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
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
* Copyright (C) 2003-2014, International Business Machines
* Corporation and others. All Rights Reserved.
*
*******************************************************************************
* file name: udataswp.c
* encoding: UTF-8
* tab size: 8 (not used)
* indentation:4
*
* created on: 2003jun05
* created by: Markus W. Scherer
*
* Definitions for ICU data transformations for different platforms,
* changing between big- and little-endian data and/or between
* charset families (ASCII<->EBCDIC).
*/
#include <stdarg.h>
#include "unicode/utypes.h"
#include "unicode/udata.h" /* UDataInfo */
#include "ucmndata.h" /* DataHeader */
#include "cmemory.h"
#include "udataswp.h"
/* swapping primitives ------------------------------------------------------ */
static int32_t U_CALLCONV
uprv_swapArray16(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const uint16_t *p;
uint16_t *q;
int32_t count;
uint16_t x;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&1)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
/* setup and swapping */
p = static_cast<const uint16_t*>(inData);
q = static_cast<uint16_t*>(outData);
count=length/2;
while(count>0) {
x=*p++;
*q++ = static_cast<uint16_t>((x << 8) | (x >> 8));
--count;
}
return length;
}
static int32_t U_CALLCONV
uprv_copyArray16(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&1)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
if(length>0 && inData!=outData) {
uprv_memcpy(outData, inData, length);
}
return length;
}
static int32_t U_CALLCONV
uprv_swapArray32(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const uint32_t *p;
uint32_t *q;
int32_t count;
uint32_t x;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&3)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
/* setup and swapping */
p = static_cast<const uint32_t*>(inData);
q = static_cast<uint32_t*>(outData);
count=length/4;
while(count>0) {
x=*p++;
*q++ = (x << 24) | ((x << 8) & 0xff0000) | ((x >> 8) & 0xff00) | (x >> 24);
--count;
}
return length;
}
static int32_t U_CALLCONV
uprv_copyArray32(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&3)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
if(length>0 && inData!=outData) {
uprv_memcpy(outData, inData, length);
}
return length;
}
static int32_t U_CALLCONV
uprv_swapArray64(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const uint64_t *p;
uint64_t *q;
int32_t count;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&7)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
/* setup and swapping */
p = static_cast<const uint64_t*>(inData);
q = static_cast<uint64_t*>(outData);
count=length/8;
while(count>0) {
uint64_t x=*p++;
x=(x<<56)|((x&0xff00)<<40)|((x&0xff0000)<<24)|((x&0xff000000)<<8)|
((x>>8)&0xff000000)|((x>>24)&0xff0000)|((x>>40)&0xff00)|(x>>56);
*q++=x;
--count;
}
return length;
}
static int32_t U_CALLCONV
uprv_copyArray64(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length&7)!=0 || outData==nullptr) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
if(length>0 && inData!=outData) {
uprv_memcpy(outData, inData, length);
}
return length;
}
static uint16_t U_CALLCONV
uprv_readSwapUInt16(uint16_t x) {
return static_cast<uint16_t>((x << 8) | (x >> 8));
}
static uint16_t U_CALLCONV
uprv_readDirectUInt16(uint16_t x) {
return x;
}
static uint32_t U_CALLCONV
uprv_readSwapUInt32(uint32_t x) {
return (x << 24) | ((x << 8) & 0xff0000) | ((x >> 8) & 0xff00) | (x >> 24);
}
static uint32_t U_CALLCONV
uprv_readDirectUInt32(uint32_t x) {
return x;
}
static void U_CALLCONV
uprv_writeSwapUInt16(uint16_t *p, uint16_t x) {
*p = static_cast<uint16_t>((x << 8) | (x >> 8));
}
static void U_CALLCONV
uprv_writeDirectUInt16(uint16_t *p, uint16_t x) {
*p=x;
}
static void U_CALLCONV
uprv_writeSwapUInt32(uint32_t *p, uint32_t x) {
*p = (x << 24) | ((x << 8) & 0xff0000) | ((x >> 8) & 0xff00) | (x >> 24);
}
static void U_CALLCONV
uprv_writeDirectUInt32(uint32_t *p, uint32_t x) {
*p=x;
}
U_CAPI int16_t U_EXPORT2
udata_readInt16(const UDataSwapper *ds, int16_t x) {
return (int16_t)ds->readUInt16((uint16_t)x);
}
U_CAPI int32_t U_EXPORT2
udata_readInt32(const UDataSwapper *ds, int32_t x) {
return (int32_t)ds->readUInt32((uint32_t)x);
}
/**
* Swap a block of invariant, NUL-terminated strings, but not padding
* bytes after the last string.
