summaryrefslogtreecommitdiff
path: root/i18npool/source/breakiterator/breakiterator_unicode.cxx
blob: 34e6918f51827d2b7f76b02963dcf4612b5ba95c (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
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*************************************************************************
 *
 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
 *
 * Copyright 2000, 2010 Oracle and/or its affiliates.
 *
 * OpenOffice.org - a multi-platform office productivity suite
 *
 * This file is part of OpenOffice.org.
 *
 * OpenOffice.org is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Lesser General Public License version 3
 * only, as published by the Free Software Foundation.
 *
 * OpenOffice.org 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 version 3 for more details
 * (a copy is included in the LICENSE file that accompanied this code).
 *
 * You should have received a copy of the GNU Lesser General Public License
 * version 3 along with OpenOffice.org.  If not, see
 * <http://www.openoffice.org/license.html>
 * for a copy of the LGPLv3 License.
 *
 ************************************************************************/

#include <breakiterator_unicode.hxx>
#include <localedata.hxx>
#include <unicode/uchar.h>
#include <unicode/locid.h>
#include <unicode/rbbi.h>
#include <unicode/udata.h>
#include <rtl/strbuf.hxx>
#include <rtl/ustring.hxx>
#include <string.h>

U_CDECL_BEGIN
extern const char OpenOffice_dat[];
U_CDECL_END

using namespace ::com::sun::star;
using namespace ::com::sun::star::lang;
using namespace ::rtl;

namespace com { namespace sun { namespace star { namespace i18n {

#define ERROR ::com::sun::star::uno::RuntimeException()

//#define ImplementName "com.sun.star.i18n.BreakIterator_Unicode";


BreakIterator_Unicode::BreakIterator_Unicode() :
    cBreakIterator( "com.sun.star.i18n.BreakIterator_Unicode" ),    // implementation name
    wordRule( "word" ),
    lineRule( "line" ),
    result(),
    character(),
    word(),
    sentence(),
    line(),
    icuBI( NULL ),
    aLocale(),
    aBreakType(),
    aWordType()
{
}


BreakIterator_Unicode::~BreakIterator_Unicode()
{
        if (icuBI && icuBI->aBreakIterator) {
            delete icuBI->aBreakIterator;
            icuBI->aBreakIterator=NULL;
        }
        if (character.aBreakIterator) delete character.aBreakIterator;
        if (word.aBreakIterator) delete word.aBreakIterator;
        if (sentence.aBreakIterator) delete sentence.aBreakIterator;
        if (line.aBreakIterator) delete line.aBreakIterator;
}

/*
    Wrapper class to provide public access to the RuleBasedBreakIterator's
    setbreakType method.
*/
class OOoRuleBasedBreakIterator : public RuleBasedBreakIterator {
    public:
        inline void publicSetBreakType(int32_t type) {
            setBreakType(type);
        };
        OOoRuleBasedBreakIterator(UDataMemory* image,
                UErrorCode &status) :
            RuleBasedBreakIterator(image, status) { };

};

// loading ICU breakiterator on demand.
void SAL_CALL BreakIterator_Unicode::loadICUBreakIterator(const com::sun::star::lang::Locale& rLocale,
        sal_Int16 rBreakType, sal_Int16 rWordType, const sal_Char *rule, const OUString& rText) throw(uno::RuntimeException)
{
    sal_Bool newBreak = sal_False;
    UErrorCode status = U_ZERO_ERROR;
    sal_Int16 breakType = 0;
    switch (rBreakType) {
        case LOAD_CHARACTER_BREAKITERATOR: icuBI=&character; breakType = 3; break;
        case LOAD_WORD_BREAKITERATOR: icuBI=&word;
            switch (rWordType) {
                case WordType::ANYWORD_IGNOREWHITESPACES: breakType = 0; rule=wordRule = "edit_word"; break;
                case WordType::DICTIONARY_WORD: breakType = 1; rule=wordRule = "dict_word"; break;
                case WordType::WORD_COUNT: breakType = 2; rule=wordRule = "count_word"; break;
            }
            break;
        case LOAD_SENTENCE_BREAKITERATOR: icuBI=&sentence; breakType = 5; break;
        case LOAD_LINE_BREAKITERATOR: icuBI=&line; breakType = 4; break;
    }
    if (!icuBI->aBreakIterator || rWordType != aWordType ||
            rLocale.Language != aLocale.Language || rLocale.Country != aLocale.Country ||
            rLocale.Variant != aLocale.Variant) {
        if (icuBI->aBreakIterator) {
            delete icuBI->aBreakIterator;
            icuBI->aBreakIterator=NULL;
        }
        if (rule) {
            uno::Sequence< OUString > breakRules = LocaleData().getBreakIteratorRules(rLocale);

