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
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
|
/* -*- Mode: C++; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 4 -*- */
/*
* Version: MPL 1.1 / GPLv3+ / LGPLv3+
*
* The contents of this file are subject to the Mozilla Public License Version
* 1.1 (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
* http://www.mozilla.org/MPL/
*
* Software distributed under the License is distributed on an "AS IS" basis,
* WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
* for the specific language governing rights and limitations under the
* License.
*
* The Initial Developer of the Original Code is
* Caolán McNamara <caolanm@redhat.com>
*
* Contributor(s):
* Caolán McNamara <caolanm@redhat.com>
*
* Alternatively, the contents of this file may be used under the terms of
* either the GNU General Public License Version 3 or later (the "GPLv3+"), or
* the GNU Lesser General Public License Version 3 or later (the "LGPLv3+"),
* in which case the provisions of the GPLv3+ or the LGPLv3+ are applicable
* instead of those above.
*/
#ifdef IOS
#define CPPUNIT_PLUGIN_EXPORTED_NAME cppunitTest_i18npool_breakiterator
#endif
#include <cppuhelper/compbase1.hxx>
#include <cppuhelper/bootstrap.hxx>
#include <cppuhelper/basemutex.hxx>
#include <com/sun/star/i18n/XBreakIterator.hpp>
#include <com/sun/star/i18n/CharacterIteratorMode.hpp>
#include <com/sun/star/i18n/ScriptType.hpp>
#include <com/sun/star/i18n/WordType.hpp>
#include <unotest/bootstrapfixturebase.hxx>
#include <unicode/uvernum.h>
#include <rtl/strbuf.hxx>
#include <rtl/ustrbuf.hxx>
#include <string.h>
using namespace ::com::sun::star;
class TestBreakIterator : public test::BootstrapFixtureBase
{
public:
virtual void setUp();
virtual void tearDown();
void testLineBreaking();
void testWordBoundaries();
void testGraphemeIteration();
void testWeak();
void testAsian();
void testThai();
#if TODO
void testNorthernThai();
#endif
#if (U_ICU_VERSION_MAJOR_NUM > 4)
void testKhmer();
#endif
CPPUNIT_TEST_SUITE(TestBreakIterator);
CPPUNIT_TEST(testLineBreaking);
CPPUNIT_TEST(testWordBoundaries);
CPPUNIT_TEST(testGraphemeIteration);
CPPUNIT_TEST(testWeak);
CPPUNIT_TEST(testAsian);
CPPUNIT_TEST(testThai);
#if TODO
CPPUNIT_TEST(testNorthernThai);
#endif
#if (U_ICU_VERSION_MAJOR_NUM > 4)
CPPUNIT_TEST(testKhmer);
#endif
CPPUNIT_TEST_SUITE_END();
private:
uno::Reference<i18n::XBreakIterator> m_xBreak;
};
void TestBreakIterator::testLineBreaking()
{
i18n::LineBreakHyphenationOptions aHyphOptions;
i18n::LineBreakUserOptions aUserOptions;
lang::Locale aLocale;
//See https://bugs.freedesktop.org/show_bug.cgi?id=31271
{
::rtl::OUString aTest(RTL_CONSTASCII_USTRINGPARAM("(some text here)"));
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
{
//Here we want the line break to leave text here) on the next line
i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, strlen("(some tex"), aLocale, 0, aHyphOptions, aUserOptions);
CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 6);
}
{
//Here we want the line break to leave "here)" on the next line
i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, strlen("(some text here"), aLocale, 0, aHyphOptions, aUserOptions);
CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == 11);
}
}
//See https://bugs.freedesktop.org/show_bug.cgi?id=49849
{
const sal_Unicode HEBREW1[] = { 0x05DE, 0x05D9, 0x05DC, 0x05D9, 0x5DD };
::rtl::OUString aWord(HEBREW1, SAL_N_ELEMENTS(HEBREW1));
