summaryrefslogtreecommitdiff
path: root/Build/source/libs/icu/icu-src/source/test/intltest/csdetest.cpp
blob: 95f19d43d1adc41fbd954a1f1e6d480ff331c82c (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
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
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
 **********************************************************************
 *   Copyright (C) 2005-2016, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 **********************************************************************
 */


#include "unicode/utypes.h"
#include "unicode/ucsdet.h"
#include "unicode/ucnv.h"
#include "unicode/unistr.h"
#include "unicode/putil.h"
#include "unicode/uniset.h"

#include "intltest.h"
#include "csdetest.h"

#include "xmlparser.h"

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

#ifdef DEBUG_DETECT
#include <stdio.h>
#endif


#define CH_SPACE 0x0020
#define CH_SLASH 0x002F

#define TEST_ASSERT(x) UPRV_BLOCK_MACRO_BEGIN { \
    if (!(x)) { \
        errln("Failure in file %s, line %d", __FILE__, __LINE__); \
    } \
} UPRV_BLOCK_MACRO_END

#define TEST_ASSERT_SUCCESS(errcode) UPRV_BLOCK_MACRO_BEGIN { \
    if (U_FAILURE(errcode)) { \
        errcheckln(errcode, "Failure in file %s, line %d, status = \"%s\"", __FILE__, __LINE__, u_errorName(errcode)); \
        return; \
    } \
} UPRV_BLOCK_MACRO_END


//---------------------------------------------------------------------------
//
//  Test class boilerplate
//
//---------------------------------------------------------------------------
CharsetDetectionTest::CharsetDetectionTest()
{
}


CharsetDetectionTest::~CharsetDetectionTest()
{
}



void CharsetDetectionTest::runIndexedTest( int32_t index, UBool exec, const char* &name, char* /*par*/ )
{
    if (exec) logln("TestSuite CharsetDetectionTest: ");
    switch (index) {
       case 0: name = "ConstructionTest";
            if (exec) ConstructionTest();
            break;

       case 1: name = "UTF8Test";
            if (exec) UTF8Test();
            break;

       case 2: name = "UTF16Test";
            if (exec) UTF16Test();
            break;

       case 3: name = "C1BytesTest";
            if (exec) C1BytesTest();
            break;

       case 4: name = "InputFilterTest";
            if (exec) InputFilterTest();
            break;

       case 5: name = "DetectionTest";
            if (exec) DetectionTest();
            break;
#if !UCONFIG_NO_LEGACY_CONVERSION
       case 6: name = "IBM424Test";
            if (exec) IBM424Test();
            break;

       case 7: name = "IBM420Test";
            if (exec) IBM420Test();
            break;
#else
       case 6:
       case 7: name = "skip"; break;
#endif
       case 8: name = "Ticket6394Test";
            if (exec) Ticket6394Test();
            break;

       case 9: name = "Ticket6954Test";
            if (exec) Ticket6954Test();
            break;

       case 10: name = "Ticket21823Test";
            if (exec) Ticket21823Test();
            break;

        default: name = "";
            break; //needed to end loop
    }
}

static UnicodeString *split(const UnicodeString &src, UChar ch, int32_t &splits)
{
    int32_t offset = -1;

    splits = 1;
    while((offset = src.indexOf(ch, offset + 1)) >= 0) {
        splits += 1;
    }

    UnicodeString *result = new UnicodeString[splits];

    int32_t start = 0;
    int32_t split = 0;
    int32_t end;

    while((end = src.indexOf(ch, start)) >= 0) {
        src.extractBetween(start, end, result[split++]);
        start = end + 1;
    }

    src.extractBetween(start, src.length(), result[split]);

    return result;
}

static char *extractBytes(const UnicodeString &source, const char *codepage, int32_t &length)
{
    int32_t sLength = source.length();
    char *bytes = NULL;

    length = source.extract(0, sLength, NULL, codepage);

    if (length > 0) {
        bytes = new char[length + 1];
        source.extract(0, sLength, bytes, codepage);
    }
    
    return bytes;
}

void CharsetDetectionTest::checkEncoding(const UnicodeString &testString, const UnicodeString &encoding, const UnicodeString &id)
{
    int32_t splits = 0;
    int32_t testLength = testString.length();
    std::unique_ptr<UnicodeString []> eSplit(split(encoding, CH_SLASH, splits));
    UErrorCode status = U_ZERO_ERROR;
    int32_t cpLength = eSplit[0].length();
    char codepage[64];

    u_UCharsToChars(eSplit[0].getBuffer(), codepage, cpLength);
    codepage[cpLength] = '\0';

    LocalUCharsetDetectorPointer csd(ucsdet_open(&status));

    int32_t byteLength = 0;
    std::unique_ptr<char []> bytes(extractBytes(testString, codepage, byteLength));

    if (! bytes) {
#if !UCONFIG_NO_LEGACY_CONVERSION
        dataerrln("Can't open a " + encoding + " converter for " + id);
#endif
        return;
    }

    ucsdet_setText(csd.getAlias(), bytes.get(), byteLength, &status);

    int32_t matchCount = 0;
    const UCharsetMatch **matches = ucsdet_detectAll(csd.getAlias(), &matchCount, &status);


