\0" - "(?+ or (?- or (?(+ or (?(- must be followed by a non-zero number\0" - "(*VERB) with an argument is not supported\0" - /* 60 */ - "(*VERB) not recognized\0" - "number is too big"; - - -/* Table to identify digits and hex digits. This is used when compiling -patterns. Note that the tables in chartables are dependent on the locale, and -may mark arbitrary characters as digits - but the PCRE compiling code expects -to handle only 0-9, a-z, and A-Z as digits when compiling. That is why we have -a private table here. It costs 256 bytes, but it is a lot faster than doing -character value tests (at least in some simple cases I timed), and in some -applications one wants PCRE to compile efficiently as well as match -efficiently. - -For convenience, we use the same bit definitions as in chartables: - - 0x04 decimal digit - 0x08 hexadecimal digit - -Then we can use ctype_digit and ctype_xdigit in the code. */ - -#ifndef EBCDIC /* This is the "normal" case, for ASCII systems */ -static const unsigned char digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - ' */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ( - / */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00, /* 8 - ? */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* @ - G */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H - O */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* P - W */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* X - _ */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* ` - g */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h - o */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* p - w */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* x -127 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 128-135 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 136-143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144-151 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 152-159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160-167 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 168-175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 176-183 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 192-199 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 200-207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 208-215 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 216-223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 224-231 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 232-239 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 240-247 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00};/* 248-255 */ - -#else /* This is the "abnormal" case, for EBCDIC systems */ -static const unsigned char digitab[] = - { - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 0- 7 0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 16- 23 10 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 32- 39 20 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 30 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 40 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 50 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 60 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 70 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* 128- g 80 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 144- p 90 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 160- x A0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 B0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x00,0x08,0x08,0x08,0x08,0x08,0x08,0x00, /* { - G C0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* } - P D0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* \ - X E0 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c,0x0c, /* 0 - 7 F0 */ - 0x0c,0x0c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ - -static const unsigned char ebcdic_chartab[] = { /* chartable partial dup */ - 0x80,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 0- 7 */ - 0x00,0x00,0x00,0x00,0x01,0x01,0x00,0x00, /* 8- 15 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 16- 23 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 24- 31 */ - 0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00, /* 32- 39 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 40- 47 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 48- 55 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 56- 63 */ - 0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - 71 */ - 0x00,0x00,0x00,0x80,0x00,0x80,0x80,0x80, /* 72- | */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* & - 87 */ - 0x00,0x00,0x00,0x80,0x80,0x80,0x00,0x00, /* 88- 95 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* - -103 */ - 0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x80, /* 104- ? */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 112-119 */ - 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 120- " */ - 0x00,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* 128- g */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* h -143 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* 144- p */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* q -159 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* 160- x */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* y -175 */ - 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* ^ -183 */ - 0x00,0x00,0x80,0x00,0x00,0x00,0x00,0x00, /* 184-191 */ - 0x80,0x1a,0x1a,0x1a,0x1a,0x1a,0x1a,0x12, /* { - G */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* H -207 */ - 0x00,0x12,0x12,0x12,0x12,0x12,0x12,0x12, /* } - P */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Q -223 */ - 0x00,0x00,0x12,0x12,0x12,0x12,0x12,0x12, /* \ - X */ - 0x12,0x12,0x00,0x00,0x00,0x00,0x00,0x00, /* Y -239 */ - 0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c,0x1c, /* 0 - 7 */ - 0x1c,0x1c,0x00,0x00,0x00,0x00,0x00,0x00};/* 8 -255 */ -#endif - - -/* Definition to allow mutual recursion */ - -static BOOL - compile_regex(int, int, uschar **, const uschar **, int *, BOOL, BOOL, int, - int *, int *, branch_chain *, compile_data *, int *); - - - -/************************************************* -* Find an error text * -*************************************************/ - -/* The error texts are now all in one long string, to save on relocations. As -some of the text is of unknown length, we can't use a table of offsets. -Instead, just count through the strings. This is not a performance issue -because it happens only when there has been a compilation error. - -Argument: the error number -Returns: pointer to the error string -*/ - -static const char * -find_error_text(int n) -{ -const char *s = error_texts; -for (; n > 0; n--) while (*s++ != 0); -return s; -} - - -/************************************************* -* Handle escapes * -*************************************************/ - -/* This function is called when a \ has been encountered. It either returns a -positive value for a simple escape such as \n, or a negative value which -encodes one of the more complicated things such as \d. A backreference to group -n is returned as -(ESC_REF + n); ESC_REF is the highest ESC_xxx macro. When -UTF-8 is enabled, a positive value greater than 255 may be returned. On entry, -ptr is pointing at the \. On exit, it is on the final character of the escape -sequence. - -Arguments: - ptrptr points to the pattern position pointer - errorcodeptr points to the errorcode variable - bracount number of previous extracting brackets - options the options bits - isclass TRUE if inside a character class - -Returns: zero or positive => a data character - negative => a special escape sequence - on error, errorcodeptr is set -*/ - -static int -check_escape(const uschar **ptrptr, int *errorcodeptr, int bracount, - int options, BOOL isclass) -{ -BOOL utf8 = (options & PCRE_UTF8) != 0; -const uschar *ptr = *ptrptr + 1; -int c, i; - -GETCHARINCTEST(c, ptr); /* Get character value, increment pointer */ -ptr--; /* Set pointer back to the last byte */ - -/* If backslash is at the end of the pattern, it's an error. */ - -if (c == 0) *errorcodeptr = ERR1; - -/* Non-alphamerics are literals. For digits or letters, do an initial lookup in -a table. A non-zero result is something that can be returned immediately. -Otherwise further processing may be required. */ - -#ifndef EBCDIC /* ASCII coding */ -else if (c < '0' || c > 'z') {} /* Not alphameric */ -else if ((i = escapes[c - '0']) != 0) c = i; - -#else /* EBCDIC coding */ -else if (c < 'a' || (ebcdic_chartab[c] & 0x0E) == 0) {} /* Not alphameric */ -else if ((i = escapes[c - 0x48]) != 0) c = i; -#endif - -/* Escapes that need further processing, or are illegal. */ - -else - { - const uschar *oldptr; - BOOL braced, negated; - - switch (c) - { - /* A number of Perl escapes are not handled by PCRE. We give an explicit - error. */ - - case 'l': - case 'L': - case 'N': - case 'u': - case 'U': - *errorcodeptr = ERR37; - break; - - /* \g must be followed by a number, either plain or braced. If positive, it - is an absolute backreference. If negative, it is a relative backreference. - This is a Perl 5.10 feature. Perl 5.10 also supports \g{name} as a - reference to a named group. This is part of Perl's movement towards a - unified syntax for back references. As this is synonymous with \k{name}, we - fudge it up by pretending it really was \k. */ - - case 'g': - if (ptr[1] == '{') - { - const uschar *p; - for (p = ptr+2; *p != 0 && *p != '}'; p++) - if (*p != '-' && (digitab[*p] & ctype_digit) == 0) break; - if (*p != 0 && *p != '}') - { - c = -ESC_k; - break; - } - braced = TRUE; - ptr++; - } - else braced = FALSE; - - if (ptr[1] == '-') - { - negated = TRUE; - ptr++; - } - else negated = FALSE; - - c = 0; - while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - '0'; - - if (c < 0) - { - *errorcodeptr = ERR61; - break; - } - - if (c == 0 || (braced && *(++ptr) != '}')) - { - *errorcodeptr = ERR57; - break; - } - - if (negated) - { - if (c > bracount) - { - *errorcodeptr = ERR15; - break; - } - c = bracount - (c - 1); - } - - c = -(ESC_REF + c); - break; - - /* The handling of escape sequences consisting of a string of digits - starting with one that is not zero is not straightforward. By experiment, - the way Perl works seems to be as follows: - - Outside a character class, the digits are read as a decimal number. If the - number is less than 10, or if there are that many previous extracting - left brackets, then it is a back reference. Otherwise, up to three octal - digits are read to form an escaped byte. Thus \123 is likely to be octal - 123 (cf \0123, which is octal 012 followed by the literal 3). If the octal - value is greater than 377, the least significant 8 bits are taken. Inside a - character class, \ followed by a digit is always an octal number. */ - - case '1': case '2': case '3': case '4': case '5': - case '6': case '7': case '8': case '9': - - if (!isclass) - { - oldptr = ptr; - c -= '0'; - while ((digitab[ptr[1]] & ctype_digit) != 0) - c = c * 10 + *(++ptr) - '0'; - if (c < 0) - { - *errorcodeptr = ERR61; - break; - } - if (c < 10 || c <= bracount) - { - c = -(ESC_REF + c); - break; - } - ptr = oldptr; /* Put the pointer back and fall through */ - } - - /* Handle an octal number following \. If the first digit is 8 or 9, Perl - generates a binary zero byte and treats the digit as a following literal. - Thus we have to pull back the pointer by one. */ - - if ((c = *ptr) >= '8') - { - ptr--; - c = 0; - break; - } - - /* \0 always starts an octal number, but we may drop through to here with a - larger first octal digit. The original code used just to take the least - significant 8 bits of octal numbers (I think this is what early Perls used - to do). Nowadays we allow for larger numbers in UTF-8 mode, but no more - than 3 octal digits. */ - - case '0': - c -= '0'; - while(i++ < 2 && ptr[1] >= '0' && ptr[1] <= '7') - c = c * 8 + *(++ptr) - '0'; - if (!utf8 && c > 255) *errorcodeptr = ERR51; - break; - - /* \x is complicated. \x{ddd} is a character number which can be greater - than 0xff in utf8 mode, but only if the ddd are hex digits. If not, { is - treated as a data character. */ - - case 'x': - if (ptr[1] == '{') - { - const uschar *pt = ptr + 2; - int count = 0; - - c = 0; - while ((digitab[*pt] & ctype_xdigit) != 0) - { - register int cc = *pt++; - if (c == 0 && cc == '0') continue; /* Leading zeroes */ - count++; - -#ifndef EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = (c << 4) + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc >= 'a' && cc <= 'z') cc += 64; /* Convert to upper case */ - c = (c << 4) + cc - ((cc >= '0')? '0' : ('A' - 10)); -#endif - } - - if (*pt == '}') - { - if (c < 0 || count > (utf8? 8 : 2)) *errorcodeptr = ERR34; - ptr = pt; - break; - } - - /* If the sequence of hex digits does not end with '}', then we don't - recognize this construct; fall through to the normal \x handling. */ - } - - /* Read just a single-byte hex-defined char */ - - c = 0; - while (i++ < 2 && (digitab[ptr[1]] & ctype_xdigit) != 0) - { - int cc; /* Some compilers don't like ++ */ - cc = *(++ptr); /* in initializers */ -#ifndef EBCDIC /* ASCII coding */ - if (cc >= 'a') cc -= 32; /* Convert to upper case */ - c = c * 16 + cc - ((cc < 'A')? '0' : ('A' - 10)); -#else /* EBCDIC coding */ - if (cc <= 'z') cc += 64; /* Convert to upper case */ - c = c * 16 + cc - ((cc >= '0')? '0' : ('A' - 10)); -#endif - } - break; - - /* For \c, a following letter is upper-cased; then the 0x40 bit is flipped. - This coding is ASCII-specific, but then the whole concept of \cx is - ASCII-specific. (However, an EBCDIC equivalent has now been added.) */ - - case 'c': - c = *(++ptr); - if (c == 0) - { - *errorcodeptr = ERR2; - break; - } - -#ifndef EBCDIC /* ASCII coding */ - if (c >= 'a' && c <= 'z') c -= 32; - c ^= 0x40; -#else /* EBCDIC coding */ - if (c >= 'a' && c <= 'z') c += 64; - c ^= 0xC0; -#endif - break; - - /* PCRE_EXTRA enables extensions to Perl in the matter of escapes. Any - other alphameric following \ is an error if PCRE_EXTRA was set; otherwise, - for Perl compatibility, it is a literal. This code looks a bit odd, but - there used to be some cases other than the default, and there may be again - in future, so I haven't "optimized" it. */ - - default: - if ((options & PCRE_EXTRA) != 0) switch(c) - { - default: - *errorcodeptr = ERR3; - break; - } - break; - } - } - -*ptrptr = ptr; -return c; -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Handle \P and \p * -*************************************************/ - -/* This function is called after \P or \p has been encountered, provided that -PCRE is compiled with support for Unicode properties. On entry, ptrptr is -pointing at the P or p. On exit, it is pointing at the final character of the -escape sequence. - -Argument: - ptrptr points to the pattern position pointer - negptr points to a boolean that is set TRUE for negation else FALSE - dptr points to an int that is set to the detailed property value - errorcodeptr points to the error code variable - -Returns: type value from ucp_type_table, or -1 for an invalid type -*/ - -static int -get_ucp(const uschar **ptrptr, BOOL *negptr, int *dptr, int *errorcodeptr) -{ -int c, i, bot, top; -const uschar *ptr = *ptrptr; -char name[32]; - -c = *(++ptr); -if (c == 0) goto ERROR_RETURN; - -*negptr = FALSE; - -/* \P or \p can be followed by a name in {}, optionally preceded by ^ for -negation. */ - -if (c == '{') - { - if (ptr[1] == '^') - { - *negptr = TRUE; - ptr++; - } - for (i = 0; i < (int)sizeof(name) - 1; i++) - { - c = *(++ptr); - if (c == 0) goto ERROR_RETURN; - if (c == '}') break; - name[i] = c; - } - if (c !='}') goto ERROR_RETURN; - name[i] = 0; - } - -/* Otherwise there is just one following character */ - -else - { - name[0] = c; - name[1] = 0; - } - -*ptrptr = ptr; - -/* Search for a recognized property name using binary chop */ - -bot = 0; -top = _pcre_utt_size; - -while (bot < top) - { - i = (bot + top) >> 1; - c = strcmp(name, _pcre_utt_names + _pcre_utt[i].name_offset); - if (c == 0) - { - *dptr = _pcre_utt[i].value; - return _pcre_utt[i].type; - } - if (c > 0) bot = i + 1; else top = i; - } - -*errorcodeptr = ERR47; -*ptrptr = ptr; -return -1; - -ERROR_RETURN: -*errorcodeptr = ERR46; -*ptrptr = ptr; -return -1; -} -#endif - - - - -/************************************************* -* Check for counted repeat * -*************************************************/ - -/* This function is called when a '{' is encountered in a place where it might -start a quantifier. It looks ahead to see if it really is a quantifier or not. -It is only a quantifier if it is one of the forms {ddd} {ddd,} or {ddd,ddd} -where the ddds are digits. - -Arguments: - p pointer to the first char after '{' - -Returns: TRUE or FALSE -*/ - -static BOOL -is_counted_repeat(const uschar *p) -{ -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; -if (*p == '}') return TRUE; - -if (*p++ != ',') return FALSE; -if (*p == '}') return TRUE; - -if ((digitab[*p++] & ctype_digit) == 0) return FALSE; -while ((digitab[*p] & ctype_digit) != 0) p++; - -return (*p == '}'); -} - - - -/************************************************* -* Read repeat counts * -*************************************************/ - -/* Read an item of the form {n,m} and return the values. This is called only -after is_counted_repeat() has confirmed that a repeat-count quantifier exists, -so the syntax is guaranteed to be correct, but we need to check the values. - -Arguments: - p pointer to first char after '{' - minp pointer to int for min - maxp pointer to int for max - returned as -1 if no max - errorcodeptr points to error code variable - -Returns: pointer to '}' on success; - current ptr on error, with errorcodeptr set non-zero -*/ - -static const uschar * -read_repeat_counts(const uschar *p, int *minp, int *maxp, int *errorcodeptr) -{ -int min = 0; -int max = -1; - -/* Read the minimum value and do a paranoid check: a negative value indicates -an integer overflow. */ - -while ((digitab[*p] & ctype_digit) != 0) min = min * 10 + *p++ - '0'; -if (min < 0 || min > 65535) - { - *errorcodeptr = ERR5; - return p; - } - -/* Read the maximum value if there is one, and again do a paranoid on its size. -Also, max must not be less than min. */ - -if (*p == '}') max = min; else - { - if (*(++p) != '}') - { - max = 0; - while((digitab[*p] & ctype_digit) != 0) max = max * 10 + *p++ - '0'; - if (max < 0 || max > 65535) - { - *errorcodeptr = ERR5; - return p; - } - if (max < min) - { - *errorcodeptr = ERR4; - return p; - } - } - } - -/* Fill in the required variables, and pass back the pointer to the terminating -'}'. */ - -*minp = min; -*maxp = max; -return p; -} - - - -/************************************************* -* Find forward referenced subpattern * -*************************************************/ - -/* This function scans along a pattern's text looking for capturing -subpatterns, and counting them. If it finds a named pattern that matches the -name it is given, it returns its number. Alternatively, if the name is NULL, it -returns when it reaches a given numbered subpattern. This is used for forward -references to subpatterns. We know that if (?P< is encountered, the name will -be terminated by '>' because that is checked in the first pass. - -Arguments: - ptr current position in the pattern - count current count of capturing parens so far encountered - name name to seek, or NULL if seeking a numbered subpattern - lorn name length, or subpattern number if name is NULL - xmode TRUE if we are in /x mode - -Returns: the number of the named subpattern, or -1 if not found -*/ - -static int -find_parens(const uschar *ptr, int count, const uschar *name, int lorn, - BOOL xmode) -{ -const uschar *thisname; - -for (; *ptr != 0; ptr++) - { - int term; - - /* Skip over backslashed characters and also entire \Q...\E */ - - if (*ptr == '\\') - { - if (*(++ptr) == 0) return -1; - if (*ptr == 'Q') for (;;) - { - while (*(++ptr) != 0 && *ptr != '\\'); - if (*ptr == 0) return -1; - if (*(++ptr) == 'E') break; - } - continue; - } - - /* Skip over character classes */ - - if (*ptr == '[') - { - while (*(++ptr) != ']') - { - if (*ptr == 0) return -1; - if (*ptr == '\\') - { - if (*(++ptr) == 0) return -1; - if (*ptr == 'Q') for (;;) - { - while (*(++ptr) != 0 && *ptr != '\\'); - if (*ptr == 0) return -1; - if (*(++ptr) == 'E') break; - } - continue; - } - } - continue; - } - - /* Skip comments in /x mode */ - - if (xmode && *ptr == '#') - { - while (*(++ptr) != 0 && *ptr != '\n'); - if (*ptr == 0) return -1; - continue; - } - - /* An opening parens must now be a real metacharacter */ - - if (*ptr != '(') continue; - if (ptr[1] != '?' && ptr[1] != '*') - { - count++; - if (name == NULL && count == lorn) return count; - continue; - } - - ptr += 2; - if (*ptr == 'P') ptr++; /* Allow optional P */ - - /* We have to disambiguate (?<! and (?<= from (?<name> */ - - if ((*ptr != '<' || ptr[1] == '!' || ptr[1] == '=') && - *ptr != '\'') - continue; - - count++; - - if (name == NULL && count == lorn) return count; - term = *ptr++; - if (term == '<') term = '>'; - thisname = ptr; - while (*ptr != term) ptr++; - if (name != NULL && lorn == ptr - thisname && - strncmp((const char *)name, (const char *)thisname, lorn) == 0) - return count; - } - -return -1; -} - - - -/************************************************* -* Find first significant op code * -*************************************************/ - -/* This is called by several functions that scan a compiled expression looking -for a fixed first character, or an anchoring op code etc. It skips over things -that do not influence this. For some calls, a change of option is important. -For some calls, it makes sense to skip negative forward and all backward -assertions, and also the \b assertion; for others it does not. - -Arguments: - code pointer to the start of the group - options pointer to external options - optbit the option bit whose changing is significant, or - zero if none are - skipassert TRUE if certain assertions are to be skipped - -Returns: pointer to the first significant opcode -*/ - -static const uschar* -first_significant_code(const uschar *code, int *options, int optbit, - BOOL skipassert) -{ -for (;;) - { - switch ((int)*code) - { - case OP_OPT: - if (optbit > 0 && ((int)code[1] & optbit) != (*options & optbit)) - *options = (int)code[1]; - code += 2; - break; - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - if (!skipassert) return code; - do code += GET(code, 1); while (*code == OP_ALT); - code += _pcre_OP_lengths[*code]; - break; - - case OP_WORD_BOUNDARY: - case OP_NOT_WORD_BOUNDARY: - if (!skipassert) return code; - /* Fall through */ - - case OP_CALLOUT: - case OP_CREF: - case OP_RREF: - case OP_DEF: - code += _pcre_OP_lengths[*code]; - break; - - default: - return code; - } - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Find the fixed length of a pattern * -*************************************************/ - -/* Scan a pattern and compute the fixed length of subject that will match it, -if the length is fixed. This is needed for dealing with backward assertions. -In UTF8 mode, the result is in characters rather than bytes. - -Arguments: - code points to the start of the pattern (the bracket) - options the compiling options - -Returns: the fixed length, or -1 if there is no fixed length, - or -2 if \C was encountered -*/ - -static int -find_fixedlength(uschar *code, int options) -{ -int length = -1; - -register int branchlength = 0; -register uschar *cc = code + 1 + LINK_SIZE; - -/* Scan along the opcodes for this branch. If we get to the end of the -branch, check the length against that of the other branches. */ - -for (;;) - { - int d; - register int op = *cc; - switch (op) - { - case OP_CBRA: - case OP_BRA: - case OP_ONCE: - case OP_COND: - d = find_fixedlength(cc + ((op == OP_CBRA)? 2:0), options); - if (d < 0) return d; - branchlength += d; - do cc += GET(cc, 1); while (*cc == OP_ALT); - cc += 1 + LINK_SIZE; - break; - - /* Reached end of a branch; if it's a ket it is the end of a nested - call. If it's ALT it is an alternation in a nested call. If it is - END it's the end of the outer call. All can be handled by the same code. */ - - case OP_ALT: - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_END: - if (length < 0) length = branchlength; - else if (length != branchlength) return -1; - if (*cc != OP_ALT) return length; - cc += 1 + LINK_SIZE; - branchlength = 0; - break; - - /* Skip over assertive subpatterns */ - - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do cc += GET(cc, 1); while (*cc == OP_ALT); - /* Fall through */ - - /* Skip over things that don't match chars */ - - case OP_REVERSE: - case OP_CREF: - case OP_RREF: - case OP_DEF: - case OP_OPT: - case OP_CALLOUT: - case OP_SOD: - case OP_SOM: - case OP_EOD: - case OP_EODN: - case OP_CIRC: - case OP_DOLL: - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - cc += _pcre_OP_lengths[*cc]; - break; - - /* Handle literal characters */ - - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - branchlength++; - cc += 2; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while ((*cc & 0xc0) == 0x80) cc++; - } -#endif - break; - - /* Handle exact repetitions. The count is already in characters, but we - need to skip over a multibyte character in UTF8 mode. */ - - case OP_EXACT: - branchlength += GET2(cc,1); - cc += 4; -#ifdef SUPPORT_UTF8 - if ((options & PCRE_UTF8) != 0) - { - while((*cc & 0x80) == 0x80) cc++; - } -#endif - break; - - case OP_TYPEEXACT: - branchlength += GET2(cc,1); - if (cc[3] == OP_PROP || cc[3] == OP_NOTPROP) cc += 2; - cc += 4; - break; - - /* Handle single-char matchers */ - - case OP_PROP: - case OP_NOTPROP: - cc += 2; - /* Fall through */ - - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - branchlength++; - cc++; - break; - - /* The single-byte matcher isn't allowed */ - - case OP_ANYBYTE: - return -2; - - /* Check a class for variable quantification */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - cc += GET(cc, 1) - 33; - /* Fall through */ -#endif - - case OP_CLASS: - case OP_NCLASS: - cc += 33; - - switch (*cc) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - return -1; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (GET2(cc,1) != GET2(cc,3)) return -1; - branchlength += GET2(cc,1); - cc += 5; - break; - - default: - branchlength++; - } - break; - - /* Anything else is variable length */ - - default: - return -1; - } - } -/* Control never gets here */ -} - - - - -/************************************************* -* Scan compiled regex for numbered bracket * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds a -capturing bracket with the given number. - -Arguments: - code points to start of expression - utf8 TRUE in UTF-8 mode - number the required bracket number - -Returns: pointer to the opcode for the bracket, or NULL if not found -*/ - -static const uschar * -find_bracket(const uschar *code, BOOL utf8, int number) -{ -for (;;) - { - register int c = *code; - if (c == OP_END) return NULL; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Handle capturing bracket */ - - else if (c == OP_CBRA) - { - int n = GET2(code, 1+LINK_SIZE); - if (n == number) return (uschar *)code; - code += _pcre_OP_lengths[c]; - } - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - case OP_TYPEPOSUPTO: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - } - - /* Add in the fixed length from the table */ - - code += _pcre_OP_lengths[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed by - a multi-byte character. The length in the table is a minimum, so we have to - arrange to skip the extra bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; - break; - } -#endif - } - } -} - - - -/************************************************* -* Scan compiled regex for recursion reference * -*************************************************/ - -/* This little function scans through a compiled pattern until it finds an -instance of OP_RECURSE. - -Arguments: - code points to start of expression - utf8 TRUE in UTF-8 mode - -Returns: pointer to the opcode for OP_RECURSE, or NULL if not found -*/ - -static const uschar * -find_recurse(const uschar *code, BOOL utf8) -{ -for (;;) - { - register int c = *code; - if (c == OP_END) return NULL; - if (c == OP_RECURSE) return code; - - /* XCLASS is used for classes that cannot be represented just by a bit - map. This includes negated single high-valued characters. The length in - the table is zero; the actual length is stored in the compiled code. */ - - if (c == OP_XCLASS) code += GET(code, 1); - - /* Otherwise, we can get the item's length from the table, except that for - repeated character types, we have to test for \p and \P, which have an extra - two bytes of parameters. */ - - else - { - switch(c) - { - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSSTAR: - case OP_TYPEPOSPLUS: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - case OP_TYPEPOSUPTO: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEEXACT: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - } - - /* Add in the fixed length from the table */ - - code += _pcre_OP_lengths[c]; - - /* In UTF-8 mode, opcodes that are followed by a character may be followed - by a multi-byte character. The length in the table is a minimum, so we have - to arrange to skip the extra bytes. */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(c) - { - case OP_CHAR: - case OP_CHARNC: - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - if (code[-1] >= 0xc0) code += _pcre_utf8_table4[code[-1] & 0x3f]; - break; - } -#endif - } - } -} - - - -/************************************************* -* Scan compiled branch for non-emptiness * -*************************************************/ - -/* This function scans through a branch of a compiled pattern to see whether it -can match the empty string or not. It is called from could_be_empty() -below and from compile_branch() when checking for an unlimited repeat of a -group that can match nothing. Note that first_significant_code() skips over -assertions. If we hit an unclosed bracket, we return "empty" - this means we've -struck an inner bracket whose current branch will already have been scanned. - -Arguments: - code points to start of search - endcode points to where to stop - utf8 TRUE if in UTF8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty_branch(const uschar *code, const uschar *endcode, BOOL utf8) -{ -register int c; -for (code = first_significant_code(code + _pcre_OP_lengths[*code], NULL, 0, TRUE); - code < endcode; - code = first_significant_code(code + _pcre_OP_lengths[c], NULL, 0, TRUE)) - { - const uschar *ccode; - - c = *code; - - /* Groups with zero repeats can of course be empty; skip them. */ - - if (c == OP_BRAZERO || c == OP_BRAMINZERO) - { - code += _pcre_OP_lengths[c]; - do code += GET(code, 1); while (*code == OP_ALT); - c = *code; - continue; - } - - /* For other groups, scan the branches. */ - - if (c == OP_BRA || c == OP_CBRA || c == OP_ONCE || c == OP_COND) - { - BOOL empty_branch; - if (GET(code, 1) == 0) return TRUE; /* Hit unclosed bracket */ - - /* Scan a closed bracket */ - - empty_branch = FALSE; - do - { - if (!empty_branch && could_be_empty_branch(code, endcode, utf8)) - empty_branch = TRUE; - code += GET(code, 1); - } - while (*code == OP_ALT); - if (!empty_branch) return FALSE; /* All branches are non-empty */ - c = *code; - continue; - } - - /* Handle the other opcodes */ - - switch (c) - { - /* Check for quantifiers after a class. XCLASS is used for classes that - cannot be represented just by a bit map. This includes negated single - high-valued characters. The length in _pcre_OP_lengths[] is zero; the - actual length is stored in the compiled code, so we must update "code" - here. */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - ccode = code += GET(code, 1); - goto CHECK_CLASS_REPEAT; -#endif - - case OP_CLASS: - case OP_NCLASS: - ccode = code + 33; - -#ifdef SUPPORT_UTF8 - CHECK_CLASS_REPEAT: -#endif - - switch (*ccode) - { - case OP_CRSTAR: /* These could be empty; continue */ - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - break; - - default: /* Non-repeat => class must match */ - case OP_CRPLUS: /* These repeats aren't empty */ - case OP_CRMINPLUS: - return FALSE; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (GET2(ccode, 1) > 0) return FALSE; /* Minimum > 0 */ - break; - } - break; - - /* Opcodes that must match a character */ - - case OP_PROP: - case OP_NOTPROP: - case OP_EXTUNI: - case OP_NOT_DIGIT: - case OP_DIGIT: - case OP_NOT_WHITESPACE: - case OP_WHITESPACE: - case OP_NOT_WORDCHAR: - case OP_WORDCHAR: - case OP_ANY: - case OP_ANYBYTE: - case OP_CHAR: - case OP_CHARNC: - case OP_NOT: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_EXACT: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - case OP_NOTEXACT: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEEXACT: - return FALSE; - - /* These are going to continue, as they may be empty, but we have to - fudge the length for the \p and \P cases. */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) code += 2; - break; - - /* Same for these */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) code += 2; - break; - - /* End of branch */ - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - return TRUE; - - /* In UTF-8 mode, STAR, MINSTAR, POSSTAR, QUERY, MINQUERY, POSQUERY, UPTO, - MINUPTO, and POSUPTO may be followed by a multibyte character */ - -#ifdef SUPPORT_UTF8 - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - if (utf8) while ((code[2] & 0xc0) == 0x80) code++; - break; -#endif - } - } - -return TRUE; -} - - - -/************************************************* -* Scan compiled regex for non-emptiness * -*************************************************/ - -/* This function is called to check for left recursive calls. We want to check -the current branch of the current pattern to see if it could match the empty -string. If it could, we must look outwards for branches at other levels, -stopping when we pass beyond the bracket which is the subject of the recursion. - -Arguments: - code points to start of the recursion - endcode points to where to stop (current RECURSE item) - bcptr points to the chain of current (unclosed) branch starts - utf8 TRUE if in UTF-8 mode - -Returns: TRUE if what is matched could be empty -*/ - -static BOOL -could_be_empty(const uschar *code, const uschar *endcode, branch_chain *bcptr, - BOOL utf8) -{ -while (bcptr != NULL && bcptr->current >= code) - { - if (!could_be_empty_branch(bcptr->current, endcode, utf8)) return FALSE; - bcptr = bcptr->outer; - } -return TRUE; -} - - - -/************************************************* -* Check for POSIX class syntax * -*************************************************/ - -/* This function is called when the sequence "[:" or "[." or "[=" is -encountered in a character class. It checks whether this is followed by an -optional ^ and then a sequence of letters, terminated by a matching ":]" or -".]" or "=]". - -Argument: - ptr pointer to the initial [ - endptr where to return the end pointer - cd pointer to compile data - -Returns: TRUE or FALSE -*/ - -static BOOL -check_posix_syntax(const uschar *ptr, const uschar **endptr, compile_data *cd) -{ -int terminator; /* Don't combine these lines; the Solaris cc */ -terminator = *(++ptr); /* compiler warns about "non-constant" initializer. */ -if (*(++ptr) == '^') ptr++; -while ((cd->ctypes[*ptr] & ctype_letter) != 0) ptr++; -if (*ptr == terminator && ptr[1] == ']') - { - *endptr = ptr; - return TRUE; - } -return FALSE; -} - - - - -/************************************************* -* Check POSIX class name * -*************************************************/ - -/* This function is called to check the name given in a POSIX-style class entry -such as [:alnum:]. - -Arguments: - ptr points to the first letter - len the length of the name - -Returns: a value representing the name, or -1 if unknown -*/ - -static int -check_posix_name(const uschar *ptr, int len) -{ -const char *pn = posix_names; -register int yield = 0; -while (posix_name_lengths[yield] != 0) - { - if (len == posix_name_lengths[yield] && - strncmp((const char *)ptr, pn, len) == 0) return yield; - pn += posix_name_lengths[yield] + 1; - yield++; - } -return -1; -} - - -/************************************************* -* Adjust OP_RECURSE items in repeated group * -*************************************************/ - -/* OP_RECURSE items contain an offset from the start of the regex to the group -that is referenced. This means that groups can be replicated for fixed -repetition simply by copying (because the recursion is allowed to refer to -earlier groups that are outside the current group). However, when a group is -optional (i.e. the minimum quantifier is zero), OP_BRAZERO is inserted before -it, after it has been compiled. This means that any OP_RECURSE items within it -that refer to the group itself or any contained groups have to have their -offsets adjusted. That one of the jobs of this function. Before it is called, -the partially compiled regex must be temporarily terminated with OP_END. - -This function has been extended with the possibility of forward references for -recursions and subroutine calls. It must also check the list of such references -for the group we are dealing with. If it finds that one of the recursions in -the current group is on this list, it adjusts the offset in the list, not the -value in the reference (which is a group number). - -Arguments: - group points to the start of the group - adjust the amount by which the group is to be moved - utf8 TRUE in UTF-8 mode - cd contains pointers to tables etc. - save_hwm the hwm forward reference pointer at the start of the group - -Returns: nothing -*/ - -static void -adjust_recurse(uschar *group, int adjust, BOOL utf8, compile_data *cd, - uschar *save_hwm) -{ -uschar *ptr = group; - -while ((ptr = (uschar *)find_recurse(ptr, utf8)) != NULL) - { - int offset; - uschar *hc; - - /* See if this recursion is on the forward reference list. If so, adjust the - reference. */ - - for (hc = save_hwm; hc < cd->hwm; hc += LINK_SIZE) - { - offset = GET(hc, 0); - if (cd->start_code + offset == ptr + 1) - { - PUT(hc, 0, offset + adjust); - break; - } - } - - /* Otherwise, adjust the recursion offset if it's after the start of this - group. */ - - if (hc >= cd->hwm) - { - offset = GET(ptr, 1); - if (cd->start_code + offset >= group) PUT(ptr, 1, offset + adjust); - } - - ptr += 1 + LINK_SIZE; - } -} - - - -/************************************************* -* Insert an automatic callout point * -*************************************************/ - -/* This function is called when the PCRE_AUTO_CALLOUT option is set, to insert -callout points before each pattern item. - -Arguments: - code current code pointer - ptr current pattern pointer - cd pointers to tables etc - -Returns: new code pointer -*/ - -static uschar * -auto_callout(uschar *code, const uschar *ptr, compile_data *cd) -{ -*code++ = OP_CALLOUT; -*code++ = 255; -PUT(code, 0, ptr - cd->start_pattern); /* Pattern offset */ -PUT(code, LINK_SIZE, 0); /* Default length */ -return code + 2*LINK_SIZE; -} - - - -/************************************************* -* Complete a callout item * -*************************************************/ - -/* A callout item contains the length of the next item in the pattern, which -we can't fill in till after we have reached the relevant point. This is used -for both automatic and manual callouts. - -Arguments: - previous_callout points to previous callout item - ptr current pattern pointer - cd pointers to tables etc - -Returns: nothing -*/ - -static void -complete_callout(uschar *previous_callout, const uschar *ptr, compile_data *cd) -{ -int length = ptr - cd->start_pattern - GET(previous_callout, 2); -PUT(previous_callout, 2 + LINK_SIZE, length); -} - - - -#ifdef SUPPORT_UCP -/************************************************* -* Get othercase range * -*************************************************/ - -/* This function is passed the start and end of a class range, in UTF-8 mode -with UCP support. It searches up the characters, looking for internal ranges of -characters in the "other" case. Each call returns the next one, updating the -start address. - -Arguments: - cptr points to starting character value; updated - d end value - ocptr where to put start of othercase range - odptr where to put end of othercase range - -Yield: TRUE when range returned; FALSE when no more -*/ - -static BOOL -get_othercase_range(unsigned int *cptr, unsigned int d, unsigned int *ocptr, - unsigned int *odptr) -{ -unsigned int c, othercase, next; - -for (c = *cptr; c <= d; c++) - { if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR) break; } - -if (c > d) return FALSE; - -*ocptr = othercase; -next = othercase + 1; - -for (++c; c <= d; c++) - { - if (_pcre_ucp_othercase(c) != next) break; - next++; - } - -*odptr = next - 1; -*cptr = c; - -return TRUE; -} -#endif /* SUPPORT_UCP */ - - - -/************************************************* -* Check if auto-possessifying is possible * -*************************************************/ - -/* This function is called for unlimited repeats of certain items, to see -whether the next thing could possibly match the repeated item. If not, it makes -sense to automatically possessify the repeated item. - -Arguments: - op_code the repeated op code - this data for this item, depends on the opcode - utf8 TRUE in UTF-8 mode - utf8_char used for utf8 character bytes, NULL if not relevant - ptr next character in pattern - options options bits - cd contains pointers to tables etc. - -Returns: TRUE if possessifying is wanted -*/ - -static BOOL -check_auto_possessive(int op_code, int item, BOOL utf8, uschar *utf8_char, - const uschar *ptr, int options, compile_data *cd) -{ -int next; - -/* Skip whitespace and comments in extended mode */ - -if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; - if (*ptr == '#') - { - while (*(++ptr) != 0) - if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } - } - else break; - } - } - -/* If the next item is one that we can handle, get its value. A non-negative -value is a character, a negative value is an escape value. */ - -if (*ptr == '\\') - { - int temperrorcode = 0; - next = check_escape(&ptr, &temperrorcode, cd->bracount, options, FALSE); - if (temperrorcode != 0) return FALSE; - ptr++; /* Point after the escape sequence */ - } - -else if ((cd->ctypes[*ptr] & ctype_meta) == 0) - { -#ifdef SUPPORT_UTF8 - if (utf8) { GETCHARINC(next, ptr); } else -#endif - next = *ptr++; - } - -else return FALSE; - -/* Skip whitespace and comments in extended mode */ - -if ((options & PCRE_EXTENDED) != 0) - { - for (;;) - { - while ((cd->ctypes[*ptr] & ctype_space) != 0) ptr++; - if (*ptr == '#') - { - while (*(++ptr) != 0) - if (IS_NEWLINE(ptr)) { ptr += cd->nllen; break; } - } - else break; - } - } - -/* If the next thing is itself optional, we have to give up. */ - -if (*ptr == '*' || *ptr == '?' || strncmp((char *)ptr, "{0,", 3) == 0) - return FALSE; - -/* Now compare the next item with the previous opcode. If the previous is a -positive single character match, "item" either contains the character or, if -"item" is greater than 127 in utf8 mode, the character's bytes are in -utf8_char. */ - - -/* Handle cases when the next item is a character. */ - -if (next >= 0) switch(op_code) - { - case OP_CHAR: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#endif - return item != next; - - /* For CHARNC (caseless character) we must check the other case. If we have - Unicode property support, we can use it to test the other case of - high-valued characters. */ - - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#endif - if (item == next) return FALSE; -#ifdef SUPPORT_UTF8 - if (utf8) - { - unsigned int othercase; - if (next < 128) othercase = cd->fcc[next]; else -#ifdef SUPPORT_UCP - othercase = _pcre_ucp_othercase((unsigned int)next); -#else - othercase = NOTACHAR; -#endif - return (unsigned int)item != othercase; - } - else -#endif /* SUPPORT_UTF8 */ - return (item != cd->fcc[next]); /* Non-UTF-8 mode */ - - /* For OP_NOT, "item" must be a single-byte character. */ - - case OP_NOT: - if (next < 0) return FALSE; /* Not a character */ - if (item == next) return TRUE; - if ((options & PCRE_CASELESS) == 0) return FALSE; -#ifdef SUPPORT_UTF8 - if (utf8) - { - unsigned int othercase; - if (next < 128) othercase = cd->fcc[next]; else -#ifdef SUPPORT_UCP - othercase = _pcre_ucp_othercase(next); -#else - othercase = NOTACHAR; -#endif - return (unsigned int)item == othercase; - } - else -#endif /* SUPPORT_UTF8 */ - return (item == cd->fcc[next]); /* Non-UTF-8 mode */ - - case OP_DIGIT: - return next > 127 || (cd->ctypes[next] & ctype_digit) == 0; - - case OP_NOT_DIGIT: - return next <= 127 && (cd->ctypes[next] & ctype_digit) != 0; - - case OP_WHITESPACE: - return next > 127 || (cd->ctypes[next] & ctype_space) == 0; - - case OP_NOT_WHITESPACE: - return next <= 127 && (cd->ctypes[next] & ctype_space) != 0; - - case OP_WORDCHAR: - return next > 127 || (cd->ctypes[next] & ctype_word) == 0; - - case OP_NOT_WORDCHAR: - return next <= 127 && (cd->ctypes[next] & ctype_word) != 0; - - case OP_HSPACE: - case OP_NOT_HSPACE: - switch(next) - { - case 0x09: - case 0x20: - case 0xa0: - case 0x1680: - case 0x180e: - case 0x2000: - case 0x2001: - case 0x2002: - case 0x2003: - case 0x2004: - case 0x2005: - case 0x2006: - case 0x2007: - case 0x2008: - case 0x2009: - case 0x200A: - case 0x202f: - case 0x205f: - case 0x3000: - return op_code != OP_HSPACE; - default: - return op_code == OP_HSPACE; - } - - case OP_VSPACE: - case OP_NOT_VSPACE: - switch(next) - { - case 0x0a: - case 0x0b: - case 0x0c: - case 0x0d: - case 0x85: - case 0x2028: - case 0x2029: - return op_code != OP_VSPACE; - default: - return op_code == OP_VSPACE; - } - - default: - return FALSE; - } - - -/* Handle the case when the next item is \d, \s, etc. */ - -switch(op_code) - { - case OP_CHAR: - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8 && item > 127) { GETCHAR(item, utf8_char); } -#endif - switch(-next) - { - case ESC_d: - return item > 127 || (cd->ctypes[item] & ctype_digit) == 0; - - case ESC_D: - return item <= 127 && (cd->ctypes[item] & ctype_digit) != 0; - - case ESC_s: - return item > 127 || (cd->ctypes[item] & ctype_space) == 0; - - case ESC_S: - return item <= 127 && (cd->ctypes[item] & ctype_space) != 0; - - case ESC_w: - return item > 127 || (cd->ctypes[item] & ctype_word) == 0; - - case ESC_W: - return item <= 127 && (cd->ctypes[item] & ctype_word) != 0; - - case ESC_h: - case ESC_H: - switch(item) - { - case 0x09: - case 0x20: - case 0xa0: - case 0x1680: - case 0x180e: - case 0x2000: - case 0x2001: - case 0x2002: - case 0x2003: - case 0x2004: - case 0x2005: - case 0x2006: - case 0x2007: - case 0x2008: - case 0x2009: - case 0x200A: - case 0x202f: - case 0x205f: - case 0x3000: - return -next != ESC_h; - default: - return -next == ESC_h; - } - - case ESC_v: - case ESC_V: - switch(item) - { - case 0x0a: - case 0x0b: - case 0x0c: - case 0x0d: - case 0x85: - case 0x2028: - case 0x2029: - return -next != ESC_v; - default: - return -next == ESC_v; - } - - default: - return FALSE; - } - - case OP_DIGIT: - return next == -ESC_D || next == -ESC_s || next == -ESC_W || - next == -ESC_h || next == -ESC_v; - - case OP_NOT_DIGIT: - return next == -ESC_d; - - case OP_WHITESPACE: - return next == -ESC_S || next == -ESC_d || next == -ESC_w; - - case OP_NOT_WHITESPACE: - return next == -ESC_s || next == -ESC_h || next == -ESC_v; - - case OP_HSPACE: - return next == -ESC_S || next == -ESC_H || next == -ESC_d || next == -ESC_w; - - case OP_NOT_HSPACE: - return next == -ESC_h; - - /* Can't have \S in here because VT matches \S (Perl anomaly) */ - case OP_VSPACE: - return next == -ESC_V || next == -ESC_d || next == -ESC_w; - - case OP_NOT_VSPACE: - return next == -ESC_v; - - case OP_WORDCHAR: - return next == -ESC_W || next == -ESC_s || next == -ESC_h || next == -ESC_v; - - case OP_NOT_WORDCHAR: - return next == -ESC_w || next == -ESC_d; - - default: - return FALSE; - } - -/* Control does not reach here */ -} - - - -/************************************************* -* Compile one branch * -*************************************************/ - -/* Scan the pattern, compiling it into the a vector. If the options are -changed during the branch, the pointer is used to change the external options -bits. This function is used during the pre-compile phase when we are trying -to find out the amount of memory needed, as well as during the real compile -phase. The value of lengthptr distinguishes the two phases. - -Arguments: - optionsptr pointer to the option bits - codeptr points to the pointer to the current code point - ptrptr points to the current pattern pointer - errorcodeptr points to error code variable - firstbyteptr set to initial literal character, or < 0 (REQ_UNSET, REQ_NONE) - reqbyteptr set to the last literal character required, else < 0 - bcptr points to current branch chain - cd contains pointers to tables etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success - FALSE, with *errorcodeptr set non-zero on error -*/ - -static BOOL -compile_branch(int *optionsptr, uschar **codeptr, const uschar **ptrptr, - int *errorcodeptr, int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, - compile_data *cd, int *lengthptr) -{ -int repeat_type, op_type; -int repeat_min = 0, repeat_max = 0; /* To please picky compilers */ -int bravalue = 0; -int greedy_default, greedy_non_default; -int firstbyte, reqbyte; -int zeroreqbyte, zerofirstbyte; -int req_caseopt, reqvary, tempreqvary; -int options = *optionsptr; -int after_manual_callout = 0; -int length_prevgroup = 0; -register int c; -register uschar *code = *codeptr; -uschar *last_code = code; -uschar *orig_code = code; -uschar *tempcode; -BOOL inescq = FALSE; -BOOL groupsetfirstbyte = FALSE; -const uschar *ptr = *ptrptr; -const uschar *tempptr; -uschar *previous = NULL; -uschar *previous_callout = NULL; -uschar *save_hwm = NULL; -uschar classbits[32]; - -#ifdef SUPPORT_UTF8 -BOOL class_utf8; -BOOL utf8 = (options & PCRE_UTF8) != 0; -uschar *class_utf8data; -uschar utf8_char[6]; -#else -BOOL utf8 = FALSE; -uschar *utf8_char = NULL; -#endif - -#ifdef DEBUG -if (lengthptr != NULL) DPRINTF((">> start branch\n")); -#endif - -/* Set up the default and non-default settings for greediness */ - -greedy_default = ((options & PCRE_UNGREEDY) != 0); -greedy_non_default = greedy_default ^ 1; - -/* Initialize no first byte, no required byte. REQ_UNSET means "no char -matching encountered yet". It gets changed to REQ_NONE if we hit something that -matches a non-fixed char first char; reqbyte just remains unset if we never -find one. - -When we hit a repeat whose minimum is zero, we may have to adjust these values -to take the zero repeat into account. This is implemented by setting them to -zerofirstbyte and zeroreqbyte when such a repeat is encountered. The individual -item types that can be repeated set these backoff variables appropriately. */ - -firstbyte = reqbyte = zerofirstbyte = zeroreqbyte = REQ_UNSET; - -/* The variable req_caseopt contains either the REQ_CASELESS value or zero, -according to the current setting of the caseless flag. REQ_CASELESS is a bit -value > 255. It is added into the firstbyte or reqbyte variables to record the -case status of the value. This is used only for ASCII characters. */ - -req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - -/* Switch on next character until the end of the branch */ - -for (;; ptr++) - { - BOOL negate_class; - BOOL possessive_quantifier; - BOOL is_quantifier; - BOOL is_recurse; - BOOL reset_bracount; - int class_charcount; - int class_lastchar; - int newoptions; - int recno; - int refsign; - int skipbytes; - int subreqbyte; - int subfirstbyte; - int terminator; - int mclength; - uschar mcbuffer[8]; - - /* Get next byte in the pattern */ - - c = *ptr; - - /* If we are in the pre-compile phase, accumulate the length used for the - previous cycle of this loop. */ - - if (lengthptr != NULL) - { -#ifdef DEBUG - if (code > cd->hwm) cd->hwm = code; /* High water info */ -#endif - if (code > cd->start_workspace + COMPILE_WORK_SIZE) /* Check for overrun */ - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* There is at least one situation where code goes backwards: this is the - case of a zero quantifier after a class (e.g. [ab]{0}). At compile time, - the class is simply eliminated. However, it is created first, so we have to - allow memory for it. Therefore, don't ever reduce the length at this point. - */ - - if (code < last_code) code = last_code; - - /* Paranoid check for integer overflow */ - - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - - *lengthptr += code - last_code; - DPRINTF(("length=%d added %d c=%c\n", *lengthptr, code - last_code, c)); - - /* If "previous" is set and it is not at the start of the work space, move - it back to there, in order to avoid filling up the work space. Otherwise, - if "previous" is NULL, reset the current code pointer to the start. */ - - if (previous != NULL) - { - if (previous > orig_code) - { - memmove(orig_code, previous, code - previous); - code -= previous - orig_code; - previous = orig_code; - } - } - else code = orig_code; - - /* Remember where this code item starts so we can pick up the length - next time round. */ - - last_code = code; - } - - /* In the real compile phase, just check the workspace used by the forward - reference list. */ - - else if (cd->hwm > cd->start_workspace + COMPILE_WORK_SIZE) - { - *errorcodeptr = ERR52; - goto FAILED; - } - - /* If in \Q...