            status = U_ZERO_ERROR;
            udata_setAppData("OpenOffice", OpenOffice_dat, &status);
            if ( !U_SUCCESS(status) ) throw ERROR;

            OOoRuleBasedBreakIterator *rbi = NULL;

            if (breakRules.getLength() > breakType && !breakRules[breakType].isEmpty())
            {
                rbi = new OOoRuleBasedBreakIterator(udata_open("OpenOffice", "brk",
                    OUStringToOString(breakRules[breakType], RTL_TEXTENCODING_ASCII_US).getStr(), &status), status);
            }
            else if ( rLocale.Language != "th" ) //use icu's breakiterator for Thai
            {
                status = U_ZERO_ERROR;
                OStringBuffer aUDName(64);
                aUDName.append(rule);
                aUDName.append('_');
                aUDName.append( OUStringToOString(rLocale.Language, RTL_TEXTENCODING_ASCII_US));
                UDataMemory* pUData = udata_open("OpenOffice", "brk", aUDName.getStr(), &status);
                if( U_SUCCESS(status) )
                    rbi = new OOoRuleBasedBreakIterator( pUData, status);
                if (!U_SUCCESS(status) ) {
                    status = U_ZERO_ERROR;
                    pUData = udata_open("OpenOffice", "brk", rule, &status);
                    if( U_SUCCESS(status) )
                        rbi = new OOoRuleBasedBreakIterator( pUData, status);
                    if (!U_SUCCESS(status) ) icuBI->aBreakIterator=NULL;
                }
            }
            if (rbi) {
                switch (rBreakType) {
                    case LOAD_CHARACTER_BREAKITERATOR: rbi->publicSetBreakType(UBRK_CHARACTER); break;
                    case LOAD_WORD_BREAKITERATOR: rbi->publicSetBreakType(UBRK_WORD); break;
                    case LOAD_SENTENCE_BREAKITERATOR: rbi->publicSetBreakType(UBRK_SENTENCE); break;
                    case LOAD_LINE_BREAKITERATOR: rbi->publicSetBreakType(UBRK_LINE); break;
                }
                icuBI->aBreakIterator = rbi;
            }
        }

        if (!icuBI->aBreakIterator) {
            icu::Locale icuLocale(
                    OUStringToOString(rLocale.Language, RTL_TEXTENCODING_ASCII_US).getStr(),
                    OUStringToOString(rLocale.Country, RTL_TEXTENCODING_ASCII_US).getStr(),
                    OUStringToOString(rLocale.Variant, RTL_TEXTENCODING_ASCII_US).getStr());

            status = U_ZERO_ERROR;
            switch (rBreakType) {
                case LOAD_CHARACTER_BREAKITERATOR:
                    icuBI->aBreakIterator =  icu::BreakIterator::createCharacterInstance(icuLocale, status);
                    break;
                case LOAD_WORD_BREAKITERATOR:
                    icuBI->aBreakIterator =  icu::BreakIterator::createWordInstance(icuLocale, status);
                    break;
                case LOAD_SENTENCE_BREAKITERATOR:
                    icuBI->aBreakIterator = icu::BreakIterator::createSentenceInstance(icuLocale, status);
                    break;
                case LOAD_LINE_BREAKITERATOR:
                    icuBI->aBreakIterator = icu::BreakIterator::createLineInstance(icuLocale, status);
                    break;
            }
            if ( !U_SUCCESS(status) ) {
                icuBI->aBreakIterator=NULL;
                throw ERROR;
            }
        }
        if (icuBI->aBreakIterator) {
            aLocale=rLocale;
            aWordType=rWordType;
            aBreakType=rBreakType;
            newBreak=sal_True;
        } else {
            throw ERROR;
        }
    }