    UnicodeString name(ucsdet_getName(matches[0], &status));
    UnicodeString lang(ucsdet_getLanguage(matches[0], &status));
    UChar *decoded = NULL;
    int32_t dLength = 0;

    if (matchCount == 0) {
        errln("Encoding detection failure for " + id + ": expected " + eSplit[0] + ", got no matches");
        return;
    }

    if (name.compare(eSplit[0]) != 0) {
        errln("Encoding detection failure for " + id + ": expected " + eSplit[0] + ", got " + name);

#ifdef DEBUG_DETECT
        for (int32_t m = 0; m < matchCount; m += 1) {
            const char *name = ucsdet_getName(matches[m], &status);
            const char *lang = ucsdet_getLanguage(matches[m], &status);
            int32_t confidence = ucsdet_getConfidence(matches[m], &status);

            printf("%s (%s) %d\n", name, lang, confidence);
        }
#endif
        return;
    }

    if (splits > 1 && lang.compare(eSplit[1]) != 0) {
        errln("Language detection failure for " + id + ", " + eSplit[0] + ": expected " + eSplit[1] + ", got " + lang);
        return;
    }

    decoded = new UChar[testLength];
    dLength = ucsdet_getUChars(matches[0], decoded, testLength, &status);

    if (testString.compare(decoded, dLength) != 0) {
        errln("Round-trip error for " + id + ", " + eSplit[0] + ": getUChars() didn't yield the original string.");

#ifdef DEBUG_DETECT
        for(int32_t i = 0; i < testLength; i += 1) {
            if(testString[i] != decoded[i]) {
                printf("Strings differ at byte %d\n", i);
                break;
            }
        }
#endif

    }

    delete[] decoded;
}

const char *CharsetDetectionTest::getPath(char buffer[2048], const char *filename) {
    UErrorCode status = U_ZERO_ERROR;
    const char *testDataDirectory = IntlTest::getSourceTestData(status);

    if (U_FAILURE(status)) {
        errln("ERROR: getPath() failed - %s", u_errorName(status));
        return NULL;
    }

    strcpy(buffer, testDataDirectory);
    strcat(buffer, filename);
    return buffer;
}

void CharsetDetectionTest::ConstructionTest()
{
    IcuTestErrorCode status(*this, "ConstructionTest");
    LocalUCharsetDetectorPointer csd(ucsdet_open(status));
    LocalUEnumerationPointer e(ucsdet_getAllDetectableCharsets(csd.getAlias(), status));
    int32_t count = uenum_count(e.getAlias(), status);

#ifdef DEBUG_DETECT
    printf("There are %d recognizers.\n", count);
#endif

    for(int32_t i = 0; i < count; i += 1) {
        int32_t length;
        const char *name = uenum_next(e.getAlias(), &length, status);

        if(name == NULL || length <= 0) {
            errln("ucsdet_getAllDetectableCharsets() returned a null or empty name!");
        }

#ifdef DEBUG_DETECT
        printf("%s\n", name);
#endif
    }

    const char* defDisabled[] = {
        "IBM420_rtl", "IBM420_ltr",
        "IBM424_rtl", "IBM424_ltr",
        0
    };

    LocalUEnumerationPointer eActive(ucsdet_getDetectableCharsets(csd.getAlias(), status));
    const char *activeName = NULL;

    while ((activeName = uenum_next(eActive.getAlias(), NULL, status))) {
        // the charset must be included in all list
        UBool found = FALSE;

        const char *name = NULL;
        uenum_reset(e.getAlias(), status);
        while ((name = uenum_next(e.getAlias(), NULL, status))) {
            if (strcmp(activeName, name) == 0) {
                found = TRUE;
                break;
            }
        }

        if (!found) {
            errln(UnicodeString(activeName) + " is not included in the all charset list.");
        }

        // some charsets are disabled by default
        found = FALSE;
        for (int32_t i = 0; defDisabled[i] != 0; i++) {
            if (strcmp(activeName, defDisabled[i]) == 0) {
                found = TRUE;
                break;
            }
        }
        if (found) {
            errln(UnicodeString(activeName) + " should not be included in the default charset list.");
        }
    }
}

void CharsetDetectionTest::UTF8Test()
{
    UErrorCode status = U_ZERO_ERROR;
    UnicodeString ss = "This is a string with some non-ascii characters that will "
                       "be converted to UTF-8, then shoved through the detection process.  "
                       "\\u0391\\u0392\\u0393\\u0394\\u0395"
                       "Sure would be nice if our source could contain Unicode directly!";
    UnicodeString s = ss.unescape();
    int32_t byteLength = 0, sLength = s.length();
    char *bytes = extractBytes(s, "UTF-8", byteLength);
    UCharsetDetector *csd = ucsdet_open(&status);
    const UCharsetMatch *match;
    UChar *detected = new UChar[sLength];

    ucsdet_setText(csd, bytes, byteLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("Detection failure for UTF-8: got no matches.");
        goto bail;
    }

    ucsdet_getUChars(match, detected, sLength, &status);

    if (s.compare(detected, sLength) != 0) {
        errln("Round-trip test failed!");
    }