::rtl::OUString aTest(rtl::OUStringBuffer(aWord).append(' ').append(aWord).makeStringAndClear());
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("he"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("IL"));
{
//Here we want the line break to happen at the whitespace
i18n::LineBreakResults aResult = m_xBreak->getLineBreak(aTest, aTest.getLength()-1, aLocale, 0, aHyphOptions, aUserOptions);
CPPUNIT_ASSERT_MESSAGE("Expected a break at the the start of the word", aResult.breakIndex == aWord.getLength()+1);
}
}
}
//See https://bugs.freedesktop.org/show_bug.cgi?id=49629
void TestBreakIterator::testWordBoundaries()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
i18n::Boundary aBounds;
//See https://issues.apache.org/ooo/show_bug.cgi?id=11993
{
::rtl::OUString aTest("abcd ef ghi??? KLM");
CPPUNIT_ASSERT(!m_xBreak->isBeginWord(aTest, 4, aLocale, i18n::WordType::DICTIONARY_WORD));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 4, aLocale, i18n::WordType::DICTIONARY_WORD));
aBounds = m_xBreak->getWordBoundary(aTest, 4, aLocale, i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 4);
CPPUNIT_ASSERT(!m_xBreak->isBeginWord(aTest, 8, aLocale, i18n::WordType::DICTIONARY_WORD));
CPPUNIT_ASSERT(!m_xBreak->isEndWord(aTest, 8, aLocale, i18n::WordType::DICTIONARY_WORD));
//next word
aBounds = m_xBreak->getWordBoundary(aTest, 8, aLocale, i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 9 && aBounds.endPos == 12);
//previous word
aBounds = m_xBreak->getWordBoundary(aTest, 8, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 5 && aBounds.endPos == 7);
CPPUNIT_ASSERT(!m_xBreak->isBeginWord(aTest, 12, aLocale, i18n::WordType::DICTIONARY_WORD));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 12, aLocale, i18n::WordType::DICTIONARY_WORD));
aBounds = m_xBreak->getWordBoundary(aTest, 12, aLocale, i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 9 && aBounds.endPos == 12);
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, 16, aLocale, i18n::WordType::DICTIONARY_WORD));
CPPUNIT_ASSERT(!m_xBreak->isEndWord(aTest, 16, aLocale, i18n::WordType::DICTIONARY_WORD));
aBounds = m_xBreak->getWordBoundary(aTest, 16, aLocale, i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 16 && aBounds.endPos == 19);
}
//See https://issues.apache.org/ooo/show_bug.cgi?id=21907
{
::rtl::OUString aTest("b a?");
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, 1, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, 2, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, 3, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, 3, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 1, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 2, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 3, aLocale, i18n::WordType::ANY_WORD));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, 3, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES));
}
//See https://issues.apache.org/ooo/show_bug.cgi?id=14904
{
const sal_Unicode TEST1[] =
{
'W', 'o', 'r', 'k', 'i', 'n', 'g', ' ', 0x201C, 'W', 'o', 'r', 'd', 's',
' ', 's', 't', 'a', 'r', 't', 'i', 'n', 'g', ' ', 'w', 'i', 't',
'h', ' ', 'q', 'u', 'o', 't', 'e', 's', 0x201D, ' ', 'W', 'o', 'r', 'k',
'i', 'n', 'g', ' ', 0x2018, 'B', 'r', 'o', 'k', 'e', 'n', 0x2019, ' ',
'?', 'S', 'p', 'a', 'n', 'i', 's', 'h', '?', ' ', 'd', 'o', 'e',
's', 'n', 0x2019, 't', ' ', 'w', 'o', 'r', 'k', '.', ' ', 'N', 'o',
't', ' ', 'e', 'v', 'e', 'n', ' ' , 0x00BF, 'r', 'e', 'a', 'l', '?', ' ',
