summaryrefslogtreecommitdiffstats
path: root/tdespell2/plugins/ispell/ispell_checker.cpp
blob: 2bcf7ec92966f4c48bb5c24d5ec1ce868b66f04b (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
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
/* vim: set sw=8: -*- Mode: C++; tab-width: 8; indent-tabs-mode: t; c-basic-offset: 8 -*- */
/* tdespell2 - adopted from Enchant
 * Copyright (C) 2003 Dom Lachowicz
 * Copyright (C) 2004 Zack Rusin <zack@kde.org>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the
 * Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
 * Boston, MA 02110-1301, USA.
 *
 * In addition, as a special exception, Dom Lachowicz
 * gives permission to link the code of this program with
 * non-LGPL Spelling Provider libraries (eg: a MSFT Office
 * spell checker backend) and distribute linked combinations including
 * the two.  You must obey the GNU Lesser General Public License in all
 * respects for all of the code used other than said providers.  If you modify
 * this file, you may extend this exception to your version of the
 * file, but you are not obligated to do so.  If you do not wish to
 * do so, delete this exception statement from your version.
 */

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <string>
#include <vector>

#include "sp_spell.h"
#include "ispell_checker.h"

#include <tqmap.h>
#include <tqdir.h>
#include <tqfileinfo.h>

/***************************************************************************/

typedef struct str_ispell_map
{
	const char * lang;
	const char * dict;
	const char * enc;
} IspellMap;