    ucsdet_setDeclaredEncoding(csd, "UTF-8", 5, &status); /* for coverage */

bail:
    delete[] detected;
    delete[] bytes;
    ucsdet_close(csd);
}

void CharsetDetectionTest::UTF16Test()
{
    UErrorCode status = U_ZERO_ERROR;
    /* Notice the BOM on the start of this string */
    UChar chars[] = {
        0xFEFF, 0x0623, 0x0648, 0x0631, 0x0648, 0x0628, 0x0627, 0x002C,
        0x0020, 0x0628, 0x0631, 0x0645, 0x062c, 0x064a, 0x0627, 0x062a,
        0x0020, 0x0627, 0x0644, 0x062d, 0x0627, 0x0633, 0x0648, 0x0628,
        0x0020, 0x002b, 0x0020, 0x0627, 0x0646, 0x062a, 0x0631, 0x0646,
        0x064a, 0x062a, 0x0000};
    UnicodeString s(chars);
    int32_t beLength = 0, leLength = 0;
    std::unique_ptr<char []>beBytes(extractBytes(s, "UTF-16BE", beLength));
    std::unique_ptr<char []>leBytes(extractBytes(s, "UTF-16LE", leLength));
    LocalUCharsetDetectorPointer csd(ucsdet_open(&status));
    const UCharsetMatch *match;
    const char *name;
    int32_t conf;

    ucsdet_setText(csd.getAlias(), beBytes.get(), beLength, &status);
    match = ucsdet_detect(csd.getAlias(), &status);

    if (match == NULL) {
        errln("Encoding detection failure for UTF-16BE: got no matches.");
    } else {

        name  = ucsdet_getName(match, &status);
        conf  = ucsdet_getConfidence(match, &status);

        if (strcmp(name, "UTF-16BE") != 0) {
            errln("Encoding detection failure for UTF-16BE: got %s", name);
        } else if (conf != 100) {
            errln("Did not get 100%% confidence for UTF-16BE: got %d", conf);
        }
    }

    ucsdet_setText(csd.getAlias(), leBytes.get(), leLength, &status);
    match = ucsdet_detect(csd.getAlias(), &status);

    if (match == NULL) {
        errln("Encoding detection failure for UTF-16LE: got no matches.");
        return;
    }

    name  = ucsdet_getName(match, &status);
    conf = ucsdet_getConfidence(match, &status);

    if (strcmp(name, "UTF-16LE") != 0) {
        errln("Encoding detection failure for UTF-16LE: got %s", name);
        return;
    }

    if (conf != 100) {
        errln("Did not get 100%% confidence for UTF-16LE: got %d", conf);
    }
}

void CharsetDetectionTest::InputFilterTest()
{
    UErrorCode status = U_ZERO_ERROR;
    UnicodeString s(u"<a> <lot> <of> <English> <inside> <the> <markup> Un très petit peu de Français. <to> <confuse> <the> <detector>");
    int32_t byteLength = 0;
    char *bytes = extractBytes(s, "ISO-8859-1", byteLength);
    UCharsetDetector *csd = ucsdet_open(&status);
    const UCharsetMatch *match;
    const char *lang, *name;

    ucsdet_enableInputFilter(csd, TRUE);

    if (!ucsdet_isInputFilterEnabled(csd)) {
        errln("ucsdet_enableInputFilter(csd, TRUE) did not enable input filter!");
    }


    ucsdet_setText(csd, bytes, byteLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("Turning on the input filter resulted in no matches.");
        goto turn_off;
    }

    name = ucsdet_getName(match, &status);

    if (name == NULL || strcmp(name, "ISO-8859-1") != 0) {
        errln("Turning on the input filter resulted in %s rather than ISO-8859-1.", name);
    } else {
        lang = ucsdet_getLanguage(match, &status);

        if (lang == NULL || strcmp(lang, "fr") != 0) {
            errln("Input filter did not strip markup!");
        }
    }

turn_off:
    ucsdet_enableInputFilter(csd, FALSE);
    ucsdet_setText(csd, bytes, byteLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("Turning off the input filter resulted in no matches.");
        goto bail;
    }

    name = ucsdet_getName(match, &status);

    if (name == NULL || strcmp(name, "ISO-8859-1") != 0) {
        errln("Turning off the input filter resulted in %s rather than ISO-8859-1.", name);
    } else {
        lang = ucsdet_getLanguage(match, &status);

        if (lang == NULL || strcmp(lang, "en") != 0) {
            errln("Unfiltered input did not detect as English!");
        }
    }

bail:
    delete[] bytes;
    ucsdet_close(csd);
}

void CharsetDetectionTest::C1BytesTest()
{
#if !UCONFIG_NO_LEGACY_CONVERSION
    UErrorCode status = U_ZERO_ERROR;
    UnicodeString sISO = "This is a small sample of some English text. Just enough to be sure that it detects correctly.";
    UnicodeString ssWindows("This is another small sample of some English text. Just enough to be sure that it detects correctly. It also includes some \\u201CC1\\u201D bytes.", -1, US_INV);
    UnicodeString sWindows  = ssWindows.unescape();
    int32_t lISO = 0, lWindows = 0;
    char *bISO = extractBytes(sISO, "ISO-8859-1", lISO);
    char *bWindows = extractBytes(sWindows, "windows-1252", lWindows);
    UCharsetDetector *csd = ucsdet_open(&status);
    const UCharsetMatch *match;
    const char *name;

    ucsdet_setText(csd, bWindows, lWindows, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errcheckln(status, "English test with C1 bytes got no matches. - %s", u_errorName(status));
        goto bail;
    }

    name  = ucsdet_getName(match, &status);