'S', 'p', 'a', 'n', 'i', 's', 'h'
};
::rtl::OUString aTest(TEST1, SAL_N_ELEMENTS(TEST1));
aBounds = m_xBreak->getWordBoundary(aTest, 4, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 7);
aBounds = m_xBreak->getWordBoundary(aTest, 12, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 9 && aBounds.endPos == 14);
aBounds = m_xBreak->getWordBoundary(aTest, 40, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 37 && aBounds.endPos == 44);
aBounds = m_xBreak->getWordBoundary(aTest, 49, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 46 && aBounds.endPos == 52);
aBounds = m_xBreak->getWordBoundary(aTest, 58, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 55 && aBounds.endPos == 62);
aBounds = m_xBreak->getWordBoundary(aTest, 67, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 64 && aBounds.endPos == 71);
aBounds = m_xBreak->getWordBoundary(aTest, 90, aLocale, i18n::WordType::DICTIONARY_WORD, false);
CPPUNIT_ASSERT(aBounds.startPos == 88 && aBounds.endPos == 92);
}
//See https://bugs.freedesktop.org/show_bug.cgi?id=49629
sal_Unicode aBreakTests[] = { ' ', 1, 2, 3, 4, 5, 6, 7, 0x91, 0x92, 0x200B, 0xE8FF, 0xF8FF };
for (int mode = i18n::WordType::ANY_WORD; mode <= i18n::WordType::WORD_COUNT; ++mode)
{
//make sure that in all cases isBeginWord and isEndWord matches getWordBoundary
for (size_t i = 0; i < SAL_N_ELEMENTS(aBreakTests); ++i)
{
::rtl::OUString aTest("Word");
aTest += rtl::OUString(aBreakTests[i]) + rtl::OUString("Word");
aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale, mode, true);
switch (mode)
{
case i18n::WordType::ANY_WORD:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 4);
break;
case i18n::WordType::ANYWORD_IGNOREWHITESPACES:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 4);
break;
case i18n::WordType::DICTIONARY_WORD:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 4);
break;
case i18n::WordType::WORD_COUNT:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 4);
break;
}
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, aBounds.startPos, aLocale, mode));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, aBounds.endPos, aLocale, mode));
}
}
sal_Unicode aJoinTests[] = { 'X', 0x200C, 0x200D, 0x2060, 0xFEFF, 0xFFF9, 0xFFFA, 0xFFFB };
for (int mode = i18n::WordType::ANY_WORD; mode <= i18n::WordType::WORD_COUNT; ++mode)
{
//make sure that in all cases isBeginWord and isEndWord matches getWordBoundary
for (size_t i = 0; i < SAL_N_ELEMENTS(aJoinTests); ++i)
{
::rtl::OUString aTest("Word");
aTest += rtl::OUString(aJoinTests[i]) + rtl::OUString("Word");
aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale, mode, true);
switch (mode)
{
case i18n::WordType::ANY_WORD:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 9);
break;
case i18n::WordType::ANYWORD_IGNOREWHITESPACES:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 9);
break;
case i18n::WordType::DICTIONARY_WORD:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 9);
break;
case i18n::WordType::WORD_COUNT:
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 9);
break;
}
CPPUNIT_ASSERT(m_xBreak->isBeginWord(aTest, aBounds.startPos, aLocale, mode));
CPPUNIT_ASSERT(m_xBreak->isEndWord(aTest, aBounds.endPos, aLocale, mode));
}
}
//See https://issues.apache.org/ooo/show_bug.cgi?id=13494
{
const rtl::OUString aBase("xxAAxxBBxxCCxx");
const sal_Unicode aTests[] =
{
'\'', ';', ',', '.', '!', '@', '#', '%', '&', '*',
'(', ')', '_', '-', '{', '}', '[', ']', '\"', '/',