static const char *ispell_dirs [] = {
	"/usr/lib/ispell",
	"/usr/local/lib/ispell",
	"/usr/local/share/ispell",
	"/usr/share/ispell",
	"/usr/pkg/lib",
	0
};
static const IspellMap ispell_map [] = {
	{"ca"    ,"catala.hash"         ,"iso-8859-1" },
	{"ca_ES" ,"catala.hash"         ,"iso-8859-1" },
	{"cs"    ,"czech.hash"          ,"iso-8859-2" },
	{"cs_CZ" ,"czech.hash"          ,"iso-8859-2" },
	{"da"    ,"dansk.hash"          ,"iso-8859-1" },
	{"da_DK" ,"dansk.hash"          ,"iso-8859-1" },
	{"de"    ,"deutsch.hash"        ,"iso-8859-1" },
	{"de_CH" ,"swiss.hash"          ,"iso-8859-1" },
	{"de_AT" ,"deutsch.hash"        ,"iso-8859-1" },
	{"de_DE" ,"deutsch.hash"        ,"iso-8859-1" },
	{"el"    ,"ellhnika.hash"       ,"iso-8859-7" },
	{"el_GR" ,"ellhnika.hash"       ,"iso-8859-7" },
	{"en"    ,"british.hash"        ,"iso-8859-1" },
	{"en_AU" ,"british.hash"        ,"iso-8859-1" },
	{"en_BZ" ,"british.hash"        ,"iso-8859-1" },
	{"en_CA" ,"british.hash"        ,"iso-8859-1" },
	{"en_GB" ,"british.hash"        ,"iso-8859-1" },
	{"en_IE" ,"british.hash"        ,"iso-8859-1" },
	{"en_JM" ,"british.hash"        ,"iso-8859-1" },
	{"en_NZ" ,"british.hash"        ,"iso-8859-1" },
	{"en_TT" ,"british.hash"        ,"iso-8859-1" },
	{"en_ZA" ,"british.hash"        ,"iso-8859-1" },
	{"en_ZW" ,"british.hash"        ,"iso-8859-1" },
	{"en_PH" ,"american.hash"       ,"iso-8859-1" },
	{"en_US" ,"american.hash"       ,"iso-8859-1" },
	{"eo"    ,"esperanto.hash"      ,"iso-8859-3" },
	{"es"    ,"espanol.hash"        ,"iso-8859-1" },
	{"es_AR" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_BO" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_CL" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_CO" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_CR" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_DO" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_EC" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_ES" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_GT" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_HN" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_MX" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_NI" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_PA" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_PE" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_PR" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_PY" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_SV" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_UY" ,"espanol.hash"        ,"iso-8859-1" },
	{"es_VE" ,"espanol.hash"        ,"iso-8859-1" },
	{"fi"    ,"finnish.hash"        ,"iso-8859-1" },
	{"fi_FI" ,"finnish.hash"        ,"iso-8859-1" },
	{"fr"    ,"francais.hash"       ,"iso-8859-1" },
	{"fr_BE" ,"francais.hash"       ,"iso-8859-1" },
	{"fr_CA" ,"francais.hash"       ,"iso-8859-1" },
	{"fr_CH" ,"francais.hash"       ,"iso-8859-1" },
	{"fr_FR" ,"francais.hash"       ,"iso-8859-1" },
	{"fr_LU" ,"francais.hash"       ,"iso-8859-1" },
	{"fr_MC" ,"francais.hash"       ,"iso-8859-1" },
	{"hu"    ,"hungarian.hash"      ,"iso-8859-2" },
	{"hu_HU" ,"hungarian.hash"      ,"iso-8859-2" },
	{"ga"    ,"irish.hash"          ,"iso-8859-1" },
	{"ga_IE" ,"irish.hash"          ,"iso-8859-1" },
	{"gl"    ,"galician.hash"       ,"iso-8859-1" },
	{"gl_ES" ,"galician.hash"       ,"iso-8859-1" },
	{"ia"    ,"interlingua.hash"    ,"iso-8859-1" },
	{"it"    ,"italian.hash"        ,"iso-8859-1" },
	{"it_IT" ,"italian.hash"        ,"iso-8859-1" },
	{"it_CH" ,"italian.hash"        ,"iso-8859-1" },
	{"la"    ,"mlatin.hash"         ,"iso-8859-1" },
	{"la_IT" ,"mlatin.hash"         ,"iso-8859-1" },
	{"lt"    ,"lietuviu.hash"       ,"iso-8859-13" },
	{"lt_LT" ,"lietuviu.hash"       ,"iso-8859-13" },
	{"nl"    ,"nederlands.hash"     ,"iso-8859-1" },
	{"nl_NL" ,"nederlands.hash"     ,"iso-8859-1" },
	{"nl_BE" ,"nederlands.hash"     ,"iso-8859-1" },
	{"nb"    ,"norsk.hash"          ,"iso-8859-1" },
	{"nb_NO" ,"norsk.hash"          ,"iso-8859-1" },
	{"nn"    ,"nynorsk.hash"        ,"iso-8859-1" },
	{"nn_NO" ,"nynorsk.hash"        ,"iso-8859-1" },
	{"no"    ,"norsk.hash"          ,"iso-8859-1" },
	{"no_NO" ,"norsk.hash"          ,"iso-8859-1" },
	{"pl"    ,"polish.hash"         ,"iso-8859-2" },
	{"pl_PL" ,"polish.hash"         ,"iso-8859-2" },
	{"pt"    ,"brazilian.hash"      ,"iso-8859-1" },
	{"pt_BR" ,"brazilian.hash"      ,"iso-8859-1" },
	{"pt_PT" ,"portugues.hash"      ,"iso-8859-1" },
	{"ru"    ,"russian.hash"        ,"koi8-r" },
	{"ru_MD" ,"russian.hash"        ,"koi8-r" },
	{"ru_RU" ,"russian.hash"        ,"koi8-r" },
	{"sc"    ,"sardinian.hash"      ,"iso-8859-1" },
	{"sc_IT" ,"sardinian.hash"      ,"iso-8859-1" },
	{"sk"    ,"slovak.hash"         ,"iso-8859-2" },
	{"sk_SK" ,"slovak.hash"         ,"iso-8859-2" },
	{"sl"    ,"slovensko.hash"      ,"iso-8859-2" },
	{"sl_SI" ,"slovensko.hash"      ,"iso-8859-2" },
	{"sv"    ,"svenska.hash"        ,"iso-8859-1" },
	{"sv_SE" ,"svenska.hash"        ,"iso-8859-1" },
	{"uk"    ,"ukrainian.hash"      ,"koi8-u" },
	{"uk_UA" ,"ukrainian.hash"      ,"koi8-u" },
	{"yi"    ,"yiddish-yivo.hash"   ,"utf-8" }
};

static const size_t size_ispell_map = ( sizeof(ispell_map) / sizeof((ispell_map)[0]) );
static TQMap<TQString, TQString> ispell_dict_map;


void
ISpellChecker::try_autodetect_charset(const char * const inEncoding)
{
	if (inEncoding && strlen(inEncoding))
		{
			m_translate_in = TQTextCodec::codecForName(inEncoding);
		}
}

/***************************************************************************/
/***************************************************************************/

