/
ft_mcharsetdetector.cpp
2019 lines (1953 loc) · 61.9 KB
/
ft_mcharsetdetector.cpp
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
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/***************************************************************************
**
** Copyright (C) 2010, 2011 Nokia Corporation and/or its subsidiary(-ies).
** All rights reserved.
** Contact: Nokia Corporation (directui@nokia.com)
**
** This file is part of libmeegotouch.
**
** If you have questions regarding the use of this file, please contact
** Nokia at directui@nokia.com.
**
** This library is free software; you can redistribute it and/or
** modify it under the terms of the GNU Lesser General Public
** License version 2.1 as published by the Free Software Foundation
** and appearing in the file LICENSE.LGPL included in the packaging
** of this file.
**
****************************************************************************/
#include "ft_mcharsetdetector.h"
#define VERBOSE_OUTPUT
using ML10N::MCharsetMatch;
using ML10N::MCharsetDetector;
void Ft_MCharsetDetector::initTestCase()
{
}
void Ft_MCharsetDetector::cleanupTestCase()
{
}
void Ft_MCharsetDetector::init()
{
}
void Ft_MCharsetDetector::cleanup()
{
}
void Ft_MCharsetDetector::testMCharsetMatch_data()
{
QTest::addColumn<QStringList>("names");
QTest::addColumn<QStringList>("languages");
QTest::addColumn<QStringList>("confidences");
QTest::addColumn<QStringList>("namesSorted");
QTest::addColumn<QStringList>("languagesSorted");
QTest::addColumn<QStringList>("confidencesSorted");
QTest::newRow("matches")
<< (QStringList()
<< "ISO-8859-1" << "ISO-8859-2" << "UTF-8" << "Shift_JIS")
<< (QStringList()
<< "de" << "cs" << "" << "ja")
<< (QStringList()
<< "85" << "97" << "99" << "10")
<< (QStringList()
<< "UTF-8" << "ISO-8859-2" << "ISO-8859-1" << "Shift_JIS")
<< (QStringList()
<< "" << "cs" << "de" << "ja")
<< (QStringList()
<< "99" << "97" << "85" << "10")
;
}
void Ft_MCharsetDetector::testMCharsetMatch()
{
QFETCH(QStringList, names);
QFETCH(QStringList, languages);
QFETCH(QStringList, confidences);
QFETCH(QStringList, namesSorted);
QFETCH(QStringList, languagesSorted);
QFETCH(QStringList, confidencesSorted);
QList<MCharsetMatch> mCharsetMatchList;
for(int i = 0; i < names.size(); ++i) {
MCharsetMatch match(names[i], languages[i], confidences[i].toInt());
mCharsetMatchList << match;
}
QList<MCharsetMatch> mCharsetMatchListSorted;
for(int i = 0; i < names.size(); ++i) {
MCharsetMatch match;
// use the setters here to get more test coverage
match.setName(namesSorted[i]);
match.setLanguage(languagesSorted[i]);
match.setConfidence(confidencesSorted[i].toInt());
mCharsetMatchListSorted << match;
}
qSort(mCharsetMatchList.begin(), mCharsetMatchList.end(),
qGreater<MCharsetMatch>());
#if defined(VERBOSE_OUTPUT)
for(int i = 0; i < names.size(); ++i) {
qDebug() << mCharsetMatchList[i].name()
<< mCharsetMatchListSorted[i].name();
qDebug() << mCharsetMatchList[i].language()
<< mCharsetMatchListSorted[i].language();
qDebug() << mCharsetMatchList[i].confidence()
<< mCharsetMatchListSorted[i].confidence();
}
#endif
for(int i = 0; i < names.size(); ++i) {
QCOMPARE(mCharsetMatchList[i].name(),
mCharsetMatchListSorted[i].name());
QCOMPARE(mCharsetMatchList[i].language(),
mCharsetMatchListSorted[i].language());
QCOMPARE(mCharsetMatchList[i].confidence(),
mCharsetMatchListSorted[i].confidence());
}
}
void Ft_MCharsetDetector::testConstructors_data()
{
QTest::addColumn<QString>("charsetName");
QTest::addColumn<QByteArray>("byteArray");
QTest::addColumn<QString>("textResult");
QTest::addColumn<bool>("hasError");
QTest::newRow("UTF-8")
<< "UTF-8"
<< QString::fromUtf8("Hello Wörld, こんにちは日本。").toUtf8()
<< QString::fromUtf8("Hello Wörld, こんにちは日本。")
<< false;
QTest::newRow("ISO-8859-1")
<< "ISO-8859-1"
<< QString::fromUtf8("Hello Wörld, täst, Grüße.").toLatin1()
<< QString::fromUtf8("Hello Wörld, täst, Grüße.")
