summaryrefslogtreecommitdiff
path: root/Build/source/libs/icu/icu-4.4/tools/toolutil/swapimpl.cpp
blob: 011cae5eecbbef3d531c46680b489d2d209041d7 (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
/*
*******************************************************************************
*
*   Copyright (C) 2005-2010, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  swapimpl.cpp
*   encoding:   US-ASCII
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2005may05
*   created by: Markus W. Scherer
*
*   Data file swapping functions moved here from the common library
*   because some data is hardcoded in ICU4C and needs not be swapped any more.
*   Moving the functions here simplifies testing (for code coverage) because
*   we need not jump through hoops (like adding snapshots of these files
*   to testdata).
*
*   The declarations for these functions remain in the internal header files
*   in icu/source/common/
*/

#include "unicode/utypes.h"
#include "unicode/putil.h"
#include "unicode/udata.h"

/* Explicit include statement for std_string.h is needed
 * for compilation on certain platforms. (e.g. AIX/VACPP)
 */
#include "unicode/std_string.h"

#include "cmemory.h"
#include "cstring.h"
#include "uinvchar.h"
#include "uassert.h"
#include "uarrsort.h"
#include "ucmndata.h"
#include "udataswp.h"

/* swapping implementations in common */

#include "uresdata.h"
#include "ucnv_io.h"
#include "uprops.h"
#include "ucase.h"
#include "ubidi_props.h"
#include "ucol_swp.h"
#include "ucnv_bld.h"
#include "unormimp.h"
#include "normalizer2impl.h"
#include "sprpimpl.h"
#include "propname.h"
#include "rbbidata.h"
#include "triedict.h"

/* swapping implementations in i18n */

#if !UCONFIG_NO_NORMALIZATION
#include "uspoof_impl.h"
#endif


/* definitions */

#define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0]))

/* Unicode properties data swapping ----------------------------------------- */

U_CAPI int32_t U_EXPORT2
uprops_swap(const UDataSwapper *ds,
            const void *inData, int32_t length, void *outData,
            UErrorCode *pErrorCode) {
    const UDataInfo *pInfo;
    int32_t headerSize, i;

    int32_t dataIndexes[UPROPS_INDEX_COUNT];
    const int32_t *inData32;

    /* udata_swapDataHeader checks the arguments */
    headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    /* check data format and format version */
    pInfo=(const UDataInfo *)((const char *)inData+4);
    if(!(
        pInfo->dataFormat[0]==0x55 &&   /* dataFormat="UPro" */
        pInfo->dataFormat[1]==0x50 &&
        pInfo->dataFormat[2]==0x72 &&
        pInfo->dataFormat[3]==0x6f &&
        (3<=pInfo->formatVersion[0] && pInfo->formatVersion[0]<=6) &&
        pInfo->formatVersion[2]==UTRIE_SHIFT &&
        pInfo->formatVersion[3]==UTRIE_INDEX_SHIFT
    )) {
        udata_printError(ds, "uprops_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not a Unicode properties file\n",
                         pInfo->dataFormat[0], pInfo->dataFormat[1],
                         pInfo->dataFormat[2], pInfo->dataFormat[3],
                         pInfo->formatVersion[0]);
        *pErrorCode=U_UNSUPPORTED_ERROR;
        return 0;
    }

    /* the properties file must contain at least the indexes array */
    if(length>=0 && (length-headerSize)<(int32_t)sizeof(dataIndexes)) {
        udata_printError(ds, "uprops_swap(): too few bytes (%d after header) for a Unicode properties file\n",
                         length-headerSize);
        *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
        return 0;
    }

    /* read the indexes */
    inData32=(const int32_t *)((const char *)inData+headerSize);
    for(i=0; i<UPROPS_INDEX_COUNT; ++i) {
        dataIndexes[i]=udata_readInt32(ds, inData32[i]);
    }

    /*
     * comments are copied from the data format description in genprops/store.c
     * indexes[] constants are in uprops.h
     */
    if(length>=0) {
        int32_t *outData32;

        if((length-headerSize)<(4*dataIndexes[UPROPS_RESERVED_INDEX])) {
            udata_printError(ds, "uprops_swap(): too few bytes (%d after header) for a Unicode properties file\n",
                             length-headerSize);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }

        outData32=(int32_t *)((char *)outData+headerSize);

        /* copy everything for inaccessible data (padding) */
        if(inData32!=outData32) {
            uprv_memcpy(outData32, inData32, 4*dataIndexes[UPROPS_RESERVED_INDEX]);
        }

