summaryrefslogtreecommitdiff
path: root/include/hashcomp.h
blob: aa204ace60fffb164a493986578b7331766c152a (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
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
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
/*
 * InspIRCd -- Internet Relay Chat Daemon
 *
 *   Copyright (C) 2011 Adam <Adam@anope.org>
 *   Copyright (C) 2009 Daniel De Graaf <danieldg@inspircd.org>
 *   Copyright (C) 2007, 2009 Dennis Friis <peavey@inspircd.org>
 *   Copyright (C) 2005-2009 Craig Edwards <craigedwards@brainbox.cc>
 *   Copyright (C) 2007-2008 Robin Burchell <robin+git@viroteck.net>
 *   Copyright (C) 2008 Pippijn van Steenhoven <pip88nl@gmail.com>
 *
 * This file is part of InspIRCd.  InspIRCd is free software: you can
 * redistribute it and/or modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation, version 2.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE.  See the GNU General Public License for more
 * details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */


#pragma once

#include <cstring>
#include <string>
#include <vector>
#include <deque>
#include <map>
#include <set>
#include "inspircd.h"

/*******************************************************
 * This file contains classes and templates that deal
 * with the comparison and hashing of 'irc strings'.
 * An 'irc string' is a string which compares in a
 * case insensitive manner, and as per RFC 1459 will
 * treat [ identical to {, ] identical to }, and \
 * as identical to |.
 *
 * Our hashing functions are designed  to accept
 * std::string and compare/hash them as type irc::string
 * by converting them internally. This makes them
 * backwards compatible with other code which is not
 * aware of irc::string.
 *******************************************************/

/** Seperate from the other casemap tables so that code *can* still exclusively rely on RFC casemapping
 * if it must.
 *
 * This is provided as a pointer so that modules can change it to their custom mapping tables,
 * e.g. for national character support.
 */
CoreExport extern unsigned const char *national_case_insensitive_map;

/** A mapping of uppercase to lowercase, including scandinavian
 * 'oddities' as specified by RFC1459, e.g. { -> [, and | -> \
 */
CoreExport extern unsigned const char rfc_case_insensitive_map[256];

/** Case insensitive map, ASCII rules.
 * That is;
 * [ != {, but A == a.
 */
CoreExport extern unsigned const char ascii_case_insensitive_map[256];

/** Case sensitive (identity) map.
 */
CoreExport extern unsigned const char rfc_case_sensitive_map[256];

template<typename T> const T& SearchAndReplace(T& text, const T& pattern, const T& replace)
{
	T replacement;
	if ((!pattern.empty()) && (!text.empty()))
	{
		for (std::string::size_type n = 0; n != text.length(); ++n)
		{
			if (text.length() >= pattern.length() && text.substr(n, pattern.length()) == pattern)
			{
				// Found the pattern in the text, replace it, and advance
				replacement.append(replace);
				n = n + pattern.length() - 1;
			}
			else
			{
				replacement += text[n];
			}
		}
	}
	text = replacement;
	return text;
}

/** The irc namespace contains a number of helper classes.
 */
namespace irc
{

	/** Check if two IRC object (e.g. nick or channel) names are equal.
	 * This function uses national_case_insensitive_map to determine equality, which, by default does comparison
	 * according to RFC 1459, treating certain otherwise non-identical characters as identical.
	 * @param s1 First string to compare
	 * @param s2 Second string to compare
	 * @return True if the two names are equal, false otherwise
	 */
	CoreExport bool equals(const std::string& s1, const std::string& s2);

	/** This class returns true if two strings match.
	 * Case sensitivity is ignored, and the RFC 'character set'
	 * is adhered to
	 */
	struct StrHashComp
	{
		/** The operator () does the actual comparison in hash_map
		 */
		bool operator()(const std::string& s1, const std::string& s2) const
		{
			return equals(s1, s2);
		}
	};

	struct insensitive
	{
		size_t CoreExport operator()(const std::string &s) const;
	};

	struct insensitive_swo
	{
		bool CoreExport operator()(const std::string& a, const std::string& b) const;
	};

