summaryrefslogtreecommitdiff
path: root/Build/source/libs/icu-xetex/common/usprep.cpp
blob: 12d51be3caab46d57c2b63cefa7fcc7225bf86ed (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
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
/*
 *******************************************************************************
 *
 *   Copyright (C) 2003-2007, International Business Machines
 *   Corporation and others.  All Rights Reserved.
 *
 *******************************************************************************
 *   file name:  usprep.cpp
 *   encoding:   US-ASCII
 *   tab size:   8 (not used)
 *   indentation:4
 *
 *   created on: 2003jul2
 *   created by: Ram Viswanadha
 */

#include "unicode/utypes.h"

#if !UCONFIG_NO_IDNA

#include "unicode/usprep.h"

#include "unicode/unorm.h"
#include "unicode/ustring.h"
#include "unicode/uchar.h"
#include "unicode/uversion.h"
#include "umutex.h"
#include "cmemory.h"
#include "sprpimpl.h"
#include "ustr_imp.h"
#include "uhash.h"
#include "cstring.h"
#include "udataswp.h"
#include "ucln_cmn.h"
#include "unormimp.h"
#include "ubidi_props.h"

U_CDECL_BEGIN

/*
Static cache for already opened StringPrep profiles
*/
static UHashtable *SHARED_DATA_HASHTABLE = NULL;

static UMTX usprepMutex = NULL;

/* format version of spp file */
static uint8_t formatVersion[4]={ 0, 0, 0, 0 };

/* the Unicode version of the sprep data */
static UVersionInfo dataVersion={ 0, 0, 0, 0 };

static UBool U_CALLCONV
isSPrepAcceptable(void * /* context */,
             const char * /* type */, 
             const char * /* name */,
             const UDataInfo *pInfo) {
    if(
        pInfo->size>=20 &&
        pInfo->isBigEndian==U_IS_BIG_ENDIAN &&
        pInfo->charsetFamily==U_CHARSET_FAMILY &&
        pInfo->dataFormat[0]==0x53 &&   /* dataFormat="SPRP" */
        pInfo->dataFormat[1]==0x50 &&
        pInfo->dataFormat[2]==0x52 &&
        pInfo->dataFormat[3]==0x50 &&
        pInfo->formatVersion[0]==3 &&
        pInfo->formatVersion[2]==UTRIE_SHIFT &&
        pInfo->formatVersion[3]==UTRIE_INDEX_SHIFT
    ) {
        uprv_memcpy(formatVersion, pInfo->formatVersion, 4);
        uprv_memcpy(dataVersion, pInfo->dataVersion, 4);
        return TRUE;
    } else {
        return FALSE;
    }
}

static int32_t U_CALLCONV
getSPrepFoldingOffset(uint32_t data) {

    return (int32_t)data;

}

/* hashes an entry  */
static int32_t U_CALLCONV 
hashEntry(const UHashTok parm) {
    UStringPrepKey *b = (UStringPrepKey *)parm.pointer;
    UHashTok namekey, pathkey;
    namekey.pointer = b->name;
    pathkey.pointer = b->path;
    return uhash_hashChars(namekey)+37*uhash_hashChars(pathkey);
}

/* compares two entries */
static UBool U_CALLCONV 
compareEntries(const UHashTok p1, const UHashTok p2) {
    UStringPrepKey *b1 = (UStringPrepKey *)p1.pointer;
    UStringPrepKey *b2 = (UStringPrepKey *)p2.pointer;
    UHashTok name1, name2, path1, path2;
    name1.pointer = b1->name;
    name2.pointer = b2->name;
    path1.pointer = b1->path;
    path2.pointer = b2->path;
    return ((UBool)(uhash_compareChars(name1, name2) & 
        uhash_compareChars(path1, path2)));
}

static void 
usprep_unload(UStringPrepProfile* data){
    udata_close(data->sprepData);
}

static int32_t 
usprep_internal_flushCache(UBool noRefCount){
    UStringPrepProfile *profile = NULL;
    UStringPrepKey  *key  = NULL;
    int32_t pos = -1;
    int32_t deletedNum = 0;
    const UHashElement *e;