        /* swap the indexes[16] */
        ds->swapArray32(ds, inData32, 4*UPROPS_INDEX_COUNT, outData32, pErrorCode);

        /*
         * swap the main properties UTrie
         * PT serialized properties trie, see utrie.h (byte size: 4*(i0-16))
         */
        utrie_swap(ds,
            inData32+UPROPS_INDEX_COUNT,
            4*(dataIndexes[UPROPS_PROPS32_INDEX]-UPROPS_INDEX_COUNT),
            outData32+UPROPS_INDEX_COUNT,
            pErrorCode);

        /*
         * swap the properties and exceptions words
         * P  const uint32_t props32[i1-i0];
         * E  const uint32_t exceptions[i2-i1];
         */
        ds->swapArray32(ds,
            inData32+dataIndexes[UPROPS_PROPS32_INDEX],
            4*(dataIndexes[UPROPS_EXCEPTIONS_TOP_INDEX]-dataIndexes[UPROPS_PROPS32_INDEX]),
            outData32+dataIndexes[UPROPS_PROPS32_INDEX],
            pErrorCode);

        /*
         * swap the UChars
         * U  const UChar uchars[2*(i3-i2)];
         */
        ds->swapArray16(ds,
            inData32+dataIndexes[UPROPS_EXCEPTIONS_TOP_INDEX],
            4*(dataIndexes[UPROPS_ADDITIONAL_TRIE_INDEX]-dataIndexes[UPROPS_EXCEPTIONS_TOP_INDEX]),
            outData32+dataIndexes[UPROPS_EXCEPTIONS_TOP_INDEX],
            pErrorCode);

        /*
         * swap the additional UTrie
         * i3 additionalTrieIndex; -- 32-bit unit index to the additional trie for more properties
         */
        utrie_swap(ds,
            inData32+dataIndexes[UPROPS_ADDITIONAL_TRIE_INDEX],
            4*(dataIndexes[UPROPS_ADDITIONAL_VECTORS_INDEX]-dataIndexes[UPROPS_ADDITIONAL_TRIE_INDEX]),
            outData32+dataIndexes[UPROPS_ADDITIONAL_TRIE_INDEX],
            pErrorCode);

        /*
         * swap the properties vectors
         * PV const uint32_t propsVectors[(i6-i4)/i5][i5]==uint32_t propsVectors[i6-i4];
         */
        ds->swapArray32(ds,
            inData32+dataIndexes[UPROPS_ADDITIONAL_VECTORS_INDEX],
            4*(dataIndexes[UPROPS_RESERVED_INDEX]-dataIndexes[UPROPS_ADDITIONAL_VECTORS_INDEX]),
            outData32+dataIndexes[UPROPS_ADDITIONAL_VECTORS_INDEX],
            pErrorCode);
    }

    /* i6 reservedItemIndex; -- 32-bit unit index to the top of the properties vectors table */
    return headerSize+4*dataIndexes[UPROPS_RESERVED_INDEX];
}

/* Unicode case mapping data swapping --------------------------------------- */

U_CAPI int32_t U_EXPORT2
ucase_swap(const UDataSwapper *ds,
           const void *inData, int32_t length, void *outData,
           UErrorCode *pErrorCode) {
    const UDataInfo *pInfo;
    int32_t headerSize;

    const uint8_t *inBytes;
    uint8_t *outBytes;

    const int32_t *inIndexes;
    int32_t indexes[16];

    int32_t i, offset, count, size;

    /* udata_swapDataHeader checks the arguments */
    headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    /* check data format and format version */
    pInfo=(const UDataInfo *)((const char *)inData+4);
    if(!(
        pInfo->dataFormat[0]==UCASE_FMT_0 &&    /* dataFormat="cAsE" */
        pInfo->dataFormat[1]==UCASE_FMT_1 &&
        pInfo->dataFormat[2]==UCASE_FMT_2 &&
        pInfo->dataFormat[3]==UCASE_FMT_3 &&
        pInfo->formatVersion[0]==1 &&
        pInfo->formatVersion[2]==UTRIE_SHIFT &&
        pInfo->formatVersion[3]==UTRIE_INDEX_SHIFT
    )) {
        udata_printError(ds, "ucase_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as case mapping data\n",
                         pInfo->dataFormat[0], pInfo->dataFormat[1],
                         pInfo->dataFormat[2], pInfo->dataFormat[3],
                         pInfo->formatVersion[0]);
        *pErrorCode=U_UNSUPPORTED_ERROR;
        return 0;
    }

    inBytes=(const uint8_t *)inData+headerSize;
    outBytes=(uint8_t *)outData+headerSize;

    inIndexes=(const int32_t *)inBytes;

    if(length>=0) {
        length-=headerSize;
        if(length<16*4) {
            udata_printError(ds, "ucase_swap(): too few bytes (%d after header) for case mapping data\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }
    }