    if (strcmp(name, "windows-1252") != 0) {
        errln("English text with C1 bytes does not detect as windows-1252, but as %s", name);
    }

    ucsdet_setText(csd, bISO, lISO, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("English text without C1 bytes got no matches.");
        goto bail;
    }

    name  = ucsdet_getName(match, &status);

    if (strcmp(name, "ISO-8859-1") != 0) {
        errln("English text without C1 bytes does not detect as ISO-8859-1, but as %s", name);
    }

bail:
    delete[] bWindows;
    delete[] bISO;

    ucsdet_close(csd);
#endif
}

void CharsetDetectionTest::DetectionTest()
{
#if !UCONFIG_NO_REGULAR_EXPRESSIONS
    UErrorCode status = U_ZERO_ERROR;
    char path[2048];
    const char *testFilePath = getPath(path, "csdetest.xml");

    if (testFilePath == NULL) {
        return; /* Couldn't get path: error message already output. */
    }

    UXMLParser  *parser = UXMLParser::createParser(status);
    if (U_FAILURE(status)) {
        dataerrln("FAIL: UXMLParser::createParser (%s)", u_errorName(status));
        return;
    }

    UXMLElement *root   = parser->parseFile(testFilePath, status);
    if (!assertSuccess( "parseFile",status)) return;

    UnicodeString test_case = UNICODE_STRING_SIMPLE("test-case");
    UnicodeString id_attr   = UNICODE_STRING_SIMPLE("id");
    UnicodeString enc_attr  = UNICODE_STRING_SIMPLE("encodings");

    const UXMLElement *testCase;
    int32_t tc = 0;

    while((testCase = root->nextChildElement(tc)) != NULL) {
        if (testCase->getTagName().compare(test_case) == 0) {
            const UnicodeString *id = testCase->getAttribute(id_attr);
            const UnicodeString *encodings = testCase->getAttribute(enc_attr);
            const UnicodeString  text = testCase->getText(TRUE);
            int32_t encodingCount;
            UnicodeString *encodingList = split(*encodings, CH_SPACE, encodingCount);

            for(int32_t e = 0; e < encodingCount; e += 1) {
                checkEncoding(text, encodingList[e], *id);
            }

            delete[] encodingList;
        }
    }

    delete root;
    delete parser;
#endif
}

void CharsetDetectionTest::IBM424Test()
{
#if !UCONFIG_ONLY_HTML_CONVERSION
    UErrorCode status = U_ZERO_ERROR;
    
    static const UChar chars[] = {
            0x05D4, 0x05E4, 0x05E8, 0x05E7, 0x05DC, 0x05D9, 0x05D8, 0x0020, 0x05D4, 0x05E6, 0x05D1, 0x05D0, 0x05D9, 0x0020, 0x05D4, 0x05E8,
            0x05D0, 0x05E9, 0x05D9, 0x002C, 0x0020, 0x05EA, 0x05EA, 0x0020, 0x05D0, 0x05DC, 0x05D5, 0x05E3, 0x0020, 0x05D0, 0x05D1, 0x05D9,
            0x05D7, 0x05D9, 0x0020, 0x05DE, 0x05E0, 0x05D3, 0x05DC, 0x05D1, 0x05DC, 0x05D9, 0x05D8, 0x002C, 0x0020, 0x05D4, 0x05D5, 0x05E8,
            0x05D4, 0x0020, 0x05E2, 0x05DC, 0x0020, 0x05E4, 0x05EA, 0x05D9, 0x05D7, 0x05EA, 0x0020, 0x05D7, 0x05E7, 0x05D9, 0x05E8, 0x05EA,
            0x0020, 0x05DE, 0x05E6, 0x0022, 0x05D7, 0x0020, 0x05D1, 0x05E2, 0x05E7, 0x05D1, 0x05D5, 0x05EA, 0x0020, 0x05E2, 0x05D3, 0x05D5,
            0x05D9, 0x05D5, 0x05EA, 0x0020, 0x05D7, 0x05D9, 0x05D9, 0x05DC, 0x05D9, 0x0020, 0x05E6, 0x05D4, 0x0022, 0x05DC, 0x0020, 0x05DE,
            0x05DE, 0x05D1, 0x05E6, 0x05E2, 0x0020, 0x05E2, 0x05D5, 0x05E4, 0x05E8, 0x05EA, 0x0020, 0x05D9, 0x05E6, 0x05D5, 0x05E7, 0x05D4,
            0x0020, 0x05D1, 0x002B, 0x0020, 0x05E8, 0x05E6, 0x05D5, 0x05E2, 0x05EA, 0x0020, 0x05E2, 0x05D6, 0x05D4, 0x002E, 0x0020, 0x05DC,
            0x05D3, 0x05D1, 0x05E8, 0x05D9, 0x0020, 0x05D4, 0x05E4, 0x05E6, 0x0022, 0x05E8, 0x002C, 0x0020, 0x05DE, 0x05D4, 0x05E2, 0x05D3,
            0x05D5, 0x05D9, 0x05D5, 0x05EA, 0x0020, 0x05E2, 0x05D5, 0x05DC, 0x05D4, 0x0020, 0x05EA, 0x05DE, 0x05D5, 0x05E0, 0x05D4, 0x0020,
            0x05E9, 0x05DC, 0x0020, 0x0022, 0x05D4, 0x05EA, 0x05E0, 0x05D4, 0x05D2, 0x05D5, 0x05EA, 0x0020, 0x05E4, 0x05E1, 0x05D5, 0x05DC,
            0x05D4, 0x0020, 0x05DC, 0x05DB, 0x05D0, 0x05D5, 0x05E8, 0x05D4, 0x0020, 0x05E9, 0x05DC, 0x0020, 0x05D7, 0x05D9, 0x05D9, 0x05DC,
            0x05D9, 0x05DD, 0x0020, 0x05D1, 0x05DE, 0x05D4, 0x05DC, 0x05DA, 0x0020, 0x05DE, 0x05D1, 0x05E6, 0x05E2, 0x0020, 0x05E2, 0x05D5,
            0x05E4, 0x05E8, 0x05EA, 0x0020, 0x05D9, 0x05E6, 0x05D5, 0x05E7, 0x05D4, 0x0022, 0x002E, 0x0020, 0x05DE, 0x05E0, 0x05D3, 0x05DC,
            0x05D1, 0x05DC, 0x05D9, 0x05D8, 0x0020, 0x05E7, 0x05D9, 0x05D1, 0x05DC, 0x0020, 0x05D0, 0x05EA, 0x0020, 0x05D4, 0x05D7, 0x05DC,
            0x05D8, 0x05EA, 0x05D5, 0x0020, 0x05DC, 0x05D0, 0x05D7, 0x05E8, 0x0020, 0x05E9, 0x05E2, 0x05D9, 0x05D9, 0x05DF, 0x0020, 0x05D1,
            0x05EA, 0x05DE, 0x05DC, 0x05D9, 0x05DC, 0x0020, 0x05D4, 0x05E2, 0x05D3, 0x05D5, 0x05D9, 0x05D5, 0x05EA, 0x0000
    };
    
