summaryrefslogtreecommitdiff
path: root/src/modules/m_nationalchars.cpp
blob: dbeff6db9db58e7ccda4865416d2841b75ff5ce5 (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
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
/*
 * InspIRCd -- Internet Relay Chat Daemon
 *
 *   Copyright (C) 2009 Daniel De Graaf <danieldg@inspircd.org>
 *   Copyright (C) 2009 Dennis Friis <peavey@inspircd.org>
 *   Copyright (C) 2009 Craig Edwards <craigedwards@brainbox.cc>
 *   Copyright (C) 2009 Robin Burchell <robin+git@viroteck.net>
 *
 * 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/>.
 */


/* Contains a code of Unreal IRCd + Bynets patch (https://www.unrealircd.org and https://bynets.org)
   Original patch is made by Dmitry "Killer{R}" Kononko. (http://killprog.com)
   Changed at 2008-06-15 - 2009-02-11
   by Chernov-Phoenix Alexey (Phoenix@RusNet) mailto:phoenix /email address separator/ pravmail.ru */

#include "inspircd.h"
#include <fstream>

class lwbNickHandler
{
 public:
	static bool Call(const std::string&);
};

								 /*,m_reverse_additionalUp[256];*/
static unsigned char m_reverse_additional[256],m_additionalMB[256],m_additionalUtf8[256],m_additionalUtf8range[256],m_additionalUtf8interval[256];

char utf8checkrest(unsigned char * mb, unsigned char cnt)
{
	for (unsigned char * tmp=mb; tmp<mb+cnt; tmp++)
	{
		/* & is faster! -- Phoenix (char & b11000000 == b10000000) */
		if ((*tmp & 192) != 128)
			return -1;
	}
	return cnt + 1;
}


char utf8size(unsigned char * mb)
{
	if (!*mb)
		return -1;
	if (!(*mb & 128))
		return 1;
	if ((*mb & 224) == 192)
		return utf8checkrest(mb + 1,1);
	if ((*mb & 240) == 224)
		return utf8checkrest(mb + 1,2);
	if ((*mb & 248) == 240)
		return utf8checkrest(mb + 1,3);
	return -1;
}


/* Conditions added */
bool lwbNickHandler::Call(const std::string& nick)
{
	if (nick.empty())
		return false;

	const char* n = nick.c_str();
	unsigned int p = 0;
	for (const char* i = n; *i; i++, p++)
	{
		/* 1. Multibyte encodings support:  */
		/* 1.1. 16bit char. areas, e.g. chinese:*/

		/* if current character is the last, we DO NOT check it against multibyte table */
		/* if there are mbtable ranges, use ONLY them. No 8bit at all */
		if (i[1] && m_additionalMB[0])
		{
			/* otherwise let's take a look at the current character and the following one */
			bool found = false;
			for(unsigned char * mb = m_additionalMB; (*mb) && (mb < m_additionalMB + sizeof(m_additionalMB)); mb += 4)
			{
				if ( (i[0] >= mb[0]) && (i[0] <= mb[1]) && (i[1] >= mb[2]) && (i[1] <= mb[3]) )
				{
					/* multibyte range character found */
					i++;
					p++;
					found = true;
					break;
				}
			}
			if (found)
				/* next char! */
				continue;
			else
				/* there are ranges, but incorrect char (8bit?) given, sorry */
				return false;
		}

		/* 2. 8bit character support */
		if (((*i >= 'A') && (*i <= '}')) || m_reverse_additional[(unsigned char)*i])
			/* "A"-"}" can occur anywhere in a nickname */
			continue;

		if ((((*i >= '0') && (*i <= '9')) || (*i == '-')) && (i > n))
			/* "0"-"9", "-" can occur anywhere BUT the first char of a nickname */
			continue;

		/* 3.1. Check against a simple UTF-8 characters enumeration */
		int cursize, cursize2, ncursize = utf8size((unsigned char *)i);
		/* do check only if current multibyte character is valid UTF-8 only */
		if (ncursize != -1)
		{
			bool found = false;
			for (unsigned char * mb = m_additionalUtf8; (utf8size(mb) != -1) && (mb < m_additionalUtf8 + sizeof(m_additionalUtf8)); mb += cursize)
			{
				cursize = utf8size(mb);
				/* Size differs? Pick the next! */
				if (cursize != ncursize)
					continue;

				if (!strncmp(i, (char *)mb, cursize))
				{
					i += cursize - 1;
					p += cursize - 1;
					found = true;
					break;
				}
			}
			if (found)
				continue;