    /*
     * if shared data hasn't even been lazy evaluated yet
     * return 0
     */
    umtx_lock(&usprepMutex);
    if (SHARED_DATA_HASHTABLE == NULL) {
        umtx_unlock(&usprepMutex);
        return 0;
    }

    /*creates an enumeration to iterate through every element in the table */
    while ((e = uhash_nextElement(SHARED_DATA_HASHTABLE, &pos)) != NULL)
    {
        profile = (UStringPrepProfile *) e->value.pointer;
        key  = (UStringPrepKey *) e->key.pointer;

        if ((noRefCount== FALSE && profile->refCount == 0) || 
             noRefCount== TRUE) {
            deletedNum++;
            uhash_removeElement(SHARED_DATA_HASHTABLE, e);

            /* unload the data */
            usprep_unload(profile);

            if(key->name != NULL) {
                uprv_free(key->name);
                key->name=NULL;
            }
            if(key->path != NULL) {
                uprv_free(key->path);
                key->path=NULL;
            }
            uprv_free(profile);
            uprv_free(key);
        }
       
    }
    umtx_unlock(&usprepMutex);

    return deletedNum;
}

/* Works just like ucnv_flushCache() 
static int32_t 
usprep_flushCache(){
    return usprep_internal_flushCache(FALSE);
}
*/

static UBool U_CALLCONV usprep_cleanup(void){
    if (SHARED_DATA_HASHTABLE != NULL) {
        usprep_internal_flushCache(TRUE);
        if (SHARED_DATA_HASHTABLE != NULL && uhash_count(SHARED_DATA_HASHTABLE) == 0) {
            uhash_close(SHARED_DATA_HASHTABLE);
            SHARED_DATA_HASHTABLE = NULL;
        }
    }

    umtx_destroy(&usprepMutex);             /* Don't worry about destroying the mutex even  */
                                            /*  if the hash table still exists.  The mutex  */
                                            /*  will lazily re-init  itself if needed.      */
    return (SHARED_DATA_HASHTABLE == NULL);
}
U_CDECL_END

static void 
usprep_init() {
    umtx_init(&usprepMutex);
}

/** Initializes the cache for resources */
static void 
initCache(UErrorCode *status) {
    UBool makeCache;
    UMTX_CHECK(&usprepMutex, (SHARED_DATA_HASHTABLE ==  NULL), makeCache);
    if(makeCache) {
        UHashtable *newCache = uhash_open(hashEntry, compareEntries, NULL, status);
        if (U_SUCCESS(*status)) {
            umtx_lock(&usprepMutex);
            if(SHARED_DATA_HASHTABLE == NULL) {
                SHARED_DATA_HASHTABLE = newCache;
                ucln_common_registerCleanup(UCLN_COMMON_USPREP, usprep_cleanup);
                newCache = NULL;
            }
            umtx_unlock(&usprepMutex);
            if(newCache != NULL) {
                uhash_close(newCache);
            }
        }
    }
}

static UBool U_CALLCONV
loadData(UStringPrepProfile* profile, 
         const char* path, 
         const char* name, 
         const char* type, 
         UErrorCode* errorCode) {
    /* load Unicode SPREP data from file */    
    UTrie _sprepTrie={ 0,0,0,0,0,0,0 };
    UDataMemory *dataMemory;
    const int32_t *p=NULL;
    const uint8_t *pb;
    UVersionInfo normUnicodeVersion;
    int32_t normUniVer, sprepUniVer, normCorrVer;

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

    /* open the data outside the mutex block */
    //TODO: change the path
    dataMemory=udata_openChoice(path, type, name, isSPrepAcceptable, NULL, errorCode);
    if(U_FAILURE(*errorCode)) {
        return FALSE;
    }

    p=(const int32_t *)udata_getMemory(dataMemory);
    pb=(const uint8_t *)(p+_SPREP_INDEX_TOP);
    utrie_unserialize(&_sprepTrie, pb, p[_SPREP_INDEX_TRIE_SIZE], errorCode);
    _sprepTrie.getFoldingOffset=getSPrepFoldingOffset;


    if(U_FAILURE(*errorCode)) {
        udata_close(dataMemory);
        return FALSE;
    }