    if (newBreak || !icuBI->aICUText.equals(rText))
    {
        // UChar != sal_Unicode in MinGW
        const UChar *pText = reinterpret_cast<const UChar *>(rText.getStr());

        icuBI->ut = utext_openUChars(icuBI->ut, pText, rText.getLength(), &status);

        if (!U_SUCCESS(status))
            throw ERROR;

        icuBI->aBreakIterator->setText(icuBI->ut, status);

        if (!U_SUCCESS(status))
            throw ERROR;

        icuBI->aICUText = rText;
    }
}

sal_Int32 SAL_CALL BreakIterator_Unicode::nextCharacters( const OUString& Text,
        sal_Int32 nStartPos, const lang::Locale &rLocale,
        sal_Int16 nCharacterIteratorMode, sal_Int32 nCount, sal_Int32& nDone )
        throw(uno::RuntimeException)
{
        if (nCharacterIteratorMode == CharacterIteratorMode::SKIPCELL ) { // for CELL mode
            loadICUBreakIterator(rLocale, LOAD_CHARACTER_BREAKITERATOR, 0, "char", Text);
            for (nDone = 0; nDone < nCount; nDone++) {
                nStartPos = character.aBreakIterator->following(nStartPos);
                if (nStartPos == BreakIterator::DONE)
                    return Text.getLength();
            }
        } else { // for CHARACTER mode
            for (nDone = 0; nDone < nCount && nStartPos < Text.getLength(); nDone++)
                Text.iterateCodePoints(&nStartPos, 1);
        }
        return nStartPos;
}

sal_Int32 SAL_CALL BreakIterator_Unicode::previousCharacters( const OUString& Text,
        sal_Int32 nStartPos, const lang::Locale& rLocale,
        sal_Int16 nCharacterIteratorMode, sal_Int32 nCount, sal_Int32& nDone )
        throw(uno::RuntimeException)
{
        if (nCharacterIteratorMode == CharacterIteratorMode::SKIPCELL ) { // for CELL mode
            loadICUBreakIterator(rLocale, LOAD_CHARACTER_BREAKITERATOR, 0, "char", Text);
            for (nDone = 0; nDone < nCount; nDone++) {
                nStartPos = character.aBreakIterator->preceding(nStartPos);
                if (nStartPos == BreakIterator::DONE)
                    return 0;
            }
        } else { // for BS to delete one char and CHARACTER mode.
            for (nDone = 0; nDone < nCount && nStartPos > 0; nDone++)
                Text.iterateCodePoints(&nStartPos, -1);
        }
        return nStartPos;
}


Boundary SAL_CALL BreakIterator_Unicode::nextWord( const OUString& Text, sal_Int32 nStartPos,
    const lang::Locale& rLocale, sal_Int16 rWordType ) throw(uno::RuntimeException)
{
        loadICUBreakIterator(rLocale, LOAD_WORD_BREAKITERATOR, rWordType, NULL, Text);

        result.startPos = word.aBreakIterator->following(nStartPos);
        if( result.startPos >= Text.getLength() || result.startPos == BreakIterator::DONE )
            result.endPos = result.startPos;
        else {
            if ( (rWordType == WordType::ANYWORD_IGNOREWHITESPACES ||
                    rWordType == WordType::DICTIONARY_WORD ) &&
                        u_isWhitespace(Text.iterateCodePoints(&result.startPos, 0)) )
                result.startPos = word.aBreakIterator->following(result.startPos);

            result.endPos = word.aBreakIterator->following(result.startPos);
            if(result.endPos == BreakIterator::DONE)
                result.endPos = result.startPos;
        }
        return result;
}