<< false;
QTest::newRow("NONSENSE")
<< "NONSENSE"
<< QString::fromUtf8("Hello Wörld, こんにちは日本。").toUtf8()
<< QString()
<< true;
QTest::newRow("UTF-8, but force detection as ISO-8859-1")
<< "ISO-8859-1"
<< QString::fromUtf8("täst本").toUtf8()
<< QString::fromUtf8("tästæ") + QChar(0x9c) + QString::fromUtf8("¬")
<< false;
}
void Ft_MCharsetDetector::testConstructors()
{
QFETCH(QString, charsetName);
QFETCH(QByteArray, byteArray);
QFETCH(QString, textResult);
QFETCH(bool, hasError);
MCharsetMatch charsetMatch;
charsetMatch.setName(charsetName);
MCharsetDetector charsetDetector1;
charsetDetector1.setText(byteArray);
MCharsetDetector charsetDetector2(byteArray);
MCharsetDetector charsetDetector3(byteArray.constData());
MCharsetDetector charsetDetector4(byteArray.constData(), byteArray.size());
QString result1 = charsetDetector1.text(charsetMatch);
bool hasError1 = charsetDetector1.hasError();
QString result2 = charsetDetector2.text(charsetMatch);
bool hasError2 = charsetDetector2.hasError();
QString result3 = charsetDetector3.text(charsetMatch);
bool hasError3 = charsetDetector3.hasError();
QString result4 = charsetDetector4.text(charsetMatch);
bool hasError4 = charsetDetector4.hasError();
#if defined(VERBOSE_OUTPUT)
QTextStream debugStream(stdout);
debugStream.setCodec("UTF-8");
debugStream << "result1: " << result1
<< " size: " << result1.size() << "\n"
<< "textResult: " << textResult
<< " size: " << textResult.size() << "\n"
<< "hasError1: " << hasError1
<< " errorString: " << charsetDetector1.errorString() << "\n";
#endif
QCOMPARE(result1, textResult);
QCOMPARE(result2, textResult);
QCOMPARE(result3, textResult);
QCOMPARE(result4, textResult);
QCOMPARE(hasError1, hasError);
QCOMPARE(hasError2, hasError);
QCOMPARE(hasError3, hasError);
QCOMPARE(hasError4, hasError);
}
void Ft_MCharsetDetector::testInputFilterEnabledDefaultValue()
{
MCharsetDetector charsetDetector;
// The input filter is disabled by default:
QCOMPARE(charsetDetector.isInputFilterEnabled(), false);
}
void Ft_MCharsetDetector::testDetectableCharsets_data()
{
QTest::addColumn<QStringList>("expectedCharsets");
QTest::newRow("at least these charsets should be detectable")
<< (QStringList()
<< "UTF-8"
<< "UTF-16BE"
<< "UTF-16LE"
<< "UTF-32BE"
<< "UTF-32LE"
<< "ISO-8859-1"
<< "ISO-8859-2"
<< "ISO-8859-5"
<< "ISO-8859-6"
<< "ISO-8859-7"
<< "ISO-8859-8"
<< "ISO-8859-9"
<< "KOI8-R"
<< "Shift_JIS"
<< "GB18030"
<< "EUC-JP"
<< "EUC-KR"
<< "Big5"
<< "ISO-2022-JP"
<< "windows-1250"
<< "windows-1251"
<< "windows-1252"
<< "windows-1253"
<< "windows-1255"
<< "windows-1256"
<< "windows-1254")
;
}
void Ft_MCharsetDetector::testDetectableCharsets()
{
QFETCH(QStringList, expectedCharsets);
MCharsetDetector charsetDetector;
QStringList detectableCharsets
= charsetDetector.getAllDetectableCharsets();
#if defined(VERBOSE_OUTPUT)
qDebug() << "detectable charsets" << detectableCharsets;
#endif
foreach(QString cs, expectedCharsets)
QVERIFY2(detectableCharsets.contains(cs),
QString("charset %1 is missing in the list of detectable charset")
.arg(cs).toUtf8().constData());
}
static QString makeStringLonger(const QString &str, int n)
{
QString ret;
for (int i = 0; i < n; ++i)
ret += str;
return ret;
}
void Ft_MCharsetDetector::testDetection_data()
{
QTest::addColumn<QString>("text");
QTest::addColumn<QString>("declaredLocale");