ISpellChecker::ISpellChecker()
	: deftflag(-1),
     prefstringchar(-1),
     m_bSuccessfulInit(false),
     m_BC(NULL),
     m_cd(NULL),
     m_cl(NULL),
     m_cm(NULL),
     m_ho(NULL),
     m_nd(NULL),
     m_so(NULL),
     m_se(NULL),
     m_ti(NULL),
     m_te(NULL),
     m_hashstrings(NULL),
     m_hashtbl(NULL),
     m_pflaglist(NULL),
     m_sflaglist(NULL),
     m_chartypes(NULL),
     m_infile(NULL),
     m_outfile(NULL),
     m_astdefilename(NULL),
     m_Trynum(0),
     m_translate_in(0)
{
	memset(m_sflagindex,0,sizeof(m_sflagindex));
	memset(m_pflagindex,0,sizeof(m_pflagindex));
}

#ifndef FREEP
#define FREEP(p)        do { if (p) free(p); } while (0)
#endif

ISpellChecker::~ISpellChecker()
{
	if (m_bSuccessfulInit) {
		// only cleanup our mess if we were successfully initialized

		clearindex (m_pflagindex);
		clearindex (m_sflagindex);
	}

	FREEP(m_hashtbl);
	FREEP(m_hashstrings);
	FREEP(m_sflaglist);
	FREEP(m_chartypes);

	delete m_translate_in;
	m_translate_in = 0;
}

bool
ISpellChecker::checkWord( const TQString& utf8Word )
{
	ichar_t iWord[INPUTWORDLEN + MAXAFFIXLEN];
	if (!m_bSuccessfulInit)
		return false;

	if (!utf8Word || utf8Word.length() >= (INPUTWORDLEN + MAXAFFIXLEN) || utf8Word.isEmpty())
		return false;

	bool retVal = false;
	TQCString out;
	if (!m_translate_in)
		return false;
	else {
		/* convert to 8bit string and null terminate */
		int len_out = utf8Word.length();

		out = m_translate_in->fromUnicode( utf8Word, len_out );
	}

	if (!strtoichar(iWord, out.data(), INPUTWORDLEN + MAXAFFIXLEN, 0))
		{
			if (good(iWord, 0, 0, 1, 0) == 1 ||
			    compoundgood(iWord, 1) == 1)
				{
					retVal = true;
				}
		}

	return retVal;
}

TQStringList
ISpellChecker::suggestWord(const TQString& utf8Word)
{
	ichar_t  iWord[INPUTWORDLEN + MAXAFFIXLEN];
	int  c;

	if (!m_bSuccessfulInit)
		return TQStringList();

	if (utf8Word.isEmpty() || utf8Word.length() >= (INPUTWORDLEN + MAXAFFIXLEN) ||
			utf8Word.length() == 0)
		return TQStringList();

	TQCString out;
	if (!m_translate_in)
		return TQStringList();
	else
		{
			/* convert to 8bit string and null terminate */

			int len_out = utf8Word.length();
			out = m_translate_in->fromUnicode( utf8Word, len_out );
		}

	if (!strtoichar(iWord, out.data(), INPUTWORDLEN + MAXAFFIXLEN, 0))
		makepossibilities(iWord);
	else
		return TQStringList();

	TQStringList sugg_arr;
	for (c = 0; c < m_pcount; c++)
	{
		TQString utf8Word;

		if (!m_translate_in)
		{
			/* copy to 8bit string and null terminate */
			utf8Word = TQString::fromUtf8( m_possibilities[c] );
		}
		else
		{
			/* convert to 32bit string and null terminate */
			utf8Word = m_translate_in->toUnicode( m_possibilities[c] );
		}

		sugg_arr.append( utf8Word );
	}

	return sugg_arr;
}

static void
s_buildHashNames (std::vector<std::string> & names, const char * dict)
{
	const char * tmp = 0;
	int i = 0;

	names.clear ();

	while ( (tmp = ispell_dirs[i++]) ) {
		TQCString maybeFile = TQCString( tmp ) + '/';
		maybeFile += dict;
		names.push_back( maybeFile.data() );
	}
}

static void
s_allDics()
{
	const char * tmp = 0;
	int i = 0;

	while ( (tmp = ispell_dirs[i++]) ) {
		TQDir dir( tmp );
		TQStringList lst = dir.entryList( "*.hash" );
		for ( TQStringList::Iterator it = lst.begin(); it != lst.end(); ++it ) {
			TQFileInfo info( *it );
			for (size_t i = 0; i < size_ispell_map; i++)
			{
				const IspellMap * mapping = (const IspellMap *)(&(ispell_map[i]));
				if (!strcmp (info.fileName().latin1(), mapping->dict))
				{
					ispell_dict_map.insert( mapping->lang, *it );
				}
			}
		}
	}
}