    /* read the first 16 indexes (ICU 3.2/format version 1: UCASE_IX_TOP==16, might grow) */
    for(i=0; i<16; ++i) {
        indexes[i]=udata_readInt32(ds, inIndexes[i]);
    }

    /* get the total length of the data */
    size=indexes[UCASE_IX_LENGTH];

    if(length>=0) {
        if(length<size) {
            udata_printError(ds, "ucase_swap(): too few bytes (%d after header) for all of case mapping data\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }

        /* copy the data for inaccessible bytes */
        if(inBytes!=outBytes) {
            uprv_memcpy(outBytes, inBytes, size);
        }

        offset=0;

        /* swap the int32_t indexes[] */
        count=indexes[UCASE_IX_INDEX_TOP]*4;
        ds->swapArray32(ds, inBytes, count, outBytes, pErrorCode);
        offset+=count;

        /* swap the UTrie */
        count=indexes[UCASE_IX_TRIE_SIZE];
        utrie_swap(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        /* swap the uint16_t exceptions[] and unfold[] */
        count=(indexes[UCASE_IX_EXC_LENGTH]+indexes[UCASE_IX_UNFOLD_LENGTH])*2;
        ds->swapArray16(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        U_ASSERT(offset==size);
    }

    return headerSize+size;
}

/* Unicode bidi/shaping data swapping --------------------------------------- */

U_CAPI int32_t U_EXPORT2
ubidi_swap(const UDataSwapper *ds,
           const void *inData, int32_t length, void *outData,
           UErrorCode *pErrorCode) {
    const UDataInfo *pInfo;
    int32_t headerSize;

    const uint8_t *inBytes;
    uint8_t *outBytes;

    const int32_t *inIndexes;
    int32_t indexes[16];

    int32_t i, offset, count, size;

    /* udata_swapDataHeader checks the arguments */
    headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    /* check data format and format version */
    pInfo=(const UDataInfo *)((const char *)inData+4);
    if(!(
        pInfo->dataFormat[0]==UBIDI_FMT_0 &&    /* dataFormat="BiDi" */
        pInfo->dataFormat[1]==UBIDI_FMT_1 &&
        pInfo->dataFormat[2]==UBIDI_FMT_2 &&
        pInfo->dataFormat[3]==UBIDI_FMT_3 &&
        pInfo->formatVersion[0]==1 &&
        pInfo->formatVersion[2]==UTRIE_SHIFT &&
        pInfo->formatVersion[3]==UTRIE_INDEX_SHIFT
    )) {
        udata_printError(ds, "ubidi_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as bidi/shaping data\n",
                         pInfo->dataFormat[0], pInfo->dataFormat[1],
                         pInfo->dataFormat[2], pInfo->dataFormat[3],
                         pInfo->formatVersion[0]);
        *pErrorCode=U_UNSUPPORTED_ERROR;
        return 0;
    }

    inBytes=(const uint8_t *)inData+headerSize;
    outBytes=(uint8_t *)outData+headerSize;

    inIndexes=(const int32_t *)inBytes;

    if(length>=0) {
        length-=headerSize;
        if(length<16*4) {
            udata_printError(ds, "ubidi_swap(): too few bytes (%d after header) for bidi/shaping data\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }
    }

    /* read the first 16 indexes (ICU 3.4/format version 1: UBIDI_IX_TOP==16, might grow) */
    for(i=0; i<16; ++i) {
        indexes[i]=udata_readInt32(ds, inIndexes[i]);
    }

    /* get the total length of the data */
    size=indexes[UBIDI_IX_LENGTH];

    if(length>=0) {
        if(length<size) {
            udata_printError(ds, "ubidi_swap(): too few bytes (%d after header) for all of bidi/shaping data\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }

        /* copy the data for inaccessible bytes */
        if(inBytes!=outBytes) {
            uprv_memcpy(outBytes, inBytes, size);
        }

        offset=0;

        /* swap the int32_t indexes[] */
        count=indexes[UBIDI_IX_INDEX_TOP]*4;
        ds->swapArray32(ds, inBytes, count, outBytes, pErrorCode);
        offset+=count;