	/** The irc_char_traits class is used for RFC-style comparison of strings.
	 * This class is used to implement irc::string, a case-insensitive, RFC-
	 * comparing string class.
	 */
	struct CoreExport irc_char_traits : public std::char_traits<char>
	{
		/** Check if two chars match.
		 * @param c1st First character
		 * @param c2nd Second character
		 * @return true if the characters are equal
		 */
		static bool eq(char c1st, char c2nd);

		/** Check if two chars do NOT match.
		 * @param c1st First character
		 * @param c2nd Second character
		 * @return true if the characters are unequal
		 */
		static bool ne(char c1st, char c2nd);

		/** Check if one char is less than another.
		 * @param c1st First character
		 * @param c2nd Second character
		 * @return true if c1st is less than c2nd
		 */
		static bool lt(char c1st, char c2nd);

		/** Compare two strings of size n.
		 * @param str1 First string
		 * @param str2 Second string
		 * @param n Length to compare to
		 * @return similar to strcmp, zero for equal, less than zero for str1
		 * being less and greater than zero for str1 being greater than str2.
		 */
		static int compare(const char* str1, const char* str2, size_t n);

		/** Find a char within a string up to position n.
		 * @param s1 String to find in
		 * @param n Position to search up to
		 * @param c Character to search for
		 * @return Pointer to the first occurance of c in s1
		 */
		static const char* find(const char* s1, int  n, char c);
	};

	/** This typedef declares irc::string based upon irc_char_traits.
	 */
	typedef std::basic_string<char, irc_char_traits, std::allocator<char> > string;

	/** Joins the contents of a vector to a string.
	 * @param sequence Zero or more items to join.
	 * @separator The character to place between the items.
	 */
   	std::string CoreExport stringjoiner(const std::vector<std::string>& sequence, char separator = ' ');

	/** irc::sepstream allows for splitting token seperated lists.
	 * Each successive call to sepstream::GetToken() returns
	 * the next token, until none remain, at which point the method returns
	 * an empty string.
	 */
	class CoreExport sepstream
	{
	 protected:
		/** Original string.
		 */
		std::string tokens;
		/** Separator value
		 */
		char sep;
		/** Current string position
		 */
		size_t pos;
		/** If set then GetToken() can return an empty string
		 */
		bool allow_empty;
	 public:
		/** Create a sepstream and fill it with the provided data
		 */
		sepstream(const std::string &source, char separator, bool allowempty = false);

		/** Fetch the next token from the stream
		 * @param token The next token from the stream is placed here
		 * @return True if tokens still remain, false if there are none left
		 */
		bool GetToken(std::string& token);

		/** Fetch the entire remaining stream, without tokenizing
		 * @return The remaining part of the stream
		 */
		const std::string GetRemaining();

		/** Returns true if the end of the stream has been reached
		 * @return True if the end of the stream has been reached, otherwise false
		 */
		bool StreamEnd();
	};

	/** A derived form of sepstream, which seperates on commas
	 */
	class CoreExport commasepstream : public sepstream
	{
	 public:
		/** Initialize with comma separator
		 */
		commasepstream(const std::string &source, bool allowempty = false) : sepstream(source, ',', allowempty)
		{
		}
	};

	/** A derived form of sepstream, which seperates on spaces
	 */
	class CoreExport spacesepstream : public sepstream
	{
	 public:
		/** Initialize with space separator
		 */
		spacesepstream(const std::string &source, bool allowempty = false) : sepstream(source, ' ', allowempty)
		{
		}
	};

	/** irc::tokenstream reads a string formatted as per RFC1459 and RFC2812.
	 * It will split the string into 'tokens' each containing one parameter
	 * from the string.
	 * For instance, if it is instantiated with the string:
	 * "PRIVMSG #test :foo bar baz qux"
	 * then each successive call to tokenstream::GetToken() will return
	 * "PRIVMSG", "#test", "foo bar baz qux", "".
	 * Note that if the whole string starts with a colon this is not taken
	 * to mean the string is all one parameter, and the first item in the
	 * list will be ":item". This is to allow for parsing 'source' fields
	 * from data.
	 */
	class CoreExport tokenstream : private spacesepstream
	{
	 public:
		/** Create a tokenstream and fill it with the provided data
		 */
		tokenstream(const std::string &source);