'\\', '?', '~', '$', '+', '^', '=', '<', '>', '|'
};
const sal_Int32 aDoublePositions[] = {0, 2, 4, 6, 8, 10, 12, 14};
for (size_t j = 0; j < SAL_N_ELEMENTS(aTests); ++j)
{
rtl::OUString aTest = aBase.replace('x', aTests[j]);
sal_Int32 nPos = -1;
size_t i = 0;
do
{
CPPUNIT_ASSERT(i < SAL_N_ELEMENTS(aDoublePositions));
nPos = m_xBreak->nextWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aDoublePositions[i++]);
}
while (nPos < aTest.getLength());
nPos = aTest.getLength();
i = SAL_N_ELEMENTS(aDoublePositions)-1;
do
{
nPos = m_xBreak->previousWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aDoublePositions[--i]);
}
while (nPos > 0);
}
const sal_Int32 aSinglePositions[] = {0, 1, 3, 4, 6, 7, 9, 10};
for (size_t j = 1; j < SAL_N_ELEMENTS(aTests); ++j)
{
rtl::OUString aTest = aBase.replaceAll(rtl::OUString("xx"), rtl::OUString(aTests[j]));
sal_Int32 nPos = -1;
size_t i = 0;
do
{
CPPUNIT_ASSERT(i < SAL_N_ELEMENTS(aSinglePositions));
nPos = m_xBreak->nextWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aSinglePositions[i++]);
}
while (nPos < aTest.getLength());
nPos = aTest.getLength();
i = SAL_N_ELEMENTS(aSinglePositions)-1;
do
{
nPos = m_xBreak->previousWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aSinglePositions[--i]);
}
while (nPos > 0);
}
const sal_Int32 aSingleQuotePositions[] = {0, 1, 9, 10};
CPPUNIT_ASSERT(aTests[0] == '\'');
{
rtl::OUString aTest = aBase.replaceAll(rtl::OUString("xx"), rtl::OUString(aTests[0]));
sal_Int32 nPos = -1;
size_t i = 0;
do
{
CPPUNIT_ASSERT(i < SAL_N_ELEMENTS(aSingleQuotePositions));
nPos = m_xBreak->nextWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aSingleQuotePositions[i++]);
}
while (nPos < aTest.getLength());
nPos = aTest.getLength();
i = SAL_N_ELEMENTS(aSingleQuotePositions)-1;
do
{
nPos = m_xBreak->previousWord(aTest, nPos, aLocale, i18n::WordType::ANYWORD_IGNOREWHITESPACES).startPos;
CPPUNIT_ASSERT(nPos == aSingleQuotePositions[--i]);
}
while (nPos > 0);
}
}
}
//See http://qa.openoffice.org/issues/show_bug.cgi?id=111152
//See https://bugs.freedesktop.org/show_bug.cgi?id=40292
void TestBreakIterator::testGraphemeIteration()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("bn"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("IN"));
{
const sal_Unicode BA_HALANT_LA[] = { 0x09AC, 0x09CD, 0x09AF };
::rtl::OUString aTest(BA_HALANT_LA, SAL_N_ELEMENTS(BA_HALANT_LA));
sal_Int32 nDone=0;
sal_Int32 nPos;
nPos = m_xBreak->nextCharacters(aTest, 0, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == SAL_N_ELEMENTS(BA_HALANT_LA));
nPos = m_xBreak->previousCharacters(aTest, SAL_N_ELEMENTS(BA_HALANT_LA), aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == 0);
}
{
const sal_Unicode HA_HALANT_NA_VOWELSIGNI[] = { 0x09B9, 0x09CD, 0x09A3, 0x09BF };
::rtl::OUString aTest(HA_HALANT_NA_VOWELSIGNI, SAL_N_ELEMENTS(HA_HALANT_NA_VOWELSIGNI));
sal_Int32 nDone=0;
sal_Int32 nPos;
nPos = m_xBreak->nextCharacters(aTest, 0, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == SAL_N_ELEMENTS(HA_HALANT_NA_VOWELSIGNI));
nPos = m_xBreak->previousCharacters(aTest, SAL_N_ELEMENTS(HA_HALANT_NA_VOWELSIGNI), aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == 0);
}
{
const sal_Unicode TA_HALANT_MA_HALANT_YA [] = { 0x09A4, 0x09CD, 0x09AE, 0x09CD, 0x09AF };
::rtl::OUString aTest(TA_HALANT_MA_HALANT_YA, SAL_N_ELEMENTS(TA_HALANT_MA_HALANT_YA));
sal_Int32 nDone=0;
sal_Int32 nPos;
nPos = m_xBreak->nextCharacters(aTest, 0, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == SAL_N_ELEMENTS(TA_HALANT_MA_HALANT_YA));