Boundary SAL_CALL BreakIterator_Unicode::previousWord(const OUString& Text, sal_Int32 nStartPos,
        const lang::Locale& rLocale, sal_Int16 rWordType) throw(uno::RuntimeException)
{
        loadICUBreakIterator(rLocale, LOAD_WORD_BREAKITERATOR, rWordType, NULL, Text);

        result.startPos = word.aBreakIterator->preceding(nStartPos);
        if( result.startPos < 0 || result.startPos == BreakIterator::DONE)
            result.endPos = result.startPos;
        else {
            if ( (rWordType == WordType::ANYWORD_IGNOREWHITESPACES ||
                    rWordType == WordType::DICTIONARY_WORD) &&
                        u_isWhitespace(Text.iterateCodePoints(&result.startPos, 0)) )
                result.startPos = word.aBreakIterator->preceding(result.startPos);

            result.endPos = word.aBreakIterator->following(result.startPos);
            if(result.endPos == BreakIterator::DONE)
                result.endPos = result.startPos;
        }
        return result;
}


Boundary SAL_CALL BreakIterator_Unicode::getWordBoundary( const OUString& Text, sal_Int32 nPos, const lang::Locale& rLocale,
        sal_Int16 rWordType, sal_Bool bDirection ) throw(uno::RuntimeException)
{
        loadICUBreakIterator(rLocale, LOAD_WORD_BREAKITERATOR, rWordType, NULL, Text);
        sal_Int32 len = Text.getLength();

        if(word.aBreakIterator->isBoundary(nPos)) {
            result.startPos = result.endPos = nPos;
            if((bDirection || nPos == 0) && nPos < len) //forward
                result.endPos = word.aBreakIterator->following(nPos);
            else
                result.startPos = word.aBreakIterator->preceding(nPos);
        } else {
            if(nPos <= 0) {
                result.startPos = 0;
                result.endPos = len ? word.aBreakIterator->following((sal_Int32)0) : 0;
            } else if(nPos >= len) {
                result.startPos = word.aBreakIterator->preceding(len);
                result.endPos = len;
            } else {
                result.startPos = word.aBreakIterator->preceding(nPos);
                result.endPos = word.aBreakIterator->following(nPos);
            }
        }
        if (result.startPos == BreakIterator::DONE)
            result.startPos = result.endPos;
        else if (result.endPos == BreakIterator::DONE)
            result.endPos = result.startPos;

        return result;
}


sal_Int32 SAL_CALL BreakIterator_Unicode::beginOfSentence( const OUString& Text, sal_Int32 nStartPos,
        const lang::Locale &rLocale ) throw(uno::RuntimeException)
{
        loadICUBreakIterator(rLocale, LOAD_SENTENCE_BREAKITERATOR, 0, "sent", Text);

        sal_Int32 len = Text.getLength();
        if (len > 0 && nStartPos == len)
            Text.iterateCodePoints(&nStartPos, -1); // issue #i27703# treat end position as part of last sentence
        if (!sentence.aBreakIterator->isBoundary(nStartPos))
            nStartPos = sentence.aBreakIterator->preceding(nStartPos);

        // skip preceding space.
        sal_uInt32 ch = Text.iterateCodePoints(&nStartPos, 1);
        while (nStartPos < len && u_isWhitespace(ch)) ch = Text.iterateCodePoints(&nStartPos, 1);
        Text.iterateCodePoints(&nStartPos, -1);

        return nStartPos;
}

sal_Int32 SAL_CALL BreakIterator_Unicode::endOfSentence( const OUString& Text, sal_Int32 nStartPos,
        const lang::Locale &rLocale ) throw(uno::RuntimeException)
{
        loadICUBreakIterator(rLocale, LOAD_SENTENCE_BREAKITERATOR, 0, "sent", Text);

        sal_Int32 len = Text.getLength();
        if (len > 0 && nStartPos == len)
            Text.iterateCodePoints(&nStartPos, -1); // issue #i27703# treat end position as part of last sentence
        nStartPos = sentence.aBreakIterator->following(nStartPos);