    static const UChar chars_reverse[] = {
            0x05EA, 0x05D5, 0x05D9, 0x05D5, 0x05D3, 0x05E2, 0x05D4, 0x0020, 0x05DC, 0x05D9, 0x05DC, 0x05DE, 0x05EA,
            0x05D1, 0x0020, 0x05DF, 0x05D9, 0x05D9, 0x05E2, 0x05E9, 0x0020, 0x05E8, 0x05D7, 0x05D0, 0x05DC, 0x0020, 0x05D5, 0x05EA, 0x05D8,
            0x05DC, 0x05D7, 0x05D4, 0x0020, 0x05EA, 0x05D0, 0x0020, 0x05DC, 0x05D1, 0x05D9, 0x05E7, 0x0020, 0x05D8, 0x05D9, 0x05DC, 0x05D1,
            0x05DC, 0x05D3, 0x05E0, 0x05DE, 0x0020, 0x002E, 0x0022, 0x05D4, 0x05E7, 0x05D5, 0x05E6, 0x05D9, 0x0020, 0x05EA, 0x05E8, 0x05E4,
            0x05D5, 0x05E2, 0x0020, 0x05E2, 0x05E6, 0x05D1, 0x05DE, 0x0020, 0x05DA, 0x05DC, 0x05D4, 0x05DE, 0x05D1, 0x0020, 0x05DD, 0x05D9,
            0x05DC, 0x05D9, 0x05D9, 0x05D7, 0x0020, 0x05DC, 0x05E9, 0x0020, 0x05D4, 0x05E8, 0x05D5, 0x05D0, 0x05DB, 0x05DC, 0x0020, 0x05D4,
            0x05DC, 0x05D5, 0x05E1, 0x05E4, 0x0020, 0x05EA, 0x05D5, 0x05D2, 0x05D4, 0x05E0, 0x05EA, 0x05D4, 0x0022, 0x0020, 0x05DC, 0x05E9,
            0x0020, 0x05D4, 0x05E0, 0x05D5, 0x05DE, 0x05EA, 0x0020, 0x05D4, 0x05DC, 0x05D5, 0x05E2, 0x0020, 0x05EA, 0x05D5, 0x05D9, 0x05D5,
            0x05D3, 0x05E2, 0x05D4, 0x05DE, 0x0020, 0x002C, 0x05E8, 0x0022, 0x05E6, 0x05E4, 0x05D4, 0x0020, 0x05D9, 0x05E8, 0x05D1, 0x05D3,
            0x05DC, 0x0020, 0x002E, 0x05D4, 0x05D6, 0x05E2, 0x0020, 0x05EA, 0x05E2, 0x05D5, 0x05E6, 0x05E8, 0x0020, 0x002B, 0x05D1, 0x0020,
            0x05D4, 0x05E7, 0x05D5, 0x05E6, 0x05D9, 0x0020, 0x05EA, 0x05E8, 0x05E4, 0x05D5, 0x05E2, 0x0020, 0x05E2, 0x05E6, 0x05D1, 0x05DE,
            0x05DE, 0x0020, 0x05DC, 0x0022, 0x05D4, 0x05E6, 0x0020, 0x05D9, 0x05DC, 0x05D9, 0x05D9, 0x05D7, 0x0020, 0x05EA, 0x05D5, 0x05D9,
            0x05D5, 0x05D3, 0x05E2, 0x0020, 0x05EA, 0x05D5, 0x05D1, 0x05E7, 0x05E2, 0x05D1, 0x0020, 0x05D7, 0x0022, 0x05E6, 0x05DE, 0x0020,
            0x05EA, 0x05E8, 0x05D9, 0x05E7, 0x05D7, 0x0020, 0x05EA, 0x05D7, 0x05D9, 0x05EA, 0x05E4, 0x0020, 0x05DC, 0x05E2, 0x0020, 0x05D4,
            0x05E8, 0x05D5, 0x05D4, 0x0020, 0x002C, 0x05D8, 0x05D9, 0x05DC, 0x05D1, 0x05DC, 0x05D3, 0x05E0, 0x05DE, 0x0020, 0x05D9, 0x05D7,
            0x05D9, 0x05D1, 0x05D0, 0x0020, 0x05E3, 0x05D5, 0x05DC, 0x05D0, 0x0020, 0x05EA, 0x05EA, 0x0020, 0x002C, 0x05D9, 0x05E9, 0x05D0,
            0x05E8, 0x05D4, 0x0020, 0x05D9, 0x05D0, 0x05D1, 0x05E6, 0x05D4, 0x0020, 0x05D8, 0x05D9, 0x05DC, 0x05E7, 0x05E8, 0x05E4, 0x05D4,
            0x0000
    };