nPos = m_xBreak->previousCharacters(aTest, SAL_N_ELEMENTS(TA_HALANT_MA_HALANT_YA), aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == 0);
}
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("ta"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("IN"));
{
const sal_Unicode KA_VIRAMA_SSA[] = { 0x0B95, 0x0BCD, 0x0BB7 };
::rtl::OUString aTest(KA_VIRAMA_SSA, SAL_N_ELEMENTS(KA_VIRAMA_SSA));
sal_Int32 nDone=0;
sal_Int32 nPos = 0;
nPos = m_xBreak->nextCharacters(aTest, 0, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == SAL_N_ELEMENTS(KA_VIRAMA_SSA));
nPos = m_xBreak->previousCharacters(aTest, SAL_N_ELEMENTS(KA_VIRAMA_SSA), aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip full grapheme", nPos == 0);
}
{
const sal_Unicode CA_VOWELSIGNI_TA_VIRAMA_TA_VOWELSIGNI_RA_VOWELSIGNAI[] =
{ 0x0B9A, 0x0BBF, 0x0BA4, 0x0BCD, 0x0BA4, 0x0BBF, 0x0BB0, 0x0BC8 };
::rtl::OUString aTest(CA_VOWELSIGNI_TA_VIRAMA_TA_VOWELSIGNI_RA_VOWELSIGNAI,
SAL_N_ELEMENTS(CA_VOWELSIGNI_TA_VIRAMA_TA_VOWELSIGNI_RA_VOWELSIGNAI));
sal_Int32 nDone=0;
sal_Int32 nPos=0;
for (sal_Int32 i = 0; i < 4; ++i)
{
sal_Int32 nOldPos = nPos;
nPos = m_xBreak->nextCharacters(aTest, nPos, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip 2 units", nPos == nOldPos+2);
}
for (sal_Int32 i = 0; i < 4; ++i)
{
sal_Int32 nOldPos = nPos;
nPos = m_xBreak->previousCharacters(aTest, nPos, aLocale,
i18n::CharacterIteratorMode::SKIPCELL, 1, nDone);
CPPUNIT_ASSERT_MESSAGE("Should skip 2 units", nPos == nOldPos-2);
}
}
{
const sal_Unicode ALEF_QAMATS [] = { 0x05D0, 0x05B8 };
::rtl::OUString aText(ALEF_QAMATS, SAL_N_ELEMENTS(ALEF_QAMATS));
sal_Int32 nGraphemeCount = 0;
sal_Int32 nCurPos = 0;
while (nCurPos < aText.getLength())
{
sal_Int32 nCount2 = 1;
nCurPos = m_xBreak->nextCharacters(aText, nCurPos, lang::Locale(),
i18n::CharacterIteratorMode::SKIPCELL, nCount2, nCount2);
++nGraphemeCount;
}
CPPUNIT_ASSERT_MESSAGE("Should be considered 1 grapheme", nGraphemeCount == 1);
}
}
//A test to ensure that certain ranges and codepoints that are categorized as
//weak remain as weak, so that existing docs that depend on this don't silently
//change font for those weak chars
void TestBreakIterator::testWeak()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
{
const sal_Unicode WEAKS[] =
{
0x0001, 0x0002,
0x0020, 0x00A0,
0x2150, 0x215F, //Number Forms, fractions
0x2160, 0x2180, //Number Forms, roman numerals
0x2200, 0x22FF, //Mathematical Operators
0x27C0, 0x27EF, //Miscellaneous Mathematical Symbols-A
0x2980, 0x29FF, //Miscellaneous Mathematical Symbols-B
0x2A00, 0x2AFF, //Supplemental Mathematical Operators
0x2100, 0x214F, //Letterlike Symbols
0x2308, 0x230B, //Miscellaneous technical
0x25A0, 0x25FF, //Geometric Shapes
0x2B30, 0x2B4C //Miscellaneous Symbols and Arrows
};
::rtl::OUString aWeaks(WEAKS, SAL_N_ELEMENTS(WEAKS));
for (sal_Int32 i = 0; i < aWeaks.getLength(); ++i)
{
sal_Int16 nScript = m_xBreak->getScriptType(aWeaks, i);
rtl::OStringBuffer aMsg;
aMsg.append(RTL_CONSTASCII_STRINGPARAM("Char 0x"));
aMsg.append(static_cast<sal_Int32>(aWeaks.getStr()[i]), 16);
aMsg.append(RTL_CONSTASCII_STRINGPARAM(" should have been weak"));
CPPUNIT_ASSERT_MESSAGE(aMsg.getStr(),
nScript == i18n::ScriptType::WEAK);
}
}
}
//A test to ensure that certain ranges and codepoints that are categorized as
//asian remain as asian, so that existing docs that depend on this don't silently
//change font for those asian chars.