			/* 3.2. Check against an UTF-8 ranges: <start character> and <length of the range>. */
			found = false;
			for (unsigned char * mb = m_additionalUtf8range; (utf8size(mb) != -1) && (mb < m_additionalUtf8range + sizeof(m_additionalUtf8range)); mb += cursize + 1)
			{
				cursize = utf8size(mb);
				/* Size differs (or lengthbyte is zero)? Pick the next! */
				if ((cursize != ncursize) || (!mb[cursize]))
					continue;

				unsigned char uright[5] = {0,0,0,0,0}, range = mb[cursize] - 1;
				strncpy((char* ) uright, (char *) mb, cursize);

				for (int temp = cursize - 1; (temp >= 0) && range; --temp)
				{
					/* all but the first char are 64-based */
					if (temp)
					{
						char part64 = range & 63; /* i.e. % 64 */
						/* handle carrying over */
						if (uright[temp] + part64 - 1 > 191)
						{
							uright[temp] -= 64;
							range += 64;
						}
						uright[temp] += part64;
						range >>= 6; /* divide it on a 64 */
					}
					/* the first char of UTF-8 doesn't follow the rule */
					else
					{
						uright[temp] += range;
					}
				}

				if ((strncmp(i, (char *) mb, cursize) >= 0) && (strncmp(i, (char *) uright, cursize) <= 0))
				{
					i += cursize - 1;
					p += cursize - 1;
					found = true;
					break;
				}
			}
			if (found)
				continue;

			/* 3.3. Check against an UTF-8 intervals: <start character> and <end character>. */
			found = false;
			for (unsigned char * mb = m_additionalUtf8interval; (utf8size(mb) != -1) && (utf8size(mb+utf8size(mb)) != -1)
				&& (mb < m_additionalUtf8interval + sizeof(m_additionalUtf8interval)); mb += (cursize+cursize2) )
			{
				cursize = utf8size(mb);
				cursize2= utf8size(mb+cursize);

				int minlen  = cursize  > ncursize ? ncursize : cursize;
				int minlen2 = cursize2 > ncursize ? ncursize : cursize2;

				unsigned char* uright = mb + cursize;

				if ((strncmp(i, (char *) mb, minlen) >= 0) && (strncmp(i, (char *) uright, minlen2) <= 0))
				{
					i += cursize - 1;
					p += cursize - 1;
					found = true;
					break;
				}
			}
			if (found)
				continue;
		}

		/* invalid character! abort */
		return false;
	}

	/* too long? or not -- pointer arithmetic rocks */
	return (p < ServerInstance->Config->Limits.NickMax);
}


class ModuleNationalChars : public Module
{
	std::string charset;
	unsigned char m_additional[256], m_additionalUp[256], m_lower[256], m_upper[256];
	TR1NS::function<bool(const std::string&)> rememberer;
	bool forcequit;
	const unsigned char * lowermap_rememberer;
	std::string casemapping_rememberer;
	unsigned char prev_map[256];

	template <typename T>
	void RehashHashmap(T& hashmap)
	{
		T newhash(hashmap.bucket_count());
		for (typename T::const_iterator i = hashmap.begin(); i != hashmap.end(); ++i)
			newhash.insert(std::make_pair(i->first, i->second));
		hashmap.swap(newhash);
	}

	void CheckRehash()
	{
		// See if anything changed
		if (!memcmp(prev_map, national_case_insensitive_map, sizeof(prev_map)))
			return;

		memcpy(prev_map, national_case_insensitive_map, sizeof(prev_map));

		RehashHashmap(ServerInstance->Users.clientlist);
		RehashHashmap(ServerInstance->Users.uuidlist);
		RehashHashmap(ServerInstance->chanlist);
	}

 public:
	ModuleNationalChars()
		: rememberer(ServerInstance->IsNick)
		, lowermap_rememberer(national_case_insensitive_map)
		, casemapping_rememberer(ServerInstance->Config->CaseMapping)
	{
		memcpy(prev_map, national_case_insensitive_map, sizeof(prev_map));
	}

	void init() CXX11_OVERRIDE
	{
		memcpy(m_lower, rfc_case_insensitive_map, 256);
		national_case_insensitive_map = m_lower;

		ServerInstance->IsNick = &lwbNickHandler::Call;
	}

	void ReadConfig(ConfigStatus& status) CXX11_OVERRIDE
	{
		ConfigTag* tag = ServerInstance->Config->ConfValue("nationalchars");
		charset = tag->getString("file");
		std::string casemapping = tag->getString("casemapping", FileSystem::GetFileName(charset));
		if (casemapping.find(' ') != std::string::npos)
			throw ModuleException("<nationalchars:casemapping> must not contain any spaces!");
		ServerInstance->Config->CaseMapping = casemapping;
#if defined _WIN32
		if (!FileSystem::StartsWithWindowsDriveLetter(charset))
			charset.insert(0, "./locales/");
#else
		if(charset[0] != '/')
			charset.insert(0, "../locales/");
#endif
		unsigned char * tables[8] = { m_additional, m_additionalMB, m_additionalUp, m_lower, m_upper, m_additionalUtf8, m_additionalUtf8range, m_additionalUtf8interval };
		if (!loadtables(charset, tables, 8, 5))
			throw ModuleException("The locale file failed to load. Check your log file for more information.");
		forcequit = tag->getBool("forcequit");
		CheckForceQuit("National character set changed");
		CheckRehash();
	}

	void CheckForceQuit(const char * message)
	{
		if (!forcequit)
			return;

		const UserManager::LocalList& list = ServerInstance->Users.GetLocalUsers();
		for (UserManager::LocalList::const_iterator iter = list.begin(); iter != list.end(); )
		{
			/* Fix by Brain: Dont quit UID users */
			// Quitting the user removes it from the list
			User* n = *iter;
			++iter;
			if (!isdigit(n->nick[0]) && !ServerInstance->IsNick(n->nick))
				ServerInstance->Users->QuitUser(n, message);
		}
	}