QTest::addColumn<QString>("declaredEncoding");
QTest::addColumn<bool>("enableInputFilter");
QTest::addColumn<QString>("inputEncoding");
QTest::addColumn<QString>("bestMatchName");
QTest::addColumn<QString>("bestMatchLanguage");
#if !defined(ALSO_VERIFY_ICU_DOES_ITS_JOB_AS_WE_EXPECT)
QTest::newRow("Short German UTF-8")
<< "Grüße"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< ""
<< "ISO-8859-1" // declared encoding, makes it work
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< "de" // declared locale, makes it work
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de";
return;
#endif
QString longGerman("Als Menschenrechte werden subjektive Rechte bezeichnet, die jedem Menschen gleichermaßen zustehen. Das Konzept der Menschenrechte geht davon aus, dass alle Menschen allein aufgrund ihres Menschseins[1] mit gleichen Rechten ausgestattet und dass diese egalitär begründeten Rechte universell, unveräußerlich und unteilbar sind. Die Idee der Menschenrechte ist eng verbunden mit dem Humanismus und der im Zeitalter der Aufklärung entwickelten Idee des Naturrechts.");
QTest::newRow("Long German UTF-8")
<< longGerman
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long German Latin1")
<< longGerman
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de";
QTest::newRow("Short German UTF-8")
<< "Grüße"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short German UTF-8")
<< "Grüße"
<< "ja" // declared locale, should not break it
<< "Shift_JIS" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "Shift_JIS" // not fixable
<< "ja"; // not fixable
QTest::newRow("Short German Latin1")
<< "Grüße"
<< ""
<< "ISO-8859-1" // declared encoding, makes it work
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< "de" // declared locale, makes it work
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< "de_DE" // declared locale, makes it work
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de";
QTest::newRow("Short German Latin1")
<< "Grüße"
<< "de" // declared locale
<< "ISO-8859-1" // declared encoding, makes it work
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de";
QString longFrench("Le français est une langue romane parlée comme langue maternelle principalement en France (y compris outre-mer), dont elle est originaire (la « langue d’oïl »), en Belgique (en Wallonie et à Bruxelles), dans plusieurs provinces et territoires du Canada (principalement au Québec, mais aussi en Ontario et au Nouveau-Brunswick) et en Suisse romande (le français est l'une des quatre langues officielles de la Suisse). On trouve aussi des îlots de francophones natifs aux États-Unis (notamment en Louisiane et au Maine), à Haïti, aux Seychelles, à l'île Maurice, au Vanuatu, dans certaines vallées italiennes, etc...");
QTest::newRow("Long French ISO-8859-1")
<< longFrench
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "fr";
QString htmlTest("<p></p><p></p><p></p><p style='font-family: "
+ longFrench
+ ";'>"
+ longGerman
+ "</p>");
QTest::newRow("HTML test ISO-8859-1")
<< htmlTest
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "fr"; // detects as French without filtering
QTest::newRow("HTML test ISO-8859-1")
<< htmlTest
<< ""
<< ""
<< true
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "de"; // detects as German with filtering