    int32_t bLength = 0, brLength = 0;
    
    UnicodeString s1(chars);
    UnicodeString s2(chars_reverse);
    
    char *bytes = extractBytes(s1, "IBM424", bLength);
    char *bytes_r = extractBytes(s2, "IBM424", brLength);
    
    UCharsetDetector *csd = ucsdet_open(&status);
	ucsdet_setDetectableCharset(csd, "IBM424_rtl", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM424_ltr", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM420_rtl", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM420_ltr", TRUE, &status);
    if (U_FAILURE(status)) {
        errln("Error opening charset detector. - %s", u_errorName(status));
    }
    const UCharsetMatch *match;
    const char *name;

    ucsdet_setText(csd, bytes, bLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errcheckln(status, "Encoding detection failure for IBM424_rtl: got no matches. - %s", u_errorName(status));
        goto bail;
    }

    name  = ucsdet_getName(match, &status);
    if (strcmp(name, "IBM424_rtl") != 0) {
        errln("Encoding detection failure for IBM424_rtl: got %s", name);
    }
    
    ucsdet_setText(csd, bytes_r, brLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("Encoding detection failure for IBM424_ltr: got no matches.");
        goto bail;
    }

    name  = ucsdet_getName(match, &status);
    if (strcmp(name, "IBM424_ltr") != 0) {
        errln("Encoding detection failure for IBM424_ltr: got %s", name);
    }

bail:
    delete[] bytes;
    delete[] bytes_r;
    ucsdet_close(csd);
#endif
}

void CharsetDetectionTest::IBM420Test()
{
#if !UCONFIG_ONLY_HTML_CONVERSION
    UErrorCode status = U_ZERO_ERROR;
    