\E, check for the end; if not, we have a literal */ - - if (inescq && c != 0) - { - if (c == '\\' && ptr[1] == 'E') - { - inescq = FALSE; - ptr++; - continue; - } - else - { - if (previous_callout != NULL) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - if ((options & PCRE_AUTO_CALLOUT) != 0) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - goto NORMAL_CHAR; - } - } - - /* Fill in length of a previous callout, except when the next thing is - a quantifier. */ - - is_quantifier = c == '*' || c == '+' || c == '?' || - (c == '{' && is_counted_repeat(ptr+1)); - - if (!is_quantifier && previous_callout != NULL && - after_manual_callout-- <= 0) - { - if (lengthptr == NULL) /* Don't attempt in pre-compile phase */ - complete_callout(previous_callout, ptr, cd); - previous_callout = NULL; - } - - /* In extended mode, skip white space and comments */ - - if ((options & PCRE_EXTENDED) != 0) - { - if ((cd->ctypes[c] & ctype_space) != 0) continue; - if (c == '#') - { - while (*(++ptr) != 0) - { - if (IS_NEWLINE(ptr)) { ptr += cd->nllen - 1; break; } - } - if (*ptr != 0) continue; - - /* Else fall through to handle end of string */ - c = 0; - } - } - - /* No auto callout for quantifiers. */ - - if ((options & PCRE_AUTO_CALLOUT) != 0 && !is_quantifier) - { - previous_callout = code; - code = auto_callout(code, ptr, cd); - } - - switch(c) - { - /* ===================================================================*/ - case 0: /* The branch terminates at string end */ - case '|': /* or | or ) */ - case ')': - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - *codeptr = code; - *ptrptr = ptr; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < code - last_code) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += code - last_code; /* To include callout length */ - DPRINTF((">> end branch\n")); - } - return TRUE; - - - /* ===================================================================*/ - /* Handle single-character metacharacters. In multiline mode, ^ disables - the setting of any following char as a first character. */ - - case '^': - if ((options & PCRE_MULTILINE) != 0) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - } - previous = NULL; - *code++ = OP_CIRC; - break; - - case '$': - previous = NULL; - *code++ = OP_DOLL; - break; - - /* There can never be a first char if '.' is first, whatever happens about - repeats. The value of reqbyte doesn't change either. */ - - case '.': - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - previous = code; - *code++ = OP_ANY; - break; - - - /* ===================================================================*/ - /* Character classes. If the included characters are all < 256, we build a - 32-byte bitmap of the permitted characters, except in the special case - where there is only one such character. For negated classes, we build the - map as usual, then invert it at the end. However, we use a different opcode - so that data characters > 255 can be handled correctly. - - If the class contains characters outside the 0-255 range, a different - opcode is compiled. It may optionally have a bit map for characters < 256, - but those above are are explicitly listed afterwards. A flag byte tells - whether the bitmap is present, and whether this is a negated class or not. - */ - - case '[': - previous = code; - - /* PCRE supports POSIX class stuff inside a class. Perl gives an error if - they are encountered at the top level, so we'll do that too. */ - - if ((ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) - { - *errorcodeptr = (ptr[1] == ':')? ERR13 : ERR31; - goto FAILED; - } - - /* If the first character is '^', set the negation flag and skip it. Also, - if the first few characters (either before or after ^) are \Q\E or \E we - skip them too. This makes for compatibility with Perl. */ - - negate_class = FALSE; - for (;;) - { - c = *(++ptr); - if (c == '\\') - { - if (ptr[1] == 'E') ptr++; - else if (strncmp((const char *)ptr+1, "Q\\E", 3) == 0) ptr += 3; - else break; - } - else if (!negate_class && c == '^') - negate_class = TRUE; - else break; - } - - /* Keep a count of chars with values < 256 so that we can optimize the case - of just a single character (as long as it's < 256). However, For higher - valued UTF-8 characters, we don't yet do any optimization. */ - - class_charcount = 0; - class_lastchar = -1; - - /* Initialize the 32-char bit map to all zeros. We build the map in a - temporary bit of memory, in case the class contains only 1 character (less - than 256), because in that case the compiled code doesn't use the bit map. - */ - - memset(classbits, 0, 32 * sizeof(uschar)); - -#ifdef SUPPORT_UTF8 - class_utf8 = FALSE; /* No chars >= 256 */ - class_utf8data = code + LINK_SIZE + 2; /* For UTF-8 items */ -#endif - - /* Process characters until ] is reached. By writing this as a "do" it - means that an initial ] is taken as a data character. At the start of the - loop, c contains the first byte of the character. */ - - if (c != 0) do - { - const uschar *oldptr; - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - { /* Braces are required because the */ - GETCHARLEN(c, ptr, ptr); /* macro generates multiple statements */ - } -#endif - - /* Inside \Q...\E everything is literal except \E */ - - if (inescq) - { - if (c == '\\' && ptr[1] == 'E') /* If we are at \E */ - { - inescq = FALSE; /* Reset literal state */ - ptr++; /* Skip the 'E' */ - continue; /* Carry on with next */ - } - goto CHECK_RANGE; /* Could be range if \E follows */ - } - - /* Handle POSIX class names. Perl allows a negation extension of the - form [:^name:]. A square bracket that doesn't match the syntax is - treated as a literal. We also recognize the POSIX constructions - [.ch.] and [=ch=] ("collating elements") and fault them, as Perl - 5.6 and 5.8 do. */ - - if (c == '[' && - (ptr[1] == ':' || ptr[1] == '.' || ptr[1] == '=') && - check_posix_syntax(ptr, &tempptr, cd)) - { - BOOL local_negate = FALSE; - int posix_class, taboffset, tabopt; - register const uschar *cbits = cd->cbits; - uschar pbits[32]; - - if (ptr[1] != ':') - { - *errorcodeptr = ERR31; - goto FAILED; - } - - ptr += 2; - if (*ptr == '^') - { - local_negate = TRUE; - ptr++; - } - - posix_class = check_posix_name(ptr, tempptr - ptr); - if (posix_class < 0) - { - *errorcodeptr = ERR30; - goto FAILED; - } - - /* If matching is caseless, upper and lower are converted to - alpha. This relies on the fact that the class table starts with - alpha, lower, upper as the first 3 entries. */ - - if ((options & PCRE_CASELESS) != 0 && posix_class <= 2) - posix_class = 0; - - /* We build the bit map for the POSIX class in a chunk of local store - because we may be adding and subtracting from it, and we don't want to - subtract bits that may be in the main map already. At the end we or the - result into the bit map that is being built. */ - - posix_class *= 3; - - /* Copy in the first table (always present) */ - - memcpy(pbits, cbits + posix_class_maps[posix_class], - 32 * sizeof(uschar)); - - /* If there is a second table, add or remove it as required. */ - - taboffset = posix_class_maps[posix_class + 1]; - tabopt = posix_class_maps[posix_class + 2]; - - if (taboffset >= 0) - { - if (tabopt >= 0) - for (c = 0; c < 32; c++) pbits[c] |= cbits[c + taboffset]; - else - for (c = 0; c < 32; c++) pbits[c] &= ~cbits[c + taboffset]; - } - - /* Not see if we need to remove any special characters. An option - value of 1 removes vertical space and 2 removes underscore. */ - - if (tabopt < 0) tabopt = -tabopt; - if (tabopt == 1) pbits[1] &= ~0x3c; - else if (tabopt == 2) pbits[11] &= 0x7f; - - /* Add the POSIX table or its complement into the main table that is - being built and we are done. */ - - if (local_negate) - for (c = 0; c < 32; c++) classbits[c] |= ~pbits[c]; - else - for (c = 0; c < 32; c++) classbits[c] |= pbits[c]; - - ptr = tempptr + 1; - class_charcount = 10; /* Set > 1; assumes more than 1 per class */ - continue; /* End of POSIX syntax handling */ - } - - /* Backslash may introduce a single character, or it may introduce one - of the specials, which just set a flag. The sequence \b is a special - case. Inside a class (and only there) it is treated as backspace. - Elsewhere it marks a word boundary. Other escapes have preset maps ready - to 'or' into the one we are building. We assume they have more than one - character in them, so set class_charcount bigger than one. */ - - if (c == '\\') - { - c = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - if (-c == ESC_b) c = '\b'; /* \b is backslash in a class */ - else if (-c == ESC_X) c = 'X'; /* \X is literal X in a class */ - else if (-c == ESC_R) c = 'R'; /* \R is literal R in a class */ - else if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == '\\' && ptr[2] == 'E') - { - ptr += 2; /* avoid empty string */ - } - else inescq = TRUE; - continue; - } - else if (-c == ESC_E) continue; /* Ignore orphan \E */ - - if (c < 0) - { - register const uschar *cbits = cd->cbits; - class_charcount += 2; /* Greater than 1 is what matters */ - - /* Save time by not doing this in the pre-compile phase. */ - - if (lengthptr == NULL) switch (-c) - { - case ESC_d: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_digit]; - continue; - - case ESC_D: - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_digit]; - continue; - - case ESC_w: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_word]; - continue; - - case ESC_W: - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_word]; - continue; - - case ESC_s: - for (c = 0; c < 32; c++) classbits[c] |= cbits[c+cbit_space]; - classbits[1] &= ~0x08; /* Perl 5.004 onwards omits VT from \s */ - continue; - - case ESC_S: - for (c = 0; c < 32; c++) classbits[c] |= ~cbits[c+cbit_space]; - classbits[1] |= 0x08; /* Perl 5.004 onwards omits VT from \s */ - continue; - - case ESC_E: /* Perl ignores an orphan \E */ - continue; - - default: /* Not recognized; fall through */ - break; /* Need "default" setting to stop compiler warning. */ - } - - /* In the pre-compile phase, just do the recognition. */ - - else if (c == -ESC_d || c == -ESC_D || c == -ESC_w || - c == -ESC_W || c == -ESC_s || c == -ESC_S) continue; - - /* We need to deal with \H, \h, \V, and \v in both phases because - they use extra memory. */ - - if (-c == ESC_h) - { - SETBIT(classbits, 0x09); /* VT */ - SETBIT(classbits, 0x20); /* SPACE */ - SETBIT(classbits, 0xa0); /* NSBP */ -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x1680, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x180e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2000, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x200A, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x202f, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x205f, class_utf8data); - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(0x3000, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_H) - { - for (c = 0; c < 32; c++) - { - int x = 0xff; - switch (c) - { - case 0x09/8: x ^= 1 << (0x09%8); break; - case 0x20/8: x ^= 1 << (0x20%8); break; - case 0xa0/8: x ^= 1 << (0xa0%8); break; - default: break; - } - classbits[c] |= x; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x167f, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x1681, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x180d, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x180f, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x1fff, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x200B, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x202e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2030, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x205e, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2060, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2fff, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x3001, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_v) - { - SETBIT(classbits, 0x0a); /* LF */ - SETBIT(classbits, 0x0b); /* VT */ - SETBIT(classbits, 0x0c); /* FF */ - SETBIT(classbits, 0x0d); /* CR */ - SETBIT(classbits, 0x85); /* NEL */ -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2028, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); - } -#endif - continue; - } - - if (-c == ESC_V) - { - for (c = 0; c < 32; c++) - { - int x = 0xff; - switch (c) - { - case 0x0a/8: x ^= 1 << (0x0a%8); - x ^= 1 << (0x0b%8); - x ^= 1 << (0x0c%8); - x ^= 1 << (0x0d%8); - break; - case 0x85/8: x ^= 1 << (0x85%8); break; - default: break; - } - classbits[c] |= x; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x0100, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x2027, class_utf8data); - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(0x2029, class_utf8data); - class_utf8data += _pcre_ord2utf8(0x7fffffff, class_utf8data); - } -#endif - continue; - } - - /* We need to deal with \P and \p in both phases. */ - -#ifdef SUPPORT_UCP - if (-c == ESC_p || -c == ESC_P) - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; - class_utf8 = TRUE; - *class_utf8data++ = ((-c == ESC_p) != negated)? - XCL_PROP : XCL_NOTPROP; - *class_utf8data++ = ptype; - *class_utf8data++ = pdata; - class_charcount -= 2; /* Not a < 256 character */ - continue; - } -#endif - /* Unrecognized escapes are faulted if PCRE is running in its - strict mode. By default, for compatibility with Perl, they are - treated as literals. */ - - if ((options & PCRE_EXTRA) != 0) - { - *errorcodeptr = ERR7; - goto FAILED; - } - - class_charcount -= 2; /* Undo the default count from above */ - c = *ptr; /* Get the final character and fall through */ - } - - /* Fall through if we have a single character (c >= 0). This may be - greater than 256 in UTF-8 mode. */ - - } /* End of backslash handling */ - - /* A single character may be followed by '-' to form a range. However, - Perl does not permit ']' to be the end of the range. A '-' character - at the end is treated as a literal. Perl ignores orphaned \E sequences - entirely. The code for handling \Q and \E is messy. */ - - CHECK_RANGE: - while (ptr[1] == '\\' && ptr[2] == 'E') - { - inescq = FALSE; - ptr += 2; - } - - oldptr = ptr; - - /* Remember \r or \n */ - - if (c == '\r' || c == '\n') cd->external_flags |= PCRE_HASCRORLF; - - /* Check for range */ - - if (!inescq && ptr[1] == '-') - { - int d; - ptr += 2; - while (*ptr == '\\' && ptr[1] == 'E') ptr += 2; - - /* If we hit \Q (not followed by \E) at this point, go into escaped - mode. */ - - while (*ptr == '\\' && ptr[1] == 'Q') - { - ptr += 2; - if (*ptr == '\\' && ptr[1] == 'E') { ptr += 2; continue; } - inescq = TRUE; - break; - } - - if (*ptr == 0 || (!inescq && *ptr == ']')) - { - ptr = oldptr; - goto LONE_SINGLE_CHARACTER; - } - -#ifdef SUPPORT_UTF8 - if (utf8) - { /* Braces are required because the */ - GETCHARLEN(d, ptr, ptr); /* macro generates multiple statements */ - } - else -#endif - d = *ptr; /* Not UTF-8 mode */ - - /* The second part of a range can be a single-character escape, but - not any of the other escapes. Perl 5.6 treats a hyphen as a literal - in such circumstances. */ - - if (!inescq && d == '\\') - { - d = check_escape(&ptr, errorcodeptr, cd->bracount, options, TRUE); - if (*errorcodeptr != 0) goto FAILED; - - /* \b is backslash; \X is literal X; \R is literal R; any other - special means the '-' was literal */ - - if (d < 0) - { - if (d == -ESC_b) d = '\b'; - else if (d == -ESC_X) d = 'X'; - else if (d == -ESC_R) d = 'R'; else - { - ptr = oldptr; - goto LONE_SINGLE_CHARACTER; /* A few lines below */ - } - } - } - - /* Check that the two values are in the correct order. Optimize - one-character ranges */ - - if (d < c) - { - *errorcodeptr = ERR8; - goto FAILED; - } - - if (d == c) goto LONE_SINGLE_CHARACTER; /* A few lines below */ - - /* Remember \r or \n */ - - if (d == '\r' || d == '\n') cd->external_flags |= PCRE_HASCRORLF; - - /* In UTF-8 mode, if the upper limit is > 255, or > 127 for caseless - matching, we have to use an XCLASS with extra data items. Caseless - matching for characters > 127 is available only if UCP support is - available. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (d > 255 || ((options & PCRE_CASELESS) != 0 && d > 127))) - { - class_utf8 = TRUE; - - /* With UCP support, we can find the other case equivalents of - the relevant characters. There may be several ranges. Optimize how - they fit with the basic range. */ - -#ifdef SUPPORT_UCP - if ((options & PCRE_CASELESS) != 0) - { - unsigned int occ, ocd; - unsigned int cc = c; - unsigned int origd = d; - while (get_othercase_range(&cc, origd, &occ, &ocd)) - { - if (occ >= (unsigned int)c && - ocd <= (unsigned int)d) - continue; /* Skip embedded ranges */ - - if (occ < (unsigned int)c && - ocd >= (unsigned int)c - 1) /* Extend the basic range */ - { /* if there is overlap, */ - c = occ; /* noting that if occ < c */ - continue; /* we can't have ocd > d */ - } /* because a subrange is */ - if (ocd > (unsigned int)d && - occ <= (unsigned int)d + 1) /* always shorter than */ - { /* the basic range. */ - d = ocd; - continue; - } - - if (occ == ocd) - { - *class_utf8data++ = XCL_SINGLE; - } - else - { - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(occ, class_utf8data); - } - class_utf8data += _pcre_ord2utf8(ocd, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - /* Now record the original range, possibly modified for UCP caseless - overlapping ranges. */ - - *class_utf8data++ = XCL_RANGE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - class_utf8data += _pcre_ord2utf8(d, class_utf8data); - - /* With UCP support, we are done. Without UCP support, there is no - caseless matching for UTF-8 characters > 127; we can use the bit map - for the smaller ones. */ - -#ifdef SUPPORT_UCP - continue; /* With next character in the class */ -#else - if ((options & PCRE_CASELESS) == 0 || c > 127) continue; - - /* Adjust upper limit and fall through to set up the map */ - - d = 127; - -#endif /* SUPPORT_UCP */ - } -#endif /* SUPPORT_UTF8 */ - - /* We use the bit map for all cases when not in UTF-8 mode; else - ranges that lie entirely within 0-127 when there is UCP support; else - for partial ranges without UCP support. */ - - class_charcount += d - c + 1; - class_lastchar = d; - - /* We can save a bit of time by skipping this in the pre-compile. */ - - if (lengthptr == NULL) for (; c <= d; c++) - { - classbits[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - int uc = cd->fcc[c]; /* flip case */ - classbits[uc/8] |= (1 << (uc&7)); - } - } - - continue; /* Go get the next char in the class */ - } - - /* Handle a lone single character - we can get here for a normal - non-escape char, or after \ that introduces a single character or for an - apparent range that isn't. */ - - LONE_SINGLE_CHARACTER: - - /* Handle a character that cannot go in the bit map */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (c > 255 || ((options & PCRE_CASELESS) != 0 && c > 127))) - { - class_utf8 = TRUE; - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(c, class_utf8data); - -#ifdef SUPPORT_UCP - if ((options & PCRE_CASELESS) != 0) - { - unsigned int othercase; - if ((othercase = _pcre_ucp_othercase(c)) != NOTACHAR) - { - *class_utf8data++ = XCL_SINGLE; - class_utf8data += _pcre_ord2utf8(othercase, class_utf8data); - } - } -#endif /* SUPPORT_UCP */ - - } - else -#endif /* SUPPORT_UTF8 */ - - /* Handle a single-byte character */ - { - classbits[c/8] |= (1 << (c&7)); - if ((options & PCRE_CASELESS) != 0) - { - c = cd->fcc[c]; /* flip case */ - classbits[c/8] |= (1 << (c&7)); - } - class_charcount++; - class_lastchar = c; - } - } - - /* Loop until ']' reached. This "while" is the end of the "do" above. */ - - while ((c = *(++ptr)) != 0 && (c != ']' || inescq)); - - if (c == 0) /* Missing terminating ']' */ - { - *errorcodeptr = ERR6; - goto FAILED; - } - - -/* This code has been disabled because it would mean that \s counts as -an explicit \r or \n reference, and that's not really what is wanted. Now -we set the flag only if there is a literal "\r" or "\n" in the class. */ - -#if 0 - /* Remember whether \r or \n are in this class */ - - if (negate_class) - { - if ((classbits[1] & 0x24) != 0x24) cd->external_flags |= PCRE_HASCRORLF; - } - else - { - if ((classbits[1] & 0x24) != 0) cd->external_flags |= PCRE_HASCRORLF; - } -#endif - - - /* If class_charcount is 1, we saw precisely one character whose value is - less than 256. As long as there were no characters >= 128 and there was no - use of \p or \P, in other words, no use of any XCLASS features, we can - optimize. - - In UTF-8 mode, we can optimize the negative case only if there were no - characters >= 128 because OP_NOT and the related opcodes like OP_NOTSTAR - operate on single-bytes only. This is an historical hangover. Maybe one day - we can tidy these opcodes to handle multi-byte characters. - - The optimization throws away the bit map. We turn the item into a - 1-character OP_CHAR[NC] if it's positive, or OP_NOT if it's negative. Note - that OP_NOT does not support multibyte characters. In the positive case, it - can cause firstbyte to be set. Otherwise, there can be no first char if - this item is first, whatever repeat count may follow. In the case of - reqbyte, save the previous value for reinstating. */ - -#ifdef SUPPORT_UTF8 - if (class_charcount == 1 && !class_utf8 && - (!utf8 || !negate_class || class_lastchar < 128)) -#else - if (class_charcount == 1) -#endif - { - zeroreqbyte = reqbyte; - - /* The OP_NOT opcode works on one-byte characters only. */ - - if (negate_class) - { - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - *code++ = OP_NOT; - *code++ = class_lastchar; - break; - } - - /* For a single, positive character, get the value into mcbuffer, and - then we can handle this with the normal one-character code. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && class_lastchar > 127) - mclength = _pcre_ord2utf8(class_lastchar, mcbuffer); - else -#endif - { - mcbuffer[0] = class_lastchar; - mclength = 1; - } - goto ONE_CHAR; - } /* End of 1-char optimization */ - - /* The general case - not the one-char optimization. If this is the first - thing in the branch, there can be no first char setting, whatever the - repeat count. Any reqbyte setting must remain unchanged after any kind of - repeat. */ - - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* If there are characters with values > 255, we have to compile an - extended class, with its own opcode. If there are no characters < 256, - we can omit the bitmap in the actual compiled code. */ - -#ifdef SUPPORT_UTF8 - if (class_utf8) - { - *class_utf8data++ = XCL_END; /* Marks the end of extra data */ - *code++ = OP_XCLASS; - code += LINK_SIZE; - *code = negate_class? XCL_NOT : 0; - - /* If the map is required, move up the extra data to make room for it; - otherwise just move the code pointer to the end of the extra data. */ - - if (class_charcount > 0) - { - *code++ |= XCL_MAP; - memmove(code + 32, code, class_utf8data - code); - memcpy(code, classbits, 32); - code = class_utf8data + 32; - } - else code = class_utf8data; - - /* Now fill in the complete length of the item */ - - PUT(previous, 1, code - previous); - break; /* End of class handling */ - } -#endif - - /* If there are no characters > 255, negate the 32-byte map if necessary, - and copy it into the code vector. If this is the first thing in the branch, - there can be no first char setting, whatever the repeat count. Any reqbyte - setting must remain unchanged after any kind of repeat. */ - - if (negate_class) - { - *code++ = OP_NCLASS; - if (lengthptr == NULL) /* Save time in the pre-compile phase */ - for (c = 0; c < 32; c++) code[c] = ~classbits[c]; - } - else - { - *code++ = OP_CLASS; - memcpy(code, classbits, 32); - } - code += 32; - break; - - - /* ===================================================================*/ - /* Various kinds of repeat; '{' is not necessarily a quantifier, but this - has been tested above. */ - - case '{': - if (!is_quantifier) goto NORMAL_CHAR; - ptr = read_repeat_counts(ptr+1, &repeat_min, &repeat_max, errorcodeptr); - if (*errorcodeptr != 0) goto FAILED; - goto REPEAT; - - case '*': - repeat_min = 0; - repeat_max = -1; - goto REPEAT; - - case '+': - repeat_min = 1; - repeat_max = -1; - goto REPEAT; - - case '?': - repeat_min = 0; - repeat_max = 1; - - REPEAT: - if (previous == NULL) - { - *errorcodeptr = ERR9; - goto FAILED; - } - - if (repeat_min == 0) - { - firstbyte = zerofirstbyte; /* Adjust for zero repeat */ - reqbyte = zeroreqbyte; /* Ditto */ - } - - /* Remember whether this is a variable length repeat */ - - reqvary = (repeat_min == repeat_max)? 0 : REQ_VARY; - - op_type = 0; /* Default single-char op codes */ - possessive_quantifier = FALSE; /* Default not possessive quantifier */ - - /* Save start of previous item, in case we have to move it up to make space - for an inserted OP_ONCE for the additional '+' extension. */ - - tempcode = previous; - - /* If the next character is '+', we have a possessive quantifier. This - implies greediness, whatever the setting of the PCRE_UNGREEDY option. - If the next character is '?' this is a minimizing repeat, by default, - but if PCRE_UNGREEDY is set, it works the other way round. We change the - repeat type to the non-default. */ - - if (ptr[1] == '+') - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - ptr++; - } - else if (ptr[1] == '?') - { - repeat_type = greedy_non_default; - ptr++; - } - else repeat_type = greedy_default; - - /* If previous was a character match, abolish the item and generate a - repeat item instead. If a char item has a minumum of more than one, ensure - that it is set in reqbyte - it might not be if a sequence such as x{3} is - the first thing in a branch because the x will have gone into firstbyte - instead. */ - - if (*previous == OP_CHAR || *previous == OP_CHARNC) - { - /* Deal with UTF-8 characters that take up more than one byte. It's - easier to write this out separately than try to macrify it. Use c to - hold the length of the character in bytes, plus 0x80 to flag that it's a - length rather than a small character. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && (code[-1] & 0x80) != 0) - { - uschar *lastchar = code - 1; - while((*lastchar & 0xc0) == 0x80) lastchar--; - c = code - lastchar; /* Length of UTF-8 character */ - memcpy(utf8_char, lastchar, c); /* Save the char */ - c |= 0x80; /* Flag c as a length */ - } - else -#endif - - /* Handle the case of a single byte - either with no UTF8 support, or - with UTF-8 disabled, or for a UTF-8 character < 128. */ - - { - c = code[-1]; - if (repeat_min > 1) reqbyte = c | req_caseopt | cd->req_varyopt; - } - - /* If the repetition is unlimited, it pays to see if the next thing on - the line is something that cannot possibly match this character. If so, - automatically possessifying this item gains some performance in the case - where the match fails. */ - - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(*previous, c, utf8, utf8_char, ptr + 1, - options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - - goto OUTPUT_SINGLE_REPEAT; /* Code shared with single character types */ - } - - /* If previous was a single negated character ([^a] or similar), we use - one of the special opcodes, replacing it. The code is shared with single- - character repeats by setting opt_type to add a suitable offset into - repeat_type. We can also test for auto-possessification. OP_NOT is - currently used only for single-byte chars. */ - - else if (*previous == OP_NOT) - { - op_type = OP_NOTSTAR - OP_STAR; /* Use "not" opcodes */ - c = previous[1]; - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(OP_NOT, c, utf8, NULL, ptr + 1, options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - goto OUTPUT_SINGLE_REPEAT; - } - - /* If previous was a character type match (\d or similar), abolish it and - create a suitable repeat item. The code is shared with single-character - repeats by setting op_type to add a suitable offset into repeat_type. Note - the the Unicode property types will be present only when SUPPORT_UCP is - defined, but we don't wrap the little bits of code here because it just - makes it horribly messy. */ - - else if (*previous < OP_EODN) - { - uschar *oldcode; - int prop_type, prop_value; - op_type = OP_TYPESTAR - OP_STAR; /* Use type opcodes */ - c = *previous; - - if (!possessive_quantifier && - repeat_max < 0 && - check_auto_possessive(c, 0, utf8, NULL, ptr + 1, options, cd)) - { - repeat_type = 0; /* Force greedy */ - possessive_quantifier = TRUE; - } - - OUTPUT_SINGLE_REPEAT: - if (*previous == OP_PROP || *previous == OP_NOTPROP) - { - prop_type = previous[1]; - prop_value = previous[2]; - } - else prop_type = prop_value = -1; - - oldcode = code; - code = previous; /* Usually overwrite previous item */ - - /* If the maximum is zero then the minimum must also be zero; Perl allows - this case, so we do too - by simply omitting the item altogether. */ - - if (repeat_max == 0) goto END_REPEAT; - - /* All real repeats make it impossible to handle partial matching (maybe - one day we will be able to remove this restriction). */ - - if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; - - /* Combine the op_type with the repeat_type */ - - repeat_type += op_type; - - /* A minimum of zero is handled either as the special case * or ?, or as - an UPTO, with the maximum given. */ - - if (repeat_min == 0) - { - if (repeat_max == -1) *code++ = OP_STAR + repeat_type; - else if (repeat_max == 1) *code++ = OP_QUERY + repeat_type; - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - - /* A repeat minimum of 1 is optimized into some special cases. If the - maximum is unlimited, we use OP_PLUS. Otherwise, the original item is - left in place and, if the maximum is greater than 1, we use OP_UPTO with - one less than the maximum. */ - - else if (repeat_min == 1) - { - if (repeat_max == -1) - *code++ = OP_PLUS + repeat_type; - else - { - code = oldcode; /* leave previous item in place */ - if (repeat_max == 1) goto END_REPEAT; - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max - 1); - } - } - - /* The case {n,n} is just an EXACT, while the general case {n,m} is - handled as an EXACT followed by an UPTO. */ - - else - { - *code++ = OP_EXACT + op_type; /* NB EXACT doesn't have repeat_type */ - PUT2INC(code, 0, repeat_min); - - /* If the maximum is unlimited, insert an OP_STAR. Before doing so, - we have to insert the character for the previous code. For a repeated - Unicode property match, there are two extra bytes that define the - required property. In UTF-8 mode, long characters have their length in - c, with the 0x80 bit as a flag. */ - - if (repeat_max < 0) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - { - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - } - *code++ = OP_STAR + repeat_type; - } - - /* Else insert an UPTO if the max is greater than the min, again - preceded by the character, for the previously inserted code. If the - UPTO is just for 1 instance, we can use QUERY instead. */ - - else if (repeat_max != repeat_min) - { -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - *code++ = c; - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } - repeat_max -= repeat_min; - - if (repeat_max == 1) - { - *code++ = OP_QUERY + repeat_type; - } - else - { - *code++ = OP_UPTO + repeat_type; - PUT2INC(code, 0, repeat_max); - } - } - } - - /* The character or character type itself comes last in all cases. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 128) - { - memcpy(code, utf8_char, c & 7); - code += c & 7; - } - else -#endif - *code++ = c; - - /* For a repeated Unicode property match, there are two extra bytes that - define the required property. */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - *code++ = prop_type; - *code++ = prop_value; - } -#endif - } - - /* If previous was a character class or a back reference, we put the repeat - stuff after it, but just skip the item if the repeat was {0,0}. */ - - else if (*previous == OP_CLASS || - *previous == OP_NCLASS || -#ifdef SUPPORT_UTF8 - *previous == OP_XCLASS || -#endif - *previous == OP_REF) - { - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* All real repeats make it impossible to handle partial matching (maybe - one day we will be able to remove this restriction). */ - - if (repeat_max != 1) cd->external_flags |= PCRE_NOPARTIAL; - - if (repeat_min == 0 && repeat_max == -1) - *code++ = OP_CRSTAR + repeat_type; - else if (repeat_min == 1 && repeat_max == -1) - *code++ = OP_CRPLUS + repeat_type; - else if (repeat_min == 0 && repeat_max == 1) - *code++ = OP_CRQUERY + repeat_type; - else - { - *code++ = OP_CRRANGE + repeat_type; - PUT2INC(code, 0, repeat_min); - if (repeat_max == -1) repeat_max = 0; /* 2-byte encoding for max */ - PUT2INC(code, 0, repeat_max); - } - } - - /* If previous was a bracket group, we may have to replicate it in certain - cases. */ - - else if (*previous == OP_BRA || *previous == OP_CBRA || - *previous == OP_ONCE || *previous == OP_COND) - { - register int i; - int ketoffset = 0; - int len = code - previous; - uschar *bralink = NULL; - - /* Repeating a DEFINE group is pointless */ - - if (*previous == OP_COND && previous[LINK_SIZE+1] == OP_DEF) - { - *errorcodeptr = ERR55; - goto FAILED; - } - - /* If the maximum repeat count is unlimited, find the end of the bracket - by scanning through from the start, and compute the offset back to it - from the current code pointer. There may be an OP_OPT setting following - the final KET, so we can't find the end just by going back from the code - pointer. */ - - if (repeat_max == -1) - { - register uschar *ket = previous; - do ket += GET(ket, 1); while (*ket != OP_KET); - ketoffset = code - ket; - } - - /* The case of a zero minimum is special because of the need to stick - OP_BRAZERO in front of it, and because the group appears once in the - data, whereas in other cases it appears the minimum number of times. For - this reason, it is simplest to treat this case separately, as otherwise - the code gets far too messy. There are several special subcases when the - minimum is zero. */ - - if (repeat_min == 0) - { - /* If the maximum is also zero, we just omit the group from the output - altogether. */ - - if (repeat_max == 0) - { - code = previous; - goto END_REPEAT; - } - - /* If the maximum is 1 or unlimited, we just have to stick in the - BRAZERO and do no more at this point. However, we do need to adjust - any OP_RECURSE calls inside the group that refer to the group itself or - any internal or forward referenced group, because the offset is from - the start of the whole regex. Temporarily terminate the pattern while - doing this. */ - - if (repeat_max <= 1) - { - *code = OP_END; - adjust_recurse(previous, 1, utf8, cd, save_hwm); - memmove(previous+1, previous, len); - code++; - *previous++ = OP_BRAZERO + repeat_type; - } - - /* If the maximum is greater than 1 and limited, we have to replicate - in a nested fashion, sticking OP_BRAZERO before each set of brackets. - The first one has to be handled carefully because it's the original - copy, which has to be moved up. The remainder can be handled by code - that is common with the non-zero minimum case below. We have to - adjust the value or repeat_max, since one less copy is required. Once - again, we may have to adjust any OP_RECURSE calls inside the group. */ - - else - { - int offset; - *code = OP_END; - adjust_recurse(previous, 2 + LINK_SIZE, utf8, cd, save_hwm); - memmove(previous + 2 + LINK_SIZE, previous, len); - code += 2 + LINK_SIZE; - *previous++ = OP_BRAZERO + repeat_type; - *previous++ = OP_BRA; - - /* We chain together the bracket offset fields that have to be - filled in later when the ends of the brackets are reached. */ - - offset = (bralink == NULL)? 0 : previous - bralink; - bralink = previous; - PUTINC(previous, 0, offset); - } - - repeat_max--; - } - - /* If the minimum is greater than zero, replicate the group as many - times as necessary, and adjust the maximum to the number of subsequent - copies that we need. If we set a first char from the group, and didn't - set a required char, copy the latter from the former. If there are any - forward reference subroutine calls in the group, there will be entries on - the workspace list; replicate these with an appropriate increment. */ - - else - { - if (repeat_min > 1) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. Do some paranoid checks for - potential integer overflow. */ - - if (lengthptr != NULL) - { - int delta = (repeat_min - 1)*length_prevgroup; - if ((double)(repeat_min - 1)*(double)length_prevgroup > - (double)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else - { - if (groupsetfirstbyte && reqbyte < 0) reqbyte = firstbyte; - for (i = 1; i < repeat_min; i++) - { - uschar *hc; - uschar *this_hwm = cd->hwm; - memcpy(code, previous, len); - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - } - } - - if (repeat_max > 0) repeat_max -= repeat_min; - } - - /* This code is common to both the zero and non-zero minimum cases. If - the maximum is limited, it replicates the group in a nested fashion, - remembering the bracket starts on a stack. In the case of a zero minimum, - the first one was set up above. In all cases the repeat_max now specifies - the number of additional copies needed. Again, we must remember to - replicate entries on the forward reference list. */ - - if (repeat_max >= 0) - { - /* In the pre-compile phase, we don't actually do the replication. We - just adjust the length as if we had. For each repetition we must add 1 - to the length for BRAZERO and for all but the last repetition we must - add 2 + 2*LINKSIZE to allow for the nesting that occurs. Do some - paranoid checks to avoid integer overflow. */ - - if (lengthptr != NULL && repeat_max > 0) - { - int delta = repeat_max * (length_prevgroup + 1 + 2 + 2*LINK_SIZE) - - 2 - 2*LINK_SIZE; /* Last one doesn't nest */ - if ((double)repeat_max * - (double)(length_prevgroup + 1 + 2 + 2*LINK_SIZE) - > (double)INT_MAX || - OFLOW_MAX - *lengthptr < delta) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += delta; - } - - /* This is compiling for real */ - - else for (i = repeat_max - 1; i >= 0; i--) - { - uschar *hc; - uschar *this_hwm = cd->hwm; - - *code++ = OP_BRAZERO + repeat_type; - - /* All but the final copy start a new nesting, maintaining the - chain of brackets outstanding. */ - - if (i != 0) - { - int offset; - *code++ = OP_BRA; - offset = (bralink == NULL)? 0 : code - bralink; - bralink = code; - PUTINC(code, 0, offset); - } - - memcpy(code, previous, len); - for (hc = save_hwm; hc < this_hwm; hc += LINK_SIZE) - { - PUT(cd->hwm, 0, GET(hc, 0) + len + ((i != 0)? 2+LINK_SIZE : 1)); - cd->hwm += LINK_SIZE; - } - save_hwm = this_hwm; - code += len; - } - - /* Now chain through the pending brackets, and fill in their length - fields (which are holding the chain links pro tem). */ - - while (bralink != NULL) - { - int oldlinkoffset; - int offset = code - bralink + 1; - uschar *bra = code - offset; - oldlinkoffset = GET(bra, 1); - bralink = (oldlinkoffset == 0)? NULL : bralink - oldlinkoffset; - *code++ = OP_KET; - PUTINC(code, 0, offset); - PUT(bra, 1, offset); - } - } - - /* If the maximum is unlimited, set a repeater in the final copy. We - can't just offset backwards from the current code point, because we - don't know if there's been an options resetting after the ket. The - correct offset was computed above. - - Then, when we are doing the actual compile phase, check to see whether - this group is a non-atomic one that could match an empty string. If so, - convert the initial operator to the S form (e.g. OP_BRA -> OP_SBRA) so - that runtime checking can be done. [This check is also applied to - atomic groups at runtime, but in a different way.] */ - - else - { - uschar *ketcode = code - ketoffset; - uschar *bracode = ketcode - GET(ketcode, 1); - *ketcode = OP_KETRMAX + repeat_type; - if (lengthptr == NULL && *bracode != OP_ONCE) - { - uschar *scode = bracode; - do - { - if (could_be_empty_branch(scode, ketcode, utf8)) - { - *bracode += OP_SBRA - OP_BRA; - break; - } - scode += GET(scode, 1); - } - while (*scode == OP_ALT); - } - } - } - - /* Else there's some kind of shambles */ - - else - { - *errorcodeptr = ERR11; - goto FAILED; - } - - /* If the character following a repeat is '+', or if certain optimization - tests above succeeded, possessive_quantifier is TRUE. For some of the - simpler opcodes, there is an special alternative opcode for this. For - anything else, we wrap the entire repeated item inside OP_ONCE brackets. - The '+' notation is just syntactic sugar, taken from Sun's Java package, - but the special opcodes can optimize it a bit. The repeated item starts at - tempcode, not at previous, which might be the first part of a string whose - (former) last char we repeated. - - Possessifying an 'exact' quantifier has no effect, so we can ignore it. But - an 'upto' may follow. We skip over an 'exact' item, and then test the - length of what remains before proceeding. */ - - if (possessive_quantifier) - { - int len; - if (*tempcode == OP_EXACT || *tempcode == OP_TYPEEXACT || - *tempcode == OP_NOTEXACT) - tempcode += _pcre_OP_lengths[*tempcode]; - len = code - tempcode; - if (len > 0) switch (*tempcode) - { - case OP_STAR: *tempcode = OP_POSSTAR; break; - case OP_PLUS: *tempcode = OP_POSPLUS; break; - case OP_QUERY: *tempcode = OP_POSQUERY; break; - case OP_UPTO: *tempcode = OP_POSUPTO; break; - - case OP_TYPESTAR: *tempcode = OP_TYPEPOSSTAR; break; - case OP_TYPEPLUS: *tempcode = OP_TYPEPOSPLUS; break; - case OP_TYPEQUERY: *tempcode = OP_TYPEPOSQUERY; break; - case OP_TYPEUPTO: *tempcode = OP_TYPEPOSUPTO; break; - - case OP_NOTSTAR: *tempcode = OP_NOTPOSSTAR; break; - case OP_NOTPLUS: *tempcode = OP_NOTPOSPLUS; break; - case OP_NOTQUERY: *tempcode = OP_NOTPOSQUERY; break; - case OP_NOTUPTO: *tempcode = OP_NOTPOSUPTO; break; - - default: - memmove(tempcode + 1+LINK_SIZE, tempcode, len); - code += 1 + LINK_SIZE; - len += 1 + LINK_SIZE; - tempcode[0] = OP_ONCE; - *code++ = OP_KET; - PUTINC(code, 0, len); - PUT(tempcode, 1, len); - break; - } - } - - /* In all case we no longer have a previous item. We also set the - "follows varying string" flag for subsequently encountered reqbytes if - it isn't already set and we have just passed a varying length item. */ - - END_REPEAT: - previous = NULL; - cd->req_varyopt |= reqvary; - break; - - - /* ===================================================================*/ - /* Start of nested parenthesized sub-expression, or comment or lookahead or - lookbehind or option setting or condition or all the other extended - parenthesis forms. */ - - case '(': - newoptions = options; - skipbytes = 0; - bravalue = OP_CBRA; - save_hwm = cd->hwm; - reset_bracount = FALSE; - - /* First deal with various "verbs" that can be introduced by '*'. */ - - if (*(++ptr) == '*' && (cd->ctypes[ptr[1]] & ctype_letter) != 0) - { - int i, namelen; - const char *vn = verbnames; - const uschar *name = ++ptr; - previous = NULL; - while ((cd->ctypes[*++ptr] & ctype_letter) != 0); - if (*ptr == ':') - { - *errorcodeptr = ERR59; /* Not supported */ - goto FAILED; - } - if (*ptr != ')') - { - *errorcodeptr = ERR60; - goto FAILED; - } - namelen = ptr - name; - for (i = 0; i < verbcount; i++) - { - if (namelen == verbs[i].len && - strncmp((char *)name, vn, namelen) == 0) - { - *code = verbs[i].op; - if (*code++ == OP_ACCEPT) cd->had_accept = TRUE; - break; - } - vn += verbs[i].len + 1; - } - if (i < verbcount) continue; - *errorcodeptr = ERR60; - goto FAILED; - } - - /* Deal with the extended parentheses; all are introduced by '?', and the - appearance of any of them means that this is not a capturing group. */ - - else if (*ptr == '?') - { - int i, set, unset, namelen; - int *optset; - const uschar *name; - uschar *slot; - - switch (*(++ptr)) - { - case '#': /* Comment; skip to ket */ - ptr++; - while (*ptr != 0 && *ptr != ')') ptr++; - if (*ptr == 0) - { - *errorcodeptr = ERR18; - goto FAILED; - } - continue; - - - /* ------------------------------------------------------------ */ - case '|': /* Reset capture count for each branch */ - reset_bracount = TRUE; - /* Fall through */ - - /* ------------------------------------------------------------ */ - case ':': /* Non-capturing bracket */ - bravalue = OP_BRA; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case '(': - bravalue = OP_COND; /* Conditional group */ - - /* A condition can be an assertion, a number (referring to a numbered - group), a name (referring to a named group), or 'R', referring to - recursion. R<digits> and R&name are also permitted for recursion tests. - - There are several syntaxes for testing a named group: (?(name)) is used - by Python; Perl 5.10 onwards uses (?(<name>) or (?('name')). - - There are two unfortunate ambiguities, caused by history. (a) 'R' can - be the recursive thing or the name 'R' (and similarly for 'R' followed - by digits), and (b) a number could be a name that consists of digits. - In both cases, we look for a name first; if not found, we try the other - cases. */ - - /* For conditions that are assertions, check the syntax, and then exit - the switch. This will take control down to where bracketed groups, - including assertions, are processed. */ - - if (ptr[1] == '?' && (ptr[2] == '=' || ptr[2] == '!' || ptr[2] == '<')) - break; - - /* Most other conditions use OP_CREF (a couple change to OP_RREF - below), and all need to skip 3 bytes at the start of the group. */ - - code[1+LINK_SIZE] = OP_CREF; - skipbytes = 3; - refsign = -1; - - /* Check for a test for recursion in a named group. */ - - if (ptr[1] == 'R' && ptr[2] == '&') - { - terminator = -1; - ptr += 2; - code[1+LINK_SIZE] = OP_RREF; /* Change the type of test */ - } - - /* Check for a test for a named group's having been set, using the Perl - syntax (?(<name>) or (?('name') */ - - else if (ptr[1] == '<') - { - terminator = '>'; - ptr++; - } - else if (ptr[1] == '\'') - { - terminator = '\''; - ptr++; - } - else - { - terminator = 0; - if (ptr[1] == '-' || ptr[1] == '+') refsign = *(++ptr); - } - - /* We now expect to read a name; any thing else is an error */ - - if ((cd->ctypes[ptr[1]] & ctype_word) == 0) - { - ptr += 1; /* To get the right offset */ - *errorcodeptr = ERR28; - goto FAILED; - } - - /* Read the name, but also get it as a number if it's all digits */ - - recno = 0; - name = ++ptr; - while ((cd->ctypes[*ptr] & ctype_word) != 0) - { - if (recno >= 0) - recno = ((digitab[*ptr] & ctype_digit) != 0)? - recno * 10 + *ptr - '0' : -1; - ptr++; - } - namelen = ptr - name; - - if ((terminator > 0 && *ptr++ != terminator) || *ptr++ != ')') - { - ptr--; /* Error offset */ - *errorcodeptr = ERR26; - goto FAILED; - } - - /* Do no further checking in the pre-compile phase. */ - - if (lengthptr != NULL) break; - - /* In the real compile we do the work of looking for the actual - reference. If the string started with "+" or "-" we require the rest to - be digits, in which case recno will be set. */ - - if (refsign > 0) - { - if (recno <= 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - if (refsign == '-') - { - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - else recno += cd->bracount; - PUT2(code, 2+LINK_SIZE, recno); - break; - } - - /* Otherwise (did not start with "+" or "-"), start by looking for the - name. */ - - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } - - /* Found a previous named subpattern */ - - if (i < cd->names_found) - { - recno = GET2(slot, 0); - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Search the pattern for a forward reference */ - - else if ((i = find_parens(ptr, cd->bracount, name, namelen, - (options & PCRE_EXTENDED) != 0)) > 0) - { - PUT2(code, 2+LINK_SIZE, i); - } - - /* If terminator == 0 it means that the name followed directly after - the opening parenthesis [e.g. (?(abc)...] and in this case there are - some further alternatives to try. For the cases where terminator != 0 - [things like (?(<name>... or (?('name')... or (?(R&name)... ] we have - now checked all the possibilities, so give an error. */ - - else if (terminator != 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - - /* Check for (?(R) for recursion. Allow digits after R to specify a - specific group number. */ - - else if (*name == 'R') - { - recno = 0; - for (i = 1; i < namelen; i++) - { - if ((digitab[name[i]] & ctype_digit) == 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - recno = recno * 10 + name[i] - '0'; - } - if (recno == 0) recno = RREF_ANY; - code[1+LINK_SIZE] = OP_RREF; /* Change test type */ - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Similarly, check for the (?(DEFINE) "condition", which is always - false. */ - - else if (namelen == 6 && strncmp((char *)name, "DEFINE", 6) == 0) - { - code[1+LINK_SIZE] = OP_DEF; - skipbytes = 1; - } - - /* Check for the "name" actually being a subpattern number. */ - - else if (recno > 0) - { - PUT2(code, 2+LINK_SIZE, recno); - } - - /* Either an unidentified subpattern, or a reference to (?