QString longCzech("Český jazyk neboli čeština je západoslovanský jazyk, nejvíce příbuzný se slovenštinou, poté polštinou a lužickou srbštinou. Patří mezi slovanské jazyky, do rodiny jazyků indoevropských. Čeština se vyvinula ze západních nářečí praslovanštiny na konci 10. století. Česky psaná literatura se objevuje od 14. století. První písemné památky jsou však již z 12. století. Dělí se na spisovnou č., určenou pro oficiální styk (je kodifikována v mluvnicích a slovnících), a nespisovnou č., která zahrnuje dialekty (nářečí) a sociolekty (slangy) včetně vulgarismů a argotu. Spisovná čeština má dvě podoby: vypjatě spisovnou a hovorovou. Hovorovou češtinu je třeba odlišovat od češtiny obecné.");
QTest::newRow("Long Czech UTF-8")
<< longCzech
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Czech Latin2")
<< longCzech
<< ""
<< ""
<< false
<< "ISO-8859-2"
<< "ISO-8859-2"
<< "cs";
QTest::newRow("Long Czech windows-1250")
<< longCzech
<< ""
<< ""
<< false
<< "windows-1250"
<< "windows-1250"
<< "cs";
QString shortCzech("Český");
QTest::newRow("Short Czech UTF-8")
<< shortCzech
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Czech UTF-8")
<< shortCzech
<< "ja" // declared locale, should not break it
<< "Shift_JIS" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Czech UTF-8")
<< shortCzech
<< "de" // declared locale, should not break it
<< "ISO-8859-1" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Czech Latin2")
<< shortCzech
<< ""
<< ""
<< false
<< "ISO-8859-2"
<< "" // not fixable
<< "";
QTest::newRow("Short Czech Latin2")
<< shortCzech
<< ""
<< "ISO-8859-2" // declared encoding, makes it work
<< false
<< "ISO-8859-2"
<< "ISO-8859-2"
<< "";
QString longHebrew("השם עֵבֶר מופיע במקרא כשמו של אחד מאבותיו של אברהם אבינו. המושג \"עברי\" נזכר במקרא פעמים רבות ככינוי לבני ישראל, אולם שמה של שפתם של העברים אינו מוזכר במקרא. עם זאת, במלכים ב' ב' י\"ח,כו ובישעיהו ל\"ו,יא מסופר כי שליחי חזקיהו המלך מבקשים מרבשקה, שליחו של סנחריב מלך אשור, לדבר עמם ב\"ארמית\" ולא ב\"יהודית\", כדי שהעם (שכנראה לא דיבר ארמית) לא יבין את דבריהם; לפי זה נראה כי זה היה שמה של השפה, או לפחות שמו של הניב שדובר באזור ירושלים אשר בממלכת \"יהודה\".");
QTest::newRow("Long Hebrew UTF-8")
<< longHebrew
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Hebrew ISO-8859-8")
<< longHebrew
<< ""
<< ""
<< false
<< "ISO-8859-8"
<< "ISO-8859-8-I" /* ICU autodetection preffers Hebrew Logical over Hebrew Visual */
<< "he";
QTest::newRow("Short Hebrew UTF-8")
<< "עִבְרִית"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Hebrew UTF-8")
<< "עִבְרִית"
<< "de" // declared locale, should not break it
<< "ISO-8859-1" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Hebrew ISO-8859-8")
<< "עִבְרִית"
<< ""
<< ""
<< false
<< "ISO-8859-8"
<< "ISO-8859-7" // not fixable
<< "el"; // not fixable
QTest::newRow("Short Hebrew ISO-8859-8")
<< "עִבְרִית"
<< ""
<< "ISO-8859-8" // declared encoding, makes it work
<< false
<< "ISO-8859-8"
<< "ISO-8859-8"
<< "";
QTest::newRow("Short Hebrew ISO-8859-8")
<< "עִבְרִית"
<< "he" // declared locale, makes it work
<< ""
<< false
<< "ISO-8859-8"
<< "ISO-8859-8"
<< "he";
QTest::newRow("Short Hebrew ISO-8859-8")
<< "עִבְרִית"
<< "he" // declared locale
<< "ISO-8859-8" // declared encoding, makes it work
<< false
<< "ISO-8859-8"
<< "ISO-8859-8"
<< "he";
QString shortJapanese("日");
// "攀" in EUC-JP happens to be a valid UTF-8 sequence.