    static const UChar chars[] = {
        0x0648, 0x064F, 0x0636, 0x0639, 0x062A, 0x0020, 0x0648, 0x0646, 0x064F, 0x0641, 0x0630, 0x062A, 0x0020, 0x0628, 0x0631, 0x0627,
        0x0645, 0x062C, 0x0020, 0x062A, 0x0623, 0x0645, 0x064A, 0x0646, 0x0020, 0x0639, 0x062F, 0x064A, 0x062F, 0x0629, 0x0020, 0x0641,
        0x064A, 0x0020, 0x0645, 0x0624, 0x0633, 0x0633, 0x0629, 0x0020, 0x0627, 0x0644, 0x062A, 0x0623, 0x0645, 0x064A, 0x0646, 0x0020,
        0x0627, 0x0644, 0x0648, 0x0637, 0x0646, 0x064A, 0x002C, 0x0020, 0x0645, 0x0639, 0x0020, 0x0645, 0x0644, 0x0627, 0x0626, 0x0645,
        0x062A, 0x0647, 0x0627, 0x0020, 0x062F, 0x0627, 0x0626, 0x0645, 0x0627, 0x064B, 0x0020, 0x0644, 0x0644, 0x0627, 0x062D, 0x062A,
        0x064A, 0x0627, 0x062C, 0x0627, 0x062A, 0x0020, 0x0627, 0x0644, 0x0645, 0x062A, 0x063A, 0x064A, 0x0631, 0x0629, 0x0020, 0x0644,
        0x0644, 0x0645, 0x062C, 0x062A, 0x0645, 0x0639, 0x0020, 0x0648, 0x0644, 0x0644, 0x062F, 0x0648, 0x0644, 0x0629, 0x002E, 0x0020,
        0x062A, 0x0648, 0x0633, 0x0639, 0x062A, 0x0020, 0x0648, 0x062A, 0x0637, 0x0648, 0x0631, 0x062A, 0x0020, 0x0627, 0x0644, 0x0645,
        0x0624, 0x0633, 0x0633, 0x0629, 0x0020, 0x0628, 0x0647, 0x062F, 0x0641, 0x0020, 0x0636, 0x0645, 0x0627, 0x0646, 0x0020, 0x0634,
        0x0628, 0x0643, 0x0629, 0x0020, 0x0623, 0x0645, 0x0627, 0x0646, 0x0020, 0x0644, 0x0633, 0x0643, 0x0627, 0x0646, 0x0020, 0x062F,
        0x0648, 0x0644, 0x0629, 0x0020, 0x0627, 0x0633, 0x0631, 0x0627, 0x0626, 0x064A, 0x0644, 0x0020, 0x0628, 0x0648, 0x062C, 0x0647,
        0x0020, 0x0627, 0x0644, 0x0645, 0x062E, 0x0627, 0x0637, 0x0631, 0x0020, 0x0627, 0x0644, 0x0627, 0x0642, 0x062A, 0x0635, 0x0627,
        0x062F, 0x064A, 0x0629, 0x0020, 0x0648, 0x0627, 0x0644, 0x0627, 0x062C, 0x062A, 0x0645, 0x0627, 0x0639, 0x064A, 0x0629, 0x002E,
        0x0000
    };
    static const UChar chars_reverse[] = {
        0x002E, 0x0629, 0x064A, 0x0639, 0x0627, 0x0645, 0x062A, 0x062C, 0x0627, 0x0644, 0x0627, 0x0648, 0x0020, 0x0629, 0x064A, 0x062F,
        0x0627, 0x0635, 0x062A, 0x0642, 0x0627, 0x0644, 0x0627, 0x0020, 0x0631, 0x0637, 0x0627, 0x062E, 0x0645, 0x0644, 0x0627, 0x0020,
        0x0647, 0x062C, 0x0648, 0x0628, 0x0020, 0x0644, 0x064A, 0x0626, 0x0627, 0x0631, 0x0633, 0x0627, 0x0020, 0x0629, 0x0644, 0x0648,
        0x062F, 0x0020, 0x0646, 0x0627, 0x0643, 0x0633, 0x0644, 0x0020, 0x0646, 0x0627, 0x0645, 0x0623, 0x0020, 0x0629, 0x0643, 0x0628,
        0x0634, 0x0020, 0x0646, 0x0627, 0x0645, 0x0636, 0x0020, 0x0641, 0x062F, 0x0647, 0x0628, 0x0020, 0x0629, 0x0633, 0x0633, 0x0624,
        0x0645, 0x0644, 0x0627, 0x0020, 0x062A, 0x0631, 0x0648, 0x0637, 0x062A, 0x0648, 0x0020, 0x062A, 0x0639, 0x0633, 0x0648, 0x062A,
        0x0020, 0x002E, 0x0629, 0x0644, 0x0648, 0x062F, 0x0644, 0x0644, 0x0648, 0x0020, 0x0639, 0x0645, 0x062A, 0x062C, 0x0645, 0x0644,
        0x0644, 0x0020, 0x0629, 0x0631, 0x064A, 0x063A, 0x062A, 0x0645, 0x0644, 0x0627, 0x0020, 0x062A, 0x0627, 0x062C, 0x0627, 0x064A,
        0x062A, 0x062D, 0x0627, 0x0644, 0x0644, 0x0020, 0x064B, 0x0627, 0x0645, 0x0626, 0x0627, 0x062F, 0x0020, 0x0627, 0x0647, 0x062A,
        0x0645, 0x0626, 0x0627, 0x0644, 0x0645, 0x0020, 0x0639, 0x0645, 0x0020, 0x002C, 0x064A, 0x0646, 0x0637, 0x0648, 0x0644, 0x0627,
        0x0020, 0x0646, 0x064A, 0x0645, 0x0623, 0x062A, 0x0644, 0x0627, 0x0020, 0x0629, 0x0633, 0x0633, 0x0624, 0x0645, 0x0020, 0x064A,
        0x0641, 0x0020, 0x0629, 0x062F, 0x064A, 0x062F, 0x0639, 0x0020, 0x0646, 0x064A, 0x0645, 0x0623, 0x062A, 0x0020, 0x062C, 0x0645,
        0x0627, 0x0631, 0x0628, 0x0020, 0x062A, 0x0630, 0x0641, 0x064F, 0x0646, 0x0648, 0x0020, 0x062A, 0x0639, 0x0636, 0x064F, 0x0648,
        0x0000,
    };
    
    int32_t bLength = 0, brLength = 0;
    
    UnicodeString s1(chars);
    UnicodeString s2(chars_reverse);
    
    char *bytes = extractBytes(s1, "IBM420", bLength);
    char *bytes_r = extractBytes(s2, "IBM420", brLength);
    
    UCharsetDetector *csd = ucsdet_open(&status);
    if (U_FAILURE(status)) {
        errln("Error opening charset detector. - %s", u_errorName(status));
    }
	ucsdet_setDetectableCharset(csd, "IBM424_rtl", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM424_ltr", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM420_rtl", TRUE, &status);
	ucsdet_setDetectableCharset(csd, "IBM420_ltr", TRUE, &status);
    const UCharsetMatch *match;
    const char *name;

    ucsdet_setText(csd, bytes, bLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errcheckln(status, "Encoding detection failure for IBM420_rtl: got no matches. - %s", u_errorName(status));
        goto bail;
    }

    name  = ucsdet_getName(match, &status);
    if (strcmp(name, "IBM420_rtl") != 0) {
        errln("Encoding detection failure for IBM420_rtl: got %s\n", name);
    }
    
    ucsdet_setText(csd, bytes_r, brLength, &status);
    match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        errln("Encoding detection failure for IBM420_ltr: got no matches.\n");
        goto bail;
    }

    name  = ucsdet_getName(match, &status);
    if (strcmp(name, "IBM420_ltr") != 0) {
        errln("Encoding detection failure for IBM420_ltr: got %s\n", name);
    }