		/** Fetch the next token from the stream as a std::string
		 * @param token The next token available, or an empty string if none remain
		 * @return True if tokens are left to be read, false if the last token was just retrieved.
		 */
		bool GetToken(std::string &token);

		/** Fetch the next token from the stream as an integer
		 * @param token The next token available, or undefined if none remain
		 * @return True if tokens are left to be read, false if the last token was just retrieved.
		 */
		bool GetToken(int &token);

		/** Fetch the next token from the stream as a long integer
		 * @param token The next token available, or undefined if none remain
		 * @return True if tokens are left to be read, false if the last token was just retrieved.
		 */
		bool GetToken(long &token);
	};

	/** The portparser class seperates out a port range into integers.
	 * A port range may be specified in the input string in the form
	 * "6660,6661,6662-6669,7020". The end of the stream is indicated by
	 * a return value of 0 from portparser::GetToken(). If you attempt
	 * to specify an illegal range (e.g. one where start >= end, or
	 * start or end < 0) then GetToken() will return the first element
	 * of the pair of numbers.
	 */
	class CoreExport portparser
	{
	 private:

		/** Used to split on commas
		 */
		commasepstream sep;

		/** Current position in a range of ports
		 */
		long in_range;

		/** Starting port in a range of ports
		 */
		long range_begin;

		/** Ending port in a range of ports
		 */
		long range_end;

		/** Allow overlapped port ranges
		 */
		bool overlapped;

		/** Used to determine overlapping of ports
		 * without O(n) algorithm being used
		 */
		std::set<long> overlap_set;

		/** Returns true if val overlaps an existing range
		 */
		bool Overlaps(long val);
	 public:

		/** Create a portparser and fill it with the provided data
		 * @param source The source text to parse from
		 * @param allow_overlapped Allow overlapped ranges
		 */
		portparser(const std::string &source, bool allow_overlapped = true);

		/** Fetch the next token from the stream
		 * @return The next port number is returned, or 0 if none remain
		 */
		long GetToken();
	};
}

/* Define operators for using >> and << with irc::string to an ostream on an istream. */
/* This was endless fun. No. Really. */
/* It was also the first core change Ommeh made, if anyone cares */

/** Operator << for irc::string
 */
inline std::ostream& operator<<(std::ostream &os, const irc::string &str) { return os << str.c_str(); }

/** Operator >> for irc::string
 */
inline std::istream& operator>>(std::istream &is, irc::string &str)
{
	std::string tmp;
	is >> tmp;
	str = tmp.c_str();
	return is;
}

/* Define operators for + and == with irc::string to std::string for easy assignment
 * and comparison
 *
 * Operator +
 */
inline std::string operator+ (std::string& leftval, irc::string& rightval)
{
	return leftval + std::string(rightval.c_str());
}

/* Define operators for + and == with irc::string to std::string for easy assignment
 * and comparison
 *
 * Operator +
 */
inline irc::string operator+ (irc::string& leftval, std::string& rightval)
{
	return leftval + irc::string(rightval.c_str());
}

/* Define operators for + and == with irc::string to std::string for easy assignment
 * and comparison
 *
 * Operator ==
 */
inline bool operator== (const std::string& leftval, const irc::string& rightval)
{
	return (leftval.c_str() == rightval);
}

/* Define operators for + and == with irc::string to std::string for easy assignment
 * and comparison
 *
 * Operator ==
 */
inline bool operator== (const irc::string& leftval, const std::string& rightval)
{
	return (leftval == rightval.c_str());
}

/* Define operators != for irc::string to std::string for easy comparison
 */
inline bool operator!= (const irc::string& leftval, const std::string& rightval)
{
	return !(leftval == rightval.c_str());
}

/* Define operators != for std::string to irc::string for easy comparison
 */
inline bool operator!= (const std::string& leftval, const irc::string& rightval)
{
	return !(leftval.c_str() == rightval);
}

/** Assign an irc::string to a std::string.
 */
inline std::string assign(const irc::string &other) { return other.c_str(); }

/** Assign a std::string to an irc::string.
 */
inline irc::string assign(const std::string &other) { return other.c_str(); }