QTest::newRow("Short Japanese UTF-8")
<< shortJapanese
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Japanese UTF-16")
<< shortJapanese
<< ""
<< ""
<< false
<< "UTF-16LE"
<< "UTF-16LE"
<< "";
QTest::newRow("Short Japanese UTF-16BE")
<< shortJapanese
<< ""
<< ""
<< false
<< "UTF-16BE"
<< "UTF-16BE"
<< "";
QTest::newRow("Short Japanese UTF-32")
<< shortJapanese
<< ""
<< ""
<< false
<< "UTF-32LE"
<< "UTF-32LE"
<< "";
QTest::newRow("Short Japanese UTF-32BE")
<< shortJapanese
<< ""
<< ""
<< false
<< "UTF-32BE"
<< "UTF-32BE"
<< "";
QTest::newRow("Short Japanese EUC-JP")
<< shortJapanese
<< ""
<< ""
<< false
<< "EUC-JP"
<< "EUC-JP"
<< "ja";
QTest::newRow("Short Japanese Shift_JIS")
<< shortJapanese
<< ""
<< ""
<< false
<< "Shift_JIS"
<< "Shift_JIS"
<< "ja";
QTest::newRow("Short Japanese ISO-2022-JP")
<< shortJapanese
<< ""
<< ""
<< false
<< "ISO-2022-JP"
<< "ISO-2022-JP"
<< "ja";
QTest::newRow("Short Thai UTF-8")
<< "ภาษาไทย"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Tamil UTF-8")
<< "தமிழ்"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QString longGreek("Η ελληνική γλώσσα είναι μία από τις ινδοευρωπαϊκές γλώσσες, για την οποία έχουμε γραπτά κείμενα από τον 15ο αιώνα π.Χ. μέχρι σήμερα. Αποτελεί το μοναδικό μέλος ενός κλάδου της ινδοευρωπαϊκής οικογένειας γλωσσών. Ανήκει επίσης στον βαλκανικό γλωσσικό δεσμό.");
QTest::newRow("Long Greek UTF-8")
<< longGreek
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Greek ISO-8859-7")
<< longGreek
<< ""
<< ""
<< false
<< "ISO-8859-7"
<< "ISO-8859-7"
<< "el";
QTest::newRow("Short Greek UTF-8")
<< "ελληνικά"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Greek UTF-8")
<< "ελληνικά"
<< "el" // declared locale, short not break it
<< "ISO-8859-7" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Greek ISO-8859-7")
<< "ελληνικά"
<< ""
<< ""
<< false
<< "ISO-8859-7"
<< "ISO-8859-6" // not fixable
<< "ar";
QTest::newRow("Short Greek ISO-8859-7")
<< "ελληνικά"
<< ""
<< "ISO-8859-7" // declared encoding, makes it work
<< false
<< "ISO-8859-7"
<< "ISO-8859-7"
<< "";
QTest::newRow("Short Greek ISO-8859-7")
<< "ελληνικά"
<< "el" // declared locale, makes it work
<< ""
<< false
<< "ISO-8859-7"
<< "ISO-8859-7"
<< "el";
QTest::newRow("Short Greek ISO-8859-7")
<< "ελληνικά"
<< "el" // declared locale
<< "ISO-8859-7" // declared encoding, makes it work
<< false
<< "ISO-8859-7"
<< "ISO-8859-7"
<< "el";
QString longTurkish("Türkçe veya Türkiye Türkçesi, varlığı tam olarak ispatlanamamış ortak Altay dil ailesine bağlı Türk dillerinin Oğuz öbeğine üye bir dildir. Türk dilleri ailesi bünyesindeki Oğuz öbeğinde bulunur.[5] Türkçe dünyada en fazla konuşulan 15. dildir.");
QTest::newRow("Long Turkish UTF-8")
<< longTurkish
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Turkish ISO-8859-9")
<< longTurkish
<< ""
<< ""
<< false
<< "ISO-8859-9"
<< "ISO-8859-9"
<< "tr";
QString shortTurkish("Türkçe");
QTest::newRow("Short Turkish UTF-8")
<< shortTurkish
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Turkish UTF-8")
<< shortTurkish