(0) */ - - else - { - *errorcodeptr = (recno == 0)? ERR35: ERR15; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case '=': /* Positive lookahead */ - bravalue = OP_ASSERT; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case '!': /* Negative lookahead */ - ptr++; - if (*ptr == ')') /* Optimize (?!) */ - { - *code++ = OP_FAIL; - previous = NULL; - continue; - } - bravalue = OP_ASSERT_NOT; - break; - - - /* ------------------------------------------------------------ */ - case '<': /* Lookbehind or named define */ - switch (ptr[1]) - { - case '=': /* Positive lookbehind */ - bravalue = OP_ASSERTBACK; - ptr += 2; - break; - - case '!': /* Negative lookbehind */ - bravalue = OP_ASSERTBACK_NOT; - ptr += 2; - break; - - default: /* Could be name define, else bad */ - if ((cd->ctypes[ptr[1]] & ctype_word) != 0) goto DEFINE_NAME; - ptr++; /* Correct offset for error */ - *errorcodeptr = ERR24; - goto FAILED; - } - break; - - - /* ------------------------------------------------------------ */ - case '>': /* One-time brackets */ - bravalue = OP_ONCE; - ptr++; - break; - - - /* ------------------------------------------------------------ */ - case 'C': /* Callout - may be followed by digits; */ - previous_callout = code; /* Save for later completion */ - after_manual_callout = 1; /* Skip one item before completing */ - *code++ = OP_CALLOUT; - { - int n = 0; - while ((digitab[*(++ptr)] & ctype_digit) != 0) - n = n * 10 + *ptr - '0'; - if (*ptr != ')') - { - *errorcodeptr = ERR39; - goto FAILED; - } - if (n > 255) - { - *errorcodeptr = ERR38; - goto FAILED; - } - *code++ = n; - PUT(code, 0, ptr - cd->start_pattern + 1); /* Pattern offset */ - PUT(code, LINK_SIZE, 0); /* Default length */ - code += 2 * LINK_SIZE; - } - previous = NULL; - continue; - - - /* ------------------------------------------------------------ */ - case 'P': /* Python-style named subpattern handling */ - if (*(++ptr) == '=' || *ptr == '>') /* Reference or recursion */ - { - is_recurse = *ptr == '>'; - terminator = ')'; - goto NAMED_REF_OR_RECURSE; - } - else if (*ptr != '<') /* Test for Python-style definition */ - { - *errorcodeptr = ERR41; - goto FAILED; - } - /* Fall through to handle (?P< as (?< is handled */ - - - /* ------------------------------------------------------------ */ - DEFINE_NAME: /* Come here from (?< handling */ - case '\'': - { - terminator = (*ptr == '<')? '>' : '\''; - name = ++ptr; - - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = ptr - name; - - /* In the pre-compile phase, just do a syntax check. */ - - if (lengthptr != NULL) - { - if (*ptr != terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (cd->names_found >= MAX_NAME_COUNT) - { - *errorcodeptr = ERR49; - goto FAILED; - } - if (namelen + 3 > cd->name_entry_size) - { - cd->name_entry_size = namelen + 3; - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - } - } - - /* In the real compile, create the entry in the table */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - int crc = memcmp(name, slot+2, namelen); - if (crc == 0) - { - if (slot[2+namelen] == 0) - { - if ((options & PCRE_DUPNAMES) == 0) - { - *errorcodeptr = ERR43; - goto FAILED; - } - } - else crc = -1; /* Current name is substring */ - } - if (crc < 0) - { - memmove(slot + cd->name_entry_size, slot, - (cd->names_found - i) * cd->name_entry_size); - break; - } - slot += cd->name_entry_size; - } - - PUT2(slot, 0, cd->bracount + 1); - memcpy(slot + 2, name, namelen); - slot[2+namelen] = 0; - } - } - - /* In both cases, count the number of names we've encountered. */ - - ptr++; /* Move past > or ' */ - cd->names_found++; - goto NUMBERED_GROUP; - - - /* ------------------------------------------------------------ */ - case '&': /* Perl recursion/subroutine syntax */ - terminator = ')'; - is_recurse = TRUE; - /* Fall through */ - - /* We come here from the Python syntax above that handles both - references (?P=name) and recursion (?P>name), as well as falling - through from the Perl recursion syntax (?&name). */ - - NAMED_REF_OR_RECURSE: - name = ++ptr; - while ((cd->ctypes[*ptr] & ctype_word) != 0) ptr++; - namelen = ptr - name; - - /* In the pre-compile phase, do a syntax check and set a dummy - reference number. */ - - if (lengthptr != NULL) - { - if (*ptr != terminator) - { - *errorcodeptr = ERR42; - goto FAILED; - } - if (namelen > MAX_NAME_SIZE) - { - *errorcodeptr = ERR48; - goto FAILED; - } - recno = 0; - } - - /* In the real compile, seek the name in the table */ - - else - { - slot = cd->name_table; - for (i = 0; i < cd->names_found; i++) - { - if (strncmp((char *)name, (char *)slot+2, namelen) == 0) break; - slot += cd->name_entry_size; - } - - if (i < cd->names_found) /* Back reference */ - { - recno = GET2(slot, 0); - } - else if ((recno = /* Forward back reference */ - find_parens(ptr, cd->bracount, name, namelen, - (options & PCRE_EXTENDED) != 0)) <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - - /* In both phases, we can now go to the code than handles numerical - recursion or backreferences. */ - - if (is_recurse) goto HANDLE_RECURSION; - else goto HANDLE_REFERENCE; - - - /* ------------------------------------------------------------ */ - case 'R': /* Recursion */ - ptr++; /* Same as (?0) */ - /* Fall through */ - - - /* ------------------------------------------------------------ */ - case '-': case '+': - case '0': case '1': case '2': case '3': case '4': /* Recursion or */ - case '5': case '6': case '7': case '8': case '9': /* subroutine */ - { - const uschar *called; - - if ((refsign = *ptr) == '+') ptr++; - else if (refsign == '-') - { - if ((digitab[ptr[1]] & ctype_digit) == 0) - goto OTHER_CHAR_AFTER_QUERY; - ptr++; - } - - recno = 0; - while((digitab[*ptr] & ctype_digit) != 0) - recno = recno * 10 + *ptr++ - '0'; - - if (*ptr != ')') - { - *errorcodeptr = ERR29; - goto FAILED; - } - - if (refsign == '-') - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno = cd->bracount - recno + 1; - if (recno <= 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - } - else if (refsign == '+') - { - if (recno == 0) - { - *errorcodeptr = ERR58; - goto FAILED; - } - recno += cd->bracount; - } - - /* Come here from code above that handles a named recursion */ - - HANDLE_RECURSION: - - previous = code; - called = cd->start_code; - - /* When we are actually compiling, find the bracket that is being - referenced. Temporarily end the regex in case it doesn't exist before - this point. If we end up with a forward reference, first check that - the bracket does occur later so we can give the error (and position) - now. Then remember this forward reference in the workspace so it can - be filled in at the end. */ - - if (lengthptr == NULL) - { - *code = OP_END; - if (recno != 0) called = find_bracket(cd->start_code, utf8, recno); - - /* Forward reference */ - - if (called == NULL) - { - if (find_parens(ptr, cd->bracount, NULL, recno, - (options & PCRE_EXTENDED) != 0) < 0) - { - *errorcodeptr = ERR15; - goto FAILED; - } - called = cd->start_code + recno; - PUTINC(cd->hwm, 0, code + 2 + LINK_SIZE - cd->start_code); - } - - /* If not a forward reference, and the subpattern is still open, - this is a recursive call. We check to see if this is a left - recursion that could loop for ever, and diagnose that case. */ - - else if (GET(called, 1) == 0 && - could_be_empty(called, code, bcptr, utf8)) - { - *errorcodeptr = ERR40; - goto FAILED; - } - } - - /* Insert the recursion/subroutine item, automatically wrapped inside - "once" brackets. Set up a "previous group" length so that a - subsequent quantifier will work. */ - - *code = OP_ONCE; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - - *code = OP_RECURSE; - PUT(code, 1, called - cd->start_code); - code += 1 + LINK_SIZE; - - *code = OP_KET; - PUT(code, 1, 2 + 2*LINK_SIZE); - code += 1 + LINK_SIZE; - - length_prevgroup = 3 + 3*LINK_SIZE; - } - - /* Can't determine a first byte now */ - - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - continue; - - - /* ------------------------------------------------------------ */ - default: /* Other characters: check option setting */ - OTHER_CHAR_AFTER_QUERY: - set = unset = 0; - optset = &set; - - while (*ptr != ')' && *ptr != ':') - { - switch (*ptr++) - { - case '-': optset = &unset; break; - - case 'J': /* Record that it changed in the external options */ - *optset |= PCRE_DUPNAMES; - cd->external_flags |= PCRE_JCHANGED; - break; - - case 'i': *optset |= PCRE_CASELESS; break; - case 'm': *optset |= PCRE_MULTILINE; break; - case 's': *optset |= PCRE_DOTALL; break; - case 'x': *optset |= PCRE_EXTENDED; break; - case 'U': *optset |= PCRE_UNGREEDY; break; - case 'X': *optset |= PCRE_EXTRA; break; - - default: *errorcodeptr = ERR12; - ptr--; /* Correct the offset */ - goto FAILED; - } - } - - /* Set up the changed option bits, but don't change anything yet. */ - - newoptions = (options | set) & (~unset); - - /* If the options ended with ')' this is not the start of a nested - group with option changes, so the options change at this level. If this - item is right at the start of the pattern, the options can be - abstracted and made external in the pre-compile phase, and ignored in - the compile phase. This can be helpful when matching -- for instance in - caseless checking of required bytes. - - If the code pointer is not (cd->start_code + 1 + LINK_SIZE), we are - definitely *not* at the start of the pattern because something has been - compiled. In the pre-compile phase, however, the code pointer can have - that value after the start, because it gets reset as code is discarded - during the pre-compile. However, this can happen only at top level - if - we are within parentheses, the starting BRA will still be present. At - any parenthesis level, the length value can be used to test if anything - has been compiled at that level. Thus, a test for both these conditions - is necessary to ensure we correctly detect the start of the pattern in - both phases. - - If we are not at the pattern start, compile code to change the ims - options if this setting actually changes any of them. We also pass the - new setting back so that it can be put at the start of any following - branches, and when this group ends (if we are in a group), a resetting - item can be compiled. */ - - if (*ptr == ')') - { - if (code == cd->start_code + 1 + LINK_SIZE && - (lengthptr == NULL || *lengthptr == 2 + 2*LINK_SIZE)) - { - cd->external_options = newoptions; - options = newoptions; - } - else - { - if ((options & PCRE_IMS) != (newoptions & PCRE_IMS)) - { - *code++ = OP_OPT; - *code++ = newoptions & PCRE_IMS; - } - - /* Change options at this level, and pass them back for use - in subsequent branches. Reset the greedy defaults and the case - value for firstbyte and reqbyte. */ - - *optionsptr = options = newoptions; - greedy_default = ((newoptions & PCRE_UNGREEDY) != 0); - greedy_non_default = greedy_default ^ 1; - req_caseopt = ((options & PCRE_CASELESS) != 0)? REQ_CASELESS : 0; - } - - previous = NULL; /* This item can't be repeated */ - continue; /* It is complete */ - } - - /* If the options ended with ':' we are heading into a nested group - with possible change of options. Such groups are non-capturing and are - not assertions of any kind. All we need to do is skip over the ':'; - the newoptions value is handled below. */ - - bravalue = OP_BRA; - ptr++; - } /* End of switch for character following (? */ - } /* End of (? handling */ - - /* Opening parenthesis not followed by '?'. If PCRE_NO_AUTO_CAPTURE is set, - all unadorned brackets become non-capturing and behave like (?:...) - brackets. */ - - else if ((options & PCRE_NO_AUTO_CAPTURE) != 0) - { - bravalue = OP_BRA; - } - - /* Else we have a capturing group. */ - - else - { - NUMBERED_GROUP: - cd->bracount += 1; - PUT2(code, 1+LINK_SIZE, cd->bracount); - skipbytes = 2; - } - - /* Process nested bracketed regex. Assertions may not be repeated, but - other kinds can be. All their opcodes are >= OP_ONCE. We copy code into a - non-register variable in order to be able to pass its address because some - compilers complain otherwise. Pass in a new setting for the ims options if - they have changed. */ - - previous = (bravalue >= OP_ONCE)? code : NULL; - *code = bravalue; - tempcode = code; - tempreqvary = cd->req_varyopt; /* Save value before bracket */ - length_prevgroup = 0; /* Initialize for pre-compile phase */ - - if (!compile_regex( - newoptions, /* The complete new option state */ - options & PCRE_IMS, /* The previous ims option state */ - &tempcode, /* Where to put code (updated) */ - &ptr, /* Input pointer (updated) */ - errorcodeptr, /* Where to put an error message */ - (bravalue == OP_ASSERTBACK || - bravalue == OP_ASSERTBACK_NOT), /* TRUE if back assert */ - reset_bracount, /* True if (?| group */ - skipbytes, /* Skip over bracket number */ - &subfirstbyte, /* For possible first char */ - &subreqbyte, /* For possible last char */ - bcptr, /* Current branch chain */ - cd, /* Tables block */ - (lengthptr == NULL)? NULL : /* Actual compile phase */ - &length_prevgroup /* Pre-compile phase */ - )) - goto FAILED; - - /* At the end of compiling, code is still pointing to the start of the - group, while tempcode has been updated to point past the end of the group - and any option resetting that may follow it. The pattern pointer (ptr) - is on the bracket. */ - - /* If this is a conditional bracket, check that there are no more than - two branches in the group, or just one if it's a DEFINE group. We do this - in the real compile phase, not in the pre-pass, where the whole group may - not be available. */ - - if (bravalue == OP_COND && lengthptr == NULL) - { - uschar *tc = code; - int condcount = 0; - - do { - condcount++; - tc += GET(tc,1); - } - while (*tc != OP_KET); - - /* A DEFINE group is never obeyed inline (the "condition" is always - false). It must have only one branch. */ - - if (code[LINK_SIZE+1] == OP_DEF) - { - if (condcount > 1) - { - *errorcodeptr = ERR54; - goto FAILED; - } - bravalue = OP_DEF; /* Just a flag to suppress char handling below */ - } - - /* A "normal" conditional group. If there is just one branch, we must not - make use of its firstbyte or reqbyte, because this is equivalent to an - empty second branch. */ - - else - { - if (condcount > 2) - { - *errorcodeptr = ERR27; - goto FAILED; - } - if (condcount == 1) subfirstbyte = subreqbyte = REQ_NONE; - } - } - - /* Error if hit end of pattern */ - - if (*ptr != ')') - { - *errorcodeptr = ERR14; - goto FAILED; - } - - /* In the pre-compile phase, update the length by the length of the group, - less the brackets at either end. Then reduce the compiled code to just a - set of non-capturing brackets so that it doesn't use much memory if it is - duplicated by a quantifier.*/ - - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length_prevgroup - 2 - 2*LINK_SIZE) - { - *errorcodeptr = ERR20; - goto FAILED; - } - *lengthptr += length_prevgroup - 2 - 2*LINK_SIZE; - *code++ = OP_BRA; - PUTINC(code, 0, 1 + LINK_SIZE); - *code++ = OP_KET; - PUTINC(code, 0, 1 + LINK_SIZE); - break; /* No need to waste time with special character handling */ - } - - /* Otherwise update the main code pointer to the end of the group. */ - - code = tempcode; - - /* For a DEFINE group, required and first character settings are not - relevant. */ - - if (bravalue == OP_DEF) break; - - /* Handle updating of the required and first characters for other types of - group. Update for normal brackets of all kinds, and conditions with two - branches (see code above). If the bracket is followed by a quantifier with - zero repeat, we have to back off. Hence the definition of zeroreqbyte and - zerofirstbyte outside the main loop so that they can be accessed for the - back off. */ - - zeroreqbyte = reqbyte; - zerofirstbyte = firstbyte; - groupsetfirstbyte = FALSE; - - if (bravalue >= OP_ONCE) - { - /* If we have not yet set a firstbyte in this branch, take it from the - subpattern, remembering that it was set here so that a repeat of more - than one can replicate it as reqbyte if necessary. If the subpattern has - no firstbyte, set "none" for the whole branch. In both cases, a zero - repeat forces firstbyte to "none". */ - - if (firstbyte == REQ_UNSET) - { - if (subfirstbyte >= 0) - { - firstbyte = subfirstbyte; - groupsetfirstbyte = TRUE; - } - else firstbyte = REQ_NONE; - zerofirstbyte = REQ_NONE; - } - - /* If firstbyte was previously set, convert the subpattern's firstbyte - into reqbyte if there wasn't one, using the vary flag that was in - existence beforehand. */ - - else if (subfirstbyte >= 0 && subreqbyte < 0) - subreqbyte = subfirstbyte | tempreqvary; - - /* If the subpattern set a required byte (or set a first byte that isn't - really the first byte - see above), set it. */ - - if (subreqbyte >= 0) reqbyte = subreqbyte; - } - - /* For a forward assertion, we take the reqbyte, if set. This can be - helpful if the pattern that follows the assertion doesn't set a different - char. For example, it's useful for /(?=abcde).+/. We can't set firstbyte - for an assertion, however because it leads to incorrect effect for patterns - such as /(?=a)a.+/ when the "real" "a" would then become a reqbyte instead - of a firstbyte. This is overcome by a scan at the end if there's no - firstbyte, looking for an asserted first char. */ - - else if (bravalue == OP_ASSERT && subreqbyte >= 0) reqbyte = subreqbyte; - break; /* End of processing '(' */ - - - /* ===================================================================*/ - /* Handle metasequences introduced by \. For ones like \d, the ESC_ values - are arranged to be the negation of the corresponding OP_values. For the - back references, the values are ESC_REF plus the reference number. Only - back references and those types that consume a character may be repeated. - We can test for values between ESC_b and ESC_Z for the latter; this may - have to change if any new ones are ever created. */ - - case '\\': - tempptr = ptr; - c = check_escape(&ptr, errorcodeptr, cd->bracount, options, FALSE); - if (*errorcodeptr != 0) goto FAILED; - - if (c < 0) - { - if (-c == ESC_Q) /* Handle start of quoted string */ - { - if (ptr[1] == '\\' && ptr[2] == 'E') ptr += 2; /* avoid empty string */ - else inescq = TRUE; - continue; - } - - if (-c == ESC_E) continue; /* Perl ignores an orphan \E */ - - /* For metasequences that actually match a character, we disable the - setting of a first character if it hasn't already been set. */ - - if (firstbyte == REQ_UNSET && -c > ESC_b && -c < ESC_Z) - firstbyte = REQ_NONE; - - /* Set values to reset to if this is followed by a zero repeat. */ - - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - - /* \k<name> or \k'name' is a back reference by name (Perl syntax). - We also support \k{name} (.NET syntax) */ - - if (-c == ESC_k && (ptr[1] == '<' || ptr[1] == '\'' || ptr[1] == '{')) - { - is_recurse = FALSE; - terminator = (*(++ptr) == '<')? '>' : (*ptr == '\'')? '\'' : '}'; - goto NAMED_REF_OR_RECURSE; - } - - /* Back references are handled specially; must disable firstbyte if - not set to cope with cases like (?=(\w+))\1: which would otherwise set - ':' later. */ - - if (-c >= ESC_REF) - { - recno = -c - ESC_REF; - - HANDLE_REFERENCE: /* Come here from named backref handling */ - if (firstbyte == REQ_UNSET) firstbyte = REQ_NONE; - previous = code; - *code++ = OP_REF; - PUT2INC(code, 0, recno); - cd->backref_map |= (recno < 32)? (1 << recno) : 1; - if (recno > cd->top_backref) cd->top_backref = recno; - } - - /* So are Unicode property matches, if supported. */ - -#ifdef SUPPORT_UCP - else if (-c == ESC_P || -c == ESC_p) - { - BOOL negated; - int pdata; - int ptype = get_ucp(&ptr, &negated, &pdata, errorcodeptr); - if (ptype < 0) goto FAILED; - previous = code; - *code++ = ((-c == ESC_p) != negated)? OP_PROP : OP_NOTPROP; - *code++ = ptype; - *code++ = pdata; - } -#else - - /* If Unicode properties are not supported, \X, \P, and \p are not - allowed. */ - - else if (-c == ESC_X || -c == ESC_P || -c == ESC_p) - { - *errorcodeptr = ERR45; - goto FAILED; - } -#endif - - /* For the rest (including \X when Unicode properties are supported), we - can obtain the OP value by negating the escape value. */ - - else - { - previous = (-c > ESC_b && -c < ESC_Z)? code : NULL; - *code++ = -c; - } - continue; - } - - /* We have a data character whose value is in c. In UTF-8 mode it may have - a value > 127. We set its representation in the length/buffer, and then - handle it as a data character. */ - -#ifdef SUPPORT_UTF8 - if (utf8 && c > 127) - mclength = _pcre_ord2utf8(c, mcbuffer); - else -#endif - - { - mcbuffer[0] = c; - mclength = 1; - } - goto ONE_CHAR; - - - /* ===================================================================*/ - /* Handle a literal character. It is guaranteed not to be whitespace or # - when the extended flag is set. If we are in UTF-8 mode, it may be a - multi-byte literal character. */ - - default: - NORMAL_CHAR: - mclength = 1; - mcbuffer[0] = c; - -#ifdef SUPPORT_UTF8 - if (utf8 && c >= 0xc0) - { - while ((ptr[1] & 0xc0) == 0x80) - mcbuffer[mclength++] = *(++ptr); - } -#endif - - /* At this point we have the character's bytes in mcbuffer, and the length - in mclength. When not in UTF-8 mode, the length is always 1. */ - - ONE_CHAR: - previous = code; - *code++ = ((options & PCRE_CASELESS) != 0)? OP_CHARNC : OP_CHAR; - for (c = 0; c < mclength; c++) *code++ = mcbuffer[c]; - - /* Remember if \r or \n were seen */ - - if (mcbuffer[0] == '\r' || mcbuffer[0] == '\n') - cd->external_flags |= PCRE_HASCRORLF; - - /* Set the first and required bytes appropriately. If no previous first - byte, set it from this character, but revert to none on a zero repeat. - Otherwise, leave the firstbyte value alone, and don't change it on a zero - repeat. */ - - if (firstbyte == REQ_UNSET) - { - zerofirstbyte = REQ_NONE; - zeroreqbyte = reqbyte; - - /* If the character is more than one byte long, we can set firstbyte - only if it is not to be matched caselessly. */ - - if (mclength == 1 || req_caseopt == 0) - { - firstbyte = mcbuffer[0] | req_caseopt; - if (mclength != 1) reqbyte = code[-1] | cd->req_varyopt; - } - else firstbyte = reqbyte = REQ_NONE; - } - - /* firstbyte was previously set; we can set reqbyte only the length is - 1 or the matching is caseful. */ - - else - { - zerofirstbyte = firstbyte; - zeroreqbyte = reqbyte; - if (mclength == 1 || req_caseopt == 0) - reqbyte = code[-1] | req_caseopt | cd->req_varyopt; - } - - break; /* End of literal character handling */ - } - } /* end of big loop */ - - -/* Control never reaches here by falling through, only by a goto for all the -error states. Pass back the position in the pattern so that it can be displayed -to the user for diagnosing the error. */ - -FAILED: -*ptrptr = ptr; -return FALSE; -} - - - - -/************************************************* -* Compile sequence of alternatives * -*************************************************/ - -/* On entry, ptr is pointing past the bracket character, but on return it -points to the closing bracket, or vertical bar, or end of string. The code -variable is pointing at the byte into which the BRA operator has been stored. -If the ims options are changed at the start (for a (?ims: group) or during any -branch, we need to insert an OP_OPT item at the start of every following branch -to ensure they get set correctly at run time, and also pass the new options -into every subsequent branch compile. - -This function is used during the pre-compile phase when we are trying to find -out the amount of memory needed, as well as during the real compile phase. The -value of lengthptr distinguishes the two phases. - -Arguments: - options option bits, including any changes for this subpattern - oldims previous settings of ims option bits - codeptr -> the address of the current code pointer - ptrptr -> the address of the current pattern pointer - errorcodeptr -> pointer to error code variable - lookbehind TRUE if this is a lookbehind assertion - reset_bracount TRUE to reset the count for each branch - skipbytes skip this many bytes at start (for brackets and OP_COND) - firstbyteptr place to put the first required character, or a negative number - reqbyteptr place to put the last required character, or a negative number - bcptr pointer to the chain of currently open branches - cd points to the data block with tables pointers etc. - lengthptr NULL during the real compile phase - points to length accumulator during pre-compile phase - -Returns: TRUE on success -*/ - -static BOOL -compile_regex(int options, int oldims, uschar **codeptr, const uschar **ptrptr, - int *errorcodeptr, BOOL lookbehind, BOOL reset_bracount, int skipbytes, - int *firstbyteptr, int *reqbyteptr, branch_chain *bcptr, compile_data *cd, - int *lengthptr) -{ -const uschar *ptr = *ptrptr; -uschar *code = *codeptr; -uschar *last_branch = code; -uschar *start_bracket = code; -uschar *reverse_count = NULL; -int firstbyte, reqbyte; -int branchfirstbyte, branchreqbyte; -int length; -int orig_bracount; -int max_bracount; -branch_chain bc; - -bc.outer = bcptr; -bc.current = code; - -firstbyte = reqbyte = REQ_UNSET; - -/* Accumulate the length for use in the pre-compile phase. Start with the -length of the BRA and KET and any extra bytes that are required at the -beginning. We accumulate in a local variable to save frequent testing of -lenthptr for NULL. We cannot do this by looking at the value of code at the -start and end of each alternative, because compiled items are discarded during -the pre-compile phase so that the work space is not exceeded. */ - -length = 2 + 2*LINK_SIZE + skipbytes; - -/* WARNING: If the above line is changed for any reason, you must also change -the code that abstracts option settings at the start of the pattern and makes -them global. It tests the value of length for (2 + 2*LINK_SIZE) in the -pre-compile phase to find out whether anything has yet been compiled or not. */ - -/* Offset is set zero to mark that this bracket is still open */ - -PUT(code, 1, 0); -code += 1 + LINK_SIZE + skipbytes; - -/* Loop for each alternative branch */ - -orig_bracount = max_bracount = cd->bracount; -for (;;) - { - /* For a (?| group, reset the capturing bracket count so that each branch - uses the same numbers. */ - - if (reset_bracount) cd->bracount = orig_bracount; - - /* Handle a change of ims options at the start of the branch */ - - if ((options & PCRE_IMS) != oldims) - { - *code++ = OP_OPT; - *code++ = options & PCRE_IMS; - length += 2; - } - - /* Set up dummy OP_REVERSE if lookbehind assertion */ - - if (lookbehind) - { - *code++ = OP_REVERSE; - reverse_count = code; - PUTINC(code, 0, 0); - length += 1 + LINK_SIZE; - } - - /* Now compile the branch; in the pre-compile phase its length gets added - into the length. */ - - if (!compile_branch(&options, &code, &ptr, errorcodeptr, &branchfirstbyte, - &branchreqbyte, &bc, cd, (lengthptr == NULL)? NULL : &length)) - { - *ptrptr = ptr; - return FALSE; - } - - /* Keep the highest bracket count in case (?| was used and some branch - has fewer than the rest. */ - - if (cd->bracount > max_bracount) max_bracount = cd->bracount; - - /* In the real compile phase, there is some post-processing to be done. */ - - if (lengthptr == NULL) - { - /* If this is the first branch, the firstbyte and reqbyte values for the - branch become the values for the regex. */ - - if (*last_branch != OP_ALT) - { - firstbyte = branchfirstbyte; - reqbyte = branchreqbyte; - } - - /* If this is not the first branch, the first char and reqbyte have to - match the values from all the previous branches, except that if the - previous value for reqbyte didn't have REQ_VARY set, it can still match, - and we set REQ_VARY for the regex. */ - - else - { - /* If we previously had a firstbyte, but it doesn't match the new branch, - we have to abandon the firstbyte for the regex, but if there was - previously no reqbyte, it takes on the value of the old firstbyte. */ - - if (firstbyte >= 0 && firstbyte != branchfirstbyte) - { - if (reqbyte < 0) reqbyte = firstbyte; - firstbyte = REQ_NONE; - } - - /* If we (now or from before) have no firstbyte, a firstbyte from the - branch becomes a reqbyte if there isn't a branch reqbyte. */ - - if (firstbyte < 0 && branchfirstbyte >= 0 && branchreqbyte < 0) - branchreqbyte = branchfirstbyte; - - /* Now ensure that the reqbytes match */ - - if ((reqbyte & ~REQ_VARY) != (branchreqbyte & ~REQ_VARY)) - reqbyte = REQ_NONE; - else reqbyte |= branchreqbyte; /* To "or" REQ_VARY */ - } - - /* If lookbehind, check that this branch matches a fixed-length string, and - put the length into the OP_REVERSE item. Temporarily mark the end of the - branch with OP_END. */ - - if (lookbehind) - { - int fixed_length; - *code = OP_END; - fixed_length = find_fixedlength(last_branch, options); - DPRINTF(("fixed length = %d\n", fixed_length)); - if (fixed_length < 0) - { - *errorcodeptr = (fixed_length == -2)? ERR36 : ERR25; - *ptrptr = ptr; - return FALSE; - } - PUT(reverse_count, 0, fixed_length); - } - } - - /* Reached end of expression, either ')' or end of pattern. In the real - compile phase, go back through the alternative branches and reverse the chain - of offsets, with the field in the BRA item now becoming an offset to the - first alternative. If there are no alternatives, it points to the end of the - group. The length in the terminating ket is always the length of the whole - bracketed item. If any of the ims options were changed inside the group, - compile a resetting op-code following, except at the very end of the pattern. - Return leaving the pointer at the terminating char. */ - - if (*ptr != '|') - { - if (lengthptr == NULL) - { - int branch_length = code - last_branch; - do - { - int prev_length = GET(last_branch, 1); - PUT(last_branch, 1, branch_length); - branch_length = prev_length; - last_branch -= branch_length; - } - while (branch_length > 0); - } - - /* Fill in the ket */ - - *code = OP_KET; - PUT(code, 1, code - start_bracket); - code += 1 + LINK_SIZE; - - /* Resetting option if needed */ - - if ((options & PCRE_IMS) != oldims && *ptr == ')') - { - *code++ = OP_OPT; - *code++ = oldims; - length += 2; - } - - /* Retain the highest bracket number, in case resetting was used. */ - - cd->bracount = max_bracount; - - /* Set values to pass back */ - - *codeptr = code; - *ptrptr = ptr; - *firstbyteptr = firstbyte; - *reqbyteptr = reqbyte; - if (lengthptr != NULL) - { - if (OFLOW_MAX - *lengthptr < length) - { - *errorcodeptr = ERR20; - return FALSE; - } - *lengthptr += length; - } - return TRUE; - } - - /* Another branch follows. In the pre-compile phase, we can move the code - pointer back to where it was for the start of the first branch. (That is, - pretend that each branch is the only one.) - - In the real compile phase, insert an ALT node. Its length field points back - to the previous branch while the bracket remains open. At the end the chain - is reversed. It's done like this so that the start of the bracket has a - zero offset until it is closed, making it possible to detect recursion. */ - - if (lengthptr != NULL) - { - code = *codeptr + 1 + LINK_SIZE + skipbytes; - length += 1 + LINK_SIZE; - } - else - { - *code = OP_ALT; - PUT(code, 1, code - last_branch); - bc.current = last_branch = code; - code += 1 + LINK_SIZE; - } - - ptr++; - } -/* Control never reaches here */ -} - - - - -/************************************************* -* Check for anchored expression * -*************************************************/ - -/* Try to find out if this is an anchored regular expression. Consider each -alternative branch. If they all start with OP_SOD or OP_CIRC, or with a bracket -all of whose alternatives start with OP_SOD or OP_CIRC (recurse ad lib), then -it's anchored. However, if this is a multiline pattern, then only OP_SOD -counts, since OP_CIRC can match in the middle. - -We can also consider a regex to be anchored if OP_SOM starts all its branches. -This is the code for \G, which means "match at start of match position, taking -into account the match offset". - -A branch is also implicitly anchored if it starts with .* and DOTALL is set, -because that will try the rest of the pattern at all possible matching points, -so there is no point trying again.... er .... - -.... except when the .* appears inside capturing parentheses, and there is a -subsequent back reference to those parentheses. We haven't enough information -to catch that case precisely. - -At first, the best we could do was to detect when .* was in capturing brackets -and the highest back reference was greater than or equal to that level. -However, by keeping a bitmap of the first 31 back references, we can catch some -of the more common cases more precisely. - -Arguments: - code points to start of expression (the bracket) - options points to the options setting - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - backref_map the back reference bitmap - -Returns: TRUE or FALSE -*/ - -static BOOL -is_anchored(register const uschar *code, int *options, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], - options, PCRE_MULTILINE, FALSE); - register int op = *scode; - - /* Non-capturing brackets */ - - if (op == OP_BRA) - { - if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_anchored(scode, options, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { - if (!is_anchored(scode, options, bracket_map, backref_map)) return FALSE; - } - - /* .* is not anchored unless DOTALL is set and it isn't in brackets that - are or may be referenced. */ - - else if ((op == OP_TYPESTAR || op == OP_TYPEMINSTAR || - op == OP_TYPEPOSSTAR) && - (*options & PCRE_DOTALL) != 0) - { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; - } - - /* Check for explicit anchoring */ - - else if (op != OP_SOD && op != OP_SOM && - ((*options & PCRE_MULTILINE) != 0 || op != OP_CIRC)) - return FALSE; - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for starting with ^ or .* * -*************************************************/ - -/* This is called to find out if every branch starts with ^ or .* so that -"first char" processing can be done to speed things up in multiline -matching and for non-DOTALL patterns that start with .* (which must start at -the beginning or after \n). As in the case of is_anchored() (see above), we -have to take account of back references to capturing brackets that contain .* -because in that case we can't make the assumption. - -Arguments: - code points to start of expression (the bracket) - bracket_map a bitmap of which brackets we are inside while testing; this - handles up to substring 31; after that we just have to take - the less precise approach - backref_map the back reference bitmap - -Returns: TRUE or FALSE -*/ - -static BOOL -is_startline(const uschar *code, unsigned int bracket_map, - unsigned int backref_map) -{ -do { - const uschar *scode = first_significant_code(code + _pcre_OP_lengths[*code], - NULL, 0, FALSE); - register int op = *scode; - - /* Non-capturing brackets */ - - if (op == OP_BRA) - { - if (!is_startline(scode, bracket_map, backref_map)) return FALSE; - } - - /* Capturing brackets */ - - else if (op == OP_CBRA) - { - int n = GET2(scode, 1+LINK_SIZE); - int new_map = bracket_map | ((n < 32)? (1 << n) : 1); - if (!is_startline(scode, new_map, backref_map)) return FALSE; - } - - /* Other brackets */ - - else if (op == OP_ASSERT || op == OP_ONCE || op == OP_COND) - { if (!is_startline(scode, bracket_map, backref_map)) return FALSE; } - - /* .* means "start at start or after \n" if it isn't in brackets that - may be referenced. */ - - else if (op == OP_TYPESTAR || op == OP_TYPEMINSTAR || op == OP_TYPEPOSSTAR) - { - if (scode[1] != OP_ANY || (bracket_map & backref_map) != 0) return FALSE; - } - - /* Check for explicit circumflex */ - - else if (op != OP_CIRC) return FALSE; - - /* Move on to the next alternative */ - - code += GET(code, 1); - } -while (*code == OP_ALT); /* Loop for each alternative */ -return TRUE; -} - - - -/************************************************* -* Check for asserted fixed first char * -*************************************************/ - -/* During compilation, the "first char" settings from forward assertions are -discarded, because they can cause conflicts with actual literals that follow. -However, if we end up without a first char setting for an unanchored pattern, -it is worth scanning the regex to see if there is an initial asserted first -char. If all branches start with the same asserted char, or with a bracket all -of whose alternatives start with the same asserted char (recurse ad lib), then -we return that char, otherwise -1. - -Arguments: - code points to start of expression (the bracket) - options pointer to the options (used to check casing changes) - inassert TRUE if in an assertion - -Returns: -1 or the fixed first char -*/ - -static int -find_firstassertedchar(const uschar *code, int *options, BOOL inassert) -{ -register int c = -1; -do { - int d; - const uschar *scode = - first_significant_code(code + 1+LINK_SIZE, options, PCRE_CASELESS, TRUE); - register int op = *scode; - - switch(op) - { - default: - return -1; - - case OP_BRA: - case OP_CBRA: - case OP_ASSERT: - case OP_ONCE: - case OP_COND: - if ((d = find_firstassertedchar(scode, options, op == OP_ASSERT)) < 0) - return -1; - if (c < 0) c = d; else if (c != d) return -1; - break; - - case OP_EXACT: /* Fall through */ - scode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - if (!inassert) return -1; - if (c < 0) - { - c = scode[1]; - if ((*options & PCRE_CASELESS) != 0) c |= REQ_CASELESS; - } - else if (c != scode[1]) return -1; - break; - } - - code += GET(code, 1); - } -while (*code == OP_ALT); -return c; -} - - - -/************************************************* -* Compile a Regular Expression * -*************************************************/ - -/* This function takes a string and returns a pointer to a block of store -holding a compiled version of the expression. The original API for this -function had no error code return variable; it is retained for backwards -compatibility. The new function is given a new name. - -Arguments: - pattern the regular expression - options various option bits - errorcodeptr pointer to error code variable (pcre_compile2() only) - can be NULL if you don't want a code value - errorptr pointer to pointer to error text - erroroffset ptr offset in pattern where error was detected - tables pointer to character tables or NULL - -Returns: pointer to compiled data block, or NULL on error, - with errorptr and erroroffset set -*/ - -PCRE_EXP_DEFN pcre * -pcre_compile(const char *pattern, int options, const char **errorptr, - int *erroroffset, const unsigned char *tables) -{ -return pcre_compile2(pattern, options, NULL, errorptr, erroroffset, tables); -} - - -PCRE_EXP_DEFN pcre * -pcre_compile2(const char *pattern, int options, int *errorcodeptr, - const char **errorptr, int *erroroffset, const unsigned char *tables) -{ -real_pcre *re; -int length = 1; /* For final END opcode */ -int firstbyte, reqbyte, newline; -int errorcode = 0; -int skipatstart = 0; -#ifdef SUPPORT_UTF8 -BOOL utf8; -#endif -size_t size; -uschar *code; -const uschar *codestart; -const uschar *ptr; -compile_data compile_block; -compile_data *cd = &compile_block; - -/* This space is used for "compiling" into during the first phase, when we are -computing the amount of memory that is needed. Compiled items are thrown away -as soon as possible, so that a fairly large buffer should be sufficient for -this purpose. The same space is used in the second phase for remembering where -to fill in forward references to subpatterns. */ - -uschar cworkspace[COMPILE_WORK_SIZE]; - - -/* Set this early so that early errors get offset 0. */ - -ptr = (const uschar *)pattern; - -/* We can't pass back an error message if errorptr is NULL; I guess the best we -can do is just return NULL, but we can set a code value if there is a code -pointer. */ - -if (errorptr == NULL) - { - if (errorcodeptr != NULL) *errorcodeptr = 99; - return NULL; - } - -*errorptr = NULL; -if (errorcodeptr != NULL) *errorcodeptr = ERR0; - -/* However, we can give a message for this error */ - -if (erroroffset == NULL) - { - errorcode = ERR16; - goto PCRE_EARLY_ERROR_RETURN2; - } - -*erroroffset = 0; - -/* Can't support UTF8 unless PCRE has been compiled to include the code. */ - -#ifdef SUPPORT_UTF8 -utf8 = (options & PCRE_UTF8) != 0; -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0 && - (*erroroffset = _pcre_valid_utf8((uschar *)pattern, -1)) >= 0) - { - errorcode = ERR44; - goto PCRE_EARLY_ERROR_RETURN2; - } -#else -if ((options & PCRE_UTF8) != 0) - { - errorcode = ERR32; - goto PCRE_EARLY_ERROR_RETURN; - } -#endif - -if ((options & ~PUBLIC_OPTIONS) != 0) - { - errorcode = ERR17; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Set up pointers to the individual character tables */ - -if (tables == NULL) tables = _pcre_default_tables; -cd->lcc = tables + lcc_offset; -cd->fcc = tables + fcc_offset; -cd->cbits = tables + cbits_offset; -cd->ctypes = tables + ctypes_offset; - -/* Check for global one-time settings at the start of the pattern, and remember -the offset for later. */ - -while (ptr[skipatstart] == '(' && ptr[skipatstart+1] == '*') - { - int newnl = 0; - int newbsr = 0; - - if (strncmp((char *)(ptr+skipatstart+2), "CR)", 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_CR; } - else if (strncmp((char *)(ptr+skipatstart+2), "LF)", 3) == 0) - { skipatstart += 5; newnl = PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+skipatstart+2), "CRLF)", 5) == 0) - { skipatstart += 7; newnl = PCRE_NEWLINE_CR + PCRE_NEWLINE_LF; } - else if (strncmp((char *)(ptr+skipatstart+2), "ANY)", 4) == 0) - { skipatstart += 6; newnl = PCRE_NEWLINE_ANY; } - else if (strncmp((char *)(ptr+skipatstart+2), "ANYCRLF)", 8) == 0) - { skipatstart += 10; newnl = PCRE_NEWLINE_ANYCRLF; } - - else if (strncmp((char *)(ptr+skipatstart+2), "BSR_ANYCRLF)", 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_ANYCRLF; } - else if (strncmp((char *)(ptr+skipatstart+2), "BSR_UNICODE)", 12) == 0) - { skipatstart += 14; newbsr = PCRE_BSR_UNICODE; } - - if (newnl != 0) - options = (options & ~PCRE_NEWLINE_BITS) | newnl; - else if (newbsr != 0) - options = (options & ~(PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) | newbsr; - else break; - } - -/* Check validity of \R options. */ - -switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - case 0: - case PCRE_BSR_ANYCRLF: - case PCRE_BSR_UNICODE: - break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -/* Handle different types of newline. The three bits give seven cases. The -current code allows for fixed one- or two-byte sequences, plus "any" and -"anycrlf". */ - -switch (options & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Build-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: errorcode = ERR56; goto PCRE_EARLY_ERROR_RETURN; - } - -if (newline == -2) - { - cd->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - cd->nltype = NLTYPE_ANY; - } -else - { - cd->nltype = NLTYPE_FIXED; - if (newline > 255) - { - cd->nllen = 2; - cd->nl[0] = (newline >> 8) & 255; - cd->nl[1] = newline & 255; - } - else - { - cd->nllen = 1; - cd->nl[0] = newline; - } - } - -/* Maximum back reference and backref bitmap. The bitmap records up to 31 back -references to help in deciding whether (.*) can be treated as anchored or not. -*/ - -cd->top_backref = 0; -cd->backref_map = 0; - -/* Reflect pattern for debugging output */ - -DPRINTF(("------------------------------------------------------------------\n")); -DPRINTF(("%s\n", pattern)); - -/* Pretend to compile the pattern while actually just accumulating the length -of memory required. This behaviour is triggered by passing a non-NULL final -argument to compile_regex(). We pass a block of workspace (cworkspace) for it -to compile parts of the pattern into; the compiled code is discarded when it is -no longer needed, so hopefully this workspace will never overflow, though there -is a test for its doing so. */ - -cd->bracount = 0; -cd->names_found = 0; -cd->name_entry_size = 0; -cd->name_table = NULL; -cd->start_workspace = cworkspace; -cd->start_code = cworkspace; -cd->hwm = cworkspace; -cd->start_pattern = (const uschar *)pattern; -cd->end_pattern = (const uschar *)(pattern + strlen(pattern)); -cd->req_varyopt = 0; -cd->external_options = options; -cd->external_flags = 0; - -/* Now do the pre-compile. On error, errorcode will be set non-zero, so we -don't need to look at the result of the function here. The initial options have -been put into the cd block so that they can be changed if an option setting is -found within the regex right at the beginning. Bringing initial option settings -outside can help speed up starting point checks. */ - -ptr += skipatstart; -code = cworkspace; -*code = OP_BRA; -(void)compile_regex(cd->external_options, cd->external_options & PCRE_IMS, - &code, &ptr, &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, - &length); -if (errorcode != 0) goto PCRE_EARLY_ERROR_RETURN; - -DPRINTF(("end pre-compile: length=%d workspace=%d\n", length, - cd->hwm - cworkspace)); - -if (length > MAX_PATTERN_SIZE) - { - errorcode = ERR20; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Compute the size of data block needed and get it, either from malloc or -externally provided function. Integer overflow should no longer be possible -because nowadays we limit the maximum value of cd->names_found and -cd->name_entry_size. */ - -size = length + sizeof(real_pcre) + cd->names_found * (cd->name_entry_size + 3); -re = (real_pcre *)(pcre_malloc)(size); - -if (re == NULL) - { - errorcode = ERR21; - goto PCRE_EARLY_ERROR_RETURN; - } - -/* Put in the magic number, and save the sizes, initial options, internal -flags, and character table pointer. NULL is used for the default character -tables. The nullpad field is at the end; it's there to help in the case when a -regex compiled on a system with 4-byte pointers is run on another with 8-byte -pointers. */ - -re->magic_number = MAGIC_NUMBER; -re->size = size; -re->options = cd->external_options; -re->flags = cd->external_flags; -re->dummy1 = 0; -re->first_byte = 0; -re->req_byte = 0; -re->name_table_offset = sizeof(real_pcre); -re->name_entry_size = cd->name_entry_size; -re->name_count = cd->names_found; -re->ref_count = 0; -re->tables = (tables == _pcre_default_tables)? NULL : tables; -re->nullpad = NULL; - -/* The starting points of the name/number translation table and of the code are -passed around in the compile data block. The start/end pattern and initial -options are already set from the pre-compile phase, as is the name_entry_size -field. Reset the bracket count and the names_found field. Also reset the hwm -field; this time it's used for remembering forward references to subpatterns. -*/ - -cd->bracount = 0; -cd->names_found = 0; -cd->name_table = (uschar *)re + re->name_table_offset; -codestart = cd->name_table + re->name_entry_size * re->name_count; -cd->start_code = codestart; -cd->hwm = cworkspace; -cd->req_varyopt = 0; -cd->had_accept = FALSE; - -/* Set up a starting, non-extracting bracket, then compile the expression. On -error, errorcode will be set non-zero, so we don't need to look at the result -of the function here. */ - -ptr = (const uschar *)pattern + skipatstart; -code = (uschar *)codestart; -*code = OP_BRA; -(void)compile_regex(re->options, re->options & PCRE_IMS, &code, &ptr, - &errorcode, FALSE, FALSE, 0, &firstbyte, &reqbyte, NULL, cd, NULL); -re->top_bracket = cd->bracount; -re->top_backref = cd->top_backref; -re->flags = cd->external_flags; - -if (cd->had_accept) reqbyte = -1; /* Must disable after (*ACCEPT) */ - -/* If not reached end of pattern on success, there's an excess bracket. */ - -if (errorcode == 0 && *ptr != 0) errorcode = ERR22; - -/* Fill in the terminating state and check for disastrous overflow, but -if debugging, leave the test till after things are printed out. */ - -*code++ = OP_END; - -#ifndef DEBUG -if (code - codestart > length) errorcode = ERR23; -#endif - -/* Fill in any forward references that are required. */ - -while (errorcode == 0 && cd->hwm > cworkspace) - { - int offset, recno; - const uschar *groupptr; - cd->hwm -= LINK_SIZE; - offset = GET(cd->hwm, 0); - recno = GET(codestart, offset); - groupptr = find_bracket(codestart, (re->options & PCRE_UTF8) != 0, recno); - if (groupptr == NULL) errorcode = ERR53; - else PUT(((uschar *)codestart), offset, groupptr - codestart); - } - -/* Give an error if there's back reference to a non-existent capturing -subpattern. */ - -if (errorcode == 0 && re->top_backref > re->top_bracket) errorcode = ERR15; - -/* Failed to compile, or error while post-processing */ - -if (errorcode != 0) - { - (pcre_free)(re); - PCRE_EARLY_ERROR_RETURN: - *erroroffset = ptr - (const uschar *)pattern; - PCRE_EARLY_ERROR_RETURN2: - *errorptr = find_error_text(errorcode); - if (errorcodeptr != NULL) *errorcodeptr = errorcode; - return NULL; - } - -/* If the anchored option was not passed, set the flag if we can determine that -the pattern is anchored by virtue of ^ characters or \A or anything else (such -as starting with .* when DOTALL is set). - -Otherwise, if we know what the first byte has to be, save it, because that -speeds up unanchored matches no end. If not, see if we can set the -PCRE_STARTLINE flag. This is helpful for multiline matches when all branches -start with ^. and also when all branches start with .* for non-DOTALL matches. -*/ - -if ((re->options & PCRE_ANCHORED) == 0) - { - int temp_options = re->options; /* May get changed during these scans */ - if (is_anchored(codestart, &temp_options, 0, cd->backref_map)) - re->options |= PCRE_ANCHORED; - else - { - if (firstbyte < 0) - firstbyte = find_firstassertedchar(codestart, &temp_options, FALSE); - if (firstbyte >= 0) /* Remove caseless flag for non-caseable chars */ - { - int ch = firstbyte & 255; - re->first_byte = ((firstbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? ch : firstbyte; - re->flags |= PCRE_FIRSTSET; - } - else if (is_startline(codestart, 0, cd->backref_map)) - re->flags |= PCRE_STARTLINE; - } - } - -/* For an anchored pattern, we use the "required byte" only if it follows a -variable length item in the regex. Remove the caseless flag for non-caseable -bytes. */ - -if (reqbyte >= 0 && - ((re->options & PCRE_ANCHORED) == 0 || (reqbyte & REQ_VARY) != 0)) - { - int ch = reqbyte & 255; - re->req_byte = ((reqbyte & REQ_CASELESS) != 0 && - cd->fcc[ch] == ch)? (reqbyte & ~REQ_CASELESS) : reqbyte; - re->flags |= PCRE_REQCHSET; - } - -/* Print out the compiled data if debugging is enabled. This is never the -case when building a production library. */ - -#ifdef DEBUG - -printf("Length = %d top_bracket = %d top_backref = %d\n", - length, re->top_bracket, re->top_backref); - -printf("Options=%08x\n", re->options); - -if ((re->flags & PCRE_FIRSTSET) != 0) - { - int ch = re->first_byte & 255; - const char *caseless = ((re->first_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("First char = %c%s\n", ch, caseless); - else printf("First char = \\x%02x%s\n", ch, caseless); - } - -if ((re->flags & PCRE_REQCHSET) != 0) - { - int ch = re->req_byte & 255; - const char *caseless = ((re->req_byte & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (isprint(ch)) printf("Req char = %c%s\n", ch, caseless); - else printf("Req char = \\x%02x%s\n", ch, caseless); - } - -pcre_printint(re, stdout, TRUE); - -/* This check is done here in the debugging case so that the code that -was compiled can be seen. */ - -if (code - codestart > length) - { - (pcre_free)(re); - *errorptr = find_error_text(ERR23); - *erroroffset = ptr - (uschar *)pattern; - if (errorcodeptr != NULL) *errorcodeptr = ERR23; - return NULL; - } -#endif /* DEBUG */ - -return (pcre *)re; -} - -/* End of pcre_compile.c */ diff --git a/src/src/pcre/pcre_config.c b/src/src/pcre/pcre_config.c deleted file mode 100644 index 131ae6410..000000000 --- a/src/src/pcre/pcre_config.c +++ /dev/null @@ -1,130 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_config.