        /* swap the UTrie */
        count=indexes[UBIDI_IX_TRIE_SIZE];
        utrie_swap(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        /* swap the uint32_t mirrors[] */
        count=indexes[UBIDI_IX_MIRROR_LENGTH]*4;
        ds->swapArray32(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        /* just skip the uint8_t jgArray[] */
        count=indexes[UBIDI_IX_JG_LIMIT]-indexes[UBIDI_IX_JG_START];
        offset+=count;

        U_ASSERT(offset==size);
    }

    return headerSize+size;
}

/* Unicode normalization data swapping -------------------------------------- */

#if !UCONFIG_NO_NORMALIZATION

U_CAPI int32_t U_EXPORT2
unorm_swap(const UDataSwapper *ds,
           const void *inData, int32_t length, void *outData,
           UErrorCode *pErrorCode) {
    const UDataInfo *pInfo;
    int32_t headerSize;

    const uint8_t *inBytes;
    uint8_t *outBytes;

    const int32_t *inIndexes;
    int32_t indexes[32];

    int32_t i, offset, count, size;

    /* udata_swapDataHeader checks the arguments */
    headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    /* check data format and format version */
    pInfo=(const UDataInfo *)((const char *)inData+4);
    if(!(
        pInfo->dataFormat[0]==0x4e &&   /* dataFormat="Norm" */
        pInfo->dataFormat[1]==0x6f &&
        pInfo->dataFormat[2]==0x72 &&
        pInfo->dataFormat[3]==0x6d &&
        pInfo->formatVersion[0]==2
    )) {
        udata_printError(ds, "unorm_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as unorm.icu\n",
                         pInfo->dataFormat[0], pInfo->dataFormat[1],
                         pInfo->dataFormat[2], pInfo->dataFormat[3],
                         pInfo->formatVersion[0]);
        *pErrorCode=U_UNSUPPORTED_ERROR;
        return 0;
    }

    inBytes=(const uint8_t *)inData+headerSize;
    outBytes=(uint8_t *)outData+headerSize;

    inIndexes=(const int32_t *)inBytes;

    if(length>=0) {
        length-=headerSize;
        if(length<32*4) {
            udata_printError(ds, "unorm_swap(): too few bytes (%d after header) for unorm.icu\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }
    }

    /* read the first 32 indexes (ICU 2.8/format version 2.2: _NORM_INDEX_TOP==32, might grow) */
    for(i=0; i<32; ++i) {
        indexes[i]=udata_readInt32(ds, inIndexes[i]);
    }

    /* calculate the total length of the data */
    size=
        32*4+ /* size of indexes[] */
        indexes[_NORM_INDEX_TRIE_SIZE]+
        indexes[_NORM_INDEX_UCHAR_COUNT]*2+
        indexes[_NORM_INDEX_COMBINE_DATA_COUNT]*2+
        indexes[_NORM_INDEX_FCD_TRIE_SIZE]+
        indexes[_NORM_INDEX_AUX_TRIE_SIZE]+
        indexes[_NORM_INDEX_CANON_SET_COUNT]*2;

    if(length>=0) {
        if(length<size) {
            udata_printError(ds, "unorm_swap(): too few bytes (%d after header) for all of unorm.icu\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }

        /* copy the data for inaccessible bytes */
        if(inBytes!=outBytes) {
            uprv_memcpy(outBytes, inBytes, size);
        }

        offset=0;

        /* swap the indexes[] */
        count=32*4;
        ds->swapArray32(ds, inBytes, count, outBytes, pErrorCode);
        offset+=count;

        /* swap the main UTrie */
        count=indexes[_NORM_INDEX_TRIE_SIZE];
        utrie_swap(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        /* swap the uint16_t extraData[] and the uint16_t combiningTable[] */
        count=(indexes[_NORM_INDEX_UCHAR_COUNT]+indexes[_NORM_INDEX_COMBINE_DATA_COUNT])*2;
        ds->swapArray16(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;

        /* swap the FCD UTrie */
        count=indexes[_NORM_INDEX_FCD_TRIE_SIZE];
        if(count!=0) {
            utrie_swap(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
            offset+=count;
        }

        /* swap the aux UTrie */
        count=indexes[_NORM_INDEX_AUX_TRIE_SIZE];
        if(count!=0) {
            utrie_swap(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
            offset+=count;
        }

