blob: 113e6f9d0bf30b3522526c57e70fa274d662c943 (
plain)
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
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
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
|
#! /usr/bin/perl
# $Cambridge: exim/doc/doc-docbook/Pre-xml,v 1.1 2005/06/16 10:32:31 ph10 Exp $
# Script to pre-process XML input before processing it for various purposes.
# Options specify which transformations are to be done. Monospaced literal
# layout blocks are never touched.
# Changes:
# -abstract: Remove the <abstract> element
# -ascii: Replace &8230; (sic, no x) with ...
# Replace ’ by '
# Replace “ by "
# Replace ” by "
# Replace – by -
# Replace † by *
# Replace ‡ by **
# Replace   by a space
# Replace © by (c)
# Put quotes round <literal> text
# Put quotes round <quote> text
# -bookinfo: Remove the <bookinfo> element from the file
# -fi: Replace "fi" by fi except when it is in an XML element, or
# inside a <literal>.
# -noindex Remove the XML to generate a Concept and an Options index.
# -oneindex Ditto, but add XML to generate a single index.
# The function that processes non-literal monospaced text
sub process()
{
my($s) = $_[0];
$s =~ s/fi(?![^<>]*>)/fi/g if $ligatures;
if ($ascii)
{
$s =~ s/…/.../g;
$s =~ s/’/'/g;
$s =~ s/“/"/g;
$s =~ s/”/"/g;
$s =~ s/–/-/g;
$s =~ s/†/*/g;
$s =~ s/‡/**/g;
$s =~ s/ / /g;
$s =~ s/©/(c)/g;
$s =~ s/<quote>/"/g;
$s =~ s/<\/quote>/"/g;
}
$s;
}
# The main program
$abstract = 0;
$ascii = 0;
$bookinfo = 0;
$inliteral = 0;
$ligatures = 0;
$madeindex = 0;
$noindex = 0;
$oneindex = 0;
foreach $arg (@ARGV)
{
if ($arg eq "-fi") { $ligatures = 1; }
elsif ($arg eq "-abstract") { $abstract = 1; }
elsif ($arg eq "-ascii") { $ascii = 1; }
elsif ($arg eq "-bookinfo") { $bookinfo = 1; }
elsif ($arg eq "-noindex") { $noindex = 1; }
elsif ($arg eq "-oneindex") { $oneindex = 1; }
else { die "** Pre-xml: Unknown option \"$arg\"\n"; }
}
while (<STDIN>)
{
# Remove <abstract> if required
next if ($abstract && /^\s*<abstract>/);
# Remove <bookinfo> if required
if ($bookinfo && /^<bookinfo/)
{
while (<STDIN>) { last if /^<\/bookinfo/; }
next;
}
# Copy monospaced literallayout blocks
if (/^<literallayout class="monospaced">/)
{
print;
while (<STDIN>)
{
print;
last if /^<\/literallayout>/;
}
next;
}
# Adjust index-generation code if required
if (($noindex || $oneindex) && /^<index[\s>]/)
{
while (<STDIN>)
{
last if /^<\/index>/;
}
if ($oneindex && !$madeindex)
{
$madeindex = 1;
print "<index><title>Index</title></index>\n";
}
next;
}
# A line that is not in a monospaced literal block; keep track of which
# parts are in <literal> and which not. The latter get processed by the
# function above.
for (;;)
{
if ($inliteral)
{
if (/^(.*?)<\/literal>(.*)$/)
{
print $1;
print "\"" if $ascii;
print "</literal>";
$inliteral = 0;
$_ = "$2\n";
}
else
{
print;
last;
}
}
# Not in literal state
else
{
if (/^(.*?)<literal>(.*)$/)
{
print &process($1);
print "<literal>";
print "\"" if $ascii;
$inliteral = 1;
$_ = "$2\n";
}
else
{
print &process($_);
last;
}
}
} # Loop for different parts of one line
} # Loop for multiple lines
# End
|