bail:
    delete[] bytes;
    delete[] bytes_r;
    ucsdet_close(csd);
#endif
}


void CharsetDetectionTest::Ticket6394Test() {
#if !UCONFIG_NO_CONVERSION
    const char charText[] =  "Here is some random English text that should be detected as ISO-8859-1."
                             "Ticket 6394 claims that ISO-8859-1 will appear in the array of detected "
                             "encodings more than once.  The hop through UnicodeString is for platforms " 
                             "where this char * string is be EBCDIC and needs conversion to Latin1.";
    char latin1Text[sizeof(charText)];
    UnicodeString(charText).extract(0, sizeof(charText)-2, latin1Text, sizeof(latin1Text), "ISO-8859-1");

    UErrorCode status = U_ZERO_ERROR;
    UCharsetDetector *csd = ucsdet_open(&status);
    ucsdet_setText(csd, latin1Text, -1, &status);
    if (U_FAILURE(status)) {
        errln("Fail at file %s, line %d.  status = %s", __FILE__, __LINE__, u_errorName(status));
        return;
    }

    int32_t matchCount = 0;
    const UCharsetMatch **matches = ucsdet_detectAll(csd, &matchCount, &status);
    if (U_FAILURE(status)) {
        errln("Fail at file %s, line %d.  status = %s", __FILE__, __LINE__, u_errorName(status));
        return;
    }

    UnicodeSet  setOfCharsetNames;    // UnicodeSets can hold strings.
    int32_t i;
    for (i=0; i<matchCount; i++) {
        UnicodeString charSetName(ucsdet_getName(matches[i], &status));
        if (U_FAILURE(status)) {
            errln("Fail at file %s, line %d.  status = %s;  i=%d", __FILE__, __LINE__, u_errorName(status), i);
            status = U_ZERO_ERROR;
        }
        if (setOfCharsetNames.contains(charSetName)) {
            errln("Fail at file %s, line %d ", __FILE__, __LINE__);
            errln(UnicodeString("   Duplicate charset name = ") + charSetName);
        }
        setOfCharsetNames.add(charSetName);
    }
    ucsdet_close(csd);
#endif
}


// Ticket 6954 - trouble with the haveC1Bytes flag that is used to distinguish between
//               similar Windows and non-Windows SBCS encodings. State was kept in the shared
//               Charset Recognizer objects, and could be overwritten.
void CharsetDetectionTest::Ticket6954Test() {
#if !UCONFIG_NO_CONVERSION && !UCONFIG_NO_LEGACY_CONVERSION && !UCONFIG_NO_FORMATTING
    UErrorCode status = U_ZERO_ERROR;
    UnicodeString sISO = "This is a small sample of some English text. Just enough to be sure that it detects correctly.";
    UnicodeString ssWindows("This is another small sample of some English text. Just enough to be sure that it detects correctly."
                            "It also includes some \\u201CC1\\u201D bytes.", -1, US_INV);
    UnicodeString sWindows  = ssWindows.unescape();
    int32_t lISO = 0, lWindows = 0;
    std::unique_ptr<char[]> bISO(extractBytes(sISO, "ISO-8859-1", lISO));
    std::unique_ptr<char[]> bWindows(extractBytes(sWindows, "windows-1252", lWindows));

    // First do a plain vanilla detect of 1252 text

    LocalUCharsetDetectorPointer csd1(ucsdet_open(&status));
    ucsdet_setText(csd1.getAlias(), bWindows.get(), lWindows, &status);
    const UCharsetMatch *match1 = ucsdet_detect(csd1.getAlias(), &status);
    const char *name1 = ucsdet_getName(match1, &status);
    TEST_ASSERT_SUCCESS(status);
    TEST_ASSERT(strcmp(name1, "windows-1252")==0);

    // Next, using a completely separate detector, detect some 8859-1 text

    LocalUCharsetDetectorPointer csd2(ucsdet_open(&status));
    ucsdet_setText(csd2.getAlias(), bISO.get(), lISO, &status);
    const UCharsetMatch *match2 = ucsdet_detect(csd2.getAlias(), &status);
    const char *name2 = ucsdet_getName(match2, &status);
    TEST_ASSERT_SUCCESS(status);
    TEST_ASSERT(strcmp(name2, "ISO-8859-1")==0);

    // Recheck the 1252 results from the first detector, which should not have been
    //  altered by the use of a different detector.

    name1 = ucsdet_getName(match1, &status);
    TEST_ASSERT_SUCCESS(status);
    TEST_ASSERT(strcmp(name1, "windows-1252")==0);
#endif
}


// Ticket 21823 - Issue with Charset Detector for ill-formed input strings. 
//                Its fix involves returning a failure based error code 
//                (U_INVALID_CHAR_FOUND) incase no charsets appear to match the input data.
void CharsetDetectionTest::Ticket21823Test() {
    UErrorCode status = U_ZERO_ERROR;
    std::string str = "\x80";
    UCharsetDetector* csd = ucsdet_open(&status);

    ucsdet_setText(csd, str.data(), str.length(), &status);
    const UCharsetMatch* match = ucsdet_detect(csd, &status);

    if (match == NULL) {
        TEST_ASSERT(U_FAILURE(status));
    }

    ucsdet_close(csd);
}