    /* in the mutex block, set the data for this process */
    umtx_lock(&usprepMutex);
    if(profile->sprepData==NULL) {
        profile->sprepData=dataMemory;
        dataMemory=NULL;
        uprv_memcpy(&profile->indexes, p, sizeof(profile->indexes));
        uprv_memcpy(&profile->sprepTrie, &_sprepTrie, sizeof(UTrie));
    } else {
        p=(const int32_t *)udata_getMemory(profile->sprepData);
    }
    umtx_unlock(&usprepMutex);
    /* initialize some variables */
    profile->mappingData=(uint16_t *)((uint8_t *)(p+_SPREP_INDEX_TOP)+profile->indexes[_SPREP_INDEX_TRIE_SIZE]);
    
    unorm_getUnicodeVersion(&normUnicodeVersion, errorCode);
    normUniVer = (normUnicodeVersion[0] << 24) + (normUnicodeVersion[1] << 16) + 
                 (normUnicodeVersion[2] << 8 ) + (normUnicodeVersion[3]);
    sprepUniVer = (dataVersion[0] << 24) + (dataVersion[1] << 16) + 
                  (dataVersion[2] << 8 ) + (dataVersion[3]);
    normCorrVer = profile->indexes[_SPREP_NORM_CORRECTNS_LAST_UNI_VERSION];
    
    if(U_FAILURE(*errorCode)){
        udata_close(dataMemory);
        return FALSE;
    }
    if( normUniVer < sprepUniVer && /* the Unicode version of SPREP file must be less than the Unicode Vesion of the normalization data */
        normUniVer < normCorrVer && /* the Unicode version of the NormalizationCorrections.txt file should be less than the Unicode Vesion of the normalization data */
        ((profile->indexes[_SPREP_OPTIONS] & _SPREP_NORMALIZATION_ON) > 0) /* normalization turned on*/
      ){
        *errorCode = U_INVALID_FORMAT_ERROR;
        udata_close(dataMemory);
        return FALSE;
    }
    profile->isDataLoaded = TRUE;

    /* if a different thread set it first, then close the extra data */
    if(dataMemory!=NULL) {
        udata_close(dataMemory); /* NULL if it was set correctly */
    }


    return profile->isDataLoaded;
}

static UStringPrepProfile* 
usprep_getProfile(const char* path, 
                  const char* name,
                  UErrorCode *status){

    UStringPrepProfile* profile = NULL;

    initCache(status);

    if(U_FAILURE(*status)){
        return NULL;
    }

    UStringPrepKey stackKey;
    /* 
     * const is cast way to save malloc, strcpy and free calls 
     * we use the passed in pointers for fetching the data from the 
     * hash table which is safe
     */
    stackKey.name = (char*) name;
    stackKey.path = (char*) path;

    /* fetch the data from the cache */
    umtx_lock(&usprepMutex);
    profile = (UStringPrepProfile*) (uhash_get(SHARED_DATA_HASHTABLE,&stackKey));
    umtx_unlock(&usprepMutex);
    
    if(profile == NULL){
        UStringPrepKey* key   = (UStringPrepKey*) uprv_malloc(sizeof(UStringPrepKey));
        if(key == NULL){
            *status = U_MEMORY_ALLOCATION_ERROR;
            return NULL;
        }
        /* else load the data and put the data in the cache */
        profile = (UStringPrepProfile*) uprv_malloc(sizeof(UStringPrepProfile));
        if(profile == NULL){
            *status = U_MEMORY_ALLOCATION_ERROR;
            uprv_free(key);
            return NULL;
        }

        /* initialize the data struct members */
        uprv_memset(profile->indexes,0,sizeof(profile->indexes));
        profile->mappingData = NULL;
        profile->sprepData   = NULL;
        profile->refCount    = 0;
    
        /* initialize the  key memebers */
        key->name  = (char*) uprv_malloc(uprv_strlen(name)+1);
        if(key->name == NULL){
            *status = U_MEMORY_ALLOCATION_ERROR;
            uprv_free(key);
            uprv_free(profile);
            return NULL;
        }

        uprv_strcpy(key->name, name);
        
        key->path=NULL;

        if(path != NULL){
            key->path      = (char*) uprv_malloc(uprv_strlen(path)+1);
            if(key->path == NULL){
                *status = U_MEMORY_ALLOCATION_ERROR;
                uprv_free(key->name);
                uprv_free(key);
                uprv_free(profile);
                return NULL;
            }
            uprv_strcpy(key->path, path);
        }        