        sal_Int32 nPos=nStartPos;
        while (nPos > 0 && u_isWhitespace(Text.iterateCodePoints(&nPos, -1))) nStartPos=nPos;

        return nStartPos;
}

LineBreakResults SAL_CALL BreakIterator_Unicode::getLineBreak(
        const OUString& Text, sal_Int32 nStartPos,
        const lang::Locale& rLocale, sal_Int32 nMinBreakPos,
        const LineBreakHyphenationOptions& hOptions,
        const LineBreakUserOptions& /*rOptions*/ ) throw(uno::RuntimeException)
{
        LineBreakResults lbr;

        if (nStartPos >= Text.getLength()) {
            lbr.breakIndex = Text.getLength();
            lbr.breakType = BreakType::WORDBOUNDARY;
            return lbr;
        }

        loadICUBreakIterator(rLocale, LOAD_LINE_BREAKITERATOR, 0, lineRule, Text);

        sal_Bool GlueSpace=sal_True;
        while (GlueSpace) {
            if (line.aBreakIterator->preceding(nStartPos + 1) == nStartPos) { //Line boundary break
                lbr.breakIndex = nStartPos;
                lbr.breakType = BreakType::WORDBOUNDARY;
            } else if (hOptions.rHyphenator.is()) { //Hyphenation break
                Boundary wBoundary = getWordBoundary( Text, nStartPos, rLocale,
                                                WordType::DICTIONARY_WORD, false);
                uno::Reference< linguistic2::XHyphenatedWord > aHyphenatedWord;
                aHyphenatedWord = hOptions.rHyphenator->hyphenate(Text.copy(wBoundary.startPos,
                    wBoundary.endPos - wBoundary.startPos), rLocale,
                    (sal_Int16) (hOptions.hyphenIndex - wBoundary.startPos), hOptions.aHyphenationOptions);
                if (aHyphenatedWord.is()) {
                    lbr.rHyphenatedWord = aHyphenatedWord;
                    if(wBoundary.startPos + aHyphenatedWord->getHyphenationPos() + 1 < nMinBreakPos )
                        lbr.breakIndex = -1;
                    else
                        lbr.breakIndex = wBoundary.startPos; //aHyphenatedWord->getHyphenationPos();
                    lbr.breakType = BreakType::HYPHENATION;
                } else {
                    lbr.breakIndex = line.aBreakIterator->preceding(nStartPos);
                    lbr.breakType = BreakType::WORDBOUNDARY;;
                }
            } else { //word boundary break
                lbr.breakIndex = line.aBreakIterator->preceding(nStartPos);
                lbr.breakType = BreakType::WORDBOUNDARY;
            }

#define WJ 0x2060   // Word Joiner
            GlueSpace=sal_False;
            if (lbr.breakType == BreakType::WORDBOUNDARY) {
                nStartPos = lbr.breakIndex;
                if (Text[nStartPos--] == WJ)
                    GlueSpace=sal_True;
                while (nStartPos >= 0 &&
                    (u_isWhitespace(Text.iterateCodePoints(&nStartPos, 0)) || Text[nStartPos] == WJ)) {
                    if (Text[nStartPos--] == WJ)
                        GlueSpace=sal_True;
                }
                if (GlueSpace && nStartPos < 0)  {
                    lbr.breakIndex = 0;
                    break;
                }
            }
        }

        return lbr;
}



OUString SAL_CALL
BreakIterator_Unicode::getImplementationName(void) throw( uno::RuntimeException )
{
        return OUString::createFromAscii(cBreakIterator);
}

sal_Bool SAL_CALL
BreakIterator_Unicode::supportsService(const OUString& rServiceName) throw( uno::RuntimeException )
{
        return !rServiceName.compareToAscii(cBreakIterator);
}

uno::Sequence< OUString > SAL_CALL
BreakIterator_Unicode::getSupportedServiceNames(void) throw( uno::RuntimeException )
{
        uno::Sequence< OUString > aRet(1);
        aRet[0] = OUString::createFromAscii(cBreakIterator);
        return aRet;
}

} } } }

/* vim:set shiftwidth=4 softtabstop=4 expandtab: */