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_config(). */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return info about what features are configured * -*************************************************/ - -/* This function has an extensible interface so that additional items can be -added compatibly. - -Arguments: - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -PCRE_EXP_DEFN int -pcre_config(int what, void *where) -{ -switch (what) - { - case PCRE_CONFIG_UTF8: -#ifdef SUPPORT_UTF8 - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_UNICODE_PROPERTIES: -#ifdef SUPPORT_UCP - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_NEWLINE: - *((int *)where) = NEWLINE; - break; - - case PCRE_CONFIG_BSR: -#ifdef BSR_ANYCRLF - *((int *)where) = 1; -#else - *((int *)where) = 0; -#endif - break; - - case PCRE_CONFIG_LINK_SIZE: - *((int *)where) = LINK_SIZE; - break; - - case PCRE_CONFIG_POSIX_MALLOC_THRESHOLD: - *((int *)where) = POSIX_MALLOC_THRESHOLD; - break; - - case PCRE_CONFIG_MATCH_LIMIT: - *((unsigned int *)where) = MATCH_LIMIT; - break; - - case PCRE_CONFIG_MATCH_LIMIT_RECURSION: - *((unsigned int *)where) = MATCH_LIMIT_RECURSION; - break; - - case PCRE_CONFIG_STACKRECURSE: -#ifdef NO_RECURSE - *((int *)where) = 0; -#else - *((int *)where) = 1; -#endif - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_config.c */ diff --git a/src/src/pcre/pcre_exec.c b/src/src/pcre/pcre_exec.c deleted file mode 100644 index 12703bfa1..000000000 --- a/src/src/pcre/pcre_exec.c +++ /dev/null @@ -1,4940 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_exec.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains pcre_exec(), the externally visible function that does -pattern matching using an NFA algorithm, trying to mimic Perl as closely as -possible. There are also some static supporting functions. */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#define NLBLOCK md /* Block containing newline information */ -#define PSSTART start_subject /* Field containing processed string start */ -#define PSEND end_subject /* Field containing processed string end */ - -#include "pcre_internal.h" - -/* Undefine some potentially clashing cpp symbols */ - -#undef min -#undef max - -/* Flag bits for the match() function */ - -#define match_condassert 0x01 /* Called to check a condition assertion */ -#define match_cbegroup 0x02 /* Could-be-empty unlimited repeat group */ - -/* Non-error returns from the match() function. Error returns are externally -defined PCRE_ERROR_xxx codes, which are all negative. */ - -#define MATCH_MATCH 1 -#define MATCH_NOMATCH 0 - -/* Special internal returns from the match() function. Make them sufficiently -negative to avoid the external error codes. */ - -#define MATCH_COMMIT (-999) -#define MATCH_PRUNE (-998) -#define MATCH_SKIP (-997) -#define MATCH_THEN (-996) - -/* Maximum number of ints of offset to save on the stack for recursive calls. -If the offset vector is bigger, malloc is used. This should be a multiple of 3, -because the offset vector is always a multiple of 3 long. */ - -#define REC_STACK_SAVE_MAX 30 - -/* Min and max values for the common repeats; for the maxima, 0 => infinity */ - -static const char rep_min[] = { 0, 0, 1, 1, 0, 0 }; -static const char rep_max[] = { 0, 0, 0, 0, 1, 1 }; - - - -#ifdef DEBUG -/************************************************* -* Debugging function to print chars * -*************************************************/ - -/* Print a sequence of chars in printable format, stopping at the end of the -subject if the requested. - -Arguments: - p points to characters - length number to print - is_subject TRUE if printing from within md->start_subject - md pointer to matching data block, if is_subject is TRUE - -Returns: nothing -*/ - -static void -pchars(const uschar *p, int length, BOOL is_subject, match_data *md) -{ -unsigned int c; -if (is_subject && length > md->end_subject - p) length = md->end_subject - p; -while (length-- > 0) - if (isprint(c = *(p++))) printf("%c", c); else printf("\\x%02x", c); -} -#endif - - - -/************************************************* -* Match a back-reference * -*************************************************/ - -/* If a back reference hasn't been set, the length that is passed is greater -than the number of characters left in the string, so the match fails. - -Arguments: - offset index into the offset vector - eptr points into the subject - length length to be matched - md points to match data block - ims the ims flags - -Returns: TRUE if matched -*/ - -static BOOL -match_ref(int offset, register USPTR eptr, int length, match_data *md, - unsigned long int ims) -{ -USPTR p = md->start_subject + md->offset_vector[offset]; - -#ifdef DEBUG -if (eptr >= md->end_subject) - printf("matching subject <null>"); -else - { - printf("matching subject "); - pchars(eptr, length, TRUE, md); - } -printf(" against backref "); -pchars(p, length, FALSE, md); -printf("\n"); -#endif - -/* Always fail if not enough characters left */ - -if (length > md->end_subject - eptr) return FALSE; - -/* Separate the caselesss case for speed */ - -if ((ims & PCRE_CASELESS) != 0) - { - while (length-- > 0) - if (md->lcc[*p++] != md->lcc[*eptr++]) return FALSE; - } -else - { while (length-- > 0) if (*p++ != *eptr++) return FALSE; } - -return TRUE; -} - - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -The match() function is highly recursive, though not every recursive call -increases the recursive depth. Nevertheless, some regular expressions can cause -it to recurse to a great depth. I was writing for Unix, so I just let it call -itself recursively. This uses the stack for saving everything that has to be -saved for a recursive call. On Unix, the stack can be large, and this works -fine. - -It turns out that on some non-Unix-like systems there are problems with -programs that use a lot of stack. (This despite the fact that every last chip -has oodles of memory these days, and techniques for extending the stack have -been known for decades.) So.... - -There is a fudge, triggered by defining NO_RECURSE, which avoids recursive -calls by keeping local variables that need to be preserved in blocks of memory -obtained from malloc() instead instead of on the stack. Macros are used to -achieve this so that the actual code doesn't look very different to what it -always used to. - -The original heap-recursive code used longjmp(). However, it seems that this -can be very slow on some operating systems. Following a suggestion from Stan -Switzer, the use of longjmp() has been abolished, at the cost of having to -provide a unique number for each call to RMATCH. There is no way of generating -a sequence of numbers at compile time in C. I have given them names, to make -them stand out more clearly. - -Crude tests on x86 Linux show a small speedup of around 5-8%. However, on -FreeBSD, avoiding longjmp() more than halves the time taken to run the standard -tests. Furthermore, not using longjmp() means that local dynamic variables -don't have indeterminate values; this has meant that the frame size can be -reduced because the result can be "passed back" by straight setting of the -variable instead of being passed in the frame. -**************************************************************************** -***************************************************************************/ - -/* Numbers for RMATCH calls. When this list is changed, the code at HEAP_RETURN -below must be updated in sync. */ - -enum { RM1=1, RM2, RM3, RM4, RM5, RM6, RM7, RM8, RM9, RM10, - RM11, RM12, RM13, RM14, RM15, RM16, RM17, RM18, RM19, RM20, - RM21, RM22, RM23, RM24, RM25, RM26, RM27, RM28, RM29, RM30, - RM31, RM32, RM33, RM34, RM35, RM36, RM37, RM38, RM39, RM40, - RM41, RM42, RM43, RM44, RM45, RM46, RM47, RM48, RM49, RM50, - RM51, RM52, RM53, RM54 }; - -/* These versions of the macros use the stack, as normal. There are debugging -versions and production versions. Note that the "rw" argument of RMATCH isn't -actuall used in this definition. */ - -#ifndef NO_RECURSE -#define REGISTER register - -#ifdef DEBUG -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ - { \ - printf("match() called in line %d\n", __LINE__); \ - rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1); \ - printf("to line %d\n", __LINE__); \ - } -#define RRETURN(ra) \ - { \ - printf("match() returned %d from line %d ", ra, __LINE__); \ - return ra; \ - } -#else -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw) \ - rrc = match(ra,rb,mstart,rc,rd,re,rf,rg,rdepth+1) -#define RRETURN(ra) return ra -#endif - -#else - - -/* These versions of the macros manage a private stack on the heap. Note that -the "rd" argument of RMATCH isn't actually used in this definition. It's the md -argument of match(), which never changes. */ - -#define REGISTER - -#define RMATCH(ra,rb,rc,rd,re,rf,rg,rw)\ - {\ - heapframe *newframe = (pcre_stack_malloc)(sizeof(heapframe));\ - frame->Xwhere = rw; \ - newframe->Xeptr = ra;\ - newframe->Xecode = rb;\ - newframe->Xmstart = mstart;\ - newframe->Xoffset_top = rc;\ - newframe->Xims = re;\ - newframe->Xeptrb = rf;\ - newframe->Xflags = rg;\ - newframe->Xrdepth = frame->Xrdepth + 1;\ - newframe->Xprevframe = frame;\ - frame = newframe;\ - DPRINTF(("restarting from line %d\n", __LINE__));\ - goto HEAP_RECURSE;\ - L_##rw:\ - DPRINTF(("jumped back to line %d\n", __LINE__));\ - } - -#define RRETURN(ra)\ - {\ - heapframe *newframe = frame;\ - frame = newframe->Xprevframe;\ - (pcre_stack_free)(newframe);\ - if (frame != NULL)\ - {\ - rrc = ra;\ - goto HEAP_RETURN;\ - }\ - return ra;\ - } - - -/* Structure for remembering the local variables in a private frame */ - -typedef struct heapframe { - struct heapframe *Xprevframe; - - /* Function arguments that may change */ - - const uschar *Xeptr; - const uschar *Xecode; - const uschar *Xmstart; - int Xoffset_top; - long int Xims; - eptrblock *Xeptrb; - int Xflags; - unsigned int Xrdepth; - - /* Function local variables */ - - const uschar *Xcallpat; - const uschar *Xcharptr; - const uschar *Xdata; - const uschar *Xnext; - const uschar *Xpp; - const uschar *Xprev; - const uschar *Xsaved_eptr; - - recursion_info Xnew_recursive; - - BOOL Xcur_is_word; - BOOL Xcondition; - BOOL Xprev_is_word; - - unsigned long int Xoriginal_ims; - -#ifdef SUPPORT_UCP - int Xprop_type; - int Xprop_value; - int Xprop_fail_result; - int Xprop_category; - int Xprop_chartype; - int Xprop_script; - int Xoclength; - uschar Xocchars[8]; -#endif - - int Xctype; - unsigned int Xfc; - int Xfi; - int Xlength; - int Xmax; - int Xmin; - int Xnumber; - int Xoffset; - int Xop; - int Xsave_capture_last; - int Xsave_offset1, Xsave_offset2, Xsave_offset3; - int Xstacksave[REC_STACK_SAVE_MAX]; - - eptrblock Xnewptrb; - - /* Where to jump back to */ - - int Xwhere; - -} heapframe; - -#endif - - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Match from current position * -*************************************************/ - -/* This function is called recursively in many circumstances. Whenever it -returns a negative (error) response, the outer incarnation must also return the -same response. - -Performance note: It might be tempting to extract commonly used fields from the -md structure (e.g. utf8, end_subject) into individual variables to improve -performance. Tests using gcc on a SPARC disproved this; in the first case, it -made performance worse. - -Arguments: - eptr pointer to current character in subject - ecode pointer to current position in compiled code - mstart pointer to the current match start position (can be modified - by encountering \K) - offset_top current top pointer - md pointer to "static" info for the match - ims current /i, /m, and /s options - eptrb pointer to chain of blocks containing eptr at start of - brackets - for testing for empty matches - flags can contain - match_condassert - this is an assertion condition - match_cbegroup - this is the start of an unlimited repeat - group that can match an empty string - rdepth the recursion depth - -Returns: MATCH_MATCH if matched ) these values are >= 0 - MATCH_NOMATCH if failed to match ) - a negative PCRE_ERROR_xxx value if aborted by an error condition - (e.g. stopped by repeated call or recursion limit) -*/ - -static int -match(REGISTER USPTR eptr, REGISTER const uschar *ecode, const uschar *mstart, - int offset_top, match_data *md, unsigned long int ims, eptrblock *eptrb, - int flags, unsigned int rdepth) -{ -/* These variables do not need to be preserved over recursion in this function, -so they can be ordinary variables in all cases. Mark some of them with -"register" because they are used a lot in loops. */ - -register int rrc; /* Returns from recursive calls */ -register int i; /* Used for loops not involving calls to RMATCH() */ -register unsigned int c; /* Character values not kept over RMATCH() calls */ -register BOOL utf8; /* Local copy of UTF-8 flag for speed */ - -BOOL minimize, possessive; /* Quantifier options */ - -/* When recursion is not being used, all "local" variables that have to be -preserved over calls to RMATCH() are part of a "frame" which is obtained from -heap storage. Set up the top-level frame here; others are obtained from the -heap whenever RMATCH() does a "recursion". See the macro definitions above. */ - -#ifdef NO_RECURSE -heapframe *frame = (pcre_stack_malloc)(sizeof(heapframe)); -frame->Xprevframe = NULL; /* Marks the top level */ - -/* Copy in the original argument variables */ - -frame->Xeptr = eptr; -frame->Xecode = ecode; -frame->Xmstart = mstart; -frame->Xoffset_top = offset_top; -frame->Xims = ims; -frame->Xeptrb = eptrb; -frame->Xflags = flags; -frame->Xrdepth = rdepth; - -/* This is where control jumps back to to effect "recursion" */ - -HEAP_RECURSE: - -/* Macros make the argument variables come from the current frame */ - -#define eptr frame->Xeptr -#define ecode frame->Xecode -#define mstart frame->Xmstart -#define offset_top frame->Xoffset_top -#define ims frame->Xims -#define eptrb frame->Xeptrb -#define flags frame->Xflags -#define rdepth frame->Xrdepth - -/* Ditto for the local variables */ - -#ifdef SUPPORT_UTF8 -#define charptr frame->Xcharptr -#endif -#define callpat frame->Xcallpat -#define data frame->Xdata -#define next frame->Xnext -#define pp frame->Xpp -#define prev frame->Xprev -#define saved_eptr frame->Xsaved_eptr - -#define new_recursive frame->Xnew_recursive - -#define cur_is_word frame->Xcur_is_word -#define condition frame->Xcondition -#define prev_is_word frame->Xprev_is_word - -#define original_ims frame->Xoriginal_ims - -#ifdef SUPPORT_UCP -#define prop_type frame->Xprop_type -#define prop_value frame->Xprop_value -#define prop_fail_result frame->Xprop_fail_result -#define prop_category frame->Xprop_category -#define prop_chartype frame->Xprop_chartype -#define prop_script frame->Xprop_script -#define oclength frame->Xoclength -#define occhars frame->Xocchars -#endif - -#define ctype frame->Xctype -#define fc frame->Xfc -#define fi frame->Xfi -#define length frame->Xlength -#define max frame->Xmax -#define min frame->Xmin -#define number frame->Xnumber -#define offset frame->Xoffset -#define op frame->Xop -#define save_capture_last frame->Xsave_capture_last -#define save_offset1 frame->Xsave_offset1 -#define save_offset2 frame->Xsave_offset2 -#define save_offset3 frame->Xsave_offset3 -#define stacksave frame->Xstacksave - -#define newptrb frame->Xnewptrb - -/* When recursion is being used, local variables are allocated on the stack and -get preserved during recursion in the normal way. In this environment, fi and -i, and fc and c, can be the same variables. */ - -#else /* NO_RECURSE not defined */ -#define fi i -#define fc c - - -#ifdef SUPPORT_UTF8 /* Many of these variables are used only */ -const uschar *charptr; /* in small blocks of the code. My normal */ -#endif /* style of coding would have declared */ -const uschar *callpat; /* them within each of those blocks. */ -const uschar *data; /* However, in order to accommodate the */ -const uschar *next; /* version of this code that uses an */ -USPTR pp; /* external "stack" implemented on the */ -const uschar *prev; /* heap, it is easier to declare them all */ -USPTR saved_eptr; /* here, so the declarations can be cut */ - /* out in a block. The only declarations */ -recursion_info new_recursive; /* within blocks below are for variables */ - /* that do not have to be preserved over */ -BOOL cur_is_word; /* a recursive call to RMATCH(). */ -BOOL condition; -BOOL prev_is_word; - -unsigned long int original_ims; - -#ifdef SUPPORT_UCP -int prop_type; -int prop_value; -int prop_fail_result; -int prop_category; -int prop_chartype; -int prop_script; -int oclength; -uschar occhars[8]; -#endif - -int ctype; -int length; -int max; -int min; -int number; -int offset; -int op; -int save_capture_last; -int save_offset1, save_offset2, save_offset3; -int stacksave[REC_STACK_SAVE_MAX]; - -eptrblock newptrb; -#endif /* NO_RECURSE */ - -/* These statements are here to stop the compiler complaining about unitialized -variables. */ - -#ifdef SUPPORT_UCP -prop_value = 0; -prop_fail_result = 0; -#endif - - -/* This label is used for tail recursion, which is used in a few cases even -when NO_RECURSE is not defined, in order to reduce the amount of stack that is -used. Thanks to Ian Taylor for noticing this possibility and sending the -original patch. */ - -TAIL_RECURSE: - -/* OK, now we can get on with the real code of the function. Recursive calls -are specified by the macro RMATCH and RRETURN is used to return. When -NO_RECURSE is *not* defined, these just turn into a recursive call to match() -and a "return", respectively (possibly with some debugging if DEBUG is -defined). However, RMATCH isn't like a function call because it's quite a -complicated macro. It has to be used in one particular way. This shouldn't, -however, impact performance when true recursion is being used. */ - -#ifdef SUPPORT_UTF8 -utf8 = md->utf8; /* Local copy of the flag */ -#else -utf8 = FALSE; -#endif - -/* First check that we haven't called match() too many times, or that we -haven't exceeded the recursive call limit. */ - -if (md->match_call_count++ >= md->match_limit) RRETURN(PCRE_ERROR_MATCHLIMIT); -if (rdepth >= md->match_limit_recursion) RRETURN(PCRE_ERROR_RECURSIONLIMIT); - -original_ims = ims; /* Save for resetting on ')' */ - -/* At the start of a group with an unlimited repeat that may match an empty -string, the match_cbegroup flag is set. When this is the case, add the current -subject pointer to the chain of such remembered pointers, to be checked when we -hit the closing ket, in order to break infinite loops that match no characters. -When match() is called in other circumstances, don't add to the chain. The -match_cbegroup flag must NOT be used with tail recursion, because the memory -block that is used is on the stack, so a new one may be required for each -match(). */ - -if ((flags & match_cbegroup) != 0) - { - newptrb.epb_saved_eptr = eptr; - newptrb.epb_prev = eptrb; - eptrb = &newptrb; - } - -/* Now start processing the opcodes. */ - -for (;;) - { - minimize = possessive = FALSE; - op = *ecode; - - /* For partial matching, remember if we ever hit the end of the subject after - matching at least one subject character. */ - - if (md->partial && - eptr >= md->end_subject && - eptr > mstart) - md->hitend = TRUE; - - switch(op) - { - case OP_FAIL: - RRETURN(MATCH_NOMATCH); - - case OP_PRUNE: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM51); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_PRUNE); - - case OP_COMMIT: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM52); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_COMMIT); - - case OP_SKIP: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM53); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - md->start_match_ptr = eptr; /* Pass back current position */ - RRETURN(MATCH_SKIP); - - case OP_THEN: - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM54); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - RRETURN(MATCH_THEN); - - /* Handle a capturing bracket. If there is space in the offset vector, save - the current subject position in the working slot at the top of the vector. - We mustn't change the current values of the data slot, because they may be - set from a previous iteration of this group, and be referred to by a - reference inside the group. - - If the bracket fails to match, we need to restore this value and also the - values of the final offsets, in case they were set by a previous iteration - of the same bracket. - - If there isn't enough space in the offset vector, treat this as if it were - a non-capturing bracket. Don't worry about setting the flag for the error - case here; that is handled in the code for KET. */ - - case OP_CBRA: - case OP_SCBRA: - number = GET2(ecode, 1+LINK_SIZE); - offset = number << 1; - -#ifdef DEBUG - printf("start bracket %d\n", number); - printf("subject="); - pchars(eptr, 16, TRUE, md); - printf("\n"); -#endif - - if (offset < md->offset_max) - { - save_offset1 = md->offset_vector[offset]; - save_offset2 = md->offset_vector[offset+1]; - save_offset3 = md->offset_vector[md->offset_end - number]; - save_capture_last = md->capture_last; - - DPRINTF(("saving %d %d %d\n", save_offset1, save_offset2, save_offset3)); - md->offset_vector[md->offset_end - number] = eptr - md->start_subject; - - flags = (op == OP_SCBRA)? match_cbegroup : 0; - do - { - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, - ims, eptrb, flags, RM1); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - md->capture_last = save_capture_last; - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); - - DPRINTF(("bracket %d failed\n", number)); - - md->offset_vector[offset] = save_offset1; - md->offset_vector[offset+1] = save_offset2; - md->offset_vector[md->offset_end - number] = save_offset3; - - RRETURN(MATCH_NOMATCH); - } - - /* FALL THROUGH ... Insufficient room for saving captured contents. Treat - as a non-capturing bracket. */ - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - DPRINTF(("insufficient capture room: treat as non-capturing\n")); - - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - /* VVVVVVVVVVVVVVVVVVVVVVVVV */ - - /* Non-capturing bracket. Loop for all the alternatives. When we get to the - final alternative within the brackets, we would return the result of a - recursive call to match() whatever happened. We can reduce stack usage by - turning this into a tail recursion, except in the case when match_cbegroup - is set.*/ - - case OP_BRA: - case OP_SBRA: - DPRINTF(("start non-capturing bracket\n")); - flags = (op >= OP_SBRA)? match_cbegroup : 0; - for (;;) - { - if (ecode[GET(ecode, 1)] != OP_ALT) /* Final alternative */ - { - if (flags == 0) /* Not a possibly empty group */ - { - ecode += _pcre_OP_lengths[*ecode]; - DPRINTF(("bracket 0 tail recursion\n")); - goto TAIL_RECURSE; - } - - /* Possibly empty group; can't use tail recursion. */ - - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, - eptrb, flags, RM48); - RRETURN(rrc); - } - - /* For non-final alternatives, continue the loop for a NOMATCH result; - otherwise return. */ - - RMATCH(eptr, ecode + _pcre_OP_lengths[*ecode], offset_top, md, ims, - eptrb, flags, RM2); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode, 1); - } - /* Control never reaches here. */ - - /* Conditional group: compilation checked that there are no more than - two branches. If the condition is false, skipping the first branch takes us - past the end if there is only one branch, but that's OK because that is - exactly what going to the ket would do. As there is only one branch to be - obeyed, we can use tail recursion to avoid using another stack frame. */ - - case OP_COND: - case OP_SCOND: - if (ecode[LINK_SIZE+1] == OP_RREF) /* Recursion test */ - { - offset = GET2(ecode, LINK_SIZE + 2); /* Recursion group number*/ - condition = md->recursive != NULL && - (offset == RREF_ANY || offset == md->recursive->group_num); - ecode += condition? 3 : GET(ecode, 1); - } - - else if (ecode[LINK_SIZE+1] == OP_CREF) /* Group used test */ - { - offset = GET2(ecode, LINK_SIZE+2) << 1; /* Doubled ref number */ - condition = offset < offset_top && md->offset_vector[offset] >= 0; - ecode += condition? 3 : GET(ecode, 1); - } - - else if (ecode[LINK_SIZE+1] == OP_DEF) /* DEFINE - always false */ - { - condition = FALSE; - ecode += GET(ecode, 1); - } - - /* The condition is an assertion. Call match() to evaluate it - setting - the final argument match_condassert causes it to stop at the end of an - assertion. */ - - else - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, - match_condassert, RM3); - if (rrc == MATCH_MATCH) - { - condition = TRUE; - ecode += 1 + LINK_SIZE + GET(ecode, LINK_SIZE + 2); - while (*ecode == OP_ALT) ecode += GET(ecode, 1); - } - else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) - { - RRETURN(rrc); /* Need braces because of following else */ - } - else - { - condition = FALSE; - ecode += GET(ecode, 1); - } - } - - /* We are now at the branch that is to be obeyed. As there is only one, - we can use tail recursion to avoid using another stack frame, except when - match_cbegroup is required for an unlimited repeat of a possibly empty - group. If the second alternative doesn't exist, we can just plough on. */ - - if (condition || *ecode == OP_ALT) - { - ecode += 1 + LINK_SIZE; - if (op == OP_SCOND) /* Possibly empty group */ - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, match_cbegroup, RM49); - RRETURN(rrc); - } - else /* Group must match something */ - { - flags = 0; - goto TAIL_RECURSE; - } - } - else /* Condition false & no 2nd alternative */ - { - ecode += 1 + LINK_SIZE; - } - break; - - - /* End of the pattern, either real or forced. If we are in a top-level - recursion, we should restore the offsets appropriately and continue from - after the call. */ - - case OP_ACCEPT: - case OP_END: - if (md->recursive != NULL && md->recursive->group_num == 0) - { - recursion_info *rec = md->recursive; - DPRINTF(("End of pattern in a (?0) recursion\n")); - md->recursive = rec->prevrec; - memmove(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - mstart = rec->save_start; - ims = original_ims; - ecode = rec->after_call; - break; - } - - /* Otherwise, if PCRE_NOTEMPTY is set, fail if we have matched an empty - string - backtracking will then try other alternatives, if any. */ - - if (md->notempty && eptr == mstart) RRETURN(MATCH_NOMATCH); - md->end_match_ptr = eptr; /* Record where we ended */ - md->end_offset_top = offset_top; /* and how many extracts were taken */ - md->start_match_ptr = mstart; /* and the start (\K can modify) */ - RRETURN(MATCH_MATCH); - - /* Change option settings */ - - case OP_OPT: - ims = ecode[1]; - ecode += 2; - DPRINTF(("ims set to %02lx\n", ims)); - break; - - /* Assertion brackets. Check the alternative branches in turn - the - matching won't pass the KET for an assertion. If any one branch matches, - the assertion is true. Lookbehind assertions have an OP_REVERSE item at the - start of each branch to move the current point backwards, so the code at - this level is identical to the lookahead case. */ - - case OP_ASSERT: - case OP_ASSERTBACK: - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, - RM4); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode, 1); - } - while (*ecode == OP_ALT); - if (*ecode == OP_KET) RRETURN(MATCH_NOMATCH); - - /* If checking an assertion for a condition, return MATCH_MATCH. */ - - if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); - - /* Continue from after the assertion, updating the offsets high water - mark, since extracts may have been taken during the assertion. */ - - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - ecode += 1 + LINK_SIZE; - offset_top = md->end_offset_top; - continue; - - /* Negative assertion: all branches must fail to match */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK_NOT: - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, NULL, 0, - RM5); - if (rrc == MATCH_MATCH) RRETURN(MATCH_NOMATCH); - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - if ((flags & match_condassert) != 0) RRETURN(MATCH_MATCH); - - ecode += 1 + LINK_SIZE; - continue; - - /* Move the subject pointer back. This occurs only at the start of - each branch of a lookbehind assertion. If we are too close to the start to - move back, this match function fails. When working with UTF-8 we move - back a number of characters, not bytes. */ - - case OP_REVERSE: -#ifdef SUPPORT_UTF8 - if (utf8) - { - i = GET(ecode, 1); - while (i-- > 0) - { - eptr--; - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - BACKCHAR(eptr); - } - } - else -#endif - - /* No UTF-8 support, or not in UTF-8 mode: count is byte count */ - - { - eptr -= GET(ecode, 1); - if (eptr < md->start_subject) RRETURN(MATCH_NOMATCH); - } - - /* Skip to next op code */ - - ecode += 1 + LINK_SIZE; - break; - - /* The callout item calls an external function, if one is provided, passing - details of the match so far. This is mainly for debugging, though the - function is able to force a failure. */ - - case OP_CALLOUT: - if (pcre_callout != NULL) - { - pcre_callout_block cb; - cb.version = 1; /* Version 1 of the callout block */ - cb.callout_number = ecode[1]; - cb.offset_vector = md->offset_vector; - cb.subject = (PCRE_SPTR)md->start_subject; - cb.subject_length = md->end_subject - md->start_subject; - cb.start_match = mstart - md->start_subject; - cb.current_position = eptr - md->start_subject; - cb.pattern_position = GET(ecode, 2); - cb.next_item_length = GET(ecode, 2 + LINK_SIZE); - cb.capture_top = offset_top/2; - cb.capture_last = md->capture_last; - cb.callout_data = md->callout_data; - if ((rrc = (*pcre_callout)(&cb)) > 0) RRETURN(MATCH_NOMATCH); - if (rrc < 0) RRETURN(rrc); - } - ecode += 2 + 2*LINK_SIZE; - break; - - /* Recursion either matches the current regex, or some subexpression. The - offset data is the offset to the starting bracket from the start of the - whole pattern. (This is so that it works from duplicated subpatterns.) - - If there are any capturing brackets started but not finished, we have to - save their starting points and reinstate them after the recursion. However, - we don't know how many such there are (offset_top records the completed - total) so we just have to save all the potential data. There may be up to - 65535 such values, which is too large to put on the stack, but using malloc - for small numbers seems expensive. As a compromise, the stack is used when - there are no more than REC_STACK_SAVE_MAX values to store; otherwise malloc - is used. A problem is what to do if the malloc fails ... there is no way of - returning to the top level with an error. Save the top REC_STACK_SAVE_MAX - values on the stack, and accept that the rest may be wrong. - - There are also other values that have to be saved. We use a chained - sequence of blocks that actually live on the stack. Thanks to Robin Houston - for the original version of this logic. */ - - case OP_RECURSE: - { - callpat = md->start_code + GET(ecode, 1); - new_recursive.group_num = (callpat == md->start_code)? 0 : - GET2(callpat, 1 + LINK_SIZE); - - /* Add to "recursing stack" */ - - new_recursive.prevrec = md->recursive; - md->recursive = &new_recursive; - - /* Find where to continue from afterwards */ - - ecode += 1 + LINK_SIZE; - new_recursive.after_call = ecode; - - /* Now save the offset data. */ - - new_recursive.saved_max = md->offset_end; - if (new_recursive.saved_max <= REC_STACK_SAVE_MAX) - new_recursive.offset_save = stacksave; - else - { - new_recursive.offset_save = - (int *)(pcre_malloc)(new_recursive.saved_max * sizeof(int)); - if (new_recursive.offset_save == NULL) RRETURN(PCRE_ERROR_NOMEMORY); - } - - memcpy(new_recursive.offset_save, md->offset_vector, - new_recursive.saved_max * sizeof(int)); - new_recursive.save_start = mstart; - mstart = eptr; - - /* OK, now we can do the recursion. For each top-level alternative we - restore the offset and recursion data. */ - - DPRINTF(("Recursing into group %d\n", new_recursive.group_num)); - flags = (*callpat >= OP_SBRA)? match_cbegroup : 0; - do - { - RMATCH(eptr, callpat + _pcre_OP_lengths[*callpat], offset_top, - md, ims, eptrb, flags, RM6); - if (rrc == MATCH_MATCH) - { - DPRINTF(("Recursion matched\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_MATCH); - } - else if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) - { - DPRINTF(("Recursion gave error %d\n", rrc)); - RRETURN(rrc); - } - - md->recursive = &new_recursive; - memcpy(md->offset_vector, new_recursive.offset_save, - new_recursive.saved_max * sizeof(int)); - callpat += GET(callpat, 1); - } - while (*callpat == OP_ALT); - - DPRINTF(("Recursion didn't match\n")); - md->recursive = new_recursive.prevrec; - if (new_recursive.offset_save != stacksave) - (pcre_free)(new_recursive.offset_save); - RRETURN(MATCH_NOMATCH); - } - /* Control never reaches here */ - - /* "Once" brackets are like assertion brackets except that after a match, - the point in the subject string is not moved back. Thus there can never be - a move back into the brackets. Friedl calls these "atomic" subpatterns. - Check the alternative branches in turn - the matching won't pass the KET - for this kind of subpattern. If any one branch matches, we carry on as at - the end of a normal bracket, leaving the subject pointer. */ - - case OP_ONCE: - prev = ecode; - saved_eptr = eptr; - - do - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM7); - if (rrc == MATCH_MATCH) break; - if (rrc != MATCH_NOMATCH && rrc != MATCH_THEN) RRETURN(rrc); - ecode += GET(ecode,1); - } - while (*ecode == OP_ALT); - - /* If hit the end of the group (which could be repeated), fail */ - - if (*ecode != OP_ONCE && *ecode != OP_ALT) RRETURN(MATCH_NOMATCH); - - /* Continue as from after the assertion, updating the offsets high water - mark, since extracts may have been taken. */ - - do ecode += GET(ecode, 1); while (*ecode == OP_ALT); - - offset_top = md->end_offset_top; - eptr = md->end_match_ptr; - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1+LINK_SIZE; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. The second "call" of match() - uses tail recursion, to avoid using another stack frame. We need to reset - any options that changed within the bracket before re-running it, so - check the next opcode. */ - - if (ecode[1+LINK_SIZE] == OP_OPT) - { - ims = (ims & ~PCRE_IMS) | ecode[4]; - DPRINTF(("ims set to %02lx at group repeat\n", ims)); - } - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM8); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode = prev; - flags = 0; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, match_cbegroup, RM9); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* An alternation is the end of a branch; scan along to find the end of the - bracketed group and go to there. */ - - case OP_ALT: - do ecode += GET(ecode,1); while (*ecode == OP_ALT); - break; - - /* BRAZERO and BRAMINZERO occur just before a bracket group, indicating - that it may occur zero times. It may repeat infinitely, or not at all - - i.e. it could be ()* or ()? in the pattern. Brackets with fixed upper - repeat limits are compiled as a number of copies, with the optional ones - preceded by BRAZERO or BRAMINZERO. */ - - case OP_BRAZERO: - { - next = ecode+1; - RMATCH(eptr, next, offset_top, md, ims, eptrb, 0, RM10); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - do next += GET(next,1); while (*next == OP_ALT); - ecode = next + 1 + LINK_SIZE; - } - break; - - case OP_BRAMINZERO: - { - next = ecode+1; - do next += GET(next, 1); while (*next == OP_ALT); - RMATCH(eptr, next + 1+LINK_SIZE, offset_top, md, ims, eptrb, 0, RM11); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode++; - } - break; - - /* End of a group, repeated or non-repeating. */ - - case OP_KET: - case OP_KETRMIN: - case OP_KETRMAX: - prev = ecode - GET(ecode, 1); - - /* If this was a group that remembered the subject start, in order to break - infinite repeats of empty string matches, retrieve the subject start from - the chain. Otherwise, set it NULL. */ - - if (*prev >= OP_SBRA) - { - saved_eptr = eptrb->epb_saved_eptr; /* Value at start of group */ - eptrb = eptrb->epb_prev; /* Backup to previous group */ - } - else saved_eptr = NULL; - - /* If we are at the end of an assertion group, stop matching and return - MATCH_MATCH, but record the current high water mark for use by positive - assertions. Do this also for the "once" (atomic) groups. */ - - if (*prev == OP_ASSERT || *prev == OP_ASSERT_NOT || - *prev == OP_ASSERTBACK || *prev == OP_ASSERTBACK_NOT || - *prev == OP_ONCE) - { - md->end_match_ptr = eptr; /* For ONCE */ - md->end_offset_top = offset_top; - RRETURN(MATCH_MATCH); - } - - /* For capturing groups we have to check the group number back at the start - and if necessary complete handling an extraction by setting the offsets and - bumping the high water mark. Note that whole-pattern recursion is coded as - a recurse into group 0, so it won't be picked up here. Instead, we catch it - when the OP_END is reached. Other recursion is handled here. */ - - if (*prev == OP_CBRA || *prev == OP_SCBRA) - { - number = GET2(prev, 1+LINK_SIZE); - offset = number << 1; - -#ifdef DEBUG - printf("end bracket %d", number); - printf("\n"); -#endif - - md->capture_last = number; - if (offset >= md->offset_max) md->offset_overflow = TRUE; else - { - md->offset_vector[offset] = - md->offset_vector[md->offset_end - number]; - md->offset_vector[offset+1] = eptr - md->start_subject; - if (offset_top <= offset) offset_top = offset + 2; - } - - /* Handle a recursively called group. Restore the offsets - appropriately and continue from after the call. */ - - if (md->recursive != NULL && md->recursive->group_num == number) - { - recursion_info *rec = md->recursive; - DPRINTF(("Recursion (%d) succeeded - continuing\n", number)); - md->recursive = rec->prevrec; - mstart = rec->save_start; - memcpy(md->offset_vector, rec->offset_save, - rec->saved_max * sizeof(int)); - ecode = rec->after_call; - ims = original_ims; - break; - } - } - - /* For both capturing and non-capturing groups, reset the value of the ims - flags, in case they got changed during the group. */ - - ims = original_ims; - DPRINTF(("ims reset to %02lx\n", ims)); - - /* For a non-repeating ket, just continue at this level. This also - happens for a repeating ket if no characters were matched in the group. - This is the forcible breaking of infinite loops as implemented in Perl - 5.005. If there is an options reset, it will get obeyed in the normal - course of events. */ - - if (*ecode == OP_KET || eptr == saved_eptr) - { - ecode += 1 + LINK_SIZE; - break; - } - - /* The repeating kets try the rest of the pattern or restart from the - preceding bracket, in the appropriate order. In the second case, we can use - tail recursion to avoid using another stack frame, unless we have an - unlimited repeat of a group that can match an empty string. */ - - flags = (*prev >= OP_SBRA)? match_cbegroup : 0; - - if (*ecode == OP_KETRMIN) - { - RMATCH(eptr, ecode + 1 + LINK_SIZE, offset_top, md, ims, eptrb, 0, RM12); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (flags != 0) /* Could match an empty string */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM50); - RRETURN(rrc); - } - ecode = prev; - goto TAIL_RECURSE; - } - else /* OP_KETRMAX */ - { - RMATCH(eptr, prev, offset_top, md, ims, eptrb, flags, RM13); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - ecode += 1 + LINK_SIZE; - flags = 0; - goto TAIL_RECURSE; - } - /* Control never gets here */ - - /* Start of subject unless notbol, or after internal newline if multiline */ - - case OP_CIRC: - if (md->notbol && eptr == md->start_subject) RRETURN(MATCH_NOMATCH); - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr != md->start_subject && - (eptr == md->end_subject || !WAS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - /* ... else fall through */ - - /* Start of subject assertion */ - - case OP_SOD: - if (eptr != md->start_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Start of match assertion */ - - case OP_SOM: - if (eptr != md->start_subject + md->start_offset) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Reset the start of match point */ - - case OP_SET_SOM: - mstart = eptr; - ecode++; - break; - - /* Assert before internal newline if multiline, or before a terminating - newline unless endonly is set, else end of subject unless noteol is set. */ - - case OP_DOLL: - if ((ims & PCRE_MULTILINE) != 0) - { - if (eptr < md->end_subject) - { if (!IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); } - else - { if (md->noteol) RRETURN(MATCH_NOMATCH); } - ecode++; - break; - } - else - { - if (md->noteol) RRETURN(MATCH_NOMATCH); - if (!md->endonly) - { - if (eptr != md->end_subject && - (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - } - } - /* ... else fall through for endonly */ - - /* End of subject assertion (\z) */ - - case OP_EOD: - if (eptr < md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* End of subject or ending \n assertion (\Z) */ - - case OP_EODN: - if (eptr != md->end_subject && - (!IS_NEWLINE(eptr) || eptr != md->end_subject - md->nllen)) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - /* Word boundary assertions */ - - case OP_NOT_WORD_BOUNDARY: - case OP_WORD_BOUNDARY: - { - - /* Find out if the previous and current characters are "word" characters. - It takes a bit more work in UTF-8 mode. Characters > 255 are assumed to - be "non-word" characters. */ - -#ifdef SUPPORT_UTF8 - if (utf8) - { - if (eptr == md->start_subject) prev_is_word = FALSE; else - { - const uschar *lastptr = eptr - 1; - while((*lastptr & 0xc0) == 0x80) lastptr--; - GETCHAR(c, lastptr); - prev_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - if (eptr >= md->end_subject) cur_is_word = FALSE; else - { - GETCHAR(c, eptr); - cur_is_word = c < 256 && (md->ctypes[c] & ctype_word) != 0; - } - } - else -#endif - - /* More streamlined when not in UTF-8 mode */ - - { - prev_is_word = (eptr != md->start_subject) && - ((md->ctypes[eptr[-1]] & ctype_word) != 0); - cur_is_word = (eptr < md->end_subject) && - ((md->ctypes[*eptr] & ctype_word) != 0); - } - - /* Now see if the situation is what we want */ - - if ((*ecode++ == OP_WORD_BOUNDARY)? - cur_is_word == prev_is_word : cur_is_word != prev_is_word) - RRETURN(MATCH_NOMATCH); - } - break; - - /* Match a single character type; inline for speed */ - - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - } - if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (utf8) - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - ecode++; - break; - - /* Match a single byte, even in UTF-8 mode. This opcode really does match - any byte, even newline, independent of the setting of PCRE_DOTALL. */ - - case OP_ANYBYTE: - if (eptr++ >= md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_digit) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_DIGIT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_digit) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_space) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WHITESPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_space) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_NOT_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c < 256 && -#endif - (md->ctypes[c] & ctype_word) != 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_WORDCHAR: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - if ( -#ifdef SUPPORT_UTF8 - c >= 256 || -#endif - (md->ctypes[c] & ctype_word) == 0 - ) - RRETURN(MATCH_NOMATCH); - ecode++; - break; - - case OP_ANYNL: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - ecode++; - break; - - case OP_NOT_HSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - - case OP_HSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - ecode++; - break; - - case OP_NOT_VSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - ecode++; - break; - - case OP_VSPACE: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - ecode++; - break; - -#ifdef SUPPORT_UCP - /* Check the next character by Unicode property. We will get here only - if the support is in the binary; otherwise a compile-time error occurs. */ - - case OP_PROP: - case OP_NOTPROP: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); - - switch(ecode[1]) - { - case PT_ANY: - if (op == OP_NOTPROP) RRETURN(MATCH_NOMATCH); - break; - - case PT_LAMP: - if ((chartype == ucp_Lu || - chartype == ucp_Ll || - chartype == ucp_Lt) == (op == OP_NOTPROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_GC: - if ((ecode[2] != category) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_PC: - if ((ecode[2] != chartype) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - case PT_SC: - if ((ecode[2] != script) == (op == OP_PROP)) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - ecode += 3; - } - break; - - /* Match an extended Unicode sequence. We will get here only if the support - is in the binary; otherwise a compile-time error occurs. */ - - case OP_EXTUNI: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - { - int chartype, script; - int category = _pcre_ucp_findprop(c, &chartype, &script); - if (category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - category = _pcre_ucp_findprop(c, &chartype, &script); - if (category != ucp_M) break; - eptr += len; - } - } - ecode++; - break; -#endif - - - /* Match a back reference, possibly repeatedly. Look past the end of the - item to see if there is repeat information following. The code is similar - to that for character classes, but repeated for efficiency. Then obey - similar code to character type repeats - written out again for speed. - However, if the referenced string is the empty string, always treat - it as matched, any number of times (otherwise there could be infinite - loops). */ - - case OP_REF: - { - offset = GET2(ecode, 1) << 1; /* Doubled ref number */ - ecode += 3; /* Advance past item */ - - /* If the reference is unset, set the length to be longer than the amount - of subject left; this ensures that every attempt at a match fails. We - can't just fail here, because of the possibility of quantifiers with zero - minima. */ - - length = (offset >= offset_top || md->offset_vector[offset] < 0)? - md->end_subject - eptr + 1 : - md->offset_vector[offset+1] - md->offset_vector[offset]; - - /* Set up for repetition, or handle the non-repeated case */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - continue; /* With the main loop */ - } - - /* If the length of the reference is zero, just continue with the - main loop. */ - - if (length == 0) continue; - - /* First, ensure the minimum number of matches are present. We get back - the length of the reference string explicitly rather than passing the - address of eptr, so that eptr can be a register variable. */ - - for (i = 1; i <= min; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) RRETURN(MATCH_NOMATCH); - eptr += length; - } - - /* If min = max, continue at the same level without recursion. - They are not both allowed to be zero. */ - - if (min == max) continue; - - /* If minimizing, keep trying and advancing the pointer */ - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM14); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || !match_ref(offset, eptr, length, md, ims)) - RRETURN(MATCH_NOMATCH); - eptr += length; - } - /* Control never gets here */ - } - - /* If maximizing, find the longest string and work backwards */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - if (!match_ref(offset, eptr, length, md, ims)) break; - eptr += length; - } - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM15); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr -= length; - } - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - - - /* Match a bit-mapped character class, possibly repeatedly. This op code is - used when all the characters in the class have values in the range 0-255, - and either the matching is caseful, or the characters are in the range - 0-127 when UTF-8 processing is enabled. The only difference between - OP_CLASS and OP_NCLASS occurs when a data character outside the range is - encountered. - - First, look past the end of the item to see if there is repeat information - following. Then obey similar code to character type repeats - written out - again for speed. */ - - case OP_NCLASS: - case OP_CLASS: - { - data = ecode + 1; /* Save for matching */ - ecode += 33; /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM16); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c > 255) - { - if (op == OP_CLASS) RRETURN(MATCH_NOMATCH); - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM17); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - c = *eptr++; - if ((data[c/8] & (1 << (c&7))) == 0) RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c > 255) - { - if (op == OP_CLASS) break; - } - else - { - if ((data[c/8] & (1 << (c&7))) == 0) break; - } - eptr += len; - } - for (;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM18); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if ((data[c/8] & (1 << (c&7))) == 0) break; - eptr++; - } - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM19); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - - /* Match an extended character class. This opcode is encountered only - in UTF-8 mode, because that's the only time it is compiled. */ - -#ifdef SUPPORT_UTF8 - case OP_XCLASS: - { - data = ecode + 1 + LINK_SIZE; /* Save for matching */ - ecode += GET(ecode, 1); /* Advance past the item */ - - switch (*ecode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - c = *ecode++ - OP_CRSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - minimize = (*ecode == OP_CRMINRANGE); - min = GET2(ecode, 1); - max = GET2(ecode, 3); - if (max == 0) max = INT_MAX; - ecode += 5; - break; - - default: /* No repeat follows */ - min = max = 1; - break; - } - - /* First, ensure the minimum number of matches are present. */ - - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); - } - - /* If max == min we can continue with the main loop without the - need to recurse. */ - - if (min == max) continue; - - /* If minimizing, keep testing the rest of the expression and advancing - the pointer while it matches the class. */ - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM20); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (!_pcre_xclass(c, data)) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* If maximizing, find the longest possible run, then work backwards. */ - - else - { - pp = eptr; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (!_pcre_xclass(c, data)) break; - eptr += len; - } - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM21); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - if (utf8) BACKCHAR(eptr); - } - RRETURN(MATCH_NOMATCH); - } - - /* Control never gets here */ - } -#endif /* End of XCLASS */ - - /* Match a single character, casefully */ - - case OP_CHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - while (length-- > 0) if (*ecode++ != *eptr++) RRETURN(MATCH_NOMATCH); - } - else -#endif - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (ecode[1] != *eptr++) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character, caselessly */ - - case OP_CHARNC: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - ecode++; - GETCHARLEN(fc, ecode, length); - - if (length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - - /* If the pattern character's value is < 128, we have only one byte, and - can use the fast lookup table. */ - - if (fc < 128) - { - if (md->lcc[*ecode++] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - /* Otherwise we must pick up the subject character */ - - else - { - unsigned int dc; - GETCHARINC(dc, eptr); - ecode += length; - - /* If we have Unicode property support, we can use it to test the other - case of the character, if there is one. */ - - if (fc != dc) - { -#ifdef SUPPORT_UCP - if (dc != _pcre_ucp_othercase(fc)) -#endif - RRETURN(MATCH_NOMATCH); - } - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Non-UTF-8 mode */ - { - if (md->end_subject - eptr < 1) RRETURN(MATCH_NOMATCH); - if (md->lcc[ecode[1]] != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - ecode += 2; - } - break; - - /* Match a single character repeatedly. */ - - case OP_EXACT: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATCHAR; - - case OP_POSUPTO: - possessive = TRUE; - /* Fall through */ - - case OP_UPTO: - case OP_MINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_MINUPTO; - ecode += 3; - goto REPEATCHAR; - - case OP_POSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATCHAR; - - case OP_POSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATCHAR; - - case OP_STAR: - case OP_MINSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_QUERY: - case OP_MINQUERY: - c = *ecode++ - OP_STAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-character matches. We can give - up quickly if there are fewer than the minimum number of characters left in - the subject. */ - - REPEATCHAR: -#ifdef SUPPORT_UTF8 - if (utf8) - { - length = 1; - charptr = ecode; - GETCHARLEN(fc, ecode, length); - if (min * length > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - ecode += length; - - /* Handle multibyte character matching specially here. There is - support for caseless matching if UCP support is present. */ - - if (length > 1) - { -#ifdef SUPPORT_UCP - unsigned int othercase; - if ((ims & PCRE_CASELESS) != 0 && - (othercase = _pcre_ucp_othercase(fc)) != NOTACHAR) - oclength = _pcre_ord2utf8(othercase, occhars); - else oclength = 0; -#endif /* SUPPORT_UCP */ - - for (i = 1; i <= min; i++) - { - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else { RRETURN(MATCH_NOMATCH); } -#endif /* SUPPORT_UCP */ - } - - if (min == max) continue; - - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM22); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - /* Need braces because of following else */ - else if (oclength == 0) { RRETURN(MATCH_NOMATCH); } - else - { - if (memcmp(eptr, occhars, oclength) != 0) RRETURN(MATCH_NOMATCH); - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else { RRETURN (MATCH_NOMATCH); } -#endif /* SUPPORT_UCP */ - } - /* Control never gets here */ - } - - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr > md->end_subject - length) break; - if (memcmp(eptr, charptr, length) == 0) eptr += length; -#ifdef SUPPORT_UCP - else if (oclength == 0) break; - else - { - if (memcmp(eptr, occhars, oclength) != 0) break; - eptr += oclength; - } -#else /* without SUPPORT_UCP */ - else break; -#endif /* SUPPORT_UCP */ - } - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM23); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr == pp) RRETURN(MATCH_NOMATCH); -#ifdef SUPPORT_UCP - eptr--; - BACKCHAR(eptr); -#else /* without SUPPORT_UCP */ - eptr -= length; -#endif /* SUPPORT_UCP */ - } - } - /* Control never gets here */ - } - - /* If the length of a UTF-8 character is 1, we fall through here, and - obey the code as for non-UTF-8 characters below, though in this case the - value of fc will always be < 128. */ - } - else -#endif /* SUPPORT_UTF8 */ - - /* When not in UTF-8 mode, load a single-byte character. */ - { - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - fc = *ecode++; - } - - /* The value of fc at this point is always less than 256, though we may or - may not be in UTF-8 mode. The code is duplicated for the caseless and - caseful cases, for speed, since matching characters is likely to be quite - common. First, ensure the minimum number of matches are present. If min = - max, continue at the same level without recursing. Otherwise, if - minimizing, keep trying the rest of the expression and advancing one - matching character if failing, up to the maximum. Alternatively, if - maximizing, find the maximum number of characters and work backwards. */ - - DPRINTF(("matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - for (i = 1; i <= min; i++) - if (fc != md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM24); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - fc != md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != md->lcc[*eptr]) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM25); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* Caseful comparisons (includes all multi-byte characters) */ - - else - { - for (i = 1; i <= min; i++) if (fc != *eptr++) RRETURN(MATCH_NOMATCH); - if (min == max) continue; - if (minimize) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM26); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc != *eptr++) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - else /* Maximize */ - { - pp = eptr; - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc != *eptr) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM27); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - /* Match a negated single one-byte character. The character we are - checking can be multibyte. */ - - case OP_NOT: - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - ecode++; - GETCHARINCTEST(c, eptr); - if ((ims & PCRE_CASELESS) != 0) - { -#ifdef SUPPORT_UTF8 - if (c < 256) -#endif - c = md->lcc[c]; - if (md->lcc[*ecode++] == c) RRETURN(MATCH_NOMATCH); - } - else - { - if (*ecode++ == c) RRETURN(MATCH_NOMATCH); - } - break; - - /* Match a negated single one-byte character repeatedly. This is almost a - repeat of the code for a repeated single character, but I haven't found a - nice way of commoning these up that doesn't require a test of the - positive/negative option for each character match. Maybe that wouldn't add - very much to the time taken, but character matching *is* what this is all - about... */ - - case OP_NOTEXACT: - min = max = GET2(ecode, 1); - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTUPTO: - case OP_NOTMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_NOTMINUPTO; - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTPOSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATNOTCHAR; - - case OP_NOTPOSUPTO: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 3; - goto REPEATNOTCHAR; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - c = *ecode++ - OP_NOTSTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single-byte matches. We can give up quickly - if there are fewer than the minimum number of bytes left in the - subject. */ - - REPEATNOTCHAR: - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - fc = *ecode++; - - /* The code is duplicated for the caseless and caseful cases, for speed, - since matching characters is likely to be quite common. First, ensure the - minimum number of matches are present. If min = max, continue at the same - level without recursing. Otherwise, if minimizing, keep trying the rest of - the expression and advancing one matching character if failing, up to the - maximum. Alternatively, if maximizing, find the maximum number of - characters and work backwards. */ - - DPRINTF(("negative matching %c{%d,%d} against subject %.*s\n", fc, min, max, - max, eptr)); - - if ((ims & PCRE_CASELESS) != 0) - { - fc = md->lcc[fc]; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == md->lcc[*eptr++]) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM28); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - GETCHARINC(d, eptr); - if (d < 256) d = md->lcc[d]; - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM29); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == md->lcc[*eptr++]) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (d < 256) d = md->lcc[d]; - if (fc == d) break; - eptr += len; - } - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM30); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == md->lcc[*eptr]) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM31); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - } - - /* Caseful comparisons */ - - else - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = 1; i <= min; i++) - { - GETCHARINC(d, eptr); - if (fc == d) RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = 1; i <= min; i++) - if (fc == *eptr++) RRETURN(MATCH_NOMATCH); - } - - if (min == max) continue; - - if (minimize) - { -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM32); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - GETCHARINC(d, eptr); - if (fi >= max || eptr >= md->end_subject || fc == d) - RRETURN(MATCH_NOMATCH); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM33); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || fc == *eptr++) - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - } - - /* Maximize case */ - - else - { - pp = eptr; - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - register unsigned int d; - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(d, eptr, len); - if (fc == d) break; - eptr += len; - } - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM34); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || fc == *eptr) break; - eptr++; - } - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM35); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - eptr--; - } - } - - RRETURN(MATCH_NOMATCH); - } - } - /* Control never gets here */ - - /* Match a single character type repeatedly; several different opcodes - share code. This is very similar to the code for single characters, but we - repeat it in the interests of efficiency. */ - - case OP_TYPEEXACT: - min = max = GET2(ecode, 1); - minimize = TRUE; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - min = 0; - max = GET2(ecode, 1); - minimize = *ecode == OP_TYPEMINUPTO; - ecode += 3; - goto REPEATTYPE; - - case OP_TYPEPOSSTAR: - possessive = TRUE; - min = 0; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSPLUS: - possessive = TRUE; - min = 1; - max = INT_MAX; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSQUERY: - possessive = TRUE; - min = 0; - max = 1; - ecode++; - goto REPEATTYPE; - - case OP_TYPEPOSUPTO: - possessive = TRUE; - min = 0; - max = GET2(ecode, 1); - ecode += 3; - goto REPEATTYPE; - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - c = *ecode++ - OP_TYPESTAR; - minimize = (c & 1) != 0; - min = rep_min[c]; /* Pick up values from tables; */ - max = rep_max[c]; /* zero for max => infinity */ - if (max == 0) max = INT_MAX; - - /* Common code for all repeated single character type matches. Note that - in UTF-8 mode, '.' matches a character of any length, but for the other - character types, the valid characters are all one-byte long. */ - - REPEATTYPE: - ctype = *ecode++; /* Code for the character type */ - -#ifdef SUPPORT_UCP - if (ctype == OP_PROP || ctype == OP_NOTPROP) - { - prop_fail_result = ctype == OP_NOTPROP; - prop_type = *ecode++; - prop_value = *ecode++; - } - else prop_type = -1; -#endif - - /* First, ensure the minimum number of matches are present. Use inline - code for maximizing the speed, and do the type test once at the start - (i.e. keep it out of the loop). Also we can test that there are at least - the minimum number of bytes before we start. This isn't as effective in - UTF-8 mode, but it does no harm. Separate the UTF-8 code completely as that - is tidier. Also separate the UCP code, which can be the same for both UTF-8 - and single-bytes. */ - - if (min > md->end_subject - eptr) RRETURN(MATCH_NOMATCH); - if (min > 0) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - } - break; - - case PT_LAMP: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_GC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_PC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - case PT_SC: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = 1; i <= min; i++) - { - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -/* Handle all other cases when the coding is UTF-8 */ - -#ifdef SUPPORT_UTF8 - if (utf8) switch(ctype) - { - case OP_ANY: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - break; - - case OP_ANYBYTE: - eptr += min; - break; - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (c < 128 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr] & ctype_space) != 0)) - RRETURN(MATCH_NOMATCH); - while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); - } - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - (*eptr < 128 && (md->ctypes[*eptr] & ctype_word) != 0)) - RRETURN(MATCH_NOMATCH); - while (++eptr < md->end_subject && (*eptr & 0xc0) == 0x80); - } - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject || - *eptr >= 128 || (md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - /* No need to skip more bytes - we know it's a 1-byte character */ - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } /* End switch(ctype) */ - - else -#endif /* SUPPORT_UTF8 */ - - /* Code for the non-UTF-8 case for minimum matching of operators other - than OP_PROP and OP_NOTPROP. We can assume that there are the minimum - number of bytes present, as this was tested above. */ - - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - for (i = 1; i <= min; i++) - { - if (IS_NEWLINE(eptr)) RRETURN(MATCH_NOMATCH); - eptr++; - } - } - else eptr += min; - break; - - case OP_ANYBYTE: - eptr += min; - break; - - /* Because of the CRLF case, we can't assume the minimum number of - bytes are present in this case. */ - - case OP_ANYNL: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - } - break; - - case OP_NOT_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_HSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - break; - } - } - break; - - case OP_NOT_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - RRETURN(MATCH_NOMATCH); - } - } - break; - - case OP_VSPACE: - for (i = 1; i <= min; i++) - { - if (eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - switch(*eptr++) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - break; - } - } - break; - - case OP_NOT_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - for (i = 1; i <= min; i++) - if ((md->ctypes[*eptr++] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* If min = max, continue at the same level without recursing */ - - if (min == max) continue; - - /* If minimizing, we have to test the rest of the pattern before each - subsequent match. Again, separate the UTF-8 case for speed, and also - separate the UCP cases. */ - - if (minimize) - { -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM36); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - if (prop_fail_result) RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_LAMP: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM37); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_GC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM38); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_PC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM39); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - case PT_SC: - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM40); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINC(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM41); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject) RRETURN(MATCH_NOMATCH); - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) RRETURN(MATCH_NOMATCH); - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - if (utf8) - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM42); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - (ctype == OP_ANY && (ims & PCRE_DOTALL) == 0 && - IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - GETCHARINC(c, eptr); - switch(ctype) - { - case OP_ANY: /* This is the DOTALL case */ - break; - - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - case 0x2028: - case 0x2029: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_HSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - break; - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_VSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - break; - } - break; - - case OP_NOT_DIGIT: - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if (c >= 256 || (md->ctypes[c] & ctype_digit) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if (c >= 256 || (md->ctypes[c] & ctype_space) == 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) - RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) - RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - else -#endif - /* Not UTF-8 mode */ - { - for (fi = min;; fi++) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM43); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (fi >= max || eptr >= md->end_subject || - ((ims & PCRE_DOTALL) == 0 && IS_NEWLINE(eptr))) - RRETURN(MATCH_NOMATCH); - - c = *eptr++; - switch(ctype) - { - case OP_ANY: /* This is the DOTALL case */ - break; - - case OP_ANYBYTE: - break; - - case OP_ANYNL: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x000d: - if (eptr < md->end_subject && *eptr == 0x0a) eptr++; - break; - - case 0x000a: - break; - - case 0x000b: - case 0x000c: - case 0x0085: - if (md->bsr_anycrlf) RRETURN(MATCH_NOMATCH); - break; - } - break; - - case OP_NOT_HSPACE: - switch(c) - { - default: break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_HSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - break; - } - break; - - case OP_NOT_VSPACE: - switch(c) - { - default: break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - RRETURN(MATCH_NOMATCH); - } - break; - - case OP_VSPACE: - switch(c) - { - default: RRETURN(MATCH_NOMATCH); - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - break; - } - break; - - case OP_NOT_DIGIT: - if ((md->ctypes[c] & ctype_digit) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_DIGIT: - if ((md->ctypes[c] & ctype_digit) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WHITESPACE: - if ((md->ctypes[c] & ctype_space) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WHITESPACE: - if ((md->ctypes[c] & ctype_space) == 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_NOT_WORDCHAR: - if ((md->ctypes[c] & ctype_word) != 0) RRETURN(MATCH_NOMATCH); - break; - - case OP_WORDCHAR: - if ((md->ctypes[c] & ctype_word) == 0) RRETURN(MATCH_NOMATCH); - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - } - } - /* Control never gets here */ - } - - /* If maximizing, it is worth using inline code for speed, doing the type - test once at the start (i.e. keep it out of the loop). Again, keep the - UTF-8 and UCP stuff separate. */ - - else - { - pp = eptr; /* Remember where we started */ - -#ifdef SUPPORT_UCP - if (prop_type >= 0) - { - switch(prop_type) - { - case PT_ANY: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (prop_fail_result) break; - eptr+= len; - } - break; - - case PT_LAMP: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == ucp_Lu || - prop_chartype == ucp_Ll || - prop_chartype == ucp_Lt) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_GC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_category == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_PC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_chartype == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - - case PT_SC: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if ((prop_script == prop_value) == prop_fail_result) - break; - eptr+= len; - } - break; - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM44); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - if (utf8) BACKCHAR(eptr); - } - } - - /* Match extended Unicode sequences. We will get here only if the - support is in the binary; otherwise a compile-time error occurs. */ - - else if (ctype == OP_EXTUNI) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - GETCHARINCTEST(c, eptr); - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category == ucp_M) break; - while (eptr < md->end_subject) - { - int len = 1; - if (!utf8) c = *eptr; else - { - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr += len; - } - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM45); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - for (;;) /* Move back over one extended */ - { - int len = 1; - if (!utf8) c = *eptr; else - { - BACKCHAR(eptr); - GETCHARLEN(c, eptr, len); - } - prop_category = _pcre_ucp_findprop(c, &prop_chartype, &prop_script); - if (prop_category != ucp_M) break; - eptr--; - } - } - } - - else -#endif /* SUPPORT_UCP */ - -#ifdef SUPPORT_UTF8 - /* UTF-8 mode */ - - if (utf8) - { - switch(ctype) - { - case OP_ANY: - if (max < INT_MAX) - { - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - else - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - } - - /* Handle unlimited UTF-8 repeat */ - - else - { - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - while (eptr < md->end_subject && (*eptr & 0xc0) == 0x80) eptr++; - } - } - else - { - eptr = md->end_subject; - } - } - break; - - /* The byte case is the same as non-UTF8 */ - - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - c = md->end_subject - eptr; - eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c == 0x000d) - { - if (++eptr >= md->end_subject) break; - if (*eptr == 0x000a) eptr++; - } - else - { - if (c != 0x000a && - (md->bsr_anycrlf || - (c != 0x000b && c != 0x000c && - c != 0x0085 && c != 0x2028 && c != 0x2029))) - break; - eptr += len; - } - } - break; - - case OP_NOT_HSPACE: - case OP_HSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - switch(c) - { - default: gotspace = FALSE; break; - case 0x09: /* HT */ - case 0x20: /* SPACE */ - case 0xa0: /* NBSP */ - case 0x1680: /* OGHAM SPACE MARK */ - case 0x180e: /* MONGOLIAN VOWEL SEPARATOR */ - case 0x2000: /* EN QUAD */ - case 0x2001: /* EM QUAD */ - case 0x2002: /* EN SPACE */ - case 0x2003: /* EM SPACE */ - case 0x2004: /* THREE-PER-EM SPACE */ - case 0x2005: /* FOUR-PER-EM SPACE */ - case 0x2006: /* SIX-PER-EM SPACE */ - case 0x2007: /* FIGURE SPACE */ - case 0x2008: /* PUNCTUATION SPACE */ - case 0x2009: /* THIN SPACE */ - case 0x200A: /* HAIR SPACE */ - case 0x202f: /* NARROW NO-BREAK SPACE */ - case 0x205f: /* MEDIUM MATHEMATICAL SPACE */ - case 0x3000: /* IDEOGRAPHIC SPACE */ - gotspace = TRUE; - break; - } - if (gotspace == (ctype == OP_NOT_HSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_VSPACE: - case OP_VSPACE: - for (i = min; i < max; i++) - { - BOOL gotspace; - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - switch(c) - { - default: gotspace = FALSE; break; - case 0x0a: /* LF */ - case 0x0b: /* VT */ - case 0x0c: /* FF */ - case 0x0d: /* CR */ - case 0x85: /* NEL */ - case 0x2028: /* LINE SEPARATOR */ - case 0x2029: /* PARAGRAPH SEPARATOR */ - gotspace = TRUE; - break; - } - if (gotspace == (ctype == OP_NOT_VSPACE)) break; - eptr += len; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_digit) != 0) break; - eptr+= len; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_digit) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_space) != 0) break; - eptr+= len; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 ||(md->ctypes[c] & ctype_space) == 0) break; - eptr+= len; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c < 256 && (md->ctypes[c] & ctype_word) != 0) break; - eptr+= len; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - int len = 1; - if (eptr >= md->end_subject) break; - GETCHARLEN(c, eptr, len); - if (c >= 256 || (md->ctypes[c] & ctype_word) == 0) break; - eptr+= len; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - for(;;) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM46); - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - if (eptr-- == pp) break; /* Stop if tried at original pos */ - BACKCHAR(eptr); - } - } - else -#endif /* SUPPORT_UTF8 */ - - /* Not UTF-8 mode */ - { - switch(ctype) - { - case OP_ANY: - if ((ims & PCRE_DOTALL) == 0) - { - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || IS_NEWLINE(eptr)) break; - eptr++; - } - break; - } - /* For DOTALL case, fall through and treat as \C */ - - case OP_ANYBYTE: - c = max - min; - if (c > (unsigned int)(md->end_subject - eptr)) - c = md->end_subject - eptr; - eptr += c; - break; - - case OP_ANYNL: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x000d) - { - if (++eptr >= md->end_subject) break; - if (*eptr == 0x000a) eptr++; - } - else - { - if (c != 0x000a && - (md->bsr_anycrlf || - (c != 0x000b && c != 0x000c && c != 0x0085))) - break; - eptr++; - } - } - break; - - case OP_NOT_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x09 || c == 0x20 || c == 0xa0) break; - eptr++; - } - break; - - case OP_HSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c != 0x09 && c != 0x20 && c != 0xa0) break; - eptr++; - } - break; - - case OP_NOT_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c == 0x0a || c == 0x0b || c == 0x0c || c == 0x0d || c == 0x85) - break; - eptr++; - } - break; - - case OP_VSPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject) break; - c = *eptr; - if (c != 0x0a && c != 0x0b && c != 0x0c && c != 0x0d && c != 0x85) - break; - eptr++; - } - break; - - case OP_NOT_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) != 0) - break; - eptr++; - } - break; - - case OP_DIGIT: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_digit) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) != 0) - break; - eptr++; - } - break; - - case OP_WHITESPACE: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_space) == 0) - break; - eptr++; - } - break; - - case OP_NOT_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) != 0) - break; - eptr++; - } - break; - - case OP_WORDCHAR: - for (i = min; i < max; i++) - { - if (eptr >= md->end_subject || (md->ctypes[*eptr] & ctype_word) == 0) - break; - eptr++; - } - break; - - default: - RRETURN(PCRE_ERROR_INTERNAL); - } - - /* eptr is now past the end of the maximum run */ - - if (possessive) continue; - while (eptr >= pp) - { - RMATCH(eptr, ecode, offset_top, md, ims, eptrb, 0, RM47); - eptr--; - if (rrc != MATCH_NOMATCH) RRETURN(rrc); - } - } - - /* Get here if we can't make it match with any permitted repetitions */ - - RRETURN(MATCH_NOMATCH); - } - /* Control never gets here */ - - /* There's been some horrible disaster. Arrival here can only mean there is - something seriously wrong in the code above or the OP_xxx definitions. */ - - default: - DPRINTF(("Unknown opcode %d\n", *ecode)); - RRETURN(PCRE_ERROR_UNKNOWN_OPCODE); - } - - /* Do not stick any code in here without much thought; it is assumed - that "continue" in the code above comes out to here to repeat the main - loop. */ - - } /* End of main loop */ -/* Control never reaches here */ - - -/* When compiling to use the heap rather than the stack for recursive calls to -match(), the RRETURN() macro jumps here. The number that is saved in -frame->Xwhere indicates which label we actually want to return to. */ - -#ifdef NO_RECURSE -#define LBL(val) case val: goto L_RM##val; -HEAP_RETURN: -switch (frame->Xwhere) - { - LBL( 1) LBL( 2) LBL( 3) LBL( 4) LBL( 5) LBL( 6) LBL( 7) LBL( 8) - LBL( 9) LBL(10) LBL(11) LBL(12) LBL(13) LBL(14) LBL(15) LBL(17) - LBL(19) LBL(24) LBL(25) LBL(26) LBL(27) LBL(29) LBL(31) LBL(33) - LBL(35) LBL(43) LBL(47) LBL(48) LBL(49) LBL(50) LBL(51) LBL(52) - LBL(53) LBL(54) -#ifdef SUPPORT_UTF8 - LBL(16) LBL(18) LBL(20) LBL(21) LBL(22) LBL(23) LBL(28) LBL(30) - LBL(32) LBL(34) LBL(42) LBL(46) -#ifdef SUPPORT_UCP - LBL(36) LBL(37) LBL(38) LBL(39) LBL(40) LBL(41) LBL(44) LBL(45) -#endif /* SUPPORT_UCP */ -#endif /* SUPPORT_UTF8 */ - default: - DPRINTF(("jump error in pcre match: label %d non-existent\n", frame->Xwhere)); - return PCRE_ERROR_INTERNAL; - } -#undef LBL -#endif /* NO_RECURSE */ -} - - -/*************************************************************************** -**************************************************************************** - RECURSION IN THE match() FUNCTION - -Undefine all the macros that were defined above to handle this. */ - -#ifdef NO_RECURSE -#undef eptr -#undef ecode -#undef mstart -#undef offset_top -#undef ims -#undef eptrb -#undef flags - -#undef callpat -#undef charptr -#undef data -#undef next -#undef pp -#undef prev -#undef saved_eptr - -#undef new_recursive - -#undef cur_is_word -#undef condition -#undef prev_is_word - -#undef original_ims - -#undef ctype -#undef length -#undef max -#undef min -#undef number -#undef offset -#undef op -#undef save_capture_last -#undef save_offset1 -#undef save_offset2 -#undef save_offset3 -#undef stacksave - -#undef newptrb - -#endif - -/* These two are defined as macros in both cases */ - -#undef fc -#undef fi - -/*************************************************************************** -***************************************************************************/ - - - -/************************************************* -* Execute a Regular Expression * -*************************************************/ - -/* This function applies a compiled re to a subject string and picks out -portions of the string if it matches. Two elements in the vector are set for -each substring: the offsets to the start and end of the substring. - -Arguments: - argument_re points to the compiled expression - extra_data points to extra data or is NULL - subject points to the subject string - length length of subject string (may contain binary zeros) - start_offset where to start in the subject string - options option bits - offsets points to a vector of ints to be filled in with offsets - offsetcount the number of elements in the vector - -Returns: > 0 => success; value is the number of elements filled in - = 0 => success, but offsets is not big enough - -1 => failed to match - < -1 => some kind of unexpected problem -*/ - -PCRE_EXP_DEFN int -pcre_exec(const pcre *argument_re, const pcre_extra *extra_data, - PCRE_SPTR subject, int length, int start_offset, int options, int *offsets, - int offsetcount) -{ -int rc, resetcount, ocount; -int first_byte = -1; -int req_byte = -1; -int req_byte2 = -1; -int newline; -unsigned long int ims; -BOOL using_temporary_offsets = FALSE; -BOOL anchored; -BOOL startline; -BOOL firstline; -BOOL first_byte_caseless = FALSE; -BOOL req_byte_caseless = FALSE; -BOOL utf8; -match_data match_block; -match_data *md = &match_block; -const uschar *tables; -const uschar *start_bits = NULL; -USPTR start_match = (USPTR)subject + start_offset; -USPTR end_subject; -USPTR req_byte_ptr = start_match - 1; - -pcre_study_data internal_study; -const pcre_study_data *study; - -real_pcre internal_re; -const real_pcre *external_re = (const real_pcre *)argument_re; -const real_pcre *re = external_re; - -/* Plausibility checks */ - -if ((options & ~PUBLIC_EXEC_OPTIONS) != 0) return PCRE_ERROR_BADOPTION; -if (re == NULL || subject == NULL || - (offsets == NULL && offsetcount > 0)) return PCRE_ERROR_NULL; -if (offsetcount < 0) return PCRE_ERROR_BADCOUNT; - -/* Fish out the optional data from the extra_data structure, first setting -the default values. */ - -study = NULL; -md->match_limit = MATCH_LIMIT; -md->match_limit_recursion = MATCH_LIMIT_RECURSION; -md->callout_data = NULL; - -/* The table pointer is always in native byte order. */ - -tables = external_re->tables; - -if (extra_data != NULL) - { - register unsigned int flags = extra_data->flags; - if ((flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - if ((flags & PCRE_EXTRA_MATCH_LIMIT) != 0) - md->match_limit = extra_data->match_limit; - if ((flags & PCRE_EXTRA_MATCH_LIMIT_RECURSION) != 0) - md->match_limit_recursion = extra_data->match_limit_recursion; - if ((flags & PCRE_EXTRA_CALLOUT_DATA) != 0) - md->callout_data = extra_data->callout_data; - if ((flags & PCRE_EXTRA_TABLES) != 0) tables = extra_data->tables; - } - -/* If the exec call supplied NULL for tables, use the inbuilt ones. This -is a feature that makes it possible to save compiled regex and re-use them -in other programs later. */ - -if (tables == NULL) tables = _pcre_default_tables; - -/* Check that the first field in the block is the magic number. If it is not, -test for a regex that was compiled on a host of opposite endianness. If this is -the case, flipped values are put in internal_re and internal_study if there was -study data too. */ - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -/* Set up other data */ - -anchored = ((re->options | options) & PCRE_ANCHORED) != 0; -startline = (re->flags & PCRE_STARTLINE) != 0; -firstline = (re->options & PCRE_FIRSTLINE) != 0; - -/* The code starts after the real_pcre block and the capture name table. */ - -md->start_code = (const uschar *)external_re + re->name_table_offset + - re->name_count * re->name_entry_size; - -md->start_subject = (USPTR)subject; -md->start_offset = start_offset; -md->end_subject = md->start_subject + length; -end_subject = md->end_subject; - -md->endonly = (re->options & PCRE_DOLLAR_ENDONLY) != 0; -utf8 = md->utf8 = (re->options & PCRE_UTF8) != 0; - -md->notbol = (options & PCRE_NOTBOL) != 0; -md->noteol = (options & PCRE_NOTEOL) != 0; -md->notempty = (options & PCRE_NOTEMPTY) != 0; -md->partial = (options & PCRE_PARTIAL) != 0; -md->hitend = FALSE; - -md->recursive = NULL; /* No recursion at top level */ - -md->lcc = tables + lcc_offset; -md->ctypes = tables + ctypes_offset; - -/* Handle different \R options. */ - -switch (options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) - { - case 0: - if ((re->options & (PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE)) != 0) - md->bsr_anycrlf = (re->options & PCRE_BSR_ANYCRLF) != 0; - else -#ifdef BSR_ANYCRLF - md->bsr_anycrlf = TRUE; -#else - md->bsr_anycrlf = FALSE; -#endif - break; - - case PCRE_BSR_ANYCRLF: - md->bsr_anycrlf = TRUE; - break; - - case PCRE_BSR_UNICODE: - md->bsr_anycrlf = FALSE; - break; - - default: return PCRE_ERROR_BADNEWLINE; - } - -/* Handle different types of newline. The three bits give eight cases. If -nothing is set at run time, whatever was used at compile time applies. */ - -switch ((((options & PCRE_NEWLINE_BITS) == 0)? re->options : - (pcre_uint32)options) & PCRE_NEWLINE_BITS) - { - case 0: newline = NEWLINE; break; /* Compile-time default */ - case PCRE_NEWLINE_CR: newline = '\r'; break; - case PCRE_NEWLINE_LF: newline = '\n'; break; - case PCRE_NEWLINE_CR+ - PCRE_NEWLINE_LF: newline = ('\r' << 8) | '\n'; break; - case PCRE_NEWLINE_ANY: newline = -1; break; - case PCRE_NEWLINE_ANYCRLF: newline = -2; break; - default: return PCRE_ERROR_BADNEWLINE; - } - -if (newline == -2) - { - md->nltype = NLTYPE_ANYCRLF; - } -else if (newline < 0) - { - md->nltype = NLTYPE_ANY; - } -else - { - md->nltype = NLTYPE_FIXED; - if (newline > 255) - { - md->nllen = 2; - md->nl[0] = (newline >> 8) & 255; - md->nl[1] = newline & 255; - } - else - { - md->nllen = 1; - md->nl[0] = newline; - } - } - -/* Partial matching is supported only for a restricted set of regexes at the -moment. */ - -if (md->partial && (re->flags & PCRE_NOPARTIAL) != 0) - return PCRE_ERROR_BADPARTIAL; - -/* Check a UTF-8 string if required. Unfortunately there's no way of passing -back the character offset. */ - -#ifdef SUPPORT_UTF8 -if (utf8 && (options & PCRE_NO_UTF8_CHECK) == 0) - { - if (_pcre_valid_utf8((uschar *)subject, length) >= 0) - return PCRE_ERROR_BADUTF8; - if (start_offset > 0 && start_offset < length) - { - int tb = ((uschar *)subject)[start_offset]; - if (tb > 127) - { - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) return PCRE_ERROR_BADUTF8_OFFSET; - } - } - } -#endif - -/* The ims options can vary during the matching as a result of the presence -of (?ims) items in the pattern. They are kept in a local variable so that -restoring at the exit of a group is easy. */ - -ims = re->options & (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL); - -/* If the expression has got more back references than the offsets supplied can -hold, we get a temporary chunk of working store to use during the matching. -Otherwise, we can use the vector supplied, rounding down its size to a multiple -of 3. */ - -ocount = offsetcount - (offsetcount % 3); - -if (re->top_backref > 0 && re->top_backref >= ocount/3) - { - ocount = re->top_backref * 3 + 3; - md->offset_vector = (int *)(pcre_malloc)(ocount * sizeof(int)); - if (md->offset_vector == NULL) return PCRE_ERROR_NOMEMORY; - using_temporary_offsets = TRUE; - DPRINTF(("Got memory to hold back references\n")); - } -else md->offset_vector = offsets; - -md->offset_end = ocount; -md->offset_max = (2*ocount)/3; -md->offset_overflow = FALSE; -md->capture_last = -1; - -/* Compute the minimum number of offsets that we need to reset each time. Doing -this makes a huge difference to execution time when there aren't many brackets -in the pattern. */ - -resetcount = 2 + re->top_bracket * 2; -if (resetcount > offsetcount) resetcount = ocount; - -/* Reset the working variable associated with each extraction. These should -never be used unless previously set, but they get saved and restored, and so we -initialize them to avoid reading uninitialized locations. */ - -if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector + ocount; - register int *iend = iptr - resetcount/2 + 1; - while (--iptr >= iend) *iptr = -1; - } - -/* Set up the first character to match, if available. The first_byte value is -never set for an anchored regular expression, but the anchoring may be forced -at run time, so we have to test for anchoring. The first char may be unset for -an unanchored pattern, of course. If there's no first char and the pattern was -studied, there may be a bitmap of possible first characters. */ - -if (!anchored) - { - if ((re->flags & PCRE_FIRSTSET) != 0) - { - first_byte = re->first_byte & 255; - if ((first_byte_caseless = ((re->first_byte & REQ_CASELESS) != 0)) == TRUE) - first_byte = md->lcc[first_byte]; - } - else - if (!startline && study != NULL && - (study->options & PCRE_STUDY_MAPPED) != 0) - start_bits = study->start_bits; - } - -/* For anchored or unanchored matches, there may be a "last known required -character" set. */ - -if ((re->flags & PCRE_REQCHSET) != 0) - { - req_byte = re->req_byte & 255; - req_byte_caseless = (re->req_byte & REQ_CASELESS) != 0; - req_byte2 = (tables + fcc_offset)[req_byte]; /* case flipped */ - } - - -/* ==========================================================================*/ - -/* Loop for handling unanchored repeated matching attempts; for anchored regexs -the loop runs just once. */ - -for(;;) - { - USPTR save_end_subject = end_subject; - USPTR new_start_match; - - /* Reset the maximum number of extractions we might see. */ - - if (md->offset_vector != NULL) - { - register int *iptr = md->offset_vector; - register int *iend = iptr + resetcount; - while (iptr < iend) *iptr++ = -1; - } - - /* Advance to a unique first char if possible. If firstline is TRUE, the - start of the match is constrained to the first line of a multiline string. - That is, the match must be before or at the first newline. Implement this by - temporarily adjusting end_subject so that we stop scanning at a newline. If - the match fails at the newline, later code breaks this loop. */ - - if (firstline) - { - USPTR t = start_match; - while (t < md->end_subject && !IS_NEWLINE(t)) t++; - end_subject = t; - } - - /* Now test for a unique first byte */ - - if (first_byte >= 0) - { - if (first_byte_caseless) - while (start_match < end_subject && - md->lcc[*start_match] != first_byte) - start_match++; - else - while (start_match < end_subject && *start_match != first_byte) - start_match++; - } - - /* Or to just after a linebreak for a multiline match if possible */ - - else if (startline) - { - if (start_match > md->start_subject + start_offset) - { - while (start_match <= end_subject && !WAS_NEWLINE(start_match)) - start_match++; - - /* If we have just passed a CR and the newline option is ANY or ANYCRLF, - and we are now at a LF, advance the match position by one more character. - */ - - if (start_match[-1] == '\r' && - (md->nltype == NLTYPE_ANY || md->nltype == NLTYPE_ANYCRLF) && - start_match < end_subject && - *start_match == '\n') - start_match++; - } - } - - /* Or to a non-unique first char after study */ - - else if (start_bits != NULL) - { - while (start_match < end_subject) - { - register unsigned int c = *start_match; - if ((start_bits[c/8] & (1 << (c&7))) == 0) start_match++; else break; - } - } - - /* Restore fudged end_subject */ - - end_subject = save_end_subject; - -#ifdef DEBUG /* Sigh. Some compilers never learn. */ - printf(">>>> Match against: "); - pchars(start_match, end_subject - start_match, TRUE, md); - printf("\n"); -#endif - - /* If req_byte is set, we know that that character must appear in the subject - for the match to succeed. If the first character is set, req_byte must be - later in the subject; otherwise the test starts at the match point. This - optimization can save a huge amount of backtracking in patterns with nested - unlimited repeats that aren't going to match. Writing separate code for - cased/caseless versions makes it go faster, as does using an autoincrement - and backing off on a match. - - HOWEVER: when the subject string is very, very long, searching to its end can - take a long time, and give bad performance on quite ordinary patterns. This - showed up when somebody was matching something like /^\d+C/ on a 32-megabyte - string... so we don't do this when the string is sufficiently long. - - ALSO: this processing is disabled when partial matching is requested. - */ - - if (req_byte >= 0 && - end_subject - start_match < REQ_BYTE_MAX && - !md->partial) - { - register USPTR p = start_match + ((first_byte >= 0)? 1 : 0); - - /* We don't need to repeat the search if we haven't yet reached the - place we found it at last time. */ - - if (p > req_byte_ptr) - { - if (req_byte_caseless) - { - while (p < end_subject) - { - register int pp = *p++; - if (pp == req_byte || pp == req_byte2) { p--; break; } - } - } - else - { - while (p < end_subject) - { - if (*p++ == req_byte) { p--; break; } - } - } - - /* If we can't find the required character, break the matching loop, - forcing a match failure. */ - - if (p >= end_subject) - { - rc = MATCH_NOMATCH; - break; - } - - /* If we have found the required character, save the point where we - found it, so that we don't search again next time round the loop if - the start hasn't passed this character yet. */ - - req_byte_ptr = p; - } - } - - /* OK, we can now run the match. */ - - md->start_match_ptr = start_match; - md->match_call_count = 0; - rc = match(start_match, md->start_code, start_match, 2, md, ims, NULL, 0, 0); - - switch(rc) - { - /* NOMATCH and PRUNE advance by one character. THEN at this level acts - exactly like PRUNE. */ - - case MATCH_NOMATCH: - case MATCH_PRUNE: - case MATCH_THEN: - new_start_match = start_match + 1; -#ifdef SUPPORT_UTF8 - if (utf8) - while(new_start_match < end_subject && (*new_start_match & 0xc0) == 0x80) - new_start_match++; -#endif - break; - - /* SKIP passes back the next starting point explicitly. */ - - case MATCH_SKIP: - new_start_match = md->start_match_ptr; - break; - - /* COMMIT disables the bumpalong, but otherwise behaves as NOMATCH. */ - - case MATCH_COMMIT: - rc = MATCH_NOMATCH; - goto ENDLOOP; - - /* Any other return is some kind of error. */ - - default: - goto ENDLOOP; - } - - /* Control reaches here for the various types of "no match at this point" - result. Reset the code to MATCH_NOMATCH for subsequent checking. */ - - rc = MATCH_NOMATCH; - - /* If PCRE_FIRSTLINE is set, the match must happen before or at the first - newline in the subject (though it may continue over the newline). Therefore, - if we have just failed to match, starting at a newline, do not continue. */ - - if (firstline && IS_NEWLINE(start_match)) break; - - /* Advance to new matching position */ - - start_match = new_start_match; - - /* Break the loop if the pattern is anchored or if we have passed the end of - the subject. */ - - if (anchored || start_match > end_subject) break; - - /* If we have just passed a CR and we are now at a LF, and the pattern does - not contain any explicit matches for \r or \n, and the newline option is CRLF - or ANY or ANYCRLF, advance the match position by one more character. */ - - if (start_match[-1] == '\r' && - start_match < end_subject && - *start_match == '\n' && - (re->flags & PCRE_HASCRORLF) == 0 && - (md->nltype == NLTYPE_ANY || - md->nltype == NLTYPE_ANYCRLF || - md->nllen == 2)) - start_match++; - - } /* End of for(;;) "bumpalong" loop */ - -/* ==========================================================================*/ - -/* We reach here when rc is not MATCH_NOMATCH, or if one of the stopping -conditions is true: - -(1) The pattern is anchored or the match was failed by (*COMMIT); - -(2) We are past the end of the subject; - -(3) PCRE_FIRSTLINE is set and we have failed to match at a newline, because - this option requests that a match occur at or before the first newline in - the subject. - -When we have a match and the offset vector is big enough to deal with any -backreferences, captured substring offsets will already be set up. In the case -where we had to get some local store to hold offsets for backreference -processing, copy those that we can. In this case there need not be overflow if -certain parts of the pattern were not used, even though there are more -capturing parentheses than vector slots. */ - -ENDLOOP: - -if (rc == MATCH_MATCH) - { - if (using_temporary_offsets) - { - if (offsetcount >= 4) - { - memcpy(offsets + 2, md->offset_vector + 2, - (offsetcount - 2) * sizeof(int)); - DPRINTF(("Copied offsets from temporary memory\n")); - } - if (md->end_offset_top > offsetcount) md->offset_overflow = TRUE; - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - - /* Set the return code to the number of captured strings, or 0 if there are - too many to fit into the vector. */ - - rc = md->offset_overflow? 0 : md->end_offset_top/2; - - /* If there is space, set up the whole thing as substring 0. The value of - md->start_match_ptr might be modified if \K was encountered on the success - matching path. */ - - if (offsetcount < 2) rc = 0; else - { - offsets[0] = md->start_match_ptr - md->start_subject; - offsets[1] = md->end_match_ptr - md->start_subject; - } - - DPRINTF((">>>> returning %d\n", rc)); - return rc; - } - -/* Control gets here if there has been an error, or if the overall match -attempt has failed at all permitted starting positions. */ - -if (using_temporary_offsets) - { - DPRINTF(("Freeing temporary memory\n")); - (pcre_free)(md->offset_vector); - } - -if (rc != MATCH_NOMATCH) - { - DPRINTF((">>>> error: returning %d\n", rc)); - return rc; - } -else if (md->partial && md->hitend) - { - DPRINTF((">>>> returning PCRE_ERROR_PARTIAL\n")); - return PCRE_ERROR_PARTIAL; - } -else - { - DPRINTF((">>>> returning PCRE_ERROR_NOMATCH\n")); - return PCRE_ERROR_NOMATCH; - } -} - -/* End of pcre_exec.c */ diff --git a/src/src/pcre/pcre_fullinfo.c b/src/src/pcre/pcre_fullinfo.c deleted file mode 100644 index 797241dd5..000000000 --- a/src/src/pcre/pcre_fullinfo.c +++ /dev/null @@ -1,167 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_fullinfo.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/*PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_fullinfo(), which returns -information about a compiled pattern. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return info about compiled pattern * -*************************************************/ - -/* This is a newer "info" function which has an extensible interface so -that additional items can be added compatibly. - -Arguments: - argument_re points to compiled code - extra_data points extra data, or NULL - what what information is required - where where to put the information - -Returns: 0 if data returned, negative on error -*/ - -PCRE_EXP_DEFN int -pcre_fullinfo(const pcre *argument_re, const pcre_extra *extra_data, int what, - void *where) -{ -real_pcre internal_re; -pcre_study_data internal_study; -const real_pcre *re = (const real_pcre *)argument_re; -const pcre_study_data *study = NULL; - -if (re == NULL || where == NULL) return PCRE_ERROR_NULL; - -if (extra_data != NULL && (extra_data->flags & PCRE_EXTRA_STUDY_DATA) != 0) - study = (const pcre_study_data *)extra_data->study_data; - -if (re->magic_number != MAGIC_NUMBER) - { - re = _pcre_try_flipped(re, &internal_re, study, &internal_study); - if (re == NULL) return PCRE_ERROR_BADMAGIC; - if (study != NULL) study = &internal_study; - } - -switch (what) - { - case PCRE_INFO_OPTIONS: - *((unsigned long int *)where) = re->options & PUBLIC_OPTIONS; - break; - - case PCRE_INFO_SIZE: - *((size_t *)where) = re->size; - break; - - case PCRE_INFO_STUDYSIZE: - *((size_t *)where) = (study == NULL)? 0 : study->size; - break; - - case PCRE_INFO_CAPTURECOUNT: - *((int *)where) = re->top_bracket; - break; - - case PCRE_INFO_BACKREFMAX: - *((int *)where) = re->top_backref; - break; - - case PCRE_INFO_FIRSTBYTE: - *((int *)where) = - ((re->flags & PCRE_FIRSTSET) != 0)? re->first_byte : - ((re->flags & PCRE_STARTLINE) != 0)? -1 : -2; - break; - - /* Make sure we pass back the pointer to the bit vector in the external - block, not the internal copy (with flipped integer fields). */ - - case PCRE_INFO_FIRSTTABLE: - *((const uschar **)where) = - (study != NULL && (study->options & PCRE_STUDY_MAPPED) != 0)? - ((const pcre_study_data *)extra_data->study_data)->start_bits : NULL; - break; - - case PCRE_INFO_LASTLITERAL: - *((int *)where) = - ((re->flags & PCRE_REQCHSET) != 0)? re->req_byte : -1; - break; - - case PCRE_INFO_NAMEENTRYSIZE: - *((int *)where) = re->name_entry_size; - break; - - case PCRE_INFO_NAMECOUNT: - *((int *)where) = re->name_count; - break; - - case PCRE_INFO_NAMETABLE: - *((const uschar **)where) = (const uschar *)re + re->name_table_offset; - break; - - case PCRE_INFO_DEFAULT_TABLES: - *((const uschar **)where) = (const uschar *)(_pcre_default_tables); - break; - - case PCRE_INFO_OKPARTIAL: - *((int *)where) = (re->flags & PCRE_NOPARTIAL) == 0; - break; - - case PCRE_INFO_JCHANGED: - *((int *)where) = (re->flags & PCRE_JCHANGED) != 0; - break; - - case PCRE_INFO_HASCRORLF: - *((int *)where) = (re->flags & PCRE_HASCRORLF) != 0; - break; - - default: return PCRE_ERROR_BADOPTION; - } - -return 0; -} - -/* End of pcre_fullinfo.c */ diff --git a/src/src/pcre/pcre_get.c b/src/src/pcre/pcre_get.c deleted file mode 100644 index 451b6d981..000000000 --- a/src/src/pcre/pcre_get.c +++ /dev/null @@ -1,467 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_get.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains some convenience functions for extracting substrings -from the subject string after a regex match has succeeded. The original idea -for these functions came from Scott Wimer. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Find number for named string * -*************************************************/ - -/* This function is used by the get_first_set() function below, as well -as being generally available. It assumes that names are unique. - -Arguments: - code the compiled regex - stringname the name whose number is required - -Returns: the number of the named parentheses, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -int -pcre_get_stringnumber(const pcre *code, const char *stringname) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; - -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) return (entry[0] << 8) + entry[1]; - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find (multiple) entries for named string * -*************************************************/ - -/* This is used by the get_first_set() function below, as well as being -generally available. It is used when duplicated names are permitted. - -Arguments: - code the compiled regex - stringname the name whose entries required - firstptr where to put the pointer to the first entry - lastptr where to put the pointer to the last entry - -Returns: the length of each entry, or a negative number - (PCRE_ERROR_NOSUBSTRING) if not found -*/ - -int -pcre_get_stringtable_entries(const pcre *code, const char *stringname, - char **firstptr, char **lastptr) -{ -int rc; -int entrysize; -int top, bot; -uschar *nametable, *lastentry; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMECOUNT, &top)) != 0) - return rc; -if (top <= 0) return PCRE_ERROR_NOSUBSTRING; - -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMEENTRYSIZE, &entrysize)) != 0) - return rc; -if ((rc = pcre_fullinfo(code, NULL, PCRE_INFO_NAMETABLE, &nametable)) != 0) - return rc; - -lastentry = nametable + entrysize * (top - 1); -bot = 0; -while (top > bot) - { - int mid = (top + bot) / 2; - uschar *entry = nametable + entrysize*mid; - int c = strcmp(stringname, (char *)(entry + 2)); - if (c == 0) - { - uschar *first = entry; - uschar *last = entry; - while (first > nametable) - { - if (strcmp(stringname, (char *)(first - entrysize + 2)) != 0) break; - first -= entrysize; - } - while (last < lastentry) - { - if (strcmp(stringname, (char *)(last + entrysize + 2)) != 0) break; - last += entrysize; - } - *firstptr = (char *)first; - *lastptr = (char *)last; - return entrysize; - } - if (c > 0) bot = mid + 1; else top = mid; - } - -return PCRE_ERROR_NOSUBSTRING; -} - - - -/************************************************* -* Find first set of multiple named strings * -*************************************************/ - -/* This function allows for duplicate names in the table of named substrings. -It returns the number of the first one that was set in a pattern match. - -Arguments: - code the compiled regex - stringname the name of the capturing substring - ovector the vector of matched substrings - -Returns: the number of the first that is set, - or the number of the last one if none are set, - or a negative number on error -*/ - -static int -get_first_set(const pcre *code, const char *stringname, int *ovector) -{ -const real_pcre *re = (const real_pcre *)code; -int entrysize; -char *first, *last; -uschar *entry; -if ((re->options & PCRE_DUPNAMES) == 0 && (re->flags & PCRE_JCHANGED) == 0) - return pcre_get_stringnumber(code, stringname); -entrysize = pcre_get_stringtable_entries(code, stringname, &first, &last); -if (entrysize <= 0) return entrysize; -for (entry = (uschar *)first; entry <= (uschar *)last; entry += entrysize) - { - int n = (entry[0] << 8) + entry[1]; - if (ovector[n*2] >= 0) return n; - } -return (first[0] << 8) + first[1]; -} - - - - -/************************************************* -* Copy captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer. -Note that we use memcpy() rather than strncpy() in case there are binary zeros -in the string. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -int -pcre_copy_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, char *buffer, int size) -{ -int yield; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -if (size < yield + 1) return PCRE_ERROR_NOMEMORY; -memcpy(buffer, subject + ovector[stringnumber], yield); -buffer[yield] = 0; -return yield; -} - - - -/************************************************* -* Copy named captured string to given buffer * -*************************************************/ - -/* This function copies a single captured substring into a given buffer, -identifying it by name. If the regex permits duplicate names, the first -substring that is set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - buffer where to put the substring - size the size of the buffer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) buffer too small - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -int -pcre_copy_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, char *buffer, int size) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_copy_substring(subject, ovector, stringcount, n, buffer, size); -} - - - -/************************************************* -* Copy all captured strings to new store * -*************************************************/ - -/* This function gets one chunk of store and builds a list of pointers and all -of the captured substrings in it. A NULL pointer is put on the end of the list. - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - listptr set to point to the list of pointers - -Returns: if successful: 0 - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store -*/ - -int -pcre_get_substring_list(const char *subject, int *ovector, int stringcount, - const char ***listptr) -{ -int i; -int size = sizeof(char *); -int double_count = stringcount * 2; -char **stringlist; -char *p; - -for (i = 0; i < double_count; i += 2) - size += sizeof(char *) + ovector[i+1] - ovector[i] + 1; - -stringlist = (char **)(pcre_malloc)(size); -if (stringlist == NULL) return PCRE_ERROR_NOMEMORY; - -*listptr = (const char **)stringlist; -p = (char *)(stringlist + stringcount + 1); - -for (i = 0; i < double_count; i += 2) - { - int len = ovector[i+1] - ovector[i]; - memcpy(p, subject + ovector[i], len); - *stringlist++ = p; - p += len; - *p++ = 0; - } - -*stringlist = NULL; -return 0; -} - - - -/************************************************* -* Free store obtained by get_substring_list * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring_list() -Returns: nothing -*/ - -void -pcre_free_substring_list(const char **pointer) -{ -(pcre_free)((void *)pointer); -} - - - -/************************************************* -* Copy captured string to new store * -*************************************************/ - -/* This function copies a single captured substring into a piece of new -store - -Arguments: - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringnumber the number of the required substring - stringptr where to put a pointer to the substring - -Returns: if successful: - the length of the string, not including the zero that - is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) failed to get store - PCRE_ERROR_NOSUBSTRING (-7) substring not present -*/ - -int -pcre_get_substring(const char *subject, int *ovector, int stringcount, - int stringnumber, const char **stringptr) -{ -int yield; -char *substring; -if (stringnumber < 0 || stringnumber >= stringcount) - return PCRE_ERROR_NOSUBSTRING; -stringnumber *= 2; -yield = ovector[stringnumber+1] - ovector[stringnumber]; -substring = (char *)(pcre_malloc)(yield + 1); -if (substring == NULL) return PCRE_ERROR_NOMEMORY; -memcpy(substring, subject + ovector[stringnumber], yield); -substring[yield] = 0; -*stringptr = substring; -return yield; -} - - - -/************************************************* -* Copy named captured string to new store * -*************************************************/ - -/* This function copies a single captured substring, identified by name, into -new store. If the regex permits duplicate names, the first substring that is -set is chosen. - -Arguments: - code the compiled regex - subject the subject string that was matched - ovector pointer to the offsets table - stringcount the number of substrings that were captured - (i.e. the yield of the pcre_exec call, unless - that was zero, in which case it should be 1/3 - of the offset table size) - stringname the name of the required substring - stringptr where to put the pointer - -Returns: if successful: - the length of the copied string, not including the zero - that is put on the end; can be zero - if not successful: - PCRE_ERROR_NOMEMORY (-6) couldn't get memory - PCRE_ERROR_NOSUBSTRING (-7) no such captured substring -*/ - -int -pcre_get_named_substring(const pcre *code, const char *subject, int *ovector, - int stringcount, const char *stringname, const char **stringptr) -{ -int n = get_first_set(code, stringname, ovector); -if (n <= 0) return n; -return pcre_get_substring(subject, ovector, stringcount, n, stringptr); -} - - - - -/************************************************* -* Free store obtained by get_substring * -*************************************************/ - -/* This function exists for the benefit of people calling PCRE from non-C -programs that can call its functions, but not free() or (pcre_free)() directly. - -Argument: the result of a previous pcre_get_substring() -Returns: nothing -*/ - -void -pcre_free_substring(const char *pointer) -{ -(pcre_free)((void *)pointer); -} - -/* End of pcre_get.c */ diff --git a/src/src/pcre/pcre_globals.c b/src/src/pcre/pcre_globals.c deleted file mode 100644 index 002a5779f..000000000 --- a/src/src/pcre/pcre_globals.c +++ /dev/null @@ -1,65 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_globals.c,v 1.6 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains global variables that are exported by the PCRE library. -PCRE is thread-clean and doesn't use any global variables in the normal sense. -However, it calls memory allocation and freeing functions via the four -indirections below, and it can optionally do callouts, using the fifth -indirection. These values can be changed by the caller, but are shared between -all threads. However, when compiling for Virtual Pascal, things are done -differently, and global variables are not used (see pcre.in). */ - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - -#ifndef VPCOMPAT -PCRE_EXP_DATA_DEFN void *(*pcre_malloc)(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*pcre_free)(void *) = free; -PCRE_EXP_DATA_DEFN void *(*pcre_stack_malloc)(size_t) = malloc; -PCRE_EXP_DATA_DEFN void (*pcre_stack_free)(void *) = free; -PCRE_EXP_DATA_DEFN int (*pcre_callout)(pcre_callout_block *) = NULL; -#endif - -/* End of pcre_globals.c */ diff --git a/src/src/pcre/pcre_internal.h b/src/src/pcre/pcre_internal.h deleted file mode 100644 index 8f4029c33..000000000 --- a/src/src/pcre/pcre_internal.h +++ /dev/null @@ -1,1119 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_internal.h,v 1.7 2007/11/12 13:02:19 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - -/* This header contains definitions that are shared between the different -modules, but which are not relevant to the exported API. This includes some -functions whose names all begin with "_pcre_". */ - -#ifndef PCRE_INTERNAL_H -#define PCRE_INTERNAL_H - -/* Define DEBUG to get debugging output on stdout. */ - -#if 0 -#define DEBUG -#endif - -/* Use a macro for debugging printing, 'cause that eliminates the use of #ifdef -inline, and there are *still* stupid compilers about that don't like indented -pre-processor statements, or at least there were when I first wrote this. After -all, it had only been about 10 years then... - -It turns out that the Mac Debugging.h header also defines the macro DPRINTF, so -be absolutely sure we get our version. */ - -#undef DPRINTF -#ifdef DEBUG -#define DPRINTF(p) printf p -#else -#define DPRINTF(p) /* Nothing */ -#endif - - -/* Standard C headers plus the external interface definition. The only time -setjmp and stdarg are used is when NO_RECURSE is set. */ - -#include <ctype.h> -#include <limits.h> -#include <setjmp.h> -#include <stdarg.h> -#include <stddef.h> -#include <stdio.h> -#include <stdlib.h> -#include <string.h> - -/* When compiling a DLL for Windows, the exported symbols have to be declared -using some MS magic. I found some useful information on this web page: -http://msdn2.microsoft.com/en-us/library/y4h7bcy6(VS.80).aspx. According to the -information there, using __declspec(dllexport) without "extern" we have a -definition; with "extern" we have a declaration. The settings here override the -setting in pcre.h (which is included below); it defines only PCRE_EXP_DECL, -which is all that is needed for applications (they just import the symbols). We -use: - - PCRE_EXP_DECL for declarations - PCRE_EXP_DEFN for definitions of exported functions - PCRE_EXP_DATA_DEFN for definitions of exported variables - -The reason for the two DEFN macros is that in non-Windows environments, one -does not want to have "extern" before variable definitions because it leads to -compiler warnings. So we distinguish between functions and variables. In -Windows, the two should always be the same. - -The reason for wrapping this in #ifndef PCRE_EXP_DECL is so that pcretest, -which is an application, but needs to import this file in order to "peek" at -internals, can #include pcre.h first to get an application's-eye view. - -In principle, people compiling for non-Windows, non-Unix-like (i.e. uncommon, -special-purpose environments) might want to stick other stuff in front of -exported symbols. That's why, in the non-Windows case, we set PCRE_EXP_DEFN and -PCRE_EXP_DATA_DEFN only if they are not already set. */ - -#ifndef PCRE_EXP_DECL -# ifdef _WIN32 -# ifndef PCRE_STATIC -# define PCRE_EXP_DECL extern __declspec(dllexport) -# define PCRE_EXP_DEFN __declspec(dllexport) -# define PCRE_EXP_DATA_DEFN __declspec(dllexport) -# else -# define PCRE_EXP_DECL extern -# define PCRE_EXP_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# else -# ifdef __cplusplus -# define PCRE_EXP_DECL extern "C" -# else -# define PCRE_EXP_DECL extern -# endif -# ifndef PCRE_EXP_DEFN -# define PCRE_EXP_DEFN PCRE_EXP_DECL -# endif -# ifndef PCRE_EXP_DATA_DEFN -# define PCRE_EXP_DATA_DEFN -# endif -# endif -#endif - -/* We need to have types that specify unsigned 16-bit and 32-bit integers. We -cannot determine these outside the compilation (e.g. by running a program as -part of "configure") because PCRE is often cross-compiled for use on other -systems. Instead we make use of the maximum sizes that are available at -preprocessor time in standard C environments. */ - -#if USHRT_MAX == 65535 - typedef unsigned short pcre_uint16; -#elif UINT_MAX == 65535 - typedef unsigned int pcre_uint16; -#else - #error Cannot determine a type for 16-bit unsigned integers -#endif - -#if UINT_MAX == 4294967295 - typedef unsigned int pcre_uint32; -#elif ULONG_MAX == 4294967295 - typedef unsigned long int pcre_uint32; -#else - #error Cannot determine a type for 32-bit unsigned integers -#endif - -/* All character handling must be done as unsigned characters. Otherwise there -are problems with top-bit-set characters and functions such as isspace(). -However, we leave the interface to the outside world as char *, because that -should make things easier for callers. We define a short type for unsigned char -to save lots of typing. I tried "uchar", but it causes problems on Digital -Unix, where it is defined in sys/types, so use "uschar" instead. */ - -typedef unsigned char uschar; - -/* This is an unsigned int value that no character can ever have. UTF-8 -characters only go up to 0x7fffffff (though Unicode doesn't go beyond -0x0010ffff). */ - -#define NOTACHAR 0xffffffff - -/* PCRE is able to support several different kinds of newline (CR, LF, CRLF, -"any" and "anycrlf" at present). The following macros are used to package up -testing for newlines. NLBLOCK, PSSTART, and PSEND are defined in the various -modules to indicate in which datablock the parameters exist, and what the -start/end of string field names are. */ - -#define NLTYPE_FIXED 0 /* Newline is a fixed length string */ -#define NLTYPE_ANY 1 /* Newline is any Unicode line ending */ -#define NLTYPE_ANYCRLF 2 /* Newline is CR, LF, or CRLF */ - -/* This macro checks for a newline at the given position */ - -#define IS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) < NLBLOCK->PSEND && \ - _pcre_is_newline((p), NLBLOCK->nltype, NLBLOCK->PSEND, &(NLBLOCK->nllen),\ - utf8)) \ - : \ - ((p) <= NLBLOCK->PSEND - NLBLOCK->nllen && \ - (p)[0] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[1] == NLBLOCK->nl[1]) \ - ) \ - ) - -/* This macro checks for a newline immediately preceding the given position */ - -#define WAS_NEWLINE(p) \ - ((NLBLOCK->nltype != NLTYPE_FIXED)? \ - ((p) > NLBLOCK->PSSTART && \ - _pcre_was_newline((p), NLBLOCK->nltype, NLBLOCK->PSSTART, \ - &(NLBLOCK->nllen), utf8)) \ - : \ - ((p) >= NLBLOCK->PSSTART + NLBLOCK->nllen && \ - (p)[-NLBLOCK->nllen] == NLBLOCK->nl[0] && \ - (NLBLOCK->nllen == 1 || (p)[-NLBLOCK->nllen+1] == NLBLOCK->nl[1]) \ - ) \ - ) - -/* When PCRE is compiled as a C++ library, the subject pointer can be replaced -with a custom type. This makes it possible, for example, to allow pcre_exec() -to process subject strings that are discontinuous by using a smart pointer -class. It must always be possible to inspect all of the subject string in -pcre_exec() because of the way it backtracks. Two macros are required in the -normal case, for sign-unspecified and unsigned char pointers. The former is -used for the external interface and appears in pcre.h, which is why its name -must begin with PCRE_. */ - -#ifdef CUSTOM_SUBJECT_PTR -#define PCRE_SPTR CUSTOM_SUBJECT_PTR -#define USPTR CUSTOM_SUBJECT_PTR -#else -#define PCRE_SPTR const char * -#define USPTR const unsigned char * -#endif - - - -/* Include the public PCRE header and the definitions of UCP character property -values. */ - -#include "pcre.h" -#include "ucp.h" - -/* When compiling for use with the Virtual Pascal compiler, these functions -need to have their names changed. PCRE must be compiled with the -DVPCOMPAT -option on the command line. */ - -#ifdef VPCOMPAT -#define strlen(s) _strlen(s) -#define strncmp(s1,s2,m) _strncmp(s1,s2,m) -#define memcmp(s,c,n) _memcmp(s,c,n) -#define memcpy(d,s,n) _memcpy(d,s,n) -#define memmove(d,s,n) _memmove(d,s,n) -#define memset(s,c,n) _memset(s,c,n) -#else /* VPCOMPAT */ - -/* To cope with SunOS4 and other systems that lack memmove() but have bcopy(), -define a macro for memmove() if HAVE_MEMMOVE is false, provided that HAVE_BCOPY -is set. Otherwise, include an emulating function for those systems that have -neither (there some non-Unix environments where this is the case). */ - -#ifndef HAVE_MEMMOVE -#undef memmove /* some systems may have a macro */ -#ifdef HAVE_BCOPY -#define memmove(a, b, c) bcopy(b, a, c) -#else /* HAVE_BCOPY */ -static void * -pcre_memmove(void *d, const void *s, size_t n) -{ -size_t i; -unsigned char *dest = (unsigned char *)d; -const unsigned char *src = (const unsigned char *)s; -if (dest > src) - { - dest += n; - src += n; - for (i = 0; i < n; ++i) *(--dest) = *(--src); - return (void *)dest; - } -else - { - for (i = 0; i < n; ++i) *dest++ = *src++; - return (void *)(dest - n); - } -} -#define memmove(a, b, c) pcre_memmove(a, b, c) -#endif /* not HAVE_BCOPY */ -#endif /* not HAVE_MEMMOVE */ -#endif /* not VPCOMPAT */ - - -/* PCRE keeps offsets in its compiled code as 2-byte quantities (always stored -in big-endian order) by default. These are used, for example, to link from the -start of a subpattern to its alternatives and its end. The use of 2 bytes per -offset limits the size of the compiled regex to around 64K, which is big enough -for almost everybody. However, I received a request for an even bigger limit. -For this reason, and also to make the code easier to maintain, the storing and -loading of offsets from the byte string is now handled by the macros that are -defined here. - -The macros are controlled by the value of LINK_SIZE. This defaults to 2 in -the config.h file, but can be overridden by using -D on the command line. This -is automated on Unix systems via the "configure" command. */ - -#if LINK_SIZE == 2 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 8), \ - (a[(n)+1] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define MAX_PATTERN_SIZE (1 << 16) - - -#elif LINK_SIZE == 3 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 16), \ - (a[(n)+1] = (d) >> 8), \ - (a[(n)+2] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 16) | ((a)[(n)+1] << 8) | (a)[(n)+2]) - -#define MAX_PATTERN_SIZE (1 << 24) - - -#elif LINK_SIZE == 4 - -#define PUT(a,n,d) \ - (a[n] = (d) >> 24), \ - (a[(n)+1] = (d) >> 16), \ - (a[(n)+2] = (d) >> 8), \ - (a[(n)+3] = (d) & 255) - -#define GET(a,n) \ - (((a)[n] << 24) | ((a)[(n)+1] << 16) | ((a)[(n)+2] << 8) | (a)[(n)+3]) - -#define MAX_PATTERN_SIZE (1 << 30) /* Keep it positive */ - - -#else -#error LINK_SIZE must be either 2, 3, or 4 -#endif - - -/* Convenience macro defined in terms of the others */ - -#define PUTINC(a,n,d) PUT(a,n,d), a += LINK_SIZE - - -/* PCRE uses some other 2-byte quantities that do not change when the size of -offsets changes. There are used for repeat counts and for other things such as -capturing parenthesis numbers in back references. */ - -#define PUT2(a,n,d) \ - a[n] = (d) >> 8; \ - a[(n)+1] = (d) & 255 - -#define GET2(a,n) \ - (((a)[n] << 8) | (a)[(n)+1]) - -#define PUT2INC(a,n,d) PUT2(a,n,d), a += 2 - - -/* When UTF-8 encoding is being used, a character is no longer just a single -byte. The macros for character handling generate simple sequences when used in -byte-mode, and more complicated ones for UTF-8 characters. BACKCHAR should -never be called in byte mode. To make sure it can never even appear when UTF-8 -support is omitted, we don't even define it. */ - -#ifndef SUPPORT_UTF8 -#define GETCHAR(c, eptr) c = *eptr; -#define GETCHARTEST(c, eptr) c = *eptr; -#define GETCHARINC(c, eptr) c = *eptr++; -#define GETCHARINCTEST(c, eptr) c = *eptr++; -#define GETCHARLEN(c, eptr, len) c = *eptr; -/* #define BACKCHAR(eptr) */ - -#else /* SUPPORT_UTF8 */ - -/* Get the next UTF-8 character, not advancing the pointer. This is called when -we know we are in UTF-8 mode. */ - -#define GETCHAR(c, eptr) \ - c = *eptr; \ - if (c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, testing for UTF-8 mode, and not advancing the -pointer. */ - -#define GETCHARTEST(c, eptr) \ - c = *eptr; \ - if (utf8 && c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, advancing the pointer. This is called when we -know we are in UTF-8 mode. */ - -#define GETCHARINC(c, eptr) \ - c = *eptr++; \ - if (c >= 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* Get the next character, testing for UTF-8 mode, and advancing the pointer */ - -#define GETCHARINCTEST(c, eptr) \ - c = *eptr++; \ - if (utf8 && c >= 0xc0) \ - { \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - while (gcaa-- > 0) \ - { \ - gcss -= 6; \ - c |= (*eptr++ & 0x3f) << gcss; \ - } \ - } - -/* Get the next UTF-8 character, not advancing the pointer, incrementing length -if there are extra bytes. This is called when we know we are in UTF-8 mode. */ - -#define GETCHARLEN(c, eptr, len) \ - c = *eptr; \ - if (c >= 0xc0) \ - { \ - int gcii; \ - int gcaa = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ \ - int gcss = 6*gcaa; \ - c = (c & _pcre_utf8_table3[gcaa]) << gcss; \ - for (gcii = 1; gcii <= gcaa; gcii++) \ - { \ - gcss -= 6; \ - c |= (eptr[gcii] & 0x3f) << gcss; \ - } \ - len += gcaa; \ - } - -/* If the pointer is not at the start of a character, move it back until -it is. This is called only in UTF-8 mode - we don't put a test within the macro -because almost all calls are already within a block of UTF-8 only code. */ - -#define BACKCHAR(eptr) while((*eptr & 0xc0) == 0x80) eptr-- - -#endif - - -/* In case there is no definition of offsetof() provided - though any proper -Standard C system should have one. */ - -#ifndef offsetof -#define offsetof(p_type,field) ((size_t)&(((p_type *)0)->field)) -#endif - - -/* These are the public options that can change during matching. */ - -#define PCRE_IMS (PCRE_CASELESS|PCRE_MULTILINE|PCRE_DOTALL) - -/* Private flags containing information about the compiled regex. They used to -live at the top end of the options word, but that got almost full, so now they -are in a 16-bit flags word. */ - -#define PCRE_NOPARTIAL 0x0001 /* can't use partial with this regex */ -#define PCRE_FIRSTSET 0x0002 /* first_byte is set */ -#define PCRE_REQCHSET 0x0004 /* req_byte is set */ -#define PCRE_STARTLINE 0x0008 /* start after \n for multiline */ -#define PCRE_JCHANGED 0x0010 /* j option used in regex */ -#define PCRE_HASCRORLF 0x0020 /* explicit \r or \n in pattern */ - -/* Options for the "extra" block produced by pcre_study(). */ - -#define PCRE_STUDY_MAPPED 0x01 /* a map of starting chars exists */ - -/* Masks for identifying the public options that are permitted at compile -time, run time, or study time, respectively. */ - -#define PCRE_NEWLINE_BITS (PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_ANY| \ - PCRE_NEWLINE_ANYCRLF) - -#define PUBLIC_OPTIONS \ - (PCRE_CASELESS|PCRE_EXTENDED|PCRE_ANCHORED|PCRE_MULTILINE| \ - PCRE_DOTALL|PCRE_DOLLAR_ENDONLY|PCRE_EXTRA|PCRE_UNGREEDY|PCRE_UTF8| \ - PCRE_NO_AUTO_CAPTURE|PCRE_NO_UTF8_CHECK|PCRE_AUTO_CALLOUT|PCRE_FIRSTLINE| \ - PCRE_DUPNAMES|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) - -#define PUBLIC_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_NEWLINE_BITS|PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) - -#define PUBLIC_DFA_EXEC_OPTIONS \ - (PCRE_ANCHORED|PCRE_NOTBOL|PCRE_NOTEOL|PCRE_NOTEMPTY|PCRE_NO_UTF8_CHECK| \ - PCRE_PARTIAL|PCRE_DFA_SHORTEST|PCRE_DFA_RESTART|PCRE_NEWLINE_BITS| \ - PCRE_BSR_ANYCRLF|PCRE_BSR_UNICODE) - -#define PUBLIC_STUDY_OPTIONS 0 /* None defined */ - -/* Magic number to provide a small check against being handed junk. Also used -to detect whether a pattern was compiled on a host of different endianness. */ - -#define MAGIC_NUMBER 0x50435245UL /* 'PCRE' */ - -/* Negative values for the firstchar and reqchar variables */ - -#define REQ_UNSET (-2) -#define REQ_NONE (-1) - -/* The maximum remaining length of subject we are prepared to search for a -req_byte match. */ - -#define REQ_BYTE_MAX 1000 - -/* Flags added to firstbyte or reqbyte; a "non-literal" item is either a -variable-length repeat, or a anything other than literal characters. */ - -#define REQ_CASELESS 0x0100 /* indicates caselessness */ -#define REQ_VARY 0x0200 /* reqbyte followed non-literal item */ - -/* Miscellaneous definitions */ - -typedef int BOOL; - -#define FALSE 0 -#define TRUE 1 - -/* Escape items that are just an encoding of a particular data value. */ - -#ifndef ESC_e -#define ESC_e 27 -#endif - -#ifndef ESC_f -#define ESC_f '\f' -#endif - -#ifndef ESC_n -#define ESC_n '\n' -#endif - -#ifndef ESC_r -#define ESC_r '\r' -#endif - -/* We can't officially use ESC_t because it is a POSIX reserved identifier -(presumably because of all the others like size_t). */ - -#ifndef ESC_tee -#define ESC_tee '\t' -#endif - -/* Codes for different types of Unicode property */ - -#define PT_ANY 0 /* Any property - matches all chars */ -#define PT_LAMP 1 /* L& - the union of Lu, Ll, Lt */ -#define PT_GC 2 /* General characteristic (e.g. L) */ -#define PT_PC 3 /* Particular characteristic (e.g. Lu) */ -#define PT_SC 4 /* Script (e.g. Han) */ - -/* Flag bits and data types for the extended class (OP_XCLASS) for classes that -contain UTF-8 characters with values greater than 255. */ - -#define XCL_NOT 0x01 /* Flag: this is a negative class */ -#define XCL_MAP 0x02 /* Flag: a 32-byte map is present */ - -#define XCL_END 0 /* Marks end of individual items */ -#define XCL_SINGLE 1 /* Single item (one multibyte char) follows */ -#define XCL_RANGE 2 /* A range (two multibyte chars) follows */ -#define XCL_PROP 3 /* Unicode property (2-byte property code follows) */ -#define XCL_NOTPROP 4 /* Unicode inverted property (ditto) */ - -/* These are escaped items that aren't just an encoding of a particular data -value such as \n. They must have non-zero values, as check_escape() returns -their negation. Also, they must appear in the same order as in the opcode -definitions below, up to ESC_z. There's a dummy for OP_ANY because it -corresponds to "." rather than an escape sequence. The final one must be -ESC_REF as subsequent values are used for backreferences (\1, \2, \3, etc). -There are two tests in the code for an escape greater than ESC_b and less than -ESC_Z to detect the types that may be repeated. These are the types that -consume characters. If any new escapes are put in between that don't consume a -character, that code will have to change. */ - -enum { ESC_A = 1, ESC_G, ESC_K, ESC_B, ESC_b, ESC_D, ESC_d, ESC_S, ESC_s, - ESC_W, ESC_w, ESC_dum1, ESC_C, ESC_P, ESC_p, ESC_R, ESC_H, ESC_h, - ESC_V, ESC_v, ESC_X, ESC_Z, ESC_z, ESC_E, ESC_Q, ESC_k, ESC_REF }; - - -/* Opcode table: Starting from 1 (i.e. after OP_END), the values up to -OP_EOD must correspond in order to the list of escapes immediately above. - -*** NOTE NOTE NOTE *** Whenever this list is updated, the two macro definitions -that follow must also be updated to match. There is also a table called -"coptable" in pcre_dfa_exec.c that must be updated. */ - -enum { - OP_END, /* 0 End of pattern */ - - /* Values corresponding to backslashed metacharacters */ - - OP_SOD, /* 1 Start of data: \A */ - OP_SOM, /* 2 Start of match (subject + offset): \G */ - OP_SET_SOM, /* 3 Set start of match (\K) */ - OP_NOT_WORD_BOUNDARY, /* 4 \B */ - OP_WORD_BOUNDARY, /* 5 \b */ - OP_NOT_DIGIT, /* 6 \D */ - OP_DIGIT, /* 7 \d */ - OP_NOT_WHITESPACE, /* 8 \S */ - OP_WHITESPACE, /* 9 \s */ - OP_NOT_WORDCHAR, /* 10 \W */ - OP_WORDCHAR, /* 11 \w */ - OP_ANY, /* 12 Match any character */ - OP_ANYBYTE, /* 13 Match any byte (\C); different to OP_ANY for UTF-8 */ - OP_NOTPROP, /* 14 \P (not Unicode property) */ - OP_PROP, /* 15 \p (Unicode property) */ - OP_ANYNL, /* 16 \R (any newline sequence) */ - OP_NOT_HSPACE, /* 17 \H (not horizontal whitespace) */ - OP_HSPACE, /* 18 \h (horizontal whitespace) */ - OP_NOT_VSPACE, /* 19 \V (not vertical whitespace) */ - OP_VSPACE, /* 20 \v (vertical whitespace) */ - OP_EXTUNI, /* 21 \X (extended Unicode sequence */ - OP_EODN, /* 22 End of data or \n at end of data: \Z. */ - OP_EOD, /* 23 End of data: \z */ - - OP_OPT, /* 24 Set runtime options */ - OP_CIRC, /* 25 Start of line - varies with multiline switch */ - OP_DOLL, /* 26 End of line - varies with multiline switch */ - OP_CHAR, /* 27 Match one character, casefully */ - OP_CHARNC, /* 28 Match one character, caselessly */ - OP_NOT, /* 29 Match one character, not the following one */ - - OP_STAR, /* 30 The maximizing and minimizing versions of */ - OP_MINSTAR, /* 31 these six opcodes must come in pairs, with */ - OP_PLUS, /* 32 the minimizing one second. */ - OP_MINPLUS, /* 33 This first set applies to single characters.*/ - OP_QUERY, /* 34 */ - OP_MINQUERY, /* 35 */ - - OP_UPTO, /* 36 From 0 to n matches */ - OP_MINUPTO, /* 37 */ - OP_EXACT, /* 38 Exactly n matches */ - - OP_POSSTAR, /* 39 Possessified star */ - OP_POSPLUS, /* 40 Possessified plus */ - OP_POSQUERY, /* 41 Posesssified query */ - OP_POSUPTO, /* 42 Possessified upto */ - - OP_NOTSTAR, /* 43 The maximizing and minimizing versions of */ - OP_NOTMINSTAR, /* 44 these six opcodes must come in pairs, with */ - OP_NOTPLUS, /* 45 the minimizing one second. They must be in */ - OP_NOTMINPLUS, /* 46 exactly the same order as those above. */ - OP_NOTQUERY, /* 47 This set applies to "not" single characters. */ - OP_NOTMINQUERY, /* 48 */ - - OP_NOTUPTO, /* 49 From 0 to n matches */ - OP_NOTMINUPTO, /* 50 */ - OP_NOTEXACT, /* 51 Exactly n matches */ - - OP_NOTPOSSTAR, /* 52 Possessified versions */ - OP_NOTPOSPLUS, /* 53 */ - OP_NOTPOSQUERY, /* 54 */ - OP_NOTPOSUPTO, /* 55 */ - - OP_TYPESTAR, /* 56 The maximizing and minimizing versions of */ - OP_TYPEMINSTAR, /* 57 these six opcodes must come in pairs, with */ - OP_TYPEPLUS, /* 58 the minimizing one second. These codes must */ - OP_TYPEMINPLUS, /* 59 be in exactly the same order as those above. */ - OP_TYPEQUERY, /* 60 This set applies to character types such as \d */ - OP_TYPEMINQUERY, /* 61 */ - - OP_TYPEUPTO, /* 62 From 0 to n matches */ - OP_TYPEMINUPTO, /* 63 */ - OP_TYPEEXACT, /* 64 Exactly n matches */ - - OP_TYPEPOSSTAR, /* 65 Possessified versions */ - OP_TYPEPOSPLUS, /* 66 */ - OP_TYPEPOSQUERY, /* 67 */ - OP_TYPEPOSUPTO, /* 68 */ - - OP_CRSTAR, /* 69 The maximizing and minimizing versions of */ - OP_CRMINSTAR, /* 70 all these opcodes must come in pairs, with */ - OP_CRPLUS, /* 71 the minimizing one second. These codes must */ - OP_CRMINPLUS, /* 72 be in exactly the same order as those above. */ - OP_CRQUERY, /* 73 These are for character classes and back refs */ - OP_CRMINQUERY, /* 74 */ - OP_CRRANGE, /* 75 These are different to the three sets above. */ - OP_CRMINRANGE, /* 76 */ - - OP_CLASS, /* 77 Match a character class, chars < 256 only */ - OP_NCLASS, /* 78 Same, but the bitmap was created from a negative - class - the difference is relevant only when a UTF-8 - character > 255 is encountered. */ - - OP_XCLASS, /* 79 Extended class for handling UTF-8 chars within the - class. This does both positive and negative. */ - - OP_REF, /* 80 Match a back reference */ - OP_RECURSE, /* 81 Match a numbered subpattern (possibly recursive) */ - OP_CALLOUT, /* 82 Call out to external function if provided */ - - OP_ALT, /* 83 Start of alternation */ - OP_KET, /* 84 End of group that doesn't have an unbounded repeat */ - OP_KETRMAX, /* 85 These two must remain together and in this */ - OP_KETRMIN, /* 86 order. They are for groups the repeat for ever. */ - - /* The assertions must come before BRA, CBRA, ONCE, and COND.*/ - - OP_ASSERT, /* 87 Positive lookahead */ - OP_ASSERT_NOT, /* 88 Negative lookahead */ - OP_ASSERTBACK, /* 89 Positive lookbehind */ - OP_ASSERTBACK_NOT, /* 90 Negative lookbehind */ - OP_REVERSE, /* 91 Move pointer back - used in lookbehind assertions */ - - /* ONCE, BRA, CBRA, and COND must come after the assertions, with ONCE first, - as there's a test for >= ONCE for a subpattern that isn't an assertion. */ - - OP_ONCE, /* 92 Atomic group */ - OP_BRA, /* 93 Start of non-capturing bracket */ - OP_CBRA, /* 94 Start of capturing bracket */ - OP_COND, /* 95 Conditional group */ - - /* These three must follow the previous three, in the same order. There's a - check for >= SBRA to distinguish the two sets. */ - - OP_SBRA, /* 96 Start of non-capturing bracket, check empty */ - OP_SCBRA, /* 97 Start of capturing bracket, check empty */ - OP_SCOND, /* 98 Conditional group, check empty */ - - OP_CREF, /* 99 Used to hold a capture number as condition */ - OP_RREF, /* 100 Used to hold a recursion number as condition */ - OP_DEF, /* 101 The DEFINE condition */ - - OP_BRAZERO, /* 102 These two must remain together and in this */ - OP_BRAMINZERO, /* 103 order. */ - - /* These are backtracking control verbs */ - - OP_PRUNE, /* 104 */ - OP_SKIP, /* 105 */ - OP_THEN, /* 106 */ - OP_COMMIT, /* 107 */ - - /* These are forced failure and success verbs */ - - OP_FAIL, /* 108 */ - OP_ACCEPT /* 109 */ -}; - - -/* This macro defines textual names for all the opcodes. These are used only -for debugging. The macro is referenced only in pcre_printint.c. */ - -#define OP_NAME_LIST \ - "End", "\\A", "\\G", "\\K", "\\B", "\\b", "\\D", "\\d", \ - "\\S", "\\s", "\\W", "\\w", "Any", "Anybyte", \ - "notprop", "prop", "\\R", "\\H", "\\h", "\\V", "\\v", \ - "extuni", "\\Z", "\\z", \ - "Opt", "^", "$", "char", "charnc", "not", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", "{", \ - "*+","++", "?+", "{", \ - "*", "*?", "+", "+?", "?", "??", "{", "{", \ - "class", "nclass", "xclass", "Ref", "Recurse", "Callout", \ - "Alt", "Ket", "KetRmax", "KetRmin", "Assert", "Assert not", \ - "AssertB", "AssertB not", "Reverse", \ - "Once", "Bra", "CBra", "Cond", "SBra", "SCBra", "SCond", \ - "Cond ref", "Cond rec", "Cond def", "Brazero", "Braminzero", \ - "*PRUNE", "*SKIP", "*THEN", "*COMMIT", "*FAIL", "*ACCEPT" - - -/* This macro defines the length of fixed length operations in the compiled -regex. The lengths are used when searching for specific things, and also in the -debugging printing of a compiled regex. We use a macro so that it can be -defined close to the definitions of the opcodes themselves. - -As things have been extended, some of these are no longer fixed lenths, but are -minima instead. For example, the length of a single-character repeat may vary -in UTF-8 mode. The code that uses this table must know about such things. */ - -#define OP_LENGTHS \ - 1, /* End */ \ - 1, 1, 1, 1, 1, /* \A, \G, \K, \B, \b */ \ - 1, 1, 1, 1, 1, 1, /* \D, \d, \S, \s, \W, \w */ \ - 1, 1, /* Any, Anybyte */ \ - 3, 3, 1, /* NOTPROP, PROP, EXTUNI */ \ - 1, 1, 1, 1, 1, /* \R, \H, \h, \V, \v */ \ - 1, 1, 2, 1, 1, /* \Z, \z, Opt, ^, $ */ \ - 2, /* Char - the minimum length */ \ - 2, /* Charnc - the minimum length */ \ - 2, /* not */ \ - /* Positive single-char repeats ** These are */ \ - 2, 2, 2, 2, 2, 2, /* *, *?, +, +?, ?, ?? ** minima in */ \ - 4, 4, 4, /* upto, minupto, exact ** UTF-8 mode */ \ - 2, 2, 2, 4, /* *+, ++, ?+, upto+ */ \ - /* Negative single-char repeats - only for chars < 256 */ \ - 2, 2, 2, 2, 2, 2, /* NOT *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* NOT upto, minupto, exact */ \ - 2, 2, 2, 4, /* Possessive *, +, ?, upto */ \ - /* Positive type repeats */ \ - 2, 2, 2, 2, 2, 2, /* Type *, *?, +, +?, ?, ?? */ \ - 4, 4, 4, /* Type upto, minupto, exact */ \ - 2, 2, 2, 4, /* Possessive *+, ++, ?+, upto+ */ \ - /* Character class & ref repeats */ \ - 1, 1, 1, 1, 1, 1, /* *, *?, +, +?, ?, ?? */ \ - 5, 5, /* CRRANGE, CRMINRANGE */ \ - 33, /* CLASS */ \ - 33, /* NCLASS */ \ - 0, /* XCLASS - variable length */ \ - 3, /* REF */ \ - 1+LINK_SIZE, /* RECURSE */ \ - 2+2*LINK_SIZE, /* CALLOUT */ \ - 1+LINK_SIZE, /* Alt */ \ - 1+LINK_SIZE, /* Ket */ \ - 1+LINK_SIZE, /* KetRmax */ \ - 1+LINK_SIZE, /* KetRmin */ \ - 1+LINK_SIZE, /* Assert */ \ - 1+LINK_SIZE, /* Assert not */ \ - 1+LINK_SIZE, /* Assert behind */ \ - 1+LINK_SIZE, /* Assert behind not */ \ - 1+LINK_SIZE, /* Reverse */ \ - 1+LINK_SIZE, /* ONCE */ \ - 1+LINK_SIZE, /* BRA */ \ - 3+LINK_SIZE, /* CBRA */ \ - 1+LINK_SIZE, /* COND */ \ - 1+LINK_SIZE, /* SBRA */ \ - 3+LINK_SIZE, /* SCBRA */ \ - 1+LINK_SIZE, /* SCOND */ \ - 3, /* CREF */ \ - 3, /* RREF */ \ - 1, /* DEF */ \ - 1, 1, /* BRAZERO, BRAMINZERO */ \ - 1, 1, 1, 1, /* PRUNE, SKIP, THEN, COMMIT, */ \ - 1, 1 /* FAIL, ACCEPT */ - - -/* A magic value for OP_RREF to indicate the "any recursion" condition. */ - -#define RREF_ANY 0xffff - -/* Error code numbers. They are given names so that they can more easily be -tracked. */ - -enum { ERR0, ERR1, ERR2, ERR3, ERR4, ERR5, ERR6, ERR7, ERR8, ERR9, - ERR10, ERR11, ERR12, ERR13, ERR14, ERR15, ERR16, ERR17, ERR18, ERR19, - ERR20, ERR21, ERR22, ERR23, ERR24, ERR25, ERR26, ERR27, ERR28, ERR29, - ERR30, ERR31, ERR32, ERR33, ERR34, ERR35, ERR36, ERR37, ERR38, ERR39, - ERR40, ERR41, ERR42, ERR43, ERR44, ERR45, ERR46, ERR47, ERR48, ERR49, - ERR50, ERR51, ERR52, ERR53, ERR54, ERR55, ERR56, ERR57, ERR58, ERR59, - ERR60, ERR61 }; - -/* The real format of the start of the pcre block; the index of names and the -code vector run on as long as necessary after the end. We store an explicit -offset to the name table so that if a regex is compiled on one host, saved, and -then run on another where the size of pointers is different, all might still -be well. For the case of compiled-on-4 and run-on-8, we include an extra -pointer that is always NULL. For future-proofing, a few dummy fields were -originally included - even though you can never get this planning right - but -there is only one left now. - -NOTE NOTE NOTE: -Because people can now save and re-use compiled patterns, any additions to this -structure should be made at the end, and something earlier (e.g. a new -flag in the options or one of the dummy fields) should indicate that the new -fields are present. Currently PCRE always sets the dummy fields to zero. -NOTE NOTE NOTE: -*/ - -typedef struct real_pcre { - pcre_uint32 magic_number; - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; /* Public options */ - pcre_uint16 flags; /* Private flags */ - pcre_uint16 dummy1; /* For future use */ - pcre_uint16 top_bracket; - pcre_uint16 top_backref; - pcre_uint16 first_byte; - pcre_uint16 req_byte; - pcre_uint16 name_table_offset; /* Offset to name table that follows */ - pcre_uint16 name_entry_size; /* Size of any name items */ - pcre_uint16 name_count; /* Number of name items */ - pcre_uint16 ref_count; /* Reference count */ - - const unsigned char *tables; /* Pointer to tables or NULL for std */ - const unsigned char *nullpad; /* NULL padding */ -} real_pcre; - -/* The format of the block used to store data from pcre_study(). The same -remark (see NOTE above) about extending this structure applies. */ - -typedef struct pcre_study_data { - pcre_uint32 size; /* Total that was malloced */ - pcre_uint32 options; - uschar start_bits[32]; -} pcre_study_data; - -/* Structure for passing "static" information around between the functions -doing the compiling, so that they are thread-safe. */ - -typedef struct compile_data { - const uschar *lcc; /* Points to lower casing table */ - const uschar *fcc; /* Points to case-flipping table */ - const uschar *cbits; /* Points to character type table */ - const uschar *ctypes; /* Points to table of type maps */ - const uschar *start_workspace;/* The start of working space */ - const uschar *start_code; /* The start of the compiled code */ - const uschar *start_pattern; /* The start of the pattern */ - const uschar *end_pattern; /* The end of the pattern */ - uschar *hwm; /* High watermark of workspace */ - uschar *name_table; /* The name/number table */ - int names_found; /* Number of entries so far */ - int name_entry_size; /* Size of each entry */ - int bracount; /* Count of capturing parens */ - int top_backref; /* Maximum back reference */ - unsigned int backref_map; /* Bitmap of low back refs */ - int external_options; /* External (initial) options */ - int external_flags; /* External flag bits to be set */ - int req_varyopt; /* "After variable item" flag for reqbyte */ - BOOL had_accept; /* (*ACCEPT) encountered */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed length */ -} compile_data; - -/* Structure for maintaining a chain of pointers to the currently incomplete -branches, for testing for left recursion. */ - -typedef struct branch_chain { - struct branch_chain *outer; - uschar *current; -} branch_chain; - -/* Structure for items in a linked list that represents an explicit recursive -call within the pattern. */ - -typedef struct recursion_info { - struct recursion_info *prevrec; /* Previous recursion record (or NULL) */ - int group_num; /* Number of group that was called */ - const uschar *after_call; /* "Return value": points after the call in the expr */ - USPTR save_start; /* Old value of mstart */ - int *offset_save; /* Pointer to start of saved offsets */ - int saved_max; /* Number of saved offsets */ -} recursion_info; - -/* Structure for building a chain of data for holding the values of the subject -pointer at the start of each subpattern, so as to detect when an empty string -has been matched by a subpattern - to break infinite loops. */ - -typedef struct eptrblock { - struct eptrblock *epb_prev; - USPTR epb_saved_eptr; -} eptrblock; - - -/* Structure for passing "static" information around between the functions -doing traditional NFA matching, so that they are thread-safe. */ - -typedef struct match_data { - unsigned long int match_call_count; /* As it says */ - unsigned long int match_limit; /* As it says */ - unsigned long int match_limit_recursion; /* As it says */ - int *offset_vector; /* Offset vector */ - int offset_end; /* One past the end */ - int offset_max; /* The maximum usable for return data */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed */ - const uschar *lcc; /* Points to lower casing table */ - const uschar *ctypes; /* Points to table of type maps */ - BOOL offset_overflow; /* Set if too many extractions */ - BOOL notbol; /* NOTBOL flag */ - BOOL noteol; /* NOTEOL flag */ - BOOL utf8; /* UTF8 flag */ - BOOL endonly; /* Dollar not before final \n */ - BOOL notempty; /* Empty string match not wanted */ - BOOL partial; /* PARTIAL flag */ - BOOL hitend; /* Hit the end of the subject at some point */ - BOOL bsr_anycrlf; /* \R is just any CRLF, not full Unicode */ - const uschar *start_code; /* For use when recursing */ - USPTR start_subject; /* Start of the subject string */ - USPTR end_subject; /* End of the subject string */ - USPTR start_match_ptr; /* Start of matched string */ - USPTR end_match_ptr; /* Subject position at end match */ - int end_offset_top; /* Highwater mark at end of match */ - int capture_last; /* Most recent capture number */ - int start_offset; /* The start offset value */ - eptrblock *eptrchain; /* Chain of eptrblocks for tail recursions */ - int eptrn; /* Next free eptrblock */ - recursion_info *recursive; /* Linked list of recursion data */ - void *callout_data; /* To pass back to callouts */ -} match_data; - -/* A similar structure is used for the same purpose by the DFA matching -functions. */ - -typedef struct dfa_match_data { - const uschar *start_code; /* Start of the compiled pattern */ - const uschar *start_subject; /* Start of the subject string */ - const uschar *end_subject; /* End of subject string */ - const uschar *tables; /* Character tables */ - int moptions; /* Match options */ - int poptions; /* Pattern options */ - int nltype; /* Newline type */ - int nllen; /* Newline string length */ - uschar nl[4]; /* Newline string when fixed */ - void *callout_data; /* To pass back to callouts */ -} dfa_match_data; - -/* Bit definitions for entries in the pcre_ctypes table. */ - -#define ctype_space 0x01 -#define ctype_letter 0x02 -#define ctype_digit 0x04 -#define ctype_xdigit 0x08 -#define ctype_word 0x10 /* alphameric or '_' */ -#define ctype_meta 0x80 /* regexp meta char or zero (end pattern) */ - -/* Offsets for the bitmap tables in pcre_cbits. Each table contains a set -of bits for a class map. Some classes are built by combining these tables. */ - -#define cbit_space 0 /* [:space:] or \s */ -#define cbit_xdigit 32 /* [:xdigit:] */ -#define cbit_digit 64 /* [:digit:] or \d */ -#define cbit_upper 96 /* [:upper:] */ -#define cbit_lower 128 /* [:lower:] */ -#define cbit_word 160 /* [:word:] or \w */ -#define cbit_graph 192 /* [:graph:] */ -#define cbit_print 224 /* [:print:] */ -#define cbit_punct 256 /* [:punct:] */ -#define cbit_cntrl 288 /* [:cntrl:] */ -#define cbit_length 320 /* Length of the cbits table */ - -/* Offsets of the various tables from the base tables pointer, and -total length. */ - -#define lcc_offset 0 -#define fcc_offset 256 -#define cbits_offset 512 -#define ctypes_offset (cbits_offset + cbit_length) -#define tables_length (ctypes_offset + 256) - -/* Layout of the UCP type table that translates property names into types and -codes. Each entry used to point directly to a name, but to reduce the number of -relocations in shared libraries, it now has an offset into a single string -instead. */ - -typedef struct { - pcre_uint16 name_offset; - pcre_uint16 type; - pcre_uint16 value; -} ucp_type_table; - - -/* Internal shared data tables. These are tables that are used by more than one -of the exported public functions. They have to be "external" in the C sense, -but are not part of the PCRE public API. The data for these tables is in the -pcre_tables.c module. */ - -extern const int _pcre_utf8_table1[]; -extern const int _pcre_utf8_table2[]; -extern const int _pcre_utf8_table3[]; -extern const uschar _pcre_utf8_table4[]; - -extern const int _pcre_utf8_table1_size; - -extern const char _pcre_utt_names[]; -extern const ucp_type_table _pcre_utt[]; -extern const int _pcre_utt_size; - -extern const uschar _pcre_default_tables[]; - -extern const uschar _pcre_OP_lengths[]; - - -/* Internal shared functions. These are functions that are used by more than -one of the exported public functions. They have to be "external" in the C -sense, but are not part of the PCRE public API. */ - -extern BOOL _pcre_is_newline(const uschar *, int, const uschar *, - int *, BOOL); -extern int _pcre_ord2utf8(int, uschar *); -extern real_pcre *_pcre_try_flipped(const real_pcre *, real_pcre *, - const pcre_study_data *, pcre_study_data *); -extern int _pcre_ucp_findprop(const unsigned int, int *, int *); -extern unsigned int _pcre_ucp_othercase(const unsigned int); -extern int _pcre_valid_utf8(const uschar *, int); -extern BOOL _pcre_was_newline(const uschar *, int, const uschar *, - int *, BOOL); -extern BOOL _pcre_xclass(int, const uschar *); - -#endif - -/* End of pcre_internal.h */ diff --git a/src/src/pcre/pcre_maketables.c b/src/src/pcre/pcre_maketables.c deleted file mode 100644 index 563f8745c..000000000 --- a/src/src/pcre/pcre_maketables.c +++ /dev/null @@ -1,145 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_maketables.c,v 1.6 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_maketables(), which builds -character tables for PCRE in the current locale. The file is compiled on its -own as part of the PCRE library. However, it is also included in the -compilation of dftables.c, in which case the macro DFTABLES is defined. */ - - -#ifndef DFTABLES -# ifdef HAVE_CONFIG_H -# include "config.h" -# endif -# include "pcre_internal.h" -#endif - - -/************************************************* -* Create PCRE character tables * -*************************************************/ - -/* This function builds a set of character tables for use by PCRE and returns -a pointer to them. They are build using the ctype functions, and consequently -their contents will depend upon the current locale setting. When compiled as -part of the library, the store is obtained via pcre_malloc(), but when compiled -inside dftables, use malloc(). - -Arguments: none -Returns: pointer to the contiguous block of data -*/ - -const unsigned char * -pcre_maketables(void) -{ -unsigned char *yield, *p; -int i; - -#ifndef DFTABLES -yield = (unsigned char*)(pcre_malloc)(tables_length); -#else -yield = (unsigned char*)malloc(tables_length); -#endif - -if (yield == NULL) return NULL; -p = yield; - -/* First comes the lower casing table */ - -for (i = 0; i < 256; i++) *p++ = tolower(i); - -/* Next the case-flipping table */ - -for (i = 0; i < 256; i++) *p++ = islower(i)? toupper(i) : tolower(i); - -/* Then the character class tables. Don't try to be clever and save effort on -exclusive ones - in some locales things may be different. Note that the table -for "space" includes everything "isspace" gives, including VT in the default -locale. This makes it work for the POSIX class [:space:]. Note also that it is -possible for a character to be alnum or alpha without being lower or upper, -such as "male and female ordinals" (\xAA and \xBA) in the fr_FR locale (at -least under Debian Linux's locales as of 12/2005). So we must test for alnum -specially. */ - -memset(p, 0, cbit_length); -for (i = 0; i < 256; i++) - { - if (isdigit(i)) p[cbit_digit + i/8] |= 1 << (i&7); - if (isupper(i)) p[cbit_upper + i/8] |= 1 << (i&7); - if (islower(i)) p[cbit_lower + i/8] |= 1 << (i&7); - if (isalnum(i)) p[cbit_word + i/8] |= 1 << (i&7); - if (i == '_') p[cbit_word + i/8] |= 1 << (i&7); - if (isspace(i)) p[cbit_space + i/8] |= 1 << (i&7); - if (isxdigit(i))p[cbit_xdigit + i/8] |= 1 << (i&7); - if (isgraph(i)) p[cbit_graph + i/8] |= 1 << (i&7); - if (isprint(i)) p[cbit_print + i/8] |= 1 << (i&7); - if (ispunct(i)) p[cbit_punct + i/8] |= 1 << (i&7); - if (iscntrl(i)) p[cbit_cntrl + i/8] |= 1 << (i&7); - } -p += cbit_length; - -/* Finally, the character type table. In this, we exclude VT from the white -space chars, because Perl doesn't recognize it as such for \s and for comments -within regexes. */ - -for (i = 0; i < 256; i++) - { - int x = 0; - if (i != 0x0b && isspace(i)) x += ctype_space; - if (isalpha(i)) x += ctype_letter; - if (isdigit(i)) x += ctype_digit; - if (isxdigit(i)) x += ctype_xdigit; - if (isalnum(i) || i == '_') x += ctype_word; - - /* Note: strchr includes the terminating zero in the characters it considers. - In this instance, that is ok because we want binary zero to be flagged as a - meta-character, which in this sense is any character that terminates a run - of data characters. */ - - if (strchr("\\*+?{^.$|()[", i) != 0) x += ctype_meta; - *p++ = x; - } - -return yield; -} - -/* End of pcre_maketables.c */ diff --git a/src/src/pcre/pcre_newline.c b/src/src/pcre/pcre_newline.c deleted file mode 100644 index c71dbafba..000000000 --- a/src/src/pcre/pcre_newline.c +++ /dev/null @@ -1,166 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_newline.c,v 1.3 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains internal functions for testing newlines when more than -one kind of newline is to be recognized. When a newline is found, its length is -returned. In principle, we could implement several newline "types", each -referring to a different set of newline characters. At present, PCRE supports -only NLTYPE_FIXED, which gets handled without these functions, NLTYPE_ANYCRLF, -and NLTYPE_ANY. The full list of Unicode newline characters is taken from -http://unicode.org/unicode/reports/tr18/. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - - -/************************************************* -* Check for newline at given position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is less than the end of the -string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - endptr pointer to the end of the string - lenptr where to return the length - utf8 TRUE if in utf8 mode - -Returns: TRUE or FALSE -*/ - -BOOL -_pcre_is_newline(const uschar *ptr, int type, const uschar *endptr, - int *lenptr, BOOL utf8) -{ -int c; -if (utf8) { GETCHAR(c, ptr); } else c = *ptr; - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case 0x000a: *lenptr = 1; return TRUE; /* LF */ - case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; - return TRUE; /* CR */ - default: return FALSE; - } - -/* NLTYPE_ANY */ - -else switch(c) - { - case 0x000a: /* LF */ - case 0x000b: /* VT */ - case 0x000c: *lenptr = 1; return TRUE; /* FF */ - case 0x000d: *lenptr = (ptr < endptr - 1 && ptr[1] == 0x0a)? 2 : 1; - return TRUE; /* CR */ - case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ - default: return FALSE; - } -} - - - -/************************************************* -* Check for newline at previous position * -*************************************************/ - -/* It is guaranteed that the initial value of ptr is greater than the start of -the string that is being processed. - -Arguments: - ptr pointer to possible newline - type the newline type - startptr pointer to the start of the string - lenptr where to return the length - utf8 TRUE if in utf8 mode - -Returns: TRUE or FALSE -*/ - -BOOL -_pcre_was_newline(const uschar *ptr, int type, const uschar *startptr, - int *lenptr, BOOL utf8) -{ -int c; -ptr--; -#ifdef SUPPORT_UTF8 -if (utf8) - { - BACKCHAR(ptr); - GETCHAR(c, ptr); - } -else c = *ptr; -#else /* no UTF-8 support */ -c = *ptr; -#endif /* SUPPORT_UTF8 */ - -if (type == NLTYPE_ANYCRLF) switch(c) - { - case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; - return TRUE; /* LF */ - case 0x000d: *lenptr = 1; return TRUE; /* CR */ - default: return FALSE; - } - -else switch(c) - { - case 0x000a: *lenptr = (ptr > startptr && ptr[-1] == 0x0d)? 2 : 1; - return TRUE; /* LF */ - case 0x000b: /* VT */ - case 0x000c: /* FF */ - case 0x000d: *lenptr = 1; return TRUE; /* CR */ - case 0x0085: *lenptr = utf8? 2 : 1; return TRUE; /* NEL */ - case 0x2028: /* LS */ - case 0x2029: *lenptr = 3; return TRUE; /* PS */ - default: return FALSE; - } -} - -/* End of pcre_newline.c */ diff --git a/src/src/pcre/pcre_printint.src b/src/src/pcre/pcre_printint.src deleted file mode 100644 index b32d3fbd1..000000000 --- a/src/src/pcre/pcre_printint.src +++ /dev/null @@ -1,514 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_printint.src,v 1.4 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains a PCRE private debugging function for printing out the -internal form of a compiled regular expression, along with some supporting -local functions. This source file is used in two places: - -(1) It is #included by pcre_compile.c when it is compiled in debugging mode -(DEBUG defined in pcre_internal.h). It is not included in production compiles. - -(2) It is always #included by pcretest.c, which can be asked to print out a -compiled regex for debugging purposes. */ - - -/* Macro that decides whether a character should be output as a literal or in -hexadecimal. We don't use isprint() because that can vary from system to system -(even without the use of locales) and we want the output always to be the same, -for testing purposes. This macro is used in pcretest as well as in this file. */ - -#define PRINTABLE(c) ((c) >= 32 && (c) < 127) - -/* The table of operator names. */ - -static const char *OP_names[] = { OP_NAME_LIST }; - - - -/************************************************* -* Print single- or multi-byte character * -*************************************************/ - -static int -print_char(FILE *f, uschar *ptr, BOOL utf8) -{ -int c = *ptr; - -#ifndef SUPPORT_UTF8 -utf8 = utf8; /* Avoid compiler warning */ -if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); -return 0; - -#else -if (!utf8 || (c & 0xc0) != 0xc0) - { - if (PRINTABLE(c)) fprintf(f, "%c", c); else fprintf(f, "\\x%02x", c); - return 0; - } -else - { - int i; - int a = _pcre_utf8_table4[c & 0x3f]; /* Number of additional bytes */ - int s = 6*a; - c = (c & _pcre_utf8_table3[a]) << s; - for (i = 1; i <= a; i++) - { - /* This is a check for malformed UTF-8; it should only occur if the sanity - check has been turned off. Rather than swallow random bytes, just stop if - we hit a bad one. Print it with \X instead of \x as an indication. */ - - if ((ptr[i] & 0xc0) != 0x80) - { - fprintf(f, "\\X{%x}", c); - return i - 1; - } - - /* The byte is OK */ - - s -= 6; - c |= (ptr[i] & 0x3f) << s; - } - if (c < 128) fprintf(f, "\\x%02x", c); else fprintf(f, "\\x{%x}", c); - return a; - } -#endif -} - - - -/************************************************* -* Find Unicode property name * -*************************************************/ - -static const char * -get_ucpname(int ptype, int pvalue) -{ -#ifdef SUPPORT_UCP -int i; -for (i = _pcre_utt_size - 1; i >= 0; i--) - { - if (ptype == _pcre_utt[i].type && pvalue == _pcre_utt[i].value) break; - } -return (i >= 0)? _pcre_utt_names + _pcre_utt[i].name_offset : "??"; -#else -/* It gets harder and harder to shut off unwanted compiler warnings. */ -ptype = ptype * pvalue; -return (ptype == pvalue)? "??" : "??"; -#endif -} - - - -/************************************************* -* Print compiled regex * -*************************************************/ - -/* Make this function work for a regex with integers either byte order. -However, we assume that what we are passed is a compiled regex. The -print_lengths flag controls whether offsets and lengths of items are printed. -They can be turned off from pcretest so that automatic tests on bytecode can be -written that do not depend on the value of LINK_SIZE. */ - -static void -pcre_printint(pcre *external_re, FILE *f, BOOL print_lengths) -{ -real_pcre *re = (real_pcre *)external_re; -uschar *codestart, *code; -BOOL utf8; - -unsigned int options = re->options; -int offset = re->name_table_offset; -int count = re->name_count; -int size = re->name_entry_size; - -if (re->magic_number != MAGIC_NUMBER) - { - offset = ((offset << 8) & 0xff00) | ((offset >> 8) & 0xff); - count = ((count << 8) & 0xff00) | ((count >> 8) & 0xff); - size = ((size << 8) & 0xff00) | ((size >> 8) & 0xff); - options = ((options << 24) & 0xff000000) | - ((options << 8) & 0x00ff0000) | - ((options >> 8) & 0x0000ff00) | - ((options >> 24) & 0x000000ff); - } - -code = codestart = (uschar *)re + offset + count * size; -utf8 = (options & PCRE_UTF8) != 0; - -for(;;) - { - uschar *ccode; - int c; - int extra = 0; - - if (print_lengths) - fprintf(f, "%3d ", (int)(code - codestart)); - else - fprintf(f, " "); - - switch(*code) - { - case OP_END: - fprintf(f, " %s\n", OP_names[*code]); - fprintf(f, "------------------------------------------------------------------\n"); - return; - - case OP_OPT: - fprintf(f, " %.2x %s", code[1], OP_names[*code]); - break; - - case OP_CHAR: - fprintf(f, " "); - do - { - code++; - code += 1 + print_char(f, code, utf8); - } - while (*code == OP_CHAR); - fprintf(f, "\n"); - continue; - - case OP_CHARNC: - fprintf(f, " NC "); - do - { - code++; - code += 1 + print_char(f, code, utf8); - } - while (*code == OP_CHARNC); - fprintf(f, "\n"); - continue; - - case OP_CBRA: - case OP_SCBRA: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s %d", OP_names[*code], GET2(code, 1+LINK_SIZE)); - break; - - case OP_BRA: - case OP_SBRA: - case OP_KETRMAX: - case OP_KETRMIN: - case OP_ALT: - case OP_KET: - case OP_ASSERT: - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - case OP_ONCE: - case OP_COND: - case OP_SCOND: - case OP_REVERSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_CREF: - fprintf(f, "%3d %s", GET2(code,1), OP_names[*code]); - break; - - case OP_RREF: - c = GET2(code, 1); - if (c == RREF_ANY) - fprintf(f, " Cond recurse any"); - else - fprintf(f, " Cond recurse %d", c); - break; - - case OP_DEF: - fprintf(f, " Cond def"); - break; - - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - case OP_TYPEPOSPLUS: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - fprintf(f, " "); - if (*code >= OP_TYPESTAR) - { - fprintf(f, "%s", OP_names[code[1]]); - if (code[1] == OP_PROP || code[1] == OP_NOTPROP) - { - fprintf(f, " %s ", get_ucpname(code[2], code[3])); - extra = 2; - } - } - else extra = print_char(f, code+1, utf8); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_EXACT: - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - fprintf(f, " "); - extra = print_char(f, code+3, utf8); - fprintf(f, "{"); - if (*code != OP_EXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_MINUPTO) fprintf(f, "?"); - else if (*code == OP_POSUPTO) fprintf(f, "+"); - break; - - case OP_TYPEEXACT: - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - fprintf(f, " %s", OP_names[code[3]]); - if (code[3] == OP_PROP || code[3] == OP_NOTPROP) - { - fprintf(f, " %s ", get_ucpname(code[4], code[5])); - extra = 2; - } - fprintf(f, "{"); - if (*code != OP_TYPEEXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_TYPEMINUPTO) fprintf(f, "?"); - else if (*code == OP_TYPEPOSUPTO) fprintf(f, "+"); - break; - - case OP_NOT: - c = code[1]; - if (PRINTABLE(c)) fprintf(f, " [^%c]", c); - else fprintf(f, " [^\\x%02x]", c); - break; - - case OP_NOTSTAR: - case OP_NOTMINSTAR: - case OP_NOTPOSSTAR: - case OP_NOTPLUS: - case OP_NOTMINPLUS: - case OP_NOTPOSPLUS: - case OP_NOTQUERY: - case OP_NOTMINQUERY: - case OP_NOTPOSQUERY: - c = code[1]; - if (PRINTABLE(c)) fprintf(f, " [^%c]", c); - else fprintf(f, " [^\\x%02x]", c); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_NOTEXACT: - case OP_NOTUPTO: - case OP_NOTMINUPTO: - case OP_NOTPOSUPTO: - c = code[3]; - if (PRINTABLE(c)) fprintf(f, " [^%c]{", c); - else fprintf(f, " [^\\x%02x]{", c); - if (*code != OP_NOTEXACT) fprintf(f, "0,"); - fprintf(f, "%d}", GET2(code,1)); - if (*code == OP_NOTMINUPTO) fprintf(f, "?"); - else if (*code == OP_NOTPOSUPTO) fprintf(f, "+"); - break; - - case OP_RECURSE: - if (print_lengths) fprintf(f, "%3d ", GET(code, 1)); - else fprintf(f, " "); - fprintf(f, "%s", OP_names[*code]); - break; - - case OP_REF: - fprintf(f, " \\%d", GET2(code,1)); - ccode = code + _pcre_OP_lengths[*code]; - goto CLASS_REF_REPEAT; - - case OP_CALLOUT: - fprintf(f, " %s %d %d %d", OP_names[*code], code[1], GET(code,2), - GET(code, 2 + LINK_SIZE)); - break; - - case OP_PROP: - case OP_NOTPROP: - fprintf(f, " %s %s", OP_names[*code], get_ucpname(code[1], code[2])); - break; - - /* OP_XCLASS can only occur in UTF-8 mode. However, there's no harm in - having this code always here, and it makes it less messy without all those - #ifdefs. */ - - case OP_CLASS: - case OP_NCLASS: - case OP_XCLASS: - { - int i, min, max; - BOOL printmap; - - fprintf(f, " ["); - - if (*code == OP_XCLASS) - { - extra = GET(code, 1); - ccode = code + LINK_SIZE + 1; - printmap = (*ccode & XCL_MAP) != 0; - if ((*ccode++ & XCL_NOT) != 0) fprintf(f, "^"); - } - else - { - printmap = TRUE; - ccode = code + 1; - } - - /* Print a bit map */ - - if (printmap) - { - for (i = 0; i < 256; i++) - { - if ((ccode[i/8] & (1 << (i&7))) != 0) - { - int j; - for (j = i+1; j < 256; j++) - if ((ccode[j/8] & (1 << (j&7))) == 0) break; - if (i == '-' || i == ']') fprintf(f, "\\"); - if (PRINTABLE(i)) fprintf(f, "%c", i); - else fprintf(f, "\\x%02x", i); - if (--j > i) - { - if (j != i + 1) fprintf(f, "-"); - if (j == '-' || j == ']') fprintf(f, "\\"); - if (PRINTABLE(j)) fprintf(f, "%c", j); - else fprintf(f, "\\x%02x", j); - } - i = j; - } - } - ccode += 32; - } - - /* For an XCLASS there is always some additional data */ - - if (*code == OP_XCLASS) - { - int ch; - while ((ch = *ccode++) != XCL_END) - { - if (ch == XCL_PROP) - { - int ptype = *ccode++; - int pvalue = *ccode++; - fprintf(f, "\\p{%s}", get_ucpname(ptype, pvalue)); - } - else if (ch == XCL_NOTPROP) - { - int ptype = *ccode++; - int pvalue = *ccode++; - fprintf(f, "\\P{%s}", get_ucpname(ptype, pvalue)); - } - else - { - ccode += 1 + print_char(f, ccode, TRUE); - if (ch == XCL_RANGE) - { - fprintf(f, "-"); - ccode += 1 + print_char(f, ccode, TRUE); - } - } - } - } - - /* Indicate a non-UTF8 class which was created by negation */ - - fprintf(f, "]%s", (*code == OP_NCLASS)? " (neg)" : ""); - - /* Handle repeats after a class or a back reference */ - - CLASS_REF_REPEAT: - switch(*ccode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRPLUS: - case OP_CRMINPLUS: - case OP_CRQUERY: - case OP_CRMINQUERY: - fprintf(f, "%s", OP_names[*ccode]); - extra += _pcre_OP_lengths[*ccode]; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - min = GET2(ccode,1); - max = GET2(ccode,3); - if (max == 0) fprintf(f, "{%d,}", min); - else fprintf(f, "{%d,%d}", min, max); - if (*ccode == OP_CRMINRANGE) fprintf(f, "?"); - extra += _pcre_OP_lengths[*ccode]; - break; - - /* Do nothing if it's not a repeat; this code stops picky compilers - warning about the lack of a default code path. */ - - default: - break; - } - } - break; - - /* Anything else is just an item with no data*/ - - default: - fprintf(f, " %s", OP_names[*code]); - break; - } - - code += _pcre_OP_lengths[*code] + extra; - fprintf(f, "\n"); - } -} - -/* End of pcre_printint.src */ diff --git a/src/src/pcre/pcre_study.c b/src/src/pcre/pcre_study.c deleted file mode 100644 index 6848a1967..000000000 --- a/src/src/pcre/pcre_study.c +++ /dev/null @@ -1,581 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_study.c,v 1.6 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_study(), along with local -supporting functions. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/* Returns from set_start_bits() */ - -enum { SSB_FAIL, SSB_DONE, SSB_CONTINUE }; - - -/************************************************* -* Set a bit and maybe its alternate case * -*************************************************/ - -/* Given a character, set its bit in the table, and also the bit for the other -version of a letter if we are caseless. - -Arguments: - start_bits points to the bit map - c is the character - caseless the caseless flag - cd the block with char table pointers - -Returns: nothing -*/ - -static void -set_bit(uschar *start_bits, unsigned int c, BOOL caseless, compile_data *cd) -{ -start_bits[c/8] |= (1 << (c&7)); -if (caseless && (cd->ctypes[c] & ctype_letter) != 0) - start_bits[cd->fcc[c]/8] |= (1 << (cd->fcc[c]&7)); -} - - - -/************************************************* -* Create bitmap of starting bytes * -*************************************************/ - -/* This function scans a compiled unanchored expression recursively and -attempts to build a bitmap of the set of possible starting bytes. As time goes -by, we may be able to get more clever at doing this. The SSB_CONTINUE return is -useful for parenthesized groups in patterns such as (a*)b where the group -provides some optional starting bytes but scanning must continue at the outer -level to find at least one mandatory byte. At the outermost level, this -function fails unless the result is SSB_DONE. - -Arguments: - code points to an expression - start_bits points to a 32-byte table, initialized to 0 - caseless the current state of the caseless flag - utf8 TRUE if in UTF-8 mode - cd the block with char table pointers - -Returns: SSB_FAIL => Failed to find any starting bytes - SSB_DONE => Found mandatory starting bytes - SSB_CONTINUE => Found optional starting bytes -*/ - -static int -set_start_bits(const uschar *code, uschar *start_bits, BOOL caseless, - BOOL utf8, compile_data *cd) -{ -register int c; -int yield = SSB_DONE; - -#if 0 -/* ========================================================================= */ -/* The following comment and code was inserted in January 1999. In May 2006, -when it was observed to cause compiler warnings about unused values, I took it -out again. If anybody is still using OS/2, they will have to put it back -manually. */ - -/* This next statement and the later reference to dummy are here in order to -trick the optimizer of the IBM C compiler for OS/2 into generating correct -code. Apparently IBM isn't going to fix the problem, and we would rather not -disable optimization (in this module it actually makes a big difference, and -the pcre module can use all the optimization it can get). */ - -volatile int dummy; -/* ========================================================================= */ -#endif - -do - { - const uschar *tcode = code + (((int)*code == OP_CBRA)? 3:1) + LINK_SIZE; - BOOL try_next = TRUE; - - while (try_next) /* Loop for items in this branch */ - { - int rc; - switch(*tcode) - { - /* Fail if we reach something we don't understand */ - - default: - return SSB_FAIL; - - /* If we hit a bracket or a positive lookahead assertion, recurse to set - bits from within the subpattern. If it can't find anything, we have to - give up. If it finds some mandatory character(s), we are done for this - branch. Otherwise, carry on scanning after the subpattern. */ - - case OP_BRA: - case OP_SBRA: - case OP_CBRA: - case OP_SCBRA: - case OP_ONCE: - case OP_ASSERT: - rc = set_start_bits(tcode, start_bits, caseless, utf8, cd); - if (rc == SSB_FAIL) return SSB_FAIL; - if (rc == SSB_DONE) try_next = FALSE; else - { - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - } - break; - - /* If we hit ALT or KET, it means we haven't found anything mandatory in - this branch, though we might have found something optional. For ALT, we - continue with the next alternative, but we have to arrange that the final - result from subpattern is SSB_CONTINUE rather than SSB_DONE. For KET, - return SSB_CONTINUE: if this is the top level, that indicates failure, - but after a nested subpattern, it causes scanning to continue. */ - - case OP_ALT: - yield = SSB_CONTINUE; - try_next = FALSE; - break; - - case OP_KET: - case OP_KETRMAX: - case OP_KETRMIN: - return SSB_CONTINUE; - - /* Skip over callout */ - - case OP_CALLOUT: - tcode += 2 + 2*LINK_SIZE; - break; - - /* Skip over lookbehind and negative lookahead assertions */ - - case OP_ASSERT_NOT: - case OP_ASSERTBACK: - case OP_ASSERTBACK_NOT: - do tcode += GET(tcode, 1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* Skip over an option setting, changing the caseless flag */ - - case OP_OPT: - caseless = (tcode[1] & PCRE_CASELESS) != 0; - tcode += 2; - break; - - /* BRAZERO does the bracket, but carries on. */ - - case OP_BRAZERO: - case OP_BRAMINZERO: - if (set_start_bits(++tcode, start_bits, caseless, utf8, cd) == SSB_FAIL) - return SSB_FAIL; -/* ========================================================================= - See the comment at the head of this function concerning the next line, - which was an old fudge for the benefit of OS/2. - dummy = 1; - ========================================================================= */ - do tcode += GET(tcode,1); while (*tcode == OP_ALT); - tcode += 1 + LINK_SIZE; - break; - - /* Single-char * or ? sets the bit and tries the next item */ - - case OP_STAR: - case OP_MINSTAR: - case OP_POSSTAR: - case OP_QUERY: - case OP_MINQUERY: - case OP_POSQUERY: - set_bit(start_bits, tcode[1], caseless, cd); - tcode += 2; -#ifdef SUPPORT_UTF8 - if (utf8 && tcode[-1] >= 0xc0) - tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; -#endif - break; - - /* Single-char upto sets the bit and tries the next */ - - case OP_UPTO: - case OP_MINUPTO: - case OP_POSUPTO: - set_bit(start_bits, tcode[3], caseless, cd); - tcode += 4; -#ifdef SUPPORT_UTF8 - if (utf8 && tcode[-1] >= 0xc0) - tcode += _pcre_utf8_table4[tcode[-1] & 0x3f]; -#endif - break; - - /* At least one single char sets the bit and stops */ - - case OP_EXACT: /* Fall through */ - tcode += 2; - - case OP_CHAR: - case OP_CHARNC: - case OP_PLUS: - case OP_MINPLUS: - case OP_POSPLUS: - set_bit(start_bits, tcode[1], caseless, cd); - try_next = FALSE; - break; - - /* Single character type sets the bits and stops */ - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - try_next = FALSE; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - try_next = FALSE; - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - try_next = FALSE; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - try_next = FALSE; - break; - - /* One or more character type fudges the pointer and restarts, knowing - it will hit a single character type and stop there. */ - - case OP_TYPEPLUS: - case OP_TYPEMINPLUS: - tcode++; - break; - - case OP_TYPEEXACT: - tcode += 3; - break; - - /* Zero or more repeats of character types set the bits and then - try again. */ - - case OP_TYPEUPTO: - case OP_TYPEMINUPTO: - case OP_TYPEPOSUPTO: - tcode += 2; /* Fall through */ - - case OP_TYPESTAR: - case OP_TYPEMINSTAR: - case OP_TYPEPOSSTAR: - case OP_TYPEQUERY: - case OP_TYPEMINQUERY: - case OP_TYPEPOSQUERY: - switch(tcode[1]) - { - case OP_ANY: - return SSB_FAIL; - - case OP_NOT_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_digit]; - break; - - case OP_DIGIT: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_digit]; - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_NOT_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= ~d; - } - break; - - /* The cbit_space table has vertical tab as whitespace; we have to - discard it. */ - - case OP_WHITESPACE: - for (c = 0; c < 32; c++) - { - int d = cd->cbits[c+cbit_space]; - if (c == 1) d &= ~0x08; - start_bits[c] |= d; - } - break; - - case OP_NOT_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= ~cd->cbits[c+cbit_word]; - break; - - case OP_WORDCHAR: - for (c = 0; c < 32; c++) - start_bits[c] |= cd->cbits[c+cbit_word]; - break; - } - - tcode += 2; - break; - - /* Character class where all the information is in a bit map: set the - bits and either carry on or not, according to the repeat count. If it was - a negative class, and we are operating with UTF-8 characters, any byte - with a value >= 0xc4 is a potentially valid starter because it starts a - character with a value > 255. */ - - case OP_NCLASS: -#ifdef SUPPORT_UTF8 - if (utf8) - { - start_bits[24] |= 0xf0; /* Bits for 0xc4 - 0xc8 */ - memset(start_bits+25, 0xff, 7); /* Bits for 0xc9 - 0xff */ - } -#endif - /* Fall through */ - - case OP_CLASS: - { - tcode++; - - /* In UTF-8 mode, the bits in a bit map correspond to character - values, not to byte values. However, the bit map we are constructing is - for byte values. So we have to do a conversion for characters whose - value is > 127. In fact, there are only two possible starting bytes for - characters in the range 128 - 255. */ - -#ifdef SUPPORT_UTF8 - if (utf8) - { - for (c = 0; c < 16; c++) start_bits[c] |= tcode[c]; - for (c = 128; c < 256; c++) - { - if ((tcode[c/8] && (1 << (c&7))) != 0) - { - int d = (c >> 6) | 0xc0; /* Set bit for this starter */ - start_bits[d/8] |= (1 << (d&7)); /* and then skip on to the */ - c = (c & 0xc0) + 0x40 - 1; /* next relevant character. */ - } - } - } - - /* In non-UTF-8 mode, the two bit maps are completely compatible. */ - - else -#endif - { - for (c = 0; c < 32; c++) start_bits[c] |= tcode[c]; - } - - /* Advance past the bit map, and act on what follows */ - - tcode += 32; - switch (*tcode) - { - case OP_CRSTAR: - case OP_CRMINSTAR: - case OP_CRQUERY: - case OP_CRMINQUERY: - tcode++; - break; - - case OP_CRRANGE: - case OP_CRMINRANGE: - if (((tcode[1] << 8) + tcode[2]) == 0) tcode += 5; - else try_next = FALSE; - break; - - default: - try_next = FALSE; - break; - } - } - break; /* End of bitmap class handling */ - - } /* End of switch */ - } /* End of try_next loop */ - - code += GET(code, 1); /* Advance to next branch */ - } -while (*code == OP_ALT); -return yield; -} - - - -/************************************************* -* Study a compiled expression * -*************************************************/ - -/* This function is handed a compiled expression that it must study to produce -information that will speed up the matching. It returns a pcre_extra block -which then gets handed back to pcre_exec(). - -Arguments: - re points to the compiled expression - options contains option bits - errorptr points to where to place error messages; - set NULL unless error - -Returns: pointer to a pcre_extra block, with study_data filled in and the - appropriate flag set; - NULL on error or if no optimization possible -*/ - -PCRE_EXP_DEFN pcre_extra * -pcre_study(const pcre *external_re, int options, const char **errorptr) -{ -uschar start_bits[32]; -pcre_extra *extra; -pcre_study_data *study; -const uschar *tables; -uschar *code; -compile_data compile_block; -const real_pcre *re = (const real_pcre *)external_re; - -*errorptr = NULL; - -if (re == NULL || re->magic_number != MAGIC_NUMBER) - { - *errorptr = "argument is not a compiled regular expression"; - return NULL; - } - -if ((options & ~PUBLIC_STUDY_OPTIONS) != 0) - { - *errorptr = "unknown or incorrect option bit(s) set"; - return NULL; - } - -code = (uschar *)re + re->name_table_offset + - (re->name_count * re->name_entry_size); - -/* For an anchored pattern, or an unanchored pattern that has a first char, or -a multiline pattern that matches only at "line starts", no further processing -at present. */ - -if ((re->options & PCRE_ANCHORED) != 0 || - (re->flags & (PCRE_FIRSTSET|PCRE_STARTLINE)) != 0) - return NULL; - -/* Set the character tables in the block that is passed around */ - -tables = re->tables; -if (tables == NULL) - (void)pcre_fullinfo(external_re, NULL, PCRE_INFO_DEFAULT_TABLES, - (void *)(&tables)); - -compile_block.lcc = tables + lcc_offset; -compile_block.fcc = tables + fcc_offset; -compile_block.cbits = tables + cbits_offset; -compile_block.ctypes = tables + ctypes_offset; - -/* See if we can find a fixed set of initial characters for the pattern. */ - -memset(start_bits, 0, 32 * sizeof(uschar)); -if (set_start_bits(code, start_bits, (re->options & PCRE_CASELESS) != 0, - (re->options & PCRE_UTF8) != 0, &compile_block) != SSB_DONE) return NULL; - -/* Get a pcre_extra block and a pcre_study_data block. The study data is put in -the latter, which is pointed to by the former, which may also get additional -data set later by the calling program. At the moment, the size of -pcre_study_data is fixed. We nevertheless save it in a field for returning via -the pcre_fullinfo() function so that if it becomes variable in the future, we -don't have to change that code. */ - -extra = (pcre_extra *)(pcre_malloc) - (sizeof(pcre_extra) + sizeof(pcre_study_data)); - -if (extra == NULL) - { - *errorptr = "failed to get memory"; - return NULL; - } - -study = (pcre_study_data *)((char *)extra + sizeof(pcre_extra)); -extra->flags = PCRE_EXTRA_STUDY_DATA; -extra->study_data = study; - -study->size = sizeof(pcre_study_data); -study->options = PCRE_STUDY_MAPPED; -memcpy(study->start_bits, start_bits, sizeof(start_bits)); - -return extra; -} - -/* End of pcre_study.c */ diff --git a/src/src/pcre/pcre_tables.c b/src/src/pcre/pcre_tables.c deleted file mode 100644 index 530e44038..000000000 --- a/src/src/pcre/pcre_tables.c +++ /dev/null @@ -1,320 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_tables.c,v 1.6 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains some fixed tables that are used by more than one of the -PCRE code modules. The tables are also #included by the pcretest program, which -uses macros to change their names from _pcre_xxx to xxxx, thereby avoiding name -clashes with the library. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/* Table of sizes for the fixed-length opcodes. It's defined in a macro so that -the definition is next to the definition of the opcodes in pcre_internal.h. */ - -const uschar _pcre_OP_lengths[] = { OP_LENGTHS }; - - - -/************************************************* -* Tables for UTF-8 support * -*************************************************/ - -/* These are the breakpoints for different numbers of bytes in a UTF-8 -character. */ - -#ifdef SUPPORT_UTF8 - -const int _pcre_utf8_table1[] = - { 0x7f, 0x7ff, 0xffff, 0x1fffff, 0x3ffffff, 0x7fffffff}; - -const int _pcre_utf8_table1_size = sizeof(_pcre_utf8_table1)/sizeof(int); - -/* These are the indicator bits and the mask for the data bits to set in the -first byte of a character, indexed by the number of additional bytes. */ - -const int _pcre_utf8_table2[] = { 0, 0xc0, 0xe0, 0xf0, 0xf8, 0xfc}; -const int _pcre_utf8_table3[] = { 0xff, 0x1f, 0x0f, 0x07, 0x03, 0x01}; - -/* Table of the number of extra bytes, indexed by the first byte masked with -0x3f. The highest number for a valid UTF-8 first byte is in fact 0x3d. */ - -const uschar _pcre_utf8_table4[] = { - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, - 2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, - 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5 }; - -/* The pcre_utt[] table below translates Unicode property names into type and -code values. It is searched by binary chop, so must be in collating sequence of -name. Originally, the table contained pointers to the name strings in the first -field of each entry. However, that leads to a large number of relocations when -a shared library is dynamically loaded. A significant reduction is made by -putting all the names into a single, large string and then using offsets in the -table itself. Maintenance is more error-prone, but frequent changes to this -data is unlikely. */ - -const char _pcre_utt_names[] = - "Any\0" - "Arabic\0" - "Armenian\0" - "Balinese\0" - "Bengali\0" - "Bopomofo\0" - "Braille\0" - "Buginese\0" - "Buhid\0" - "C\0" - "Canadian_Aboriginal\0" - "Cc\0" - "Cf\0" - "Cherokee\0" - "Cn\0" - "Co\0" - "Common\0" - "Coptic\0" - "Cs\0" - "Cuneiform\0" - "Cypriot\0" - "Cyrillic\0" - "Deseret\0" - "Devanagari\0" - "Ethiopic\0" - "Georgian\0" - "Glagolitic\0" - "Gothic\0" - "Greek\0" - "Gujarati\0" - "Gurmukhi\0" - "Han\0" - "Hangul\0" - "Hanunoo\0" - "Hebrew\0" - "Hiragana\0" - "Inherited\0" - "Kannada\0" - "Katakana\0" - "Kharoshthi\0" - "Khmer\0" - "L\0" - "L&\0" - "Lao\0" - "Latin\0" - "Limbu\0" - "Linear_B\0" - "Ll\0" - "Lm\0" - "Lo\0" - "Lt\0" - "Lu\0" - "M\0" - "Malayalam\0" - "Mc\0" - "Me\0" - "Mn\0" - "Mongolian\0" - "Myanmar\0" - "N\0" - "Nd\0" - "New_Tai_Lue\0" - "Nko\0" - "Nl\0" - "No\0" - "Ogham\0" - "Old_Italic\0" - "Old_Persian\0" - "Oriya\0" - "Osmanya\0" - "P\0" - "Pc\0" - "Pd\0" - "Pe\0" - "Pf\0" - "Phags_Pa\0" - "Phoenician\0" - "Pi\0" - "Po\0" - "Ps\0" - "Runic\0" - "S\0" - "Sc\0" - "Shavian\0" - "Sinhala\0" - "Sk\0" - "Sm\0" - "So\0" - "Syloti_Nagri\0" - "Syriac\0" - "Tagalog\0" - "Tagbanwa\0" - "Tai_Le\0" - "Tamil\0" - "Telugu\0" - "Thaana\0" - "Thai\0" - "Tibetan\0" - "Tifinagh\0" - "Ugaritic\0" - "Yi\0" - "Z\0" - "Zl\0" - "Zp\0" - "Zs\0"; - -const ucp_type_table _pcre_utt[] = { - { 0, PT_ANY, 0 }, - { 4, PT_SC, ucp_Arabic }, - { 11, PT_SC, ucp_Armenian }, - { 20, PT_SC, ucp_Balinese }, - { 29, PT_SC, ucp_Bengali }, - { 37, PT_SC, ucp_Bopomofo }, - { 46, PT_SC, ucp_Braille }, - { 54, PT_SC, ucp_Buginese }, - { 63, PT_SC, ucp_Buhid }, - { 69, PT_GC, ucp_C }, - { 71, PT_SC, ucp_Canadian_Aboriginal }, - { 91, PT_PC, ucp_Cc }, - { 94, PT_PC, ucp_Cf }, - { 97, PT_SC, ucp_Cherokee }, - { 106, PT_PC, ucp_Cn }, - { 109, PT_PC, ucp_Co }, - { 112, PT_SC, ucp_Common }, - { 119, PT_SC, ucp_Coptic }, - { 126, PT_PC, ucp_Cs }, - { 129, PT_SC, ucp_Cuneiform }, - { 139, PT_SC, ucp_Cypriot }, - { 147, PT_SC, ucp_Cyrillic }, - { 156, PT_SC, ucp_Deseret }, - { 164, PT_SC, ucp_Devanagari }, - { 175, PT_SC, ucp_Ethiopic }, - { 184, PT_SC, ucp_Georgian }, - { 193, PT_SC, ucp_Glagolitic }, - { 204, PT_SC, ucp_Gothic }, - { 211, PT_SC, ucp_Greek }, - { 217, PT_SC, ucp_Gujarati }, - { 226, PT_SC, ucp_Gurmukhi }, - { 235, PT_SC, ucp_Han }, - { 239, PT_SC, ucp_Hangul }, - { 246, PT_SC, ucp_Hanunoo }, - { 254, PT_SC, ucp_Hebrew }, - { 261, PT_SC, ucp_Hiragana }, - { 270, PT_SC, ucp_Inherited }, - { 280, PT_SC, ucp_Kannada }, - { 288, PT_SC, ucp_Katakana }, - { 297, PT_SC, ucp_Kharoshthi }, - { 308, PT_SC, ucp_Khmer }, - { 314, PT_GC, ucp_L }, - { 316, PT_LAMP, 0 }, - { 319, PT_SC, ucp_Lao }, - { 323, PT_SC, ucp_Latin }, - { 329, PT_SC, ucp_Limbu }, - { 335, PT_SC, ucp_Linear_B }, - { 344, PT_PC, ucp_Ll }, - { 347, PT_PC, ucp_Lm }, - { 350, PT_PC, ucp_Lo }, - { 353, PT_PC, ucp_Lt }, - { 356, PT_PC, ucp_Lu }, - { 359, PT_GC, ucp_M }, - { 361, PT_SC, ucp_Malayalam }, - { 371, PT_PC, ucp_Mc }, - { 374, PT_PC, ucp_Me }, - { 377, PT_PC, ucp_Mn }, - { 380, PT_SC, ucp_Mongolian }, - { 390, PT_SC, ucp_Myanmar }, - { 398, PT_GC, ucp_N }, - { 400, PT_PC, ucp_Nd }, - { 403, PT_SC, ucp_New_Tai_Lue }, - { 415, PT_SC, ucp_Nko }, - { 419, PT_PC, ucp_Nl }, - { 422, PT_PC, ucp_No }, - { 425, PT_SC, ucp_Ogham }, - { 431, PT_SC, ucp_Old_Italic }, - { 442, PT_SC, ucp_Old_Persian }, - { 454, PT_SC, ucp_Oriya }, - { 460, PT_SC, ucp_Osmanya }, - { 468, PT_GC, ucp_P }, - { 470, PT_PC, ucp_Pc }, - { 473, PT_PC, ucp_Pd }, - { 476, PT_PC, ucp_Pe }, - { 479, PT_PC, ucp_Pf }, - { 482, PT_SC, ucp_Phags_Pa }, - { 491, PT_SC, ucp_Phoenician }, - { 502, PT_PC, ucp_Pi }, - { 505, PT_PC, ucp_Po }, - { 508, PT_PC, ucp_Ps }, - { 511, PT_SC, ucp_Runic }, - { 517, PT_GC, ucp_S }, - { 519, PT_PC, ucp_Sc }, - { 522, PT_SC, ucp_Shavian }, - { 530, PT_SC, ucp_Sinhala }, - { 538, PT_PC, ucp_Sk }, - { 541, PT_PC, ucp_Sm }, - { 544, PT_PC, ucp_So }, - { 547, PT_SC, ucp_Syloti_Nagri }, - { 560, PT_SC, ucp_Syriac }, - { 567, PT_SC, ucp_Tagalog }, - { 575, PT_SC, ucp_Tagbanwa }, - { 584, PT_SC, ucp_Tai_Le }, - { 591, PT_SC, ucp_Tamil }, - { 597, PT_SC, ucp_Telugu }, - { 604, PT_SC, ucp_Thaana }, - { 611, PT_SC, ucp_Thai }, - { 616, PT_SC, ucp_Tibetan }, - { 624, PT_SC, ucp_Tifinagh }, - { 633, PT_SC, ucp_Ugaritic }, - { 642, PT_SC, ucp_Yi }, - { 645, PT_GC, ucp_Z }, - { 647, PT_PC, ucp_Zl }, - { 650, PT_PC, ucp_Zp }, - { 653, PT_PC, ucp_Zs } -}; - -const int _pcre_utt_size = sizeof(_pcre_utt)/sizeof(ucp_type_table); - -#endif /* SUPPORT_UTF8 */ - -/* End of pcre_tables.c */ diff --git a/src/src/pcre/pcre_try_flipped.c b/src/src/pcre/pcre_try_flipped.c deleted file mode 100644 index ba97ccb7a..000000000 --- a/src/src/pcre/pcre_try_flipped.c +++ /dev/null @@ -1,139 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_try_flipped.c,v 1.6 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains an internal function that tests a compiled pattern to -see if it was compiled with the opposite endianness. If so, it uses an -auxiliary local function to flip the appropriate bytes. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Flip bytes in an integer * -*************************************************/ - -/* This function is called when the magic number in a regex doesn't match, in -order to flip its bytes to see if we are dealing with a pattern that was -compiled on a host of different endianness. If so, this function is used to -flip other byte values. - -Arguments: - value the number to flip - n the number of bytes to flip (assumed to be 2 or 4) - -Returns: the flipped value -*/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - -/************************************************* -* Test for a byte-flipped compiled regex * -*************************************************/ - -/* This function is called from pcre_exec(), pcre_dfa_exec(), and also from -pcre_fullinfo(). Its job is to test whether the regex is byte-flipped - that -is, it was compiled on a system of opposite endianness. The function is called -only when the native MAGIC_NUMBER test fails. If the regex is indeed flipped, -we flip all the relevant values into a different data block, and return it. - -Arguments: - re points to the regex - study points to study data, or NULL - internal_re points to a new regex block - internal_study points to a new study block - -Returns: the new block if is is indeed a byte-flipped regex - NULL if it is not -*/ - -real_pcre * -_pcre_try_flipped(const real_pcre *re, real_pcre *internal_re, - const pcre_study_data *study, pcre_study_data *internal_study) -{ -if (byteflip(re->magic_number, sizeof(re->magic_number)) != MAGIC_NUMBER) - return NULL; - -*internal_re = *re; /* To copy other fields */ -internal_re->size = byteflip(re->size, sizeof(re->size)); -internal_re->options = byteflip(re->options, sizeof(re->options)); -internal_re->flags = (pcre_uint16)byteflip(re->flags, sizeof(re->flags)); -internal_re->top_bracket = - (pcre_uint16)byteflip(re->top_bracket, sizeof(re->top_bracket)); -internal_re->top_backref = - (pcre_uint16)byteflip(re->top_backref, sizeof(re->top_backref)); -internal_re->first_byte = - (pcre_uint16)byteflip(re->first_byte, sizeof(re->first_byte)); -internal_re->req_byte = - (pcre_uint16)byteflip(re->req_byte, sizeof(re->req_byte)); -internal_re->name_table_offset = - (pcre_uint16)byteflip(re->name_table_offset, sizeof(re->name_table_offset)); -internal_re->name_entry_size = - (pcre_uint16)byteflip(re->name_entry_size, sizeof(re->name_entry_size)); -internal_re->name_count = - (pcre_uint16)byteflip(re->name_count, sizeof(re->name_count)); - -if (study != NULL) - { - *internal_study = *study; /* To copy other fields */ - internal_study->size = byteflip(study->size, sizeof(study->size)); - internal_study->options = byteflip(study->options, sizeof(study->options)); - } - -return internal_re; -} - -/* End of pcre_tryflipped.c */ diff --git a/src/src/pcre/pcre_version.c b/src/src/pcre/pcre_version.c deleted file mode 100644 index fa9a7bc9c..000000000 --- a/src/src/pcre/pcre_version.c +++ /dev/null @@ -1,92 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcre_version.c,v 1.6 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* PCRE is a library of functions to support regular expressions whose syntax -and semantics are as close as possible to those of the Perl 5 language. - - Written by Philip Hazel - Copyright (c) 1997-2007 University of Cambridge - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -/* This module contains the external function pcre_version(), which returns a -string that identifies the PCRE version that is in use. */ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include "pcre_internal.h" - - -/************************************************* -* Return version string * -*************************************************/ - -/* These macros are the standard way of turning unquoted text into C strings. -They allow macros like PCRE_MAJOR to be defined without quotes, which is -convenient for user programs that want to test its value. */ - -#define STRING(a) # a -#define XSTRING(s) STRING(s) - -/* A problem turned up with PCRE_PRERELEASE, which is defined empty for -production releases. Originally, it was used naively in this code: - - return XSTRING(PCRE_MAJOR) - "." XSTRING(PCRE_MINOR) - XSTRING(PCRE_PRERELEASE) - " " XSTRING(PCRE_DATE); - -However, when PCRE_PRERELEASE is empty, this leads to an attempted expansion of -STRING(). The C standard states: "If (before argument substitution) any -argument consists of no preprocessing tokens, the behavior is undefined." It -turns out the gcc treats this case as a single empty string - which is what we -really want - but Visual C grumbles about the lack of an argument for the -macro. Unfortunately, both are within their rights. To cope with both ways of -handling this, I had resort to some messy hackery that does a test at run time. -I could find no way of detecting that a macro is defined as an empty string at -pre-processor time. This hack uses a standard trick for avoiding calling -the STRING macro with an empty argument when doing the test. */ - -PCRE_EXP_DEFN const char * -pcre_version(void) -{ -return (XSTRING(Z PCRE_PRERELEASE)[1] == 0)? - XSTRING(PCRE_MAJOR.PCRE_MINOR PCRE_DATE) : - XSTRING(PCRE_MAJOR.PCRE_MINOR) XSTRING(PCRE_PRERELEASE PCRE_DATE); -} - -/* End of pcre_version.c */ diff --git a/src/src/pcre/pcretest.c b/src/src/pcre/pcretest.c deleted file mode 100644 index 77f6c16db..000000000 --- a/src/src/pcre/pcretest.c +++ /dev/null @@ -1,2398 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/pcretest.c,v 1.8 2007/11/12 13:02:20 nm4 Exp $ */ - -/************************************************* -* PCRE testing program * -*************************************************/ - -/* This program was hacked up as a tester for PCRE. I really should have -written it more tidily in the first place. Will I ever learn? It has grown and -been extended and consequently is now rather, er, *very* untidy in places. - ------------------------------------------------------------------------------ -Redistribution and use in source and binary forms, with or without -modification, are permitted provided that the following conditions are met: - - * Redistributions of source code must retain the above copyright notice, - this list of conditions and the following disclaimer. - - * Redistributions in binary form must reproduce the above copyright - notice, this list of conditions and the following disclaimer in the - documentation and/or other materials provided with the distribution. - - * Neither the name of the University of Cambridge nor the names of its - contributors may be used to endorse or promote products derived from - this software without specific prior written permission. - -THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" -AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE -IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE -ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE -LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR -CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF -SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS -INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN -CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) -ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE -POSSIBILITY OF SUCH DAMAGE. ------------------------------------------------------------------------------ -*/ - - -#ifdef HAVE_CONFIG_H -#include "config.h" -#endif - -#include <ctype.h> -#include <stdio.h> -#include <string.h> -#include <stdlib.h> -#include <time.h> -#include <locale.h> -#include <errno.h> - - -/* A number of things vary for Windows builds. Originally, pcretest opened its -input and output without "b"; then I was told that "b" was needed in some -environments, so it was added for release 5.0 to both the input and output. (It -makes no difference on Unix-like systems.) Later I was told that it is wrong -for the input on Windows. I've now abstracted the modes into two macros that -are set here, to make it easier to fiddle with them, and removed "b" from the -input mode under Windows. */ - -#if defined(_WIN32) || defined(WIN32) -#include <io.h> /* For _setmode() */ -#include <fcntl.h> /* For _O_BINARY */ -#define INPUT_MODE "r" -#define OUTPUT_MODE "wb" - -#else -#include <sys/time.h> /* These two includes are needed */ -#include <sys/resource.h> /* for setrlimit(). */ -#define INPUT_MODE "rb" -#define OUTPUT_MODE "wb" -#endif - - -/* We have to include pcre_internal.h because we need the internal info for -displaying the results of pcre_study() and we also need to know about the -internal macros, structures, and other internal data values; pcretest has -"inside information" compared to a program that strictly follows the PCRE API. - -Although pcre_internal.h does itself include pcre.h, we explicitly include it -here before pcre_internal.h so that the PCRE_EXP_xxx macros get set -appropriately for an application, not for building PCRE. */ - -#include "pcre.h" -#include "pcre_internal.h" - -/* We need access to the data tables that PCRE uses. So as not to have to keep -two copies, we include the source file here, changing the names of the external -symbols to prevent clashes. */ - -#define _pcre_utf8_table1 utf8_table1 -#define _pcre_utf8_table1_size utf8_table1_size -#define _pcre_utf8_table2 utf8_table2 -#define _pcre_utf8_table3 utf8_table3 -#define _pcre_utf8_table4 utf8_table4 -#define _pcre_utt utt -#define _pcre_utt_size utt_size -#define _pcre_utt_names utt_names -#define _pcre_OP_lengths OP_lengths - -#include "pcre_tables.c" - -/* We also need the pcre_printint() function for printing out compiled -patterns. This function is in a separate file so that it can be included in -pcre_compile.c when that module is compiled with debugging enabled. - -The definition of the macro PRINTABLE, which determines whether to print an -output character as-is or as a hex value when showing compiled patterns, is -contained in this file. We uses it here also, in cases when the locale has not -been explicitly changed, so as to get consistent output from systems that -differ in their output from isprint() even in the "C" locale. */ - -#include "pcre_printint.src" - -#define PRINTHEX(c) (locale_set? isprint(c) : PRINTABLE(c)) - - -/* It is possible to compile this test program without including support for -testing the POSIX interface, though this is not available via the standard -Makefile. */ - -#if !defined NOPOSIX -#include "pcreposix.h" -#endif - -/* It is also possible, for the benefit of the version currently imported into -Exim, to build pcretest without support for UTF8 (define NOUTF8), without the -interface to the DFA matcher (NODFA), and without the doublecheck of the old -"info" function (define NOINFOCHECK). In fact, we automatically cut out the -UTF8 support if PCRE is built without it. */ - -#ifndef SUPPORT_UTF8 -#ifndef NOUTF8 -#define NOUTF8 -#endif -#endif - - -/* Other parameters */ - -#ifndef CLOCKS_PER_SEC -#ifdef CLK_TCK -#define CLOCKS_PER_SEC CLK_TCK -#else -#define CLOCKS_PER_SEC 100 -#endif -#endif - -/* This is the default loop count for timing. */ - -#define LOOPREPEAT 500000 - -/* Static variables */ - -static FILE *outfile; -static int log_store = 0; -static int callout_count; -static int callout_extra; -static int callout_fail_count; -static int callout_fail_id; -static int debug_lengths; -static int first_callout; -static int locale_set = 0; -static int show_malloc; -static int use_utf8; -static size_t gotten_store; - -/* The buffers grow automatically if very long input lines are encountered. */ - -static int buffer_size = 50000; -static uschar *buffer = NULL; -static uschar *dbuffer = NULL; -static uschar *pbuffer = NULL; - - - -/************************************************* -* Read or extend an input line * -*************************************************/ - -/* Input lines are read into buffer, but both patterns and data lines can be -continued over multiple input lines. In addition, if the buffer fills up, we -want to automatically expand it so as to be able to handle extremely large -lines that are needed for certain stress tests. When the input buffer is -expanded, the other two buffers must also be expanded likewise, and the -contents of pbuffer, which are a copy of the input for callouts, must be -preserved (for when expansion happens for a data line). This is not the most -optimal way of handling this, but hey, this is just a test program! - -Arguments: - f the file to read - start where in buffer to start (this *must* be within buffer) - -Returns: pointer to the start of new data - could be a copy of start, or could be moved - NULL if no data read and EOF reached -*/ - -static uschar * -extend_inputline(FILE *f, uschar *start) -{ -uschar *here = start; - -for (;;) - { - int rlen = buffer_size - (here - buffer); - - if (rlen > 1000) - { - int dlen; - if (fgets((char *)here, rlen, f) == NULL) - return (here == start)? NULL : start; - dlen = (int)strlen((char *)here); - if (dlen > 0 && here[dlen - 1] == '\n') return start; - here += dlen; - } - - else - { - int new_buffer_size = 2*buffer_size; - uschar *new_buffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_dbuffer = (unsigned char *)malloc(new_buffer_size); - uschar *new_pbuffer = (unsigned char *)malloc(new_buffer_size); - - if (new_buffer == NULL || new_dbuffer == NULL || new_pbuffer == NULL) - { - fprintf(stderr, "pcretest: malloc(%d) failed\n", new_buffer_size); - exit(1); - } - - memcpy(new_buffer, buffer, buffer_size); - memcpy(new_pbuffer, pbuffer, buffer_size); - - buffer_size = new_buffer_size; - - start = new_buffer + (start - buffer); - here = new_buffer + (here - buffer); - - free(buffer); - free(dbuffer); - free(pbuffer); - - buffer = new_buffer; - dbuffer = new_dbuffer; - pbuffer = new_pbuffer; - } - } - -return NULL; /* Control never gets here */ -} - - - - - - - -/************************************************* -* Read number from string * -*************************************************/ - -/* We don't use strtoul() because SunOS4 doesn't have it. Rather than mess -around with conditional compilation, just do the job by hand. It is only used -for unpicking arguments, so just keep it simple. - -Arguments: - str string to be converted - endptr where to put the end pointer - -Returns: the unsigned long -*/ - -static int -get_value(unsigned char *str, unsigned char **endptr) -{ -int result = 0; -while(*str != 0 && isspace(*str)) str++; -while (isdigit(*str)) result = result * 10 + (int)(*str++ - '0'); -*endptr = str; -return(result); -} - - - - -/************************************************* -* Convert UTF-8 string to value * -*************************************************/ - -/* This function takes one or more bytes that represents a UTF-8 character, -and returns the value of the character. - -Argument: - utf8bytes a pointer to the byte vector - vptr a pointer to an int to receive the value - -Returns: > 0 => the number of bytes consumed - -6 to 0 => malformed UTF-8 character at offset = (-return) -*/ - -#if !defined NOUTF8 - -static int -utf82ord(unsigned char *utf8bytes, int *vptr) -{ -int c = *utf8bytes++; -int d = c; -int i, j, s; - -for (i = -1; i < 6; i++) /* i is number of additional bytes */ - { - if ((d & 0x80) == 0) break; - d <<= 1; - } - -if (i == -1) { *vptr = c; return 1; } /* ascii character */ -if (i == 0 || i == 6) return 0; /* invalid UTF-8 */ - -/* i now has a value in the range 1-5 */ - -s = 6*i; -d = (c & utf8_table3[i]) << s; - -for (j = 0; j < i; j++) - { - c = *utf8bytes++; - if ((c & 0xc0) != 0x80) return -(j+1); - s -= 6; - d |= (c & 0x3f) << s; - } - -/* Check that encoding was the correct unique one */ - -for (j = 0; j < utf8_table1_size; j++) - if (d <= utf8_table1[j]) break; -if (j != i) return -(i+1); - -/* Valid value */ - -*vptr = d; -return i+1; -} - -#endif - - - -/************************************************* -* Convert character value to UTF-8 * -*************************************************/ - -/* This function takes an integer value in the range 0 - 0x7fffffff -and encodes it as a UTF-8 character in 0 to 6 bytes. - -Arguments: - cvalue the character value - utf8bytes pointer to buffer for result - at least 6 bytes long - -Returns: number of characters placed in the buffer -*/ - -#if !defined NOUTF8 - -static int -ord2utf8(int cvalue, uschar *utf8bytes) -{ -register int i, j; -for (i = 0; i < utf8_table1_size; i++) - if (cvalue <= utf8_table1[i]) break; -utf8bytes += i; -for (j = i; j > 0; j--) - { - *utf8bytes-- = 0x80 | (cvalue & 0x3f); - cvalue >>= 6; - } -*utf8bytes = utf8_table2[i] | cvalue; -return i + 1; -} - -#endif - - - -/************************************************* -* Print character string * -*************************************************/ - -/* Character string printing function. Must handle UTF-8 strings in utf8 -mode. Yields number of characters printed. If handed a NULL file, just counts -chars without printing. */ - -static int pchars(unsigned char *p, int length, FILE *f) -{ -int c = 0; -int yield = 0; - -while (length-- > 0) - { -#if !defined NOUTF8 - if (use_utf8) - { - int rc = utf82ord(p, &c); - - if (rc > 0 && rc <= length + 1) /* Mustn't run over the end */ - { - length -= rc - 1; - p += rc; - if (PRINTHEX(c)) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - int n = 4; - if (f != NULL) fprintf(f, "\\x{%02x}", c); - yield += (n <= 0x000000ff)? 2 : - (n <= 0x00000fff)? 3 : - (n <= 0x0000ffff)? 4 : - (n <= 0x000fffff)? 