        /* load the data */
        if(!loadData(profile, path, name, _SPREP_DATA_TYPE, status) || U_FAILURE(*status) ){
            uprv_free(key->path);
            uprv_free(key->name);
            uprv_free(key);
            uprv_free(profile);
            return NULL;
        }
        
        /* get the options */
        profile->doNFKC            = (UBool)((profile->indexes[_SPREP_OPTIONS] & _SPREP_NORMALIZATION_ON) > 0);
        profile->checkBiDi         = (UBool)((profile->indexes[_SPREP_OPTIONS] & _SPREP_CHECK_BIDI_ON) > 0);

        if(profile->checkBiDi) {
            profile->bdp = ubidi_getSingleton(status);
            if(U_FAILURE(*status)) {
                usprep_unload(profile);
                uprv_free(key->path);
                uprv_free(key->name);
                uprv_free(key);
                uprv_free(profile);
                return NULL;
            }
        } else {
            profile->bdp = NULL;
        }
        
        umtx_lock(&usprepMutex);
        /* add the data object to the cache */
        uhash_put(SHARED_DATA_HASHTABLE, key, profile, status);
        umtx_unlock(&usprepMutex);
    }
    umtx_lock(&usprepMutex);
    /* increment the refcount */
    profile->refCount++;
    umtx_unlock(&usprepMutex);

    return profile;
}

U_CAPI UStringPrepProfile* U_EXPORT2
usprep_open(const char* path, 
            const char* name,
            UErrorCode* status){

    if(status == NULL || U_FAILURE(*status)){
        return NULL;
    }
    /* initialize the mutex */
    usprep_init();
       
    /* initialize the profile struct members */
    return usprep_getProfile(path,name,status);
}

U_CAPI void U_EXPORT2
usprep_close(UStringPrepProfile* profile){
    if(profile==NULL){
        return;
    }

    umtx_lock(&usprepMutex);
    /* decrement the ref count*/
    if(profile->refCount > 0){
        profile->refCount--;
    }
    umtx_unlock(&usprepMutex);
    
}

U_CFUNC void 
uprv_syntaxError(const UChar* rules, 
                 int32_t pos,
                 int32_t rulesLen,
                 UParseError* parseError){
    if(parseError == NULL){
        return;
    }
    parseError->offset = pos;
    parseError->line = 0 ; // we are not using line numbers 
    
    // for pre-context
    int32_t start = (pos < U_PARSE_CONTEXT_LEN)? 0 : (pos - (U_PARSE_CONTEXT_LEN-1));
    int32_t limit = pos;
    
    u_memcpy(parseError->preContext,rules+start,limit-start);
    //null terminate the buffer
    parseError->preContext[limit-start] = 0;
    
    // for post-context; include error rules[pos]
    start = pos;
    limit = start + (U_PARSE_CONTEXT_LEN-1);
    if (limit > rulesLen) {
        limit = rulesLen;
    }
    if (start < rulesLen) {
        u_memcpy(parseError->postContext,rules+start,limit-start);
    }
    //null terminate the buffer
    parseError->postContext[limit-start]= 0;
}


static inline UStringPrepType
getValues(uint16_t trieWord, int16_t& value, UBool& isIndex){

    UStringPrepType type;
    if(trieWord == 0){
        /* 
         * Initial value stored in the mapping table 
         * just return USPREP_TYPE_LIMIT .. so that
         * the source codepoint is copied to the destination
         */
        type = USPREP_TYPE_LIMIT;
        isIndex =FALSE;
        value = 0;
    }else if(trieWord >= _SPREP_TYPE_THRESHOLD){
        type = (UStringPrepType) (trieWord - _SPREP_TYPE_THRESHOLD);
        isIndex =FALSE;
        value = 0;
    }else{
        /* get the type */
        type = USPREP_MAP;
        /* ascertain if the value is index or delta */
        if(trieWord & 0x02){
            isIndex = TRUE;
            value = trieWord  >> 2; //mask off the lower 2 bits and shift
        }else{
            isIndex = FALSE;
            value = (int16_t)trieWord;
            value =  (value >> 2);
        }
 