//See https://bugs.freedesktop.org/show_bug.cgi?id=38095
void TestBreakIterator::testAsian()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("en"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("US"));
{
const sal_Unicode ASIANS[] =
{
//some typical CJK chars
0x4E00, 0x62FF,
//The full HalfWidth and FullWidth block has historically been
//designated as taking the CJK font :-(
//HalfWidth and FullWidth forms of ASCII 0-9, categorized under
//UAX24 as "Common" i.e. by that logic WEAK
0xFF10, 0xFF19,
//HalfWidth and FullWidth forms of ASCII A-z, categorized under
//UAX25 as "Latin", i.e. by that logic LATIN
0xFF21, 0xFF5A
};
::rtl::OUString aAsians(ASIANS, SAL_N_ELEMENTS(ASIANS));
for (sal_Int32 i = 0; i < aAsians.getLength(); ++i)
{
sal_Int16 nScript = m_xBreak->getScriptType(aAsians, i);
rtl::OStringBuffer aMsg;
aMsg.append(RTL_CONSTASCII_STRINGPARAM("Char 0x"));
aMsg.append(static_cast<sal_Int32>(aAsians.getStr()[i]), 16);
aMsg.append(RTL_CONSTASCII_STRINGPARAM(" should have been asian"));
CPPUNIT_ASSERT_MESSAGE(aMsg.getStr(),
nScript == i18n::ScriptType::ASIAN);
}
}
}
//A test to ensure that our thai word boundary detection is useful
//http://lists.freedesktop.org/archives/libreoffice/2012-February/025959.html
void TestBreakIterator::testThai()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("th"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("TH"));
const sal_Unicode THAI1[] = { 0x0E01, 0x0E38, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
::rtl::OUString aTest(THAI1, SAL_N_ELEMENTS(THAI1));
i18n::Boundary aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT_MESSAGE("Should skip full word",
aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
}
#if TODO
void TestBreakIterator::testNorthernThai()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("nod"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("TH"));
const sal_Unicode NORTHERN_THAI1[] = { 0x0E01, 0x0E38, 0x0E4A, 0x0E2B, 0x0E25, 0x0E32, 0x0E1A };
::rtl::OUString aTest(NORTHERN_THAI1, SAL_N_ELEMENTS(NORTHERN_THAI1));
i18n::Boundary aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT_MESSAGE("Should skip full word",
aBounds.startPos == 0 && aBounds.endPos == aTest.getLength());
}
#endif
#if (U_ICU_VERSION_MAJOR_NUM > 4)
//A test to ensure that our khmer word boundary detection is useful
//https://bugs.freedesktop.org/show_bug.cgi?id=52020
//
//icu doesn't have the Khmer word boundary dictionaries in <= 4.0.0 but does in
//the current 49.x.y . Not sure which version first had them introduced.
void TestBreakIterator::testKhmer()
{
lang::Locale aLocale;
aLocale.Language = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("km"));
aLocale.Country = ::rtl::OUString(RTL_CONSTASCII_USTRINGPARAM("KH"));
const sal_Unicode KHMER1[] = { 0x17B2, 0x17D2, 0x1799, 0x1782, 0x17C1 };
::rtl::OUString aTest(KHMER1, SAL_N_ELEMENTS(KHMER1));
i18n::Boundary aBounds = m_xBreak->getWordBoundary(aTest, 0, aLocale,
i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 0 && aBounds.endPos == 3);
aBounds = m_xBreak->getWordBoundary(aTest, aBounds.endPos, aLocale,
i18n::WordType::DICTIONARY_WORD, true);
CPPUNIT_ASSERT(aBounds.startPos == 3 && aBounds.endPos == 5);
}
#endif
void TestBreakIterator::setUp()
{
BootstrapFixtureBase::setUp();
m_xBreak = uno::Reference< i18n::XBreakIterator >(m_xSFactory->createInstance(
"com.sun.star.i18n.BreakIterator"), uno::UNO_QUERY_THROW);
}
void TestBreakIterator::tearDown()
{
BootstrapFixtureBase::tearDown();
m_xBreak.clear();
}
CPPUNIT_TEST_SUITE_REGISTRATION(TestBreakIterator);
CPPUNIT_PLUGIN_IMPLEMENT();
/* vim:set shiftwidth=4 softtabstop=4 expandtab: */
|