	~ModuleNationalChars()
	{
		ServerInstance->IsNick = rememberer;
		national_case_insensitive_map = lowermap_rememberer;
		ServerInstance->Config->CaseMapping = casemapping_rememberer;
		// The core rebuilds ISupport on module unload, but before the dtor.
		ServerInstance->ISupport.Build();
		CheckForceQuit("National characters module unloaded");
		CheckRehash();
	}

	Version GetVersion() CXX11_OVERRIDE
	{
		return Version("Provides an ability to have non-RFC1459 nicks & support for national CASEMAPPING", VF_VENDOR | VF_COMMON, charset);
	}

	/*make an array to check against it 8bit characters a bit faster. Whether allowed or uppercase (for your needs).*/
	void makereverse(unsigned char * from, unsigned  char * to, unsigned int cnt)
	{
		memset(to, 0, cnt);
		for(unsigned char * n=from; (*n) && ((*n)<cnt) && (n<from+cnt); n++)
			to[*n] = 1;
	}

	/*so Bynets Unreal distribution stuff*/
	bool loadtables(std::string filename, unsigned char ** tables, unsigned char cnt, char faillimit)
	{
		std::ifstream ifs(ServerInstance->Config->Paths.PrependConfig(filename).c_str());
		if (ifs.fail())
		{
			ServerInstance->Logs->Log(MODNAME, LOG_DEFAULT, "loadtables() called for missing file: %s", filename.c_str());
			return false;
		}

		for (unsigned char n=0; n< cnt; n++)
		{
			memset(tables[n], 0, 256);
		}

		memcpy(m_lower, rfc_case_insensitive_map, 256);

		for (unsigned char n = 0; n < cnt; n++)
		{
			if (loadtable(ifs, tables[n], 255) && (n < faillimit))
			{
				ServerInstance->Logs->Log(MODNAME, LOG_DEFAULT, "loadtables() called for illegal file: %s (line %d)", filename.c_str(), n+1);
				return false;
			}
		}

		makereverse(m_additional, m_reverse_additional, sizeof(m_additional));
		return true;
	}

	unsigned char symtoi(const char *t,unsigned char base)
	/* base = 16 for hexadecimal, 10 for decimal, 8 for octal ;) */
	{
		unsigned char tmp = 0, current;
		while ((*t) && (*t !=' ') && (*t != 13) && (*t != 10) && (*t != ','))
		{
			tmp *= base;
			current = ascii_case_insensitive_map[(unsigned char)*t];
			if (current >= 'a')
				current = current - 'a' + 10;
			else
				current = current - '0';
			tmp+=current;
			t++;
		}
		return tmp;
	}

	int loadtable(std::ifstream &ifs , unsigned char *chartable, unsigned int maxindex)
	{
		std::string buf;
		getline(ifs, buf);

		unsigned int i = 0;
		int fail = 0;

		buf.erase(buf.find_last_not_of("\n") + 1);

		if (buf[0] == '.')	/* simple plain-text string after dot */
		{
			i = buf.size() - 1;

			if (i > (maxindex + 1))
				i = maxindex + 1;

			memcpy(chartable, buf.c_str() + 1, i);
		}
		else
		{
			const char * p = buf.c_str();
			while (*p)
			{
				if (i > maxindex)
				{
					fail = 1;
					break;
				}

				if (*p != '\'')		/* decimal or hexadecimal char code */
				{
					if (*p == '0')
					{
						if (p[1] == 'x')
							 /* hex with the leading "0x" */
							chartable[i] = symtoi(p + 2, 16);
						else
							chartable[i] = symtoi(p + 1, 8);
					}
					/* hex form */
					else if (*p == 'x')
					{
						chartable[i] = symtoi(p + 1, 16);
					}else	 /* decimal form */
					{
						chartable[i] = symtoi(p, 10);
					}
				}
				else		 /* plain-text char between '' */
				{
					if (*(p + 1) == '\\')
					{
						chartable[i] = *(p + 2);
						p += 3;
					}else
					{
						chartable[i] = *(p + 1);
						p += 2;
					}
				}
				while (*p && (*p != ',') && (*p != ' ') && (*p != 13) && (*p != 10))
					p++;
				while (*p && ((*p == ',') || (*p == ' ') || (*p == 13) || (*p == 10)))
					p++;
				i++;
			}
		}
		return fail;
	}
};

MODULE_INIT(ModuleNationalChars)