<< "tr" // declared language, should not break it
<< "ISO-8859-9" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Turkish ISO-8859-9")
<< shortTurkish
<< ""
<< ""
<< false
<< "ISO-8859-9"
<< "Shift_JIS" // not fixable
<< "ja";
QTest::newRow("Short Turkish ISO-8859-9")
<< shortTurkish
<< ""
<< "ISO-8859-9" // declared encoding, makes it work
<< false
<< "ISO-8859-9"
<< "ISO-8859-9"
<< "";
QTest::newRow("Short Turkish ISO-8859-9")
<< shortTurkish
<< "tr" // declared locale
<< ""
<< false
<< "ISO-8859-9"
<< "ISO-8859-9"
<< "tr";
QTest::newRow("Short Turkish ISO-8859-9")
<< shortTurkish
<< "tr" // declared locale
<< "ISO-8859-9" // declared encoding
<< false
<< "ISO-8859-9"
<< "ISO-8859-9"
<< "tr";
QString longEnglish("English is a West Germanic language that arose in the Anglo-Saxon kingdoms of England and spread into what was to become south-east Scotland under the influence of the Anglian medieval kingdom of Northumbria.");
QTest::newRow("Long English ASCII")
<< longEnglish
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "en";
QString longEnglishWithNonAscii(
makeStringLonger("naïve ", 3)
+ // order does not matter here
makeStringLonger(longEnglish, 3)
);
QTest::newRow("Long English with non-ASCII Latin1")
<< longEnglishWithNonAscii
<< ""
<< ""
<< false
<< "ISO-8859-1"
<< "ISO-8859-1"
<< "en";
// UTF-8 detection may fail if there are very few
// UTF-8 characters in a text which is otherwise mostly ASCII
// The following input is rather long ASCII with very few
// UTF-8 characters, I added a hack to make this work as well
// and verify that it works here.
QTest::newRow("Long English with non-ASCII UTF-8")
<< longEnglishWithNonAscii
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QString longRussian("Ру́сский язы́к — один из восточнославянских языков, один из крупнейших языков мира, национальный язык русского народа. Является самым распространённым из славянских языков и самым распространённым языком Европы как географически, так и по числу носителей языка как родного (хотя также значительная и географически бо́льшая часть русского языкового ареала находится в Азии).");
QTest::newRow("Long Russian UTF-8")
<< longRussian
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Russian windows-1251")
<< longRussian
<< ""
<< ""
<< false
<< "windows-1251"
<< "windows-1251"
<< "ru";
QTest::newRow("Long Russian KOI8-R")
<< longRussian
<< ""
<< ""
<< false
<< "KOI8-R"
<< "KOI8-R"
<< "ru";
QTest::newRow("Long Russian ISO-8859-5")
<< longRussian
<< ""
<< ""
<< false
<< "ISO-8859-5"
<< "ISO-8859-5"
<< "ru";
QTest::newRow("Short Russian UTF-8")
<< "русский"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Russian windows-1251")
<< "русский"
<< ""
<< ""
<< false
<< "windows-1251"
<< "Shift_JIS" // not fixable
<< "ja";
QTest::newRow("Short Russian windows-1251")
<< "русский"
<< ""
<< "windows-1251" // declared encoding, makes it work
<< false
<< "windows-1251"
<< "windows-1251"
<< "";
QTest::newRow("Short Russian windows-1251 declared locale")
<< "русский"
<< "ru" // declared locale, makes it work (accidentally!)