5 : 6; - } - continue; - } - } -#endif - - /* Not UTF-8, or malformed UTF-8 */ - - c = *p++; - if (PRINTHEX(c)) - { - if (f != NULL) fprintf(f, "%c", c); - yield++; - } - else - { - if (f != NULL) fprintf(f, "\\x%02x", c); - yield += 4; - } - } - -return yield; -} - - - -/************************************************* -* Callout function * -*************************************************/ - -/* Called from PCRE as a result of the (?C) item. We print out where we are in -the match. Yield zero unless more callouts than the fail count, or the callout -data is not zero. */ - -static int callout(pcre_callout_block *cb) -{ -FILE *f = (first_callout | callout_extra)? outfile : NULL; -int i, pre_start, post_start, subject_length; - -if (callout_extra) - { - fprintf(f, "Callout %d: last capture = %d\n", - cb->callout_number, cb->capture_last); - - for (i = 0; i < cb->capture_top * 2; i += 2) - { - if (cb->offset_vector[i] < 0) - fprintf(f, "%2d: <unset>\n", i/2); - else - { - fprintf(f, "%2d: ", i/2); - (void)pchars((unsigned char *)cb->subject + cb->offset_vector[i], - cb->offset_vector[i+1] - cb->offset_vector[i], f); - fprintf(f, "\n"); - } - } - } - -/* Re-print the subject in canonical form, the first time or if giving full -datails. On subsequent calls in the same match, we use pchars just to find the -printed lengths of the substrings. */ - -if (f != NULL) fprintf(f, "--->"); - -pre_start = pchars((unsigned char *)cb->subject, cb->start_match, f); -post_start = pchars((unsigned char *)(cb->subject + cb->start_match), - cb->current_position - cb->start_match, f); - -subject_length = pchars((unsigned char *)cb->subject, cb->subject_length, NULL); - -(void)pchars((unsigned char *)(cb->subject + cb->current_position), - cb->subject_length - cb->current_position, f); - -if (f != NULL) fprintf(f, "\n"); - -/* Always print appropriate indicators, with callout number if not already -shown. For automatic callouts, show the pattern offset. */ - -if (cb->callout_number == 255) - { - fprintf(outfile, "%+3d ", cb->pattern_position); - if (cb->pattern_position > 99) fprintf(outfile, "\n "); - } -else - { - if (callout_extra) fprintf(outfile, " "); - else fprintf(outfile, "%3d ", cb->callout_number); - } - -for (i = 0; i < pre_start; i++) fprintf(outfile, " "); -fprintf(outfile, "^"); - -if (post_start > 0) - { - for (i = 0; i < post_start - 1; i++) fprintf(outfile, " "); - fprintf(outfile, "^"); - } - -for (i = 0; i < subject_length - pre_start - post_start + 4; i++) - fprintf(outfile, " "); - -fprintf(outfile, "%.*s", (cb->next_item_length == 0)? 1 : cb->next_item_length, - pbuffer + cb->pattern_position); - -fprintf(outfile, "\n"); -first_callout = 0; - -if (cb->callout_data != NULL) - { - int callout_data = *((int *)(cb->callout_data)); - if (callout_data != 0) - { - fprintf(outfile, "Callout data = %d\n", callout_data); - return callout_data; - } - } - -return (cb->callout_number != callout_fail_id)? 0 : - (++callout_count >= callout_fail_count)? 1 : 0; -} - - -/************************************************* -* Local malloc functions * -*************************************************/ - -/* Alternative malloc function, to test functionality and show the size of the -compiled re. */ - -static void *new_malloc(size_t size) -{ -void *block = malloc(size); -gotten_store = size; -if (show_malloc) - fprintf(outfile, "malloc %3d %p\n", (int)size, block); -return block; -} - -static void new_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "free %p\n", block); -free(block); -} - - -/* For recursion malloc/free, to test stacking calls */ - -static void *stack_malloc(size_t size) -{ -void *block = malloc(size); -if (show_malloc) - fprintf(outfile, "stack_malloc %3d %p\n", (int)size, block); -return block; -} - -static void stack_free(void *block) -{ -if (show_malloc) - fprintf(outfile, "stack_free %p\n", block); -free(block); -} - - -/************************************************* -* Call pcre_fullinfo() * -*************************************************/ - -/* Get one piece of information from the pcre_fullinfo() function */ - -static void new_info(pcre *re, pcre_extra *study, int option, void *ptr) -{ -int rc; -if ((rc = pcre_fullinfo(re, study, option, ptr)) < 0) - fprintf(outfile, "Error %d from pcre_fullinfo(%d)\n", rc, option); -} - - - -/************************************************* -* Byte flipping function * -*************************************************/ - -static unsigned long int -byteflip(unsigned long int value, int n) -{ -if (n == 2) return ((value & 0x00ff) << 8) | ((value & 0xff00) >> 8); -return ((value & 0x000000ff) << 24) | - ((value & 0x0000ff00) << 8) | - ((value & 0x00ff0000) >> 8) | - ((value & 0xff000000) >> 24); -} - - - - -/************************************************* -* Check match or recursion limit * -*************************************************/ - -static int -check_match_limit(pcre *re, pcre_extra *extra, uschar *bptr, int len, - int start_offset, int options, int *use_offsets, int use_size_offsets, - int flag, unsigned long int *limit, int errnumber, const char *msg) -{ -int count; -int min = 0; -int mid = 64; -int max = -1; - -extra->flags |= flag; - -for (;;) - { - *limit = mid; - - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, options, - use_offsets, use_size_offsets); - - if (count == errnumber) - { - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - min = mid; - mid = (mid == max - 1)? max : (max > 0)? (min + max)/2 : mid*2; - } - - else if (count >= 0 || count == PCRE_ERROR_NOMATCH || - count == PCRE_ERROR_PARTIAL) - { - if (mid == min + 1) - { - fprintf(outfile, "Minimum %s limit = %d\n", msg, mid); - break; - } - /* fprintf(outfile, "Testing %s limit = %d\n", msg, mid); */ - max = mid; - mid = (min + mid)/2; - } - else break; /* Some other error */ - } - -extra->flags &= ~flag; -return count; -} - - - -/************************************************* -* Case-independent strncmp() function * -*************************************************/ - -/* -Arguments: - s first string - t second string - n number of characters to compare - -Returns: < 0, = 0, or > 0, according to the comparison -*/ - -static int -strncmpic(uschar *s, uschar *t, int n) -{ -while (n--) - { - int c = tolower(*s++) - tolower(*t++); - if (c) return c; - } -return 0; -} - - - -/************************************************* -* Check newline indicator * -*************************************************/ - -/* This is used both at compile and run-time to check for <xxx> escapes, where -xxx is LF, CR, CRLF, ANYCRLF, or ANY. Print a message and return 0 if there is -no match. - -Arguments: - p points after the leading '<' - f file for error message - -Returns: appropriate PCRE_NEWLINE_xxx flags, or 0 -*/ - -static int -check_newline(uschar *p, FILE *f) -{ -if (strncmpic(p, (uschar *)"cr>", 3) == 0) return PCRE_NEWLINE_CR; -if (strncmpic(p, (uschar *)"lf>", 3) == 0) return PCRE_NEWLINE_LF; -if (strncmpic(p, (uschar *)"crlf>", 5) == 0) return PCRE_NEWLINE_CRLF; -if (strncmpic(p, (uschar *)"anycrlf>", 8) == 0) return PCRE_NEWLINE_ANYCRLF; -if (strncmpic(p, (uschar *)"any>", 4) == 0) return PCRE_NEWLINE_ANY; -if (strncmpic(p, (uschar *)"bsr_anycrlf>", 12) == 0) return PCRE_BSR_ANYCRLF; -if (strncmpic(p, (uschar *)"bsr_unicode>", 12) == 0) return PCRE_BSR_UNICODE; -fprintf(f, "Unknown newline type at: <%s\n", p); -return 0; -} - - - -/************************************************* -* Usage function * -*************************************************/ - -static void -usage(void) -{ -printf("Usage: pcretest [options] [<input> [<output>]]\n"); -printf(" -b show compiled code (bytecode)\n"); -printf(" -C show PCRE compile-time options and exit\n"); -printf(" -d debug: show compiled code and information (-b and -i)\n"); -#if !defined NODFA -printf(" -dfa force DFA matching for all subjects\n"); -#endif -printf(" -help show usage information\n"); -printf(" -i show information about compiled patterns\n" - " -m output memory used information\n" - " -o <n> set size of offsets vector to <n>\n"); -#if !defined NOPOSIX -printf(" -p use POSIX interface\n"); -#endif -printf(" -q quiet: do not output PCRE version number at start\n"); -printf(" -S <n> set stack size to <n> megabytes\n"); -printf(" -s output store (memory) used information\n" - " -t time compilation and execution\n"); -printf(" -t <n> time compilation and execution, repeating <n> times\n"); -printf(" -tm time execution (matching) only\n"); -printf(" -tm <n> time execution (matching) only, repeating <n> times\n"); -} - - - -/************************************************* -* Main Program * -*************************************************/ - -/* Read lines from named file or stdin and write to named file or stdout; lines -consist of a regular expression, in delimiters and optionally followed by -options, followed by a set of test data, terminated by an empty line. */ - -int main(int argc, char **argv) -{ -FILE *infile = stdin; -int options = 0; -int study_options = 0; -int op = 1; -int timeit = 0; -int timeitm = 0; -int showinfo = 0; -int showstore = 0; -int quiet = 0; -int size_offsets = 45; -int size_offsets_max; -int *offsets = NULL; -#if !defined NOPOSIX -int posix = 0; -#endif -int debug = 0; -int done = 0; -int all_use_dfa = 0; -int yield = 0; -int stack_size; - -/* These vectors store, end-to-end, a list of captured substring names. Assume -that 1024 is plenty long enough for the few names we'll be testing. */ - -uschar copynames[1024]; -uschar getnames[1024]; - -uschar *copynamesptr; -uschar *getnamesptr; - -/* Get buffers from malloc() so that Electric Fence will check their misuse -when I am debugging. They grow automatically when very long lines are read. */ - -buffer = (unsigned char *)malloc(buffer_size); -dbuffer = (unsigned char *)malloc(buffer_size); -pbuffer = (unsigned char *)malloc(buffer_size); - -/* The outfile variable is static so that new_malloc can use it. */ - -outfile = stdout; - -/* The following _setmode() stuff is some Windows magic that tells its runtime -library to translate CRLF into a single LF character. At least, that's what -I've been told: never having used Windows I take this all on trust. Originally -it set 0x8000, but then I was advised that _O_BINARY was better. */ - -#if defined(_WIN32) || defined(WIN32) -_setmode( _fileno( stdout ), _O_BINARY ); -#endif - -/* Scan options */ - -while (argc > 1 && argv[op][0] == '-') - { - unsigned char *endptr; - - if (strcmp(argv[op], "-s") == 0 || strcmp(argv[op], "-m") == 0) - showstore = 1; - else if (strcmp(argv[op], "-q") == 0) quiet = 1; - else if (strcmp(argv[op], "-b") == 0) debug = 1; - else if (strcmp(argv[op], "-i") == 0) showinfo = 1; - else if (strcmp(argv[op], "-d") == 0) showinfo = debug = 1; -#if !defined NODFA - else if (strcmp(argv[op], "-dfa") == 0) all_use_dfa = 1; -#endif - else if (strcmp(argv[op], "-o") == 0 && argc > 2 && - ((size_offsets = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { - op++; - argc--; - } - else if (strcmp(argv[op], "-t") == 0 || strcmp(argv[op], "-tm") == 0) - { - int both = argv[op][2] == 0; - int temp; - if (argc > 2 && (temp = get_value((unsigned char *)argv[op+1], &endptr), - *endptr == 0)) - { - timeitm = temp; - op++; - argc--; - } - else timeitm = LOOPREPEAT; - if (both) timeit = timeitm; - } - else if (strcmp(argv[op], "-S") == 0 && argc > 2 && - ((stack_size = get_value((unsigned char *)argv[op+1], &endptr)), - *endptr == 0)) - { -#if defined(_WIN32) || defined(WIN32) - printf("PCRE: -S not supported on this OS\n"); - exit(1); -#else - int rc; - struct rlimit rlim; - getrlimit(RLIMIT_STACK, &rlim); - rlim.rlim_cur = stack_size * 1024 * 1024; - rc = setrlimit(RLIMIT_STACK, &rlim); - if (rc != 0) - { - printf("PCRE: setrlimit() failed with error %d\n", rc); - exit(1); - } - op++; - argc--; -#endif - } -#if !defined NOPOSIX - else if (strcmp(argv[op], "-p") == 0) posix = 1; -#endif - else if (strcmp(argv[op], "-C") == 0) - { - int rc; - printf("PCRE version %s\n", pcre_version()); - printf("Compiled with\n"); - (void)pcre_config(PCRE_CONFIG_UTF8, &rc); - printf(" %sUTF-8 support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_UNICODE_PROPERTIES, &rc); - printf(" %sUnicode properties support\n", rc? "" : "No "); - (void)pcre_config(PCRE_CONFIG_NEWLINE, &rc); - printf(" Newline sequence is %s\n", (rc == '\r')? "CR" : - (rc == '\n')? "LF" : (rc == ('\r'<<8 | '\n'))? "CRLF" : - (rc == -2)? "ANYCRLF" : - (rc == -1)? "ANY" : "???"); - (void)pcre_config(PCRE_CONFIG_BSR, &rc); - printf(" \\R matches %s\n", rc? "CR, LF, or CRLF only" : - "all Unicode newlines"); - (void)pcre_config(PCRE_CONFIG_LINK_SIZE, &rc); - printf(" Internal link size = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_POSIX_MALLOC_THRESHOLD, &rc); - printf(" POSIX malloc threshold = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT, &rc); - printf(" Default match limit = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_MATCH_LIMIT_RECURSION, &rc); - printf(" Default recursion depth limit = %d\n", rc); - (void)pcre_config(PCRE_CONFIG_STACKRECURSE, &rc); - printf(" Match recursion uses %s\n", rc? "stack" : "heap"); - goto EXIT; - } - else if (strcmp(argv[op], "-help") == 0 || - strcmp(argv[op], "--help") == 0) - { - usage(); - goto EXIT; - } - else - { - printf("** Unknown or malformed option %s\n", argv[op]); - usage(); - yield = 1; - goto EXIT; - } - op++; - argc--; - } - -/* Get the store for the offsets vector, and remember what it was */ - -size_offsets_max = size_offsets; -offsets = (int *)malloc(size_offsets_max * sizeof(int)); -if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - -/* Sort out the input and output files */ - -if (argc > 1) - { - infile = fopen(argv[op], INPUT_MODE); - if (infile == NULL) - { - printf("** Failed to open %s\n", argv[op]); - yield = 1; - goto EXIT; - } - } - -if (argc > 2) - { - outfile = fopen(argv[op+1], OUTPUT_MODE); - if (outfile == NULL) - { - printf("** Failed to open %s\n", argv[op+1]); - yield = 1; - goto EXIT; - } - } - -/* Set alternative malloc function */ - -pcre_malloc = new_malloc; -pcre_free = new_free; -pcre_stack_malloc = stack_malloc; -pcre_stack_free = stack_free; - -/* Heading line unless quiet, then prompt for first regex if stdin */ - -if (!quiet) fprintf(outfile, "PCRE version %s\n\n", pcre_version()); - -/* Main loop */ - -while (!done) - { - pcre *re = NULL; - pcre_extra *extra = NULL; - -#if !defined NOPOSIX /* There are still compilers that require no indent */ - regex_t preg; - int do_posix = 0; -#endif - - const char *error; - unsigned char *p, *pp, *ppp; - unsigned char *to_file = NULL; - const unsigned char *tables = NULL; - unsigned long int true_size, true_study_size = 0; - size_t size, regex_gotten_store; - int do_study = 0; - int do_debug = debug; - int do_G = 0; - int do_g = 0; - int do_showinfo = showinfo; - int do_showrest = 0; - int do_flip = 0; - int erroroffset, len, delimiter, poffset; - - use_utf8 = 0; - debug_lengths = 1; - - if (infile == stdin) printf(" re> "); - if (extend_inputline(infile, buffer) == NULL) break; - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - fflush(outfile); - - p = buffer; - while (isspace(*p)) p++; - if (*p == 0) continue; - - /* See if the pattern is to be loaded pre-compiled from a file. */ - - if (*p == '<' && strchr((char *)(p+1), '<') == NULL) - { - unsigned long int magic, get_options; - uschar sbuf[8]; - FILE *f; - - p++; - pp = p + (int)strlen((char *)p); - while (isspace(pp[-1])) pp--; - *pp = 0; - - f = fopen((char *)p, "rb"); - if (f == NULL) - { - fprintf(outfile, "Failed to open %s: %s\n", p, strerror(errno)); - continue; - } - - if (fread(sbuf, 1, 8, f) != 8) goto FAIL_READ; - - true_size = - (sbuf[0] << 24) | (sbuf[1] << 16) | (sbuf[2] << 8) | sbuf[3]; - true_study_size = - (sbuf[4] << 24) | (sbuf[5] << 16) | (sbuf[6] << 8) | sbuf[7]; - - re = (real_pcre *)new_malloc(true_size); - regex_gotten_store = gotten_store; - - if (fread(re, 1, true_size, f) != true_size) goto FAIL_READ; - - magic = ((real_pcre *)re)->magic_number; - if (magic != MAGIC_NUMBER) - { - if (byteflip(magic, sizeof(magic)) == MAGIC_NUMBER) - { - do_flip = 1; - } - else - { - fprintf(outfile, "Data in %s is not a compiled PCRE regex\n", p); - fclose(f); - continue; - } - } - - fprintf(outfile, "Compiled regex%s loaded from %s\n", - do_flip? " (byte-inverted)" : "", p); - - /* Need to know if UTF-8 for printing data strings */ - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - use_utf8 = (get_options & PCRE_UTF8) != 0; - - /* Now see if there is any following study data */ - - if (true_study_size != 0) - { - pcre_study_data *psd; - - extra = (pcre_extra *)new_malloc(sizeof(pcre_extra) + true_study_size); - extra->flags = PCRE_EXTRA_STUDY_DATA; - - psd = (pcre_study_data *)(((char *)extra) + sizeof(pcre_extra)); - extra->study_data = psd; - - if (fread(psd, 1, true_study_size, f) != true_study_size) - { - FAIL_READ: - fprintf(outfile, "Failed to read data from %s\n", p); - if (extra != NULL) new_free(extra); - if (re != NULL) new_free(re); - fclose(f); - continue; - } - fprintf(outfile, "Study data loaded from %s\n", p); - do_study = 1; /* To get the data output if requested */ - } - else fprintf(outfile, "No study data\n"); - - fclose(f); - goto SHOW_INFO; - } - - /* In-line pattern (the usual case). Get the delimiter and seek the end of - the pattern; if is isn't complete, read more. */ - - delimiter = *p++; - - if (isalnum(delimiter) || delimiter == '\\') - { - fprintf(outfile, "** Delimiter must not be alphameric or \\\n"); - goto SKIP_DATA; - } - - pp = p; - poffset = p - buffer; - - for(;;) - { - while (*pp != 0) - { - if (*pp == '\\' && pp[1] != 0) pp++; - else if (*pp == delimiter) break; - pp++; - } - if (*pp != 0) break; - if (infile == stdin) printf(" > "); - if ((pp = extend_inputline(infile, pp)) == NULL) - { - fprintf(outfile, "** Unexpected EOF\n"); - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)pp); - } - - /* The buffer may have moved while being extended; reset the start of data - pointer to the correct relative point in the buffer. */ - - p = buffer + poffset; - - /* If the first character after the delimiter is backslash, make - the pattern end with backslash. This is purely to provide a way - of testing for the error message when a pattern ends with backslash. */ - - if (pp[1] == '\\') *pp++ = '\\'; - - /* Terminate the pattern at the delimiter, and save a copy of the pattern - for callouts. */ - - *pp++ = 0; - strcpy((char *)pbuffer, (char *)p); - - /* Look for options after final delimiter */ - - options = 0; - study_options = 0; - log_store = showstore; /* default from command line */ - - while (*pp != 0) - { - switch (*pp++) - { - case 'f': options |= PCRE_FIRSTLINE; break; - case 'g': do_g = 1; break; - case 'i': options |= PCRE_CASELESS; break; - case 'm': options |= PCRE_MULTILINE; break; - case 's': options |= PCRE_DOTALL; break; - case 'x': options |= PCRE_EXTENDED; break; - - case '+': do_showrest = 1; break; - case 'A': options |= PCRE_ANCHORED; break; - case 'B': do_debug = 1; break; - case 'C': options |= PCRE_AUTO_CALLOUT; break; - case 'D': do_debug = do_showinfo = 1; break; - case 'E': options |= PCRE_DOLLAR_ENDONLY; break; - case 'F': do_flip = 1; break; - case 'G': do_G = 1; break; - case 'I': do_showinfo = 1; break; - case 'J': options |= PCRE_DUPNAMES; break; - case 'M': log_store = 1; break; - case 'N': options |= PCRE_NO_AUTO_CAPTURE; break; - -#if !defined NOPOSIX - case 'P': do_posix = 1; break; -#endif - - case 'S': do_study = 1; break; - case 'U': options |= PCRE_UNGREEDY; break; - case 'X': options |= PCRE_EXTRA; break; - case 'Z': debug_lengths = 0; break; - case '8': options |= PCRE_UTF8; use_utf8 = 1; break; - case '?': options |= PCRE_NO_UTF8_CHECK; break; - - case 'L': - ppp = pp; - /* The '\r' test here is so that it works on Windows. */ - /* The '0' test is just in case this is an unterminated line. */ - while (*ppp != 0 && *ppp != '\n' && *ppp != '\r' && *ppp != ' ') ppp++; - *ppp = 0; - if (setlocale(LC_CTYPE, (const char *)pp) == NULL) - { - fprintf(outfile, "** Failed to set locale \"%s\"\n", pp); - goto SKIP_DATA; - } - locale_set = 1; - tables = pcre_maketables(); - pp = ppp; - break; - - case '>': - to_file = pp; - while (*pp != 0) pp++; - while (isspace(pp[-1])) pp--; - *pp = 0; - break; - - case '<': - { - int x = check_newline(pp, outfile); - if (x == 0) goto SKIP_DATA; - options |= x; - while (*pp++ != '>'); - } - break; - - case '\r': /* So that it works in Windows */ - case '\n': - case ' ': - break; - - default: - fprintf(outfile, "** Unknown option '%c'\n", pp[-1]); - goto SKIP_DATA; - } - } - - /* Handle compiling via the POSIX interface, which doesn't support the - timing, showing, or debugging options, nor the ability to pass over - local character tables. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int cflags = 0; - - if ((options & PCRE_CASELESS) != 0) cflags |= REG_ICASE; - if ((options & PCRE_MULTILINE) != 0) cflags |= REG_NEWLINE; - if ((options & PCRE_DOTALL) != 0) cflags |= REG_DOTALL; - if ((options & PCRE_NO_AUTO_CAPTURE) != 0) cflags |= REG_NOSUB; - if ((options & PCRE_UTF8) != 0) cflags |= REG_UTF8; - - rc = regcomp(&preg, (char *)p, cflags); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "Failed: POSIX code %d: %s\n", rc, buffer); - goto SKIP_DATA; - } - } - - /* Handle compiling via the native interface */ - - else -#endif /* !defined NOPOSIX */ - - { - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - { - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - if (re != NULL) free(re); - } - time_taken = clock() - start_time; - fprintf(outfile, "Compile time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - - re = pcre_compile((char *)p, options, &error, &erroroffset, tables); - - /* Compilation failed; go back for another re, skipping to blank line - if non-interactive. */ - - if (re == NULL) - { - fprintf(outfile, "Failed: %s at offset %d\n", error, erroroffset); - SKIP_DATA: - if (infile != stdin) - { - for (;;) - { - if (extend_inputline(infile, buffer) == NULL) - { - done = 1; - goto CONTINUE; - } - len = (int)strlen((char *)buffer); - while (len > 0 && isspace(buffer[len-1])) len--; - if (len == 0) break; - } - fprintf(outfile, "\n"); - } - goto CONTINUE; - } - - /* Compilation succeeded; print data if required. There are now two - info-returning functions. The old one has a limited interface and - returns only limited data. Check that it agrees with the newer one. */ - - if (log_store) - fprintf(outfile, "Memory allocation (code space): %d\n", - (int)(gotten_store - - sizeof(real_pcre) - - ((real_pcre *)re)->name_count * ((real_pcre *)re)->name_entry_size)); - - /* Extract the size for possible writing before possibly flipping it, - and remember the store that was got. */ - - true_size = ((real_pcre *)re)->size; - regex_gotten_store = gotten_store; - - /* If /S was present, study the regexp to generate additional info to - help with the matching. */ - - if (do_study) - { - if (timeit > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - for (i = 0; i < timeit; i++) - extra = pcre_study(re, study_options, &error); - time_taken = clock() - start_time; - if (extra != NULL) free(extra); - fprintf(outfile, " Study time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeit) / - (double)CLOCKS_PER_SEC); - } - extra = pcre_study(re, study_options, &error); - if (error != NULL) - fprintf(outfile, "Failed to study: %s\n", error); - else if (extra != NULL) - true_study_size = ((pcre_study_data *)(extra->study_data))->size; - } - - /* If the 'F' option was present, we flip the bytes of all the integer - fields in the regex data block and the study block. This is to make it - possible to test PCRE's handling of byte-flipped patterns, e.g. those - compiled on a different architecture. */ - - if (do_flip) - { - real_pcre *rre = (real_pcre *)re; - rre->magic_number = - byteflip(rre->magic_number, sizeof(rre->magic_number)); - rre->size = byteflip(rre->size, sizeof(rre->size)); - rre->options = byteflip(rre->options, sizeof(rre->options)); - rre->flags = (pcre_uint16)byteflip(rre->flags, sizeof(rre->flags)); - rre->top_bracket = - (pcre_uint16)byteflip(rre->top_bracket, sizeof(rre->top_bracket)); - rre->top_backref = - (pcre_uint16)byteflip(rre->top_backref, sizeof(rre->top_backref)); - rre->first_byte = - (pcre_uint16)byteflip(rre->first_byte, sizeof(rre->first_byte)); - rre->req_byte = - (pcre_uint16)byteflip(rre->req_byte, sizeof(rre->req_byte)); - rre->name_table_offset = (pcre_uint16)byteflip(rre->name_table_offset, - sizeof(rre->name_table_offset)); - rre->name_entry_size = (pcre_uint16)byteflip(rre->name_entry_size, - sizeof(rre->name_entry_size)); - rre->name_count = (pcre_uint16)byteflip(rre->name_count, - sizeof(rre->name_count)); - - if (extra != NULL) - { - pcre_study_data *rsd = (pcre_study_data *)(extra->study_data); - rsd->size = byteflip(rsd->size, sizeof(rsd->size)); - rsd->options = byteflip(rsd->options, sizeof(rsd->options)); - } - } - - /* Extract information from the compiled data if required */ - - SHOW_INFO: - - if (do_debug) - { - fprintf(outfile, "------------------------------------------------------------------\n"); - pcre_printint(re, outfile, debug_lengths); - } - - if (do_showinfo) - { - unsigned long int get_options, all_options; -#if !defined NOINFOCHECK - int old_first_char, old_options, old_count; -#endif - int count, backrefmax, first_char, need_char, okpartial, jchanged, - hascrorlf; - int nameentrysize, namecount; - const uschar *nametable; - - new_info(re, NULL, PCRE_INFO_OPTIONS, &get_options); - new_info(re, NULL, PCRE_INFO_SIZE, &size); - new_info(re, NULL, PCRE_INFO_CAPTURECOUNT, &count); - new_info(re, NULL, PCRE_INFO_BACKREFMAX, &backrefmax); - new_info(re, NULL, PCRE_INFO_FIRSTBYTE, &first_char); - new_info(re, NULL, PCRE_INFO_LASTLITERAL, &need_char); - new_info(re, NULL, PCRE_INFO_NAMEENTRYSIZE, &nameentrysize); - new_info(re, NULL, PCRE_INFO_NAMECOUNT, &namecount); - new_info(re, NULL, PCRE_INFO_NAMETABLE, (void *)&nametable); - new_info(re, NULL, PCRE_INFO_OKPARTIAL, &okpartial); - new_info(re, NULL, PCRE_INFO_JCHANGED, &jchanged); - new_info(re, NULL, PCRE_INFO_HASCRORLF, &hascrorlf); - -#if !defined NOINFOCHECK - old_count = pcre_info(re, &old_options, &old_first_char); - if (count < 0) fprintf(outfile, - "Error %d from pcre_info()\n", count); - else - { - if (old_count != count) fprintf(outfile, - "Count disagreement: pcre_fullinfo=%d pcre_info=%d\n", count, - old_count); - - if (old_first_char != first_char) fprintf(outfile, - "First char disagreement: pcre_fullinfo=%d pcre_info=%d\n", - first_char, old_first_char); - - if (old_options != (int)get_options) fprintf(outfile, - "Options disagreement: pcre_fullinfo=%ld pcre_info=%d\n", - get_options, old_options); - } -#endif - - if (size != regex_gotten_store) fprintf(outfile, - "Size disagreement: pcre_fullinfo=%d call to malloc for %d\n", - (int)size, (int)regex_gotten_store); - - fprintf(outfile, "Capturing subpattern count = %d\n", count); - if (backrefmax > 0) - fprintf(outfile, "Max back reference = %d\n", backrefmax); - - if (namecount > 0) - { - fprintf(outfile, "Named capturing subpatterns:\n"); - while (namecount-- > 0) - { - fprintf(outfile, " %s %*s%3d\n", nametable + 2, - nameentrysize - 3 - (int)strlen((char *)nametable + 2), "", - GET2(nametable, 0)); - nametable += nameentrysize; - } - } - - if (!okpartial) fprintf(outfile, "Partial matching not supported\n"); - if (hascrorlf) fprintf(outfile, "Contains explicit CR or LF match\n"); - - all_options = ((real_pcre *)re)->options; - if (do_flip) all_options = byteflip(all_options, sizeof(all_options)); - - if (get_options == 0) fprintf(outfile, "No options\n"); - else fprintf(outfile, "Options:%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n", - ((get_options & PCRE_ANCHORED) != 0)? " anchored" : "", - ((get_options & PCRE_CASELESS) != 0)? " caseless" : "", - ((get_options & PCRE_EXTENDED) != 0)? " extended" : "", - ((get_options & PCRE_MULTILINE) != 0)? " multiline" : "", - ((get_options & PCRE_FIRSTLINE) != 0)? " firstline" : "", - ((get_options & PCRE_DOTALL) != 0)? " dotall" : "", - ((get_options & PCRE_BSR_ANYCRLF) != 0)? " bsr_anycrlf" : "", - ((get_options & PCRE_BSR_UNICODE) != 0)? " bsr_unicode" : "", - ((get_options & PCRE_DOLLAR_ENDONLY) != 0)? " dollar_endonly" : "", - ((get_options & PCRE_EXTRA) != 0)? " extra" : "", - ((get_options & PCRE_UNGREEDY) != 0)? " ungreedy" : "", - ((get_options & PCRE_NO_AUTO_CAPTURE) != 0)? " no_auto_capture" : "", - ((get_options & PCRE_UTF8) != 0)? " utf8" : "", - ((get_options & PCRE_NO_UTF8_CHECK) != 0)? " no_utf8_check" : "", - ((get_options & PCRE_DUPNAMES) != 0)? " dupnames" : ""); - - if (jchanged) fprintf(outfile, "Duplicate name status changes\n"); - - switch (get_options & PCRE_NEWLINE_BITS) - { - case PCRE_NEWLINE_CR: - fprintf(outfile, "Forced newline sequence: CR\n"); - break; - - case PCRE_NEWLINE_LF: - fprintf(outfile, "Forced newline sequence: LF\n"); - break; - - case PCRE_NEWLINE_CRLF: - fprintf(outfile, "Forced newline sequence: CRLF\n"); - break; - - case PCRE_NEWLINE_ANYCRLF: - fprintf(outfile, "Forced newline sequence: ANYCRLF\n"); - break; - - case PCRE_NEWLINE_ANY: - fprintf(outfile, "Forced newline sequence: ANY\n"); - break; - - default: - break; - } - - if (first_char == -1) - { - fprintf(outfile, "First char at start or follows newline\n"); - } - else if (first_char < 0) - { - fprintf(outfile, "No first char\n"); - } - else - { - int ch = first_char & 255; - const char *caseless = ((first_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (PRINTHEX(ch)) - fprintf(outfile, "First char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "First char = %d%s\n", ch, caseless); - } - - if (need_char < 0) - { - fprintf(outfile, "No need char\n"); - } - else - { - int ch = need_char & 255; - const char *caseless = ((need_char & REQ_CASELESS) == 0)? - "" : " (caseless)"; - if (PRINTHEX(ch)) - fprintf(outfile, "Need char = \'%c\'%s\n", ch, caseless); - else - fprintf(outfile, "Need char = %d%s\n", ch, caseless); - } - - /* Don't output study size; at present it is in any case a fixed - value, but it varies, depending on the computer architecture, and - so messes up the test suite. (And with the /F option, it might be - flipped.) */ - - if (do_study) - { - if (extra == NULL) - fprintf(outfile, "Study returned NULL\n"); - else - { - uschar *start_bits = NULL; - new_info(re, extra, PCRE_INFO_FIRSTTABLE, &start_bits); - - if (start_bits == NULL) - fprintf(outfile, "No starting byte set\n"); - else - { - int i; - int c = 24; - fprintf(outfile, "Starting byte set: "); - for (i = 0; i < 256; i++) - { - if ((start_bits[i/8] & (1<<(i&7))) != 0) - { - if (c > 75) - { - fprintf(outfile, "\n "); - c = 2; - } - if (PRINTHEX(i) && i != ' ') - { - fprintf(outfile, "%c ", i); - c += 2; - } - else - { - fprintf(outfile, "\\x%02x ", i); - c += 5; - } - } - } - fprintf(outfile, "\n"); - } - } - } - } - - /* If the '>' option was present, we write out the regex to a file, and - that is all. The first 8 bytes of the file are the regex length and then - the study length, in big-endian order. */ - - if (to_file != NULL) - { - FILE *f = fopen((char *)to_file, "wb"); - if (f == NULL) - { - fprintf(outfile, "Unable to open %s: %s\n", to_file, strerror(errno)); - } - else - { - uschar sbuf[8]; - sbuf[0] = (uschar)((true_size >> 24) & 255); - sbuf[1] = (uschar)((true_size >> 16) & 255); - sbuf[2] = (uschar)((true_size >> 8) & 255); - sbuf[3] = (uschar)((true_size) & 255); - - sbuf[4] = (uschar)((true_study_size >> 24) & 255); - sbuf[5] = (uschar)((true_study_size >> 16) & 255); - sbuf[6] = (uschar)((true_study_size >> 8) & 255); - sbuf[7] = (uschar)((true_study_size) & 255); - - if (fwrite(sbuf, 1, 8, f) < 8 || - fwrite(re, 1, true_size, f) < true_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, strerror(errno)); - } - else - { - fprintf(outfile, "Compiled regex written to %s\n", to_file); - if (extra != NULL) - { - if (fwrite(extra->study_data, 1, true_study_size, f) < - true_study_size) - { - fprintf(outfile, "Write error on %s: %s\n", to_file, - strerror(errno)); - } - else fprintf(outfile, "Study data written to %s\n", to_file); - - } - } - fclose(f); - } - - new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) new_free((void *)tables); - continue; /* With next regex */ - } - } /* End of non-POSIX compile */ - - /* Read data lines and test them */ - - for (;;) - { - uschar *q; - uschar *bptr; - int *use_offsets = offsets; - int use_size_offsets = size_offsets; - int callout_data = 0; - int callout_data_set = 0; - int count, c; - int copystrings = 0; - int find_match_limit = 0; - int getstrings = 0; - int getlist = 0; - int gmatched = 0; - int start_offset = 0; - int g_notempty = 0; - int use_dfa = 0; - - options = 0; - - *copynames = 0; - *getnames = 0; - - copynamesptr = copynames; - getnamesptr = getnames; - - pcre_callout = callout; - first_callout = 1; - callout_extra = 0; - callout_count = 0; - callout_fail_count = 999999; - callout_fail_id = -1; - show_malloc = 0; - - if (extra != NULL) extra->flags &= - ~(PCRE_EXTRA_MATCH_LIMIT|PCRE_EXTRA_MATCH_LIMIT_RECURSION); - - len = 0; - for (;;) - { - if (infile == stdin) printf("data> "); - if (extend_inputline(infile, buffer + len) == NULL) - { - if (len > 0) break; - done = 1; - goto CONTINUE; - } - if (infile != stdin) fprintf(outfile, "%s", (char *)buffer); - len = (int)strlen((char *)buffer); - if (buffer[len-1] == '\n') break; - } - - while (len > 0 && isspace(buffer[len-1])) len--; - buffer[len] = 0; - if (len == 0) break; - - p = buffer; - while (isspace(*p)) p++; - - bptr = q = dbuffer; - while ((c = *p++) != 0) - { - int i = 0; - int n = 0; - - if (c == '\\') switch ((c = *p++)) - { - case 'a': c = 7; break; - case 'b': c = '\b'; break; - case 'e': c = 27; break; - case 'f': c = '\f'; break; - case 'n': c = '\n'; break; - case 'r': c = '\r'; break; - case 't': c = '\t'; break; - case 'v': c = '\v'; break; - - case '0': case '1': case '2': case '3': - case '4': case '5': case '6': case '7': - c -= '0'; - while (i++ < 2 && isdigit(*p) && *p != '8' && *p != '9') - c = c * 8 + *p++ - '0'; - -#if !defined NOUTF8 - if (use_utf8 && c > 255) - { - unsigned char buff8[8]; - int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - } -#endif - break; - - case 'x': - - /* Handle \x{..} specially - new Perl thing for utf8 */ - -#if !defined NOUTF8 - if (*p == '{') - { - unsigned char *pt = p; - c = 0; - while (isxdigit(*(++pt))) - c = c * 16 + tolower(*pt) - ((isdigit(*pt))? '0' : 'W'); - if (*pt == '}') - { - unsigned char buff8[8]; - int ii, utn; - utn = ord2utf8(c, buff8); - for (ii = 0; ii < utn - 1; ii++) *q++ = buff8[ii]; - c = buff8[ii]; /* Last byte */ - p = pt + 1; - break; - } - /* Not correct form; fall through */ - } -#endif - - /* Ordinary \x */ - - c = 0; - while (i++ < 2 && isxdigit(*p)) - { - c = c * 16 + tolower(*p) - ((isdigit(*p))? '0' : 'W'); - p++; - } - break; - - case 0: /* \ followed by EOF allows for an empty line */ - p--; - continue; - - case '>': - while(isdigit(*p)) start_offset = start_offset * 10 + *p++ - '0'; - continue; - - case 'A': /* Option setting */ - options |= PCRE_ANCHORED; - continue; - - case 'B': - options |= PCRE_NOTBOL; - continue; - - case 'C': - if (isdigit(*p)) /* Set copy string */ - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - copystrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = copynamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)copynamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", copynamesptr); - copynamesptr = npp; - } - else if (*p == '+') - { - callout_extra = 1; - p++; - } - else if (*p == '-') - { - pcre_callout = NULL; - p++; - } - else if (*p == '!') - { - callout_fail_id = 0; - p++; - while(isdigit(*p)) - callout_fail_id = callout_fail_id * 10 + *p++ - '0'; - callout_fail_count = 0; - if (*p == '!') - { - p++; - while(isdigit(*p)) - callout_fail_count = callout_fail_count * 10 + *p++ - '0'; - } - } - else if (*p == '*') - { - int sign = 1; - callout_data = 0; - if (*(++p) == '-') { sign = -1; p++; } - while(isdigit(*p)) - callout_data = callout_data * 10 + *p++ - '0'; - callout_data *= sign; - callout_data_set = 1; - } - continue; - -#if !defined NODFA - case 'D': -#if !defined NOPOSIX - if (posix || do_posix) - printf("** Can't use dfa matching in POSIX mode: \\D ignored\n"); - else -#endif - use_dfa = 1; - continue; - - case 'F': - options |= PCRE_DFA_SHORTEST; - continue; -#endif - - case 'G': - if (isdigit(*p)) - { - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - getstrings |= 1 << n; - } - else if (isalnum(*p)) - { - uschar *npp = getnamesptr; - while (isalnum(*p)) *npp++ = *p++; - *npp++ = 0; - *npp = 0; - n = pcre_get_stringnumber(re, (char *)getnamesptr); - if (n < 0) - fprintf(outfile, "no parentheses with name \"%s\"\n", getnamesptr); - getnamesptr = npp; - } - continue; - - case 'L': - getlist = 1; - continue; - - case 'M': - find_match_limit = 1; - continue; - - case 'N': - options |= PCRE_NOTEMPTY; - continue; - - case 'O': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (n > size_offsets_max) - { - size_offsets_max = n; - free(offsets); - use_offsets = offsets = (int *)malloc(size_offsets_max * sizeof(int)); - if (offsets == NULL) - { - printf("** Failed to get %d bytes of memory for offsets vector\n", - (int)(size_offsets_max * sizeof(int))); - yield = 1; - goto EXIT; - } - } - use_size_offsets = n; - if (n == 0) use_offsets = NULL; /* Ensures it can't write to it */ - continue; - - case 'P': - options |= PCRE_PARTIAL; - continue; - - case 'Q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT_RECURSION; - extra->match_limit_recursion = n; - continue; - - case 'q': - while(isdigit(*p)) n = n * 10 + *p++ - '0'; - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_MATCH_LIMIT; - extra->match_limit = n; - continue; - -#if !defined NODFA - case 'R': - options |= PCRE_DFA_RESTART; - continue; -#endif - - case 'S': - show_malloc = 1; - continue; - - case 'Z': - options |= PCRE_NOTEOL; - continue; - - case '?': - options |= PCRE_NO_UTF8_CHECK; - continue; - - case '<': - { - int x = check_newline(p, outfile); - if (x == 0) goto NEXT_DATA; - options |= x; - while (*p++ != '>'); - } - continue; - } - *q++ = c; - } - *q = 0; - len = q - dbuffer; - - if ((all_use_dfa || use_dfa) && find_match_limit) - { - printf("**Match limit not relevant for DFA matching: ignored\n"); - find_match_limit = 0; - } - - /* Handle matching via the POSIX interface, which does not - support timing or playing with the match limit or callout data. */ - -#if !defined NOPOSIX - if (posix || do_posix) - { - int rc; - int eflags = 0; - regmatch_t *pmatch = NULL; - if (use_size_offsets > 0) - pmatch = (regmatch_t *)malloc(sizeof(regmatch_t) * use_size_offsets); - if ((options & PCRE_NOTBOL) != 0) eflags |= REG_NOTBOL; - if ((options & PCRE_NOTEOL) != 0) eflags |= REG_NOTEOL; - - rc = regexec(&preg, (const char *)bptr, use_size_offsets, pmatch, eflags); - - if (rc != 0) - { - (void)regerror(rc, &preg, (char *)buffer, buffer_size); - fprintf(outfile, "No match: POSIX code %d: %s\n", rc, buffer); - } - else if ((((const pcre *)preg.re_pcre)->options & PCRE_NO_AUTO_CAPTURE) - != 0) - { - fprintf(outfile, "Matched with REG_NOSUB\n"); - } - else - { - size_t i; - for (i = 0; i < (size_t)use_size_offsets; i++) - { - if (pmatch[i].rm_so >= 0) - { - fprintf(outfile, "%2d: ", (int)i); - (void)pchars(dbuffer + pmatch[i].rm_so, - pmatch[i].rm_eo - pmatch[i].rm_so, outfile); - fprintf(outfile, "\n"); - if (i == 0 && do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(dbuffer + pmatch[i].rm_eo, len - pmatch[i].rm_eo, - outfile); - fprintf(outfile, "\n"); - } - } - } - } - free(pmatch); - } - - /* Handle matching via the native interface - repeats for /g and /G */ - - else -#endif /* !defined NOPOSIX */ - - for (;; gmatched++) /* Loop for /g or /G */ - { - if (timeitm > 0) - { - register int i; - clock_t time_taken; - clock_t start_time = clock(); - -#if !defined NODFA - if (all_use_dfa || use_dfa) - { - int workspace[1000]; - for (i = 0; i < timeitm; i++) - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - } - else -#endif - - for (i = 0; i < timeitm; i++) - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - - time_taken = clock() - start_time; - fprintf(outfile, "Execute time %.4f milliseconds\n", - (((double)time_taken * 1000.0) / (double)timeitm) / - (double)CLOCKS_PER_SEC); - } - - /* If find_match_limit is set, we want to do repeated matches with - varying limits in order to find the minimum value for the match limit and - for the recursion limit. */ - - if (find_match_limit) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - - (void)check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT, &(extra->match_limit), - PCRE_ERROR_MATCHLIMIT, "match()"); - - count = check_match_limit(re, extra, bptr, len, start_offset, - options|g_notempty, use_offsets, use_size_offsets, - PCRE_EXTRA_MATCH_LIMIT_RECURSION, &(extra->match_limit_recursion), - PCRE_ERROR_RECURSIONLIMIT, "match() recursion"); - } - - /* If callout_data is set, use the interface with additional data */ - - else if (callout_data_set) - { - if (extra == NULL) - { - extra = (pcre_extra *)malloc(sizeof(pcre_extra)); - extra->flags = 0; - } - extra->flags |= PCRE_EXTRA_CALLOUT_DATA; - extra->callout_data = &callout_data; - count = pcre_exec(re, extra, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets); - extra->flags &= ~PCRE_EXTRA_CALLOUT_DATA; - } - - /* The normal case is just to do the match once, with the default - value of match_limit. */ - -#if !defined NODFA - else if (all_use_dfa || use_dfa) - { - int workspace[1000]; - count = pcre_dfa_exec(re, NULL, (char *)bptr, len, start_offset, - options | g_notempty, use_offsets, use_size_offsets, workspace, - sizeof(workspace)/sizeof(int)); - if (count == 0) - { - fprintf(outfile, "Matched, but too many subsidiary matches\n"); - count = use_size_offsets/2; - } - } -#endif - - else - { - count = pcre_exec(re, extra, (char *)bptr, len, - start_offset, options | g_notempty, use_offsets, use_size_offsets); - if (count == 0) - { - fprintf(outfile, "Matched, but too many substrings\n"); - count = use_size_offsets/3; - } - } - - /* Matched */ - - if (count >= 0) - { - int i, maxcount; - -#if !defined NODFA - if (all_use_dfa || use_dfa) maxcount = use_size_offsets/2; else -#endif - maxcount = use_size_offsets/3; - - /* This is a check against a lunatic return value. */ - - if (count > maxcount) - { - fprintf(outfile, - "** PCRE error: returned count %d is too big for offset size %d\n", - count, use_size_offsets); - count = use_size_offsets/3; - if (do_g || do_G) - { - fprintf(outfile, "** /%c loop abandoned\n", do_g? 'g' : 'G'); - do_g = do_G = FALSE; /* Break g/G loop */ - } - } - - for (i = 0; i < count * 2; i += 2) - { - if (use_offsets[i] < 0) - fprintf(outfile, "%2d: <unset>\n", i/2); - else - { - fprintf(outfile, "%2d: ", i/2); - (void)pchars(bptr + use_offsets[i], - use_offsets[i+1] - use_offsets[i], outfile); - fprintf(outfile, "\n"); - if (i == 0) - { - if (do_showrest) - { - fprintf(outfile, " 0+ "); - (void)pchars(bptr + use_offsets[i+1], len - use_offsets[i+1], - outfile); - fprintf(outfile, "\n"); - } - } - } - } - - for (i = 0; i < 32; i++) - { - if ((copystrings & (1 << i)) != 0) - { - char copybuffer[256]; - int rc = pcre_copy_substring((char *)bptr, use_offsets, count, - i, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %d failed %d\n", i, rc); - else - fprintf(outfile, "%2dC %s (%d)\n", i, copybuffer, rc); - } - } - - for (copynamesptr = copynames; - *copynamesptr != 0; - copynamesptr += (int)strlen((char*)copynamesptr) + 1) - { - char copybuffer[256]; - int rc = pcre_copy_named_substring(re, (char *)bptr, use_offsets, - count, (char *)copynamesptr, copybuffer, sizeof(copybuffer)); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", copynamesptr, rc); - else - fprintf(outfile, " C %s (%d) %s\n", copybuffer, rc, copynamesptr); - } - - for (i = 0; i < 32; i++) - { - if ((getstrings & (1 << i)) != 0) - { - const char *substring; - int rc = pcre_get_substring((char *)bptr, use_offsets, count, - i, &substring); - if (rc < 0) - fprintf(outfile, "get substring %d failed %d\n", i, rc); - else - { - fprintf(outfile, "%2dG %s (%d)\n", i, substring, rc); - pcre_free_substring(substring); - } - } - } - - for (getnamesptr = getnames; - *getnamesptr != 0; - getnamesptr += (int)strlen((char*)getnamesptr) + 1) - { - const char *substring; - int rc = pcre_get_named_substring(re, (char *)bptr, use_offsets, - count, (char *)getnamesptr, &substring); - if (rc < 0) - fprintf(outfile, "copy substring %s failed %d\n", getnamesptr, rc); - else - { - fprintf(outfile, " G %s (%d) %s\n", substring, rc, getnamesptr); - pcre_free_substring(substring); - } - } - - if (getlist) - { - const char **stringlist; - int rc = pcre_get_substring_list((char *)bptr, use_offsets, count, - &stringlist); - if (rc < 0) - fprintf(outfile, "get substring list failed %d\n", rc); - else - { - for (i = 0; i < count; i++) - fprintf(outfile, "%2dL %s\n", i, stringlist[i]); - if (stringlist[i] != NULL) - fprintf(outfile, "string list not terminated by NULL\n"); - /* free((void *)stringlist); */ - pcre_free_substring_list(stringlist); - } - } - } - - /* There was a partial match */ - - else if (count == PCRE_ERROR_PARTIAL) - { - fprintf(outfile, "Partial match"); -#if !defined NODFA - if ((all_use_dfa || use_dfa) && use_size_offsets > 2) - fprintf(outfile, ": %.*s", use_offsets[1] - use_offsets[0], - bptr + use_offsets[0]); -#endif - fprintf(outfile, "\n"); - break; /* Out of the /g loop */ - } - - /* Failed to match. If this is a /g or /G loop and we previously set - g_notempty after a null match, this is not necessarily the end. We want - to advance the start offset, and continue. We won't be at the end of the - string - that was checked before setting g_notempty. - - Complication arises in the case when the newline option is "any" or - "anycrlf". If the previous match was at the end of a line terminated by - CRLF, an advance of one character just passes the \r, whereas we should - prefer the longer newline sequence, as does the code in pcre_exec(). - Fudge the offset value to achieve this. - - Otherwise, in the case of UTF-8 matching, the advance must be one - character, not one byte. */ - - else - { - if (g_notempty != 0) - { - int onechar = 1; - unsigned int obits = ((real_pcre *)re)->options; - use_offsets[0] = start_offset; - if ((obits & PCRE_NEWLINE_BITS) == 0) - { - int d; - (void)pcre_config(PCRE_CONFIG_NEWLINE, &d); - obits = (d == '\r')? PCRE_NEWLINE_CR : - (d == '\n')? PCRE_NEWLINE_LF : - (d == ('\r'<<8 | '\n'))? PCRE_NEWLINE_CRLF : - (d == -2)? PCRE_NEWLINE_ANYCRLF : - (d == -1)? PCRE_NEWLINE_ANY : 0; - } - if (((obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANY || - (obits & PCRE_NEWLINE_BITS) == PCRE_NEWLINE_ANYCRLF) - && - start_offset < len - 1 && - bptr[start_offset] == '\r' && - bptr[start_offset+1] == '\n') - onechar++; - else if (use_utf8) - { - while (start_offset + onechar < len) - { - int tb = bptr[start_offset+onechar]; - if (tb <= 127) break; - tb &= 0xc0; - if (tb != 0 && tb != 0xc0) onechar++; - } - } - use_offsets[1] = start_offset + onechar; - } - else - { - if (count == PCRE_ERROR_NOMATCH) - { - if (gmatched == 0) fprintf(outfile, "No match\n"); - } - else fprintf(outfile, "Error %d\n", count); - break; /* Out of the /g loop */ - } - } - - /* If not /g or /G we are done */ - - if (!do_g && !do_G) break; - - /* If we have matched an empty string, first check to see if we are at - the end of the subject. If so, the /g loop is over. Otherwise, mimic - what Perl's /g options does. This turns out to be rather cunning. First - we set PCRE_NOTEMPTY and PCRE_ANCHORED and try the match again at the - same point. If this fails (picked up above) we advance to the next - character. */ - - g_notempty = 0; - - if (use_offsets[0] == use_offsets[1]) - { - if (use_offsets[0] == len) break; - g_notempty = PCRE_NOTEMPTY | PCRE_ANCHORED; - } - - /* For /g, update the start offset, leaving the rest alone */ - - if (do_g) start_offset = use_offsets[1]; - - /* For /G, update the pointer and length */ - - else - { - bptr += use_offsets[1]; - len -= use_offsets[1]; - } - } /* End of loop for /g and /G */ - - NEXT_DATA: continue; - } /* End of loop for data lines */ - - CONTINUE: - -#if !defined NOPOSIX - if (posix || do_posix) regfree(&preg); -#endif - - if (re != NULL) new_free(re); - if (extra != NULL) new_free(extra); - if (tables != NULL) - { - new_free((void *)tables); - setlocale(LC_CTYPE, "C"); - locale_set = 0; - } - } - -if (infile == stdin) fprintf(outfile, "\n"); - -EXIT: - -if (infile != NULL && infile != stdin) fclose(infile); -if (outfile != NULL && outfile != stdout) fclose(outfile); - -free(buffer); -free(dbuffer); -free(pbuffer); -free(offsets); - -return yield; -} - -/* End of pcretest.c */ diff --git a/src/src/pcre/ucp.h b/src/src/pcre/ucp.h deleted file mode 100644 index 288854e67..000000000 --- a/src/src/pcre/ucp.h +++ /dev/null @@ -1,135 +0,0 @@ -/* $Cambridge: exim/src/src/pcre/ucp.h,v 1.5 2007/06/26 11:16:54 ph10 Exp $ */ - -/************************************************* -* Unicode Property Table handler * -*************************************************/ - -#ifndef _UCP_H -#define _UCP_H - -/* This file contains definitions of the property values that are returned by -the function _pcre_ucp_findprop(). New values that are added for new releases -of Unicode should always be at the end of each enum, for backwards -compatibility. */ - -/* These are the general character categories. */ - -enum { - ucp_C, /* Other */ - ucp_L, /* Letter */ - ucp_M, /* Mark */ - ucp_N, /* Number */ - ucp_P, /* Punctuation */ - ucp_S, /* Symbol */ - ucp_Z /* Separator */ -}; - -/* These are the particular character types. */ - -enum { - ucp_Cc, /* Control */ - ucp_Cf, /* Format */ - ucp_Cn, /* Unassigned */ - ucp_Co, /* Private use */ - ucp_Cs, /* Surrogate */ - ucp_Ll, /* Lower case letter */ - ucp_Lm, /* Modifier letter */ - ucp_Lo, /* Other letter */ - ucp_Lt, /* Title case letter */ - ucp_Lu, /* Upper case letter */ - ucp_Mc, /* Spacing mark */ - ucp_Me, /* Enclosing mark */ - ucp_Mn, /* Non-spacing mark */ - ucp_Nd, /* Decimal number */ - ucp_Nl, /* Letter number */ - ucp_No, /* Other number */ - ucp_Pc, /* Connector punctuation */ - ucp_Pd, /* Dash punctuation */ - ucp_Pe, /* Close punctuation */ - ucp_Pf, /* Final punctuation */ - ucp_Pi, /* Initial punctuation */ - ucp_Po, /* Other punctuation */ - ucp_Ps, /* Open punctuation */ - ucp_Sc, /* Currency symbol */ - ucp_Sk, /* Modifier symbol */ - ucp_Sm, /* Mathematical symbol */ - ucp_So, /* Other symbol */ - ucp_Zl, /* Line separator */ - ucp_Zp, /* Paragraph separator */ - ucp_Zs /* Space separator */ -}; - -/* These are the script identifications. */ - -enum { - ucp_Arabic, - ucp_Armenian, - ucp_Bengali, - ucp_Bopomofo, - ucp_Braille, - ucp_Buginese, - ucp_Buhid, - ucp_Canadian_Aboriginal, - ucp_Cherokee, - ucp_Common, - ucp_Coptic, - ucp_Cypriot, - ucp_Cyrillic, - ucp_Deseret, - ucp_Devanagari, - ucp_Ethiopic, - ucp_Georgian, - ucp_Glagolitic, - ucp_Gothic, - ucp_Greek, - ucp_Gujarati, - ucp_Gurmukhi, - ucp_Han, - ucp_Hangul, - ucp_Hanunoo, - ucp_Hebrew, - ucp_Hiragana, - ucp_Inherited, - ucp_Kannada, - ucp_Katakana, - ucp_Kharoshthi, - ucp_Khmer, - ucp_Lao, - ucp_Latin, - ucp_Limbu, - ucp_Linear_B, - ucp_Malayalam, - ucp_Mongolian, - ucp_Myanmar, - ucp_New_Tai_Lue, - ucp_Ogham, - ucp_Old_Italic, - ucp_Old_Persian, - ucp_Oriya, - ucp_Osmanya, - ucp_Runic, - ucp_Shavian, - ucp_Sinhala, - ucp_Syloti_Nagri, - ucp_Syriac, - ucp_Tagalog, - ucp_Tagbanwa, - ucp_Tai_Le, - ucp_Tamil, - ucp_Telugu, - ucp_Thaana, - ucp_Thai, - ucp_Tibetan, - ucp_Tifinagh, - ucp_Ugaritic, - ucp_Yi, - ucp_Balinese, /* New for Unicode 5.0.0 */ - ucp_Cuneiform, /* New for Unicode 5.0.0 */ - ucp_Nko, /* New for Unicode 5.0.0 */ - ucp_Phags_Pa, /* New for Unicode 5.0.0 */ - ucp_Phoenician /* New for Unicode 5.0.0 */ -}; - -#endif - -/* End of ucp.h */ |