        if((trieWord>>2) == _SPREP_MAX_INDEX_VALUE){
            type = USPREP_DELETE;
            isIndex =FALSE;
            value = 0;
        }
    }
    return type;
}



static int32_t 
usprep_map(  const UStringPrepProfile* profile, 
             const UChar* src, int32_t srcLength, 
             UChar* dest, int32_t destCapacity,
             int32_t options,
             UParseError* parseError,
             UErrorCode* status ){
    
    uint16_t result;
    int32_t destIndex=0;
    int32_t srcIndex;
    UBool allowUnassigned = (UBool) ((options & USPREP_ALLOW_UNASSIGNED)>0);
    UStringPrepType type;
    int16_t value;
    UBool isIndex;
    const int32_t* indexes = profile->indexes;

    // no error checking the caller check for error and arguments
    // no string length check the caller finds out the string length

    for(srcIndex=0;srcIndex<srcLength;){
        UChar32 ch;

        U16_NEXT(src,srcIndex,srcLength,ch);
        
        result=0;

        UTRIE_GET16(&profile->sprepTrie,ch,result);
        
        type = getValues(result, value, isIndex);

        // check if the source codepoint is unassigned
        if(type == USPREP_UNASSIGNED && allowUnassigned == FALSE){

            uprv_syntaxError(src,srcIndex-U16_LENGTH(ch), srcLength,parseError);
            *status = U_STRINGPREP_UNASSIGNED_ERROR;
            return 0;
            
        }else if(type == USPREP_MAP){
            
            int32_t index, length;

            if(isIndex){
                index = value;
                if(index >= indexes[_SPREP_ONE_UCHAR_MAPPING_INDEX_START] &&
                         index < indexes[_SPREP_TWO_UCHARS_MAPPING_INDEX_START]){
                    length = 1;
                }else if(index >= indexes[_SPREP_TWO_UCHARS_MAPPING_INDEX_START] &&
                         index < indexes[_SPREP_THREE_UCHARS_MAPPING_INDEX_START]){
                    length = 2;
                }else if(index >= indexes[_SPREP_THREE_UCHARS_MAPPING_INDEX_START] &&
                         index < indexes[_SPREP_FOUR_UCHARS_MAPPING_INDEX_START]){
                    length = 3;
                }else{
                    length = profile->mappingData[index++];
         
                }

                /* copy mapping to destination */
                for(int32_t i=0; i< length; i++){
                    if(destIndex < destCapacity  ){
                        dest[destIndex] = profile->mappingData[index+i];
                    }
                    destIndex++; /* for pre-flighting */
                }  
                continue;
            }else{
                // subtract the delta to arrive at the code point
                ch -= value;
            }

        }else if(type==USPREP_DELETE){
             // just consume the codepoint and contine
            continue;
        }
        //copy the code point into destination
        if(ch <= 0xFFFF){
            if(destIndex < destCapacity ){
                dest[destIndex] = (UChar)ch;
            }
            destIndex++;
        }else{
            if(destIndex+1 < destCapacity ){
                dest[destIndex]   = U16_LEAD(ch);
                dest[destIndex+1] = U16_TRAIL(ch);
            }
            destIndex +=2;
        }
       
    }
        
    return u_terminateUChars(dest, destCapacity, destIndex, status);
}


static int32_t 
usprep_normalize(   const UChar* src, int32_t srcLength, 
                    UChar* dest, int32_t destCapacity,
                    UErrorCode* status ){
    /*
     * Option UNORM_BEFORE_PRI_29:
     *
     * IDNA as interpreted by IETF members (see unicode mailing list 2004H1)
     * requires strict adherence to Unicode 3.2 normalization,
     * including buggy composition from before fixing Public Review Issue #29.
     * Note that this results in some valid but nonsensical text to be
     * either corrupted or rejected, depending on the text.
     * See http://www.unicode.org/review/resolved-pri.html#pri29
     * See unorm.cpp and cnormtst.c
     */
    return unorm_normalize(
        src, srcLength,
        UNORM_NFKC, UNORM_UNICODE_3_2|UNORM_BEFORE_PRI_29,
        dest, destCapacity,
        status);
}


 /*
   1) Map -- For each character in the input, check if it has a mapping
      and, if so, replace it with its mapping.  