<< ""
<< false
<< "windows-1251"
<< "windows-1251"
<< "ru";
QTest::newRow("Short Russian KOI8-R")
<< "русский"
<< ""
<< ""
<< false
<< "KOI8-R"
<< "Shift_JIS" // not fixable
<< "ja";
QTest::newRow("Short Russian KOI8-R")
<< "русский"
<< ""
<< "KOI8-R" // delared encoding, makes it work
<< false
<< "KOI8-R"
<< "KOI8-R"
<< "";
QTest::newRow("Short Russian KOI8-R declared locale")
<< "русский"
<< "ru" // declared locale, does not help, not fixable
<< ""
<< false
<< "KOI8-R"
<< "windows-1251"
<< "ru";
QTest::newRow("Short Russian ISO-8859-5")
<< "русский"
<< ""
<< ""
<< false
<< "ISO-8859-5"
<< "Shift_JIS" // not fixable
<< "ja";
QTest::newRow("Short Russian ISO-8859-5")
<< "русский"
<< ""
<< "ISO-8859-5" // declared encoding, makes it work
<< false
<< "ISO-8859-5"
<< "ISO-8859-5"
<< "";
QTest::newRow("Short Russian ISO-8859-5 declared locale")
<< "русский"
<< "ru" // declared locale, does not help, not fixable
<< ""
<< false
<< "ISO-8859-5"
<< "windows-1251"
<< "ru";
QTest::newRow("Short Russian ISO-8859-5 declared locale")
<< "русский"
<< "ru" // declared locale
<< "ISO-8859-5" // declared encoding
<< false
<< "ISO-8859-5"
<< "ISO-8859-5"
<< "ru";
QString longKorean("한국어(韓國語)는 한국에서 사용하는 언어로, 대한민국에서는 한국어, 한국말이라고 부른다. 조선민주주의인민공화국, 중국(조선족 위주)을 비롯한 등지에서는 조선말, 조선어(朝鮮語)로, 카자흐스탄을 비롯 중앙아시아의 고려인들 사이에서는 고려말(高麗─)로 불린다.");
QTest::newRow("Long Korean UTF-8")
<< longKorean
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Long Korean EUC-KR")
<< longKorean
<< ""
<< ""
<< false
<< "EUC-KR"
<< "EUC-KR"
<< "ko";
QTest::newRow("Short Korean UTF-8")
<< "한국말"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Korean UTF-8")
<< "한국말"
<< "de" // declared locale, should not break it
<< "ISO-8859-1" // declared encoding, should not break it
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Short Korean EUC-KR")
<< "한국말"
<< ""
<< ""
<< false
<< "EUC-KR"
<< "EUC-KR"
<< "ko";
QTest::newRow("Very short Korean UTF-8")
<< "한"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Very short Korean EUC-KR")
<< "한"
<< ""
<< ""
<< false
<< "EUC-KR"
<< "EUC-KR"
<< "ko";
QTest::newRow("Very short Korean UTF-8")
<< "국"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Very short Korean EUC-KR")
<< "국"
<< ""
<< ""
<< false
<< "EUC-KR"
<< "EUC-KR"
<< "ko";
QTest::newRow("Very short Korean UTF-8")
<< "말"
<< ""
<< ""
<< false
<< "UTF-8"
<< "UTF-8"
<< "";
QTest::newRow("Very short Korean EUC-KR")
<< "말"
<< ""
<< ""
<< false