TQValueList<TQString>
ISpellChecker::allDics()
{
	if ( ispell_dict_map.empty() )
		s_allDics();

	return ispell_dict_map.keys();
}

TQString
ISpellChecker::loadDictionary (const char * szdict)
{
	std::vector<std::string> dict_names;

	s_buildHashNames (dict_names, szdict);

	for (size_t i = 0; i < dict_names.size(); i++)
		{
			if (linit(const_cast<char*>(dict_names[i].c_str())) >= 0)
				return dict_names[i].c_str();
		}

	return TQString::null;
}

/*!
 * Load ispell dictionary hash file for given language.
 *
 * \param szLang -  The language tag ("en-US") we want to use
 * \return The name of the dictionary file
 */
bool
ISpellChecker::loadDictionaryForLanguage ( const char * szLang )
{
	TQString hashname;

	const char * encoding = NULL;
	const char * szFile = NULL;

	for (size_t i = 0; i < size_ispell_map; i++)
		{
			const IspellMap * mapping = (const IspellMap *)(&(ispell_map[i]));
			if (!strcmp (szLang, mapping->lang))
				{
					szFile = mapping->dict;
					encoding = mapping->enc;
					break;
				}
		}

	if (!szFile || !strlen(szFile))
		return false;

	alloc_ispell_struct();

	hashname = loadDictionary(szFile);
	if (hashname.isEmpty())
		return false;

	// one of the two above calls succeeded
	setDictionaryEncoding (hashname, encoding);

	return true;
}

void
ISpellChecker::setDictionaryEncoding( const TQString& hashname, const char * encoding )
{
	/* Get Hash encoding from XML file. This should always work! */
	try_autodetect_charset(encoding);

	if (m_translate_in)
		{
			/* We still have to setup prefstringchar*/
			prefstringchar = findfiletype("utf8", 1, deftflag < 0 ? &deftflag
						      : static_cast<int *>(NULL));

			if (prefstringchar < 0)
				{
					std::string teststring;
					for(int n1 = 1; n1 <= 15; n1++)
						{
							teststring = "latin" + n1;
							prefstringchar = findfiletype(teststring.c_str(), 1,
										      deftflag < 0 ? &deftflag : static_cast<int *>(NULL));
							if (prefstringchar >= 0)
								break;
						}
				}

			return; /* success */
		}

	/* Test for UTF-8 first */
	prefstringchar = findfiletype("utf8", 1, deftflag < 0 ? &deftflag : static_cast<int *>(NULL));
	if (prefstringchar >= 0)
		{
			m_translate_in = TQTextCodec::codecForName("utf8");
		}

	if (m_translate_in)
		return; /* success */

	/* Test for "latinN" */
	if (!m_translate_in)
		{
			/* Look for "altstringtype" names from latin1 to latin15 */
			for(int n1 = 1; n1 <= 15; n1++)
				{
					TQString teststring = TQString("latin%1").arg(n1);
					prefstringchar = findfiletype(teststring.latin1(), 1,
								      deftflag < 0 ? &deftflag : static_cast<int *>(NULL));
					if (prefstringchar >= 0)
						{
							//FIXME: latin1 might be wrong
							m_translate_in = TQTextCodec::codecForName( teststring.latin1() );
							break;
						}
				}
		}

	/* If nothing found, use latin1 */
	if (!m_translate_in)
		{
			m_translate_in = TQTextCodec::codecForName("latin1");
		}
}

bool
ISpellChecker::requestDictionary(const char *szLang)
{
	if (!loadDictionaryForLanguage (szLang))
		{
			// handle a shortened version of the language tag: en_US => en
			std::string shortened_dict (szLang);
			size_t uscore_pos;

			if ((uscore_pos = shortened_dict.rfind ('_')) != ((size_t)-1)) {
				shortened_dict = shortened_dict.substr(0, uscore_pos);
				if (!loadDictionaryForLanguage (shortened_dict.c_str()))
					return false;
			} else
				return false;
		}

	m_bSuccessfulInit = true;

	if (prefstringchar < 0)
		m_defdupchar = 0;
	else
		m_defdupchar = prefstringchar;

	return true;
}