   2) Normalize -- Possibly normalize the result of step 1 using Unicode
      normalization. 

   3) Prohibit -- Check for any characters that are not allowed in the
      output.  If any are found, return an error.  

   4) Check bidi -- Possibly check for right-to-left characters, and if
      any are found, make sure that the whole string satisfies the
      requirements for bidirectional strings.  If the string does not
      satisfy the requirements for bidirectional strings, return an
      error.  
      [Unicode3.2] defines several bidirectional categories; each character
       has one bidirectional category assigned to it.  For the purposes of
       the requirements below, an "RandALCat character" is a character that
       has Unicode bidirectional categories "R" or "AL"; an "LCat character"
       is a character that has Unicode bidirectional category "L".  Note


       that there are many characters which fall in neither of the above
       definitions; Latin digits (<U+0030> through <U+0039>) are examples of
       this because they have bidirectional category "EN".

       In any profile that specifies bidirectional character handling, all
       three of the following requirements MUST be met:

       1) The characters in section 5.8 MUST be prohibited.

       2) If a string contains any RandALCat character, the string MUST NOT
          contain any LCat character.

       3) If a string contains any RandALCat character, a RandALCat
          character MUST be the first character of the string, and a
          RandALCat character MUST be the last character of the string.
*/

#define MAX_STACK_BUFFER_SIZE 300


U_CAPI int32_t U_EXPORT2
usprep_prepare(   const UStringPrepProfile* profile,
                  const UChar* src, int32_t srcLength, 
                  UChar* dest, int32_t destCapacity,
                  int32_t options,
                  UParseError* parseError,
                  UErrorCode* status ){

    // check error status
    if(status == NULL || U_FAILURE(*status)){
        return 0;
    }
    
    //check arguments
    if(profile==NULL || src==NULL || srcLength<-1 || (dest==NULL && destCapacity!=0)) {
        *status=U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

    UChar b1Stack[MAX_STACK_BUFFER_SIZE], b2Stack[MAX_STACK_BUFFER_SIZE];
    UChar *b1 = b1Stack, *b2 = b2Stack;
    int32_t b1Len, b2Len=0,
            b1Capacity = MAX_STACK_BUFFER_SIZE , 
            b2Capacity = MAX_STACK_BUFFER_SIZE;
    uint16_t result;
    int32_t b2Index = 0;
    UCharDirection direction=U_CHAR_DIRECTION_COUNT, firstCharDir=U_CHAR_DIRECTION_COUNT;
    UBool leftToRight=FALSE, rightToLeft=FALSE;
    int32_t rtlPos =-1, ltrPos =-1;

    //get the string length
    if(srcLength == -1){
        srcLength = u_strlen(src);
    }
    // map
    b1Len = usprep_map(profile, src, srcLength, b1, b1Capacity, options, parseError, status);

    if(*status == U_BUFFER_OVERFLOW_ERROR){
        // redo processing of string
        /* we do not have enough room so grow the buffer*/
        b1 = (UChar*) uprv_malloc(b1Len * U_SIZEOF_UCHAR);
        if(b1==NULL){
            *status = U_MEMORY_ALLOCATION_ERROR;
            goto CLEANUP;
        }

        *status = U_ZERO_ERROR; // reset error
        
        b1Len = usprep_map(profile, src, srcLength, b1, b1Len, options, parseError, status);
        
    }

    // normalize
    if(profile->doNFKC == TRUE){
        b2Len = usprep_normalize(b1,b1Len, b2,b2Capacity,status);
        
        if(*status == U_BUFFER_OVERFLOW_ERROR){
            // redo processing of string
            /* we do not have enough room so grow the buffer*/
            b2 = (UChar*) uprv_malloc(b2Len * U_SIZEOF_UCHAR);
            if(b2==NULL){
                *status = U_MEMORY_ALLOCATION_ERROR;
                goto CLEANUP;
            }

            *status = U_ZERO_ERROR; // reset error
        
            b2Len = usprep_normalize(b1,b1Len, b2,b2Len,status);
        
        }

    }else{
        b2 = b1;
        b2Len = b1Len;
    }
    

    if(U_FAILURE(*status)){
        goto CLEANUP;
    }

    UChar32 ch;
    UStringPrepType type;
    int16_t value;
    UBool isIndex;
    