        /* swap the uint16_t combiningTable[] */
        count=indexes[_NORM_INDEX_CANON_SET_COUNT]*2;
        ds->swapArray16(ds, inBytes+offset, count, outBytes+offset, pErrorCode);
        offset+=count;
    }

    return headerSize+size;
}

#endif

/* Swap 'Test' data from gentest */
U_CAPI int32_t U_EXPORT2
test_swap(const UDataSwapper *ds,
           const void *inData, int32_t length, void *outData,
           UErrorCode *pErrorCode) {
    const UDataInfo *pInfo;
    int32_t headerSize;

    const uint8_t *inBytes;
    uint8_t *outBytes;

    int32_t offset;

    /* udata_swapDataHeader checks the arguments */
    headerSize=udata_swapDataHeader(ds, inData, length, outData, pErrorCode);
    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        udata_printError(ds, "test_swap(): data header swap failed %s\n", u_errorName(*pErrorCode));
        return 0;
    }

    /* check data format and format version */
    pInfo=(const UDataInfo *)((const char *)inData+4);
    if(!(
        pInfo->dataFormat[0]==0x54 &&   /* dataFormat="Norm" */
        pInfo->dataFormat[1]==0x65 &&
        pInfo->dataFormat[2]==0x73 &&
        pInfo->dataFormat[3]==0x74 &&
        pInfo->formatVersion[0]==1
    )) {
        udata_printError(ds, "test_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as testdata\n",
                         pInfo->dataFormat[0], pInfo->dataFormat[1],
                         pInfo->dataFormat[2], pInfo->dataFormat[3],
                         pInfo->formatVersion[0]);
        *pErrorCode=U_UNSUPPORTED_ERROR;
        return 0;
    }

    inBytes=(const uint8_t *)inData+headerSize;
    outBytes=(uint8_t *)outData+headerSize;

    int32_t size16 = 2; // 16bit plus padding
    int32_t sizeStr = 5; // 4 char inv-str plus null
    int32_t size = size16 + sizeStr;

    if(length>=0) {
        if(length<size) {
            udata_printError(ds, "test_swap(): too few bytes (%d after header, wanted %d) for all of testdata\n",
                             length, size);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }

	offset =0;
	/* swap a 1 entry array */
        ds->swapArray16(ds, inBytes+offset, size16, outBytes+offset, pErrorCode);
	offset+=size16;
	ds->swapInvChars(ds, inBytes+offset, sizeStr, outBytes+offset, pErrorCode);
    }

    return headerSize+size;
}

/* swap any data (except a .dat package) ------------------------------------ */

static const struct {
    uint8_t dataFormat[4];
    UDataSwapFn *swapFn;
} swapFns[]={
    { { 0x52, 0x65, 0x73, 0x42 }, ures_swap },          /* dataFormat="ResB" */
#if !UCONFIG_NO_LEGACY_CONVERSION
    { { 0x63, 0x6e, 0x76, 0x74 }, ucnv_swap },          /* dataFormat="cnvt" */
#endif
#if !UCONFIG_NO_CONVERSION
    { { 0x43, 0x76, 0x41, 0x6c }, ucnv_swapAliases },   /* dataFormat="CvAl" */
#endif
#if !UCONFIG_NO_IDNA
    { { 0x53, 0x50, 0x52, 0x50 }, usprep_swap },        /* dataFormat="SPRP" */
#endif
    /* insert data formats here, descending by expected frequency of occurrence */
    { { 0x55, 0x50, 0x72, 0x6f }, uprops_swap },        /* dataFormat="UPro" */

    { { UCASE_FMT_0, UCASE_FMT_1, UCASE_FMT_2, UCASE_FMT_3 },
                                  ucase_swap },         /* dataFormat="cAsE" */

    { { UBIDI_FMT_0, UBIDI_FMT_1, UBIDI_FMT_2, UBIDI_FMT_3 },
                                  ubidi_swap },         /* dataFormat="BiDi" */