    // Prohibit and checkBiDi in one pass
    for(b2Index=0; b2Index<b2Len;){
        
        ch = 0;

        U16_NEXT(b2, b2Index, b2Len, ch);

        UTRIE_GET16(&profile->sprepTrie,ch,result);
        
        type = getValues(result, value, isIndex);

        if( type == USPREP_PROHIBITED || 
            ((result < _SPREP_TYPE_THRESHOLD) && (result & 0x01) /* first bit says it the code point is prohibited*/)
           ){
            *status = U_STRINGPREP_PROHIBITED_ERROR;
            uprv_syntaxError(b1, b2Index-U16_LENGTH(ch), b2Len, parseError);
            goto CLEANUP;
        }

        if(profile->checkBiDi) {
            direction = ubidi_getClass(profile->bdp, ch);
            if(firstCharDir == U_CHAR_DIRECTION_COUNT){
                firstCharDir = direction;
            }
            if(direction == U_LEFT_TO_RIGHT){
                leftToRight = TRUE;
                ltrPos = b2Index-1;
            }
            if(direction == U_RIGHT_TO_LEFT || direction == U_RIGHT_TO_LEFT_ARABIC){
                rightToLeft = TRUE;
                rtlPos = b2Index-1;
            }
        }
    }           
    if(profile->checkBiDi == TRUE){
        // satisfy 2
        if( leftToRight == TRUE && rightToLeft == TRUE){
            *status = U_STRINGPREP_CHECK_BIDI_ERROR;
            uprv_syntaxError(b2,(rtlPos>ltrPos) ? rtlPos : ltrPos, b2Len, parseError);
            goto CLEANUP;
        }

        //satisfy 3
        if( rightToLeft == TRUE && 
            !((firstCharDir == U_RIGHT_TO_LEFT || firstCharDir == U_RIGHT_TO_LEFT_ARABIC) &&
              (direction == U_RIGHT_TO_LEFT || direction == U_RIGHT_TO_LEFT_ARABIC))
           ){
            *status = U_STRINGPREP_CHECK_BIDI_ERROR;
            uprv_syntaxError(b2, rtlPos, b2Len, parseError);
            return FALSE;
        }
    }
    if(b2Len>0 && b2Len <= destCapacity){
        uprv_memmove(dest,b2, b2Len*U_SIZEOF_UCHAR);
    }

CLEANUP:
    if(b1!=b1Stack){
        uprv_free(b1);
        b1=NULL;
    }

    if(b2!=b1Stack && b2!=b2Stack && b2!=b1 /* b1 should not be freed twice */){
        uprv_free(b2);
        b2=NULL;
    }
    return u_terminateUChars(dest, destCapacity, b2Len, status);
}


/* data swapping ------------------------------------------------------------ */

U_CAPI int32_t U_EXPORT2
usprep_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]==0x53 &&   /* dataFormat="SPRP" */
        pInfo->dataFormat[1]==0x50 &&
        pInfo->dataFormat[2]==0x52 &&
        pInfo->dataFormat[3]==0x50 &&
        pInfo->formatVersion[0]==3
    )) {
        udata_printError(ds, "usprep_swap(): data format %02x.%02x.%02x.%02x (format version %02x) is not recognized as StringPrep .spp 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, "usprep_swap(): too few bytes (%d after header) for StringPrep .spp data\n",
                             length);
            *pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
            return 0;
        }
    }

    /* read the first 16 indexes (ICU 2.8/format version 3: _SPREP_INDEX_TOP==16, might grow) */
    for(i=0; i<16; ++i) {
        indexes[i]=udata_readInt32(ds, inIndexes[i]);
    }

    /* calculate the total length of the data */
    size=
        16*4+ /* size of indexes[] */
        indexes[_SPREP_INDEX_TRIE_SIZE]+
        indexes[_SPREP_INDEX_MAPPING_DATA_SIZE];

    if(length>=0) {
        if(length<size) {
            udata_printError(ds, "usprep_swap(): too few bytes (%d after header) for all of StringPrep .spp 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=16*4;
        ds->swapArray32(ds, inBytes, count, outBytes, pErrorCode);
        offset+=count;

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

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

    return headerSize+size;
}

#endif /* #if !UCONFIG_NO_IDNA */