#if !UCONFIG_NO_NORMALIZATION
    { { 0x4e, 0x6f, 0x72, 0x6d }, unorm_swap },         /* dataFormat="Norm" */
    { { 0x4e, 0x72, 0x6d, 0x32 }, unorm2_swap },        /* dataFormat="Nrm2" */
#endif
#if !UCONFIG_NO_COLLATION
    { { 0x55, 0x43, 0x6f, 0x6c }, ucol_swap },          /* dataFormat="UCol" */
    { { 0x49, 0x6e, 0x76, 0x43 }, ucol_swapInverseUCA },/* dataFormat="InvC" */
#endif
#if !UCONFIG_NO_BREAK_ITERATION
    { { 0x42, 0x72, 0x6b, 0x20 }, ubrk_swap },          /* dataFormat="Brk " */
    { { 0x54, 0x72, 0x44, 0x63 }, triedict_swap },      /* dataFormat="TrDc " */
#endif
    { { 0x70, 0x6e, 0x61, 0x6d }, upname_swap },        /* dataFormat="pnam" */
    { { 0x75, 0x6e, 0x61, 0x6d }, uchar_swapNames },    /* dataFormat="unam" */
#if !UCONFIG_NO_NORMALIZATION
    { { 0x43, 0x66, 0x75, 0x20 }, uspoof_swap },         /* dataFormat="Cfu " */
#endif
    { { 0x54, 0x65, 0x73, 0x74 }, test_swap }            /* dataFormat="Test" */
};

U_CAPI int32_t U_EXPORT2
udata_swap(const UDataSwapper *ds,
           const void *inData, int32_t length, void *outData,
           UErrorCode *pErrorCode) {
    char dataFormatChars[4];
    const UDataInfo *pInfo;
    int32_t headerSize, i, swappedLength;

    if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) {
        return 0;
    }

    /*
     * Preflight the header first; checks for illegal arguments, too.
     * Do not swap the header right away because the format-specific swapper
     * will swap it, get the headerSize again, and also use the header
     * information. Otherwise we would have to pass some of the information
     * and not be able to use the UDataSwapFn signature.
     */
    headerSize=udata_swapDataHeader(ds, inData, -1, NULL, pErrorCode);

    /*
     * If we wanted udata_swap() to also handle non-loadable data like a UTrie,
     * then we could check here for further known magic values and structures.
     */
    if(U_FAILURE(*pErrorCode)) {
        return 0; /* the data format was not recognized */
    }

    pInfo=(const UDataInfo *)((const char *)inData+4);

    {
        /* convert the data format from ASCII to Unicode to the system charset */
        UChar u[4]={
             pInfo->dataFormat[0], pInfo->dataFormat[1],
             pInfo->dataFormat[2], pInfo->dataFormat[3]
        };

        if(uprv_isInvariantUString(u, 4)) {
            u_UCharsToChars(u, dataFormatChars, 4);
        } else {
            dataFormatChars[0]=dataFormatChars[1]=dataFormatChars[2]=dataFormatChars[3]='?';
        }
    }

    /* dispatch to the swap function for the dataFormat */
    for(i=0; i<LENGTHOF(swapFns); ++i) {
        if(0==memcmp(swapFns[i].dataFormat, pInfo->dataFormat, 4)) {
            swappedLength=swapFns[i].swapFn(ds, inData, length, outData, pErrorCode);

            if(U_FAILURE(*pErrorCode)) {
                udata_printError(ds, "udata_swap(): failure swapping data format %02x.%02x.%02x.%02x (\"%c%c%c%c\") - %s\n",
                                 pInfo->dataFormat[0], pInfo->dataFormat[1],
                                 pInfo->dataFormat[2], pInfo->dataFormat[3],
                                 dataFormatChars[0], dataFormatChars[1],
                                 dataFormatChars[2], dataFormatChars[3],
                                 u_errorName(*pErrorCode));
            } else if(swappedLength<(length-15)) {
                /* swapped less than expected */
                udata_printError(ds, "udata_swap() warning: swapped only %d out of %d bytes - data format %02x.%02x.%02x.%02x (\"%c%c%c%c\")\n",
                                 swappedLength, length,
                                 pInfo->dataFormat[0], pInfo->dataFormat[1],
                                 pInfo->dataFormat[2], pInfo->dataFormat[3],
                                 dataFormatChars[0], dataFormatChars[1],
                                 dataFormatChars[2], dataFormatChars[3],
                                 u_errorName(*pErrorCode));
            }

            return swappedLength;
        }
    }

    /* the dataFormat was not recognized */
    udata_printError(ds, "udata_swap(): unknown data format %02x.%02x.%02x.%02x (\"%c%c%c%c\")\n",
                     pInfo->dataFormat[0], pInfo->dataFormat[1],
                     pInfo->dataFormat[2], pInfo->dataFormat[3],
                     dataFormatChars[0], dataFormatChars[1],
                     dataFormatChars[2], dataFormatChars[3]);

    *pErrorCode=U_UNSUPPORTED_ERROR;
    return 0;
}