* @internal
*/
U_CAPI int32_t U_EXPORT2
udata_swapInvStringBlock(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const char *inChars;
int32_t stringsLength;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<0 || (length>0 && outData==nullptr)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
/* reduce the strings length to not include bytes after the last NUL */
inChars=(const char *)inData;
stringsLength=length;
while(stringsLength>0 && inChars[stringsLength-1]!=0) {
--stringsLength;
}
/* swap up to the last NUL */
ds->swapInvChars(ds, inData, stringsLength, outData, pErrorCode);
/* copy the bytes after the last NUL */
if(inData!=outData && length>stringsLength) {
uprv_memcpy((char *)outData+stringsLength, inChars+stringsLength, length-stringsLength);
}
/* return the length including padding bytes */
if(U_SUCCESS(*pErrorCode)) {
return length;
} else {
return 0;
}
}
U_CAPI void U_EXPORT2
udata_printError(const UDataSwapper *ds,
const char *fmt,
...) {
va_list args;
if(ds->printError!=nullptr) {
va_start(args, fmt);
ds->printError(ds->printErrorContext, fmt, args);
va_end(args);
}
}
/* swap a data header ------------------------------------------------------- */
U_CAPI int32_t U_EXPORT2
udata_swapDataHeader(const UDataSwapper *ds,
const void *inData, int32_t length, void *outData,
UErrorCode *pErrorCode) {
const DataHeader *pHeader;
uint16_t headerSize, infoSize;
/* argument checking */
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return 0;
}
if(ds==nullptr || inData==nullptr || length<-1 || (length>0 && outData==nullptr)) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return 0;
}
/* check minimum length and magic bytes */
pHeader=(const DataHeader *)inData;
if( (length>=0 && length<(int32_t)sizeof(DataHeader)) ||
pHeader->dataHeader.magic1!=0xda ||
pHeader->dataHeader.magic2!=0x27 ||
pHeader->info.sizeofUChar!=2
) {
udata_printError(ds, "udata_swapDataHeader(): initial bytes do not look like ICU data\n");
*pErrorCode=U_UNSUPPORTED_ERROR;
return 0;
}
headerSize=ds->readUInt16(pHeader->dataHeader.headerSize);
infoSize=ds->readUInt16(pHeader->info.size);
if( headerSize<sizeof(DataHeader) ||
infoSize<sizeof(UDataInfo) ||
headerSize<(sizeof(pHeader->dataHeader)+infoSize) ||
(length>=0 && length<headerSize)
) {
udata_printError(ds, "udata_swapDataHeader(): header size mismatch - headerSize %d infoSize %d length %d\n",
headerSize, infoSize, length);
*pErrorCode=U_INDEX_OUTOFBOUNDS_ERROR;
return 0;
}
if(length>0) {
DataHeader *outHeader;
const char *s;
int32_t maxLength;
/* Most of the fields are just bytes and need no swapping. */
if(inData!=outData) {
uprv_memcpy(outData, inData, headerSize);
}
outHeader=(DataHeader *)outData;
outHeader->info.isBigEndian = ds->outIsBigEndian;
outHeader->info.charsetFamily = ds->outCharset;
/* swap headerSize */
ds->swapArray16(ds, &pHeader->dataHeader.headerSize, 2, &outHeader->dataHeader.headerSize, pErrorCode);
/* swap UDataInfo size and reservedWord */
ds->swapArray16(ds, &pHeader->info.size, 4, &outHeader->info.size, pErrorCode);
/* swap copyright statement after the UDataInfo */
infoSize+=sizeof(pHeader->dataHeader);
s=(const char *)inData+infoSize;
maxLength=headerSize-infoSize;
/* get the length of the string */
for(length=0; length<maxLength && s[length]!=0; ++length) {}
/* swap the string contents */
ds->swapInvChars(ds, s, length, (char *)outData+infoSize, pErrorCode);
}
return headerSize;
}
/* API functions ------------------------------------------------------------ */
U_CAPI UDataSwapper * U_EXPORT2
udata_openSwapper(UBool inIsBigEndian, uint8_t inCharset,
UBool outIsBigEndian, uint8_t outCharset,
UErrorCode *pErrorCode) {
UDataSwapper *swapper;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return nullptr;
}
if(inCharset>U_EBCDIC_FAMILY || outCharset>U_EBCDIC_FAMILY) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
/* allocate the swapper */
swapper=(UDataSwapper *)uprv_malloc(sizeof(UDataSwapper));
if(swapper==nullptr) {
*pErrorCode=U_MEMORY_ALLOCATION_ERROR;
return nullptr;
}
uprv_memset(swapper, 0, sizeof(UDataSwapper));
/* set values and functions pointers according to in/out parameters */
swapper->inIsBigEndian=inIsBigEndian;
swapper->inCharset=inCharset;
swapper->outIsBigEndian=outIsBigEndian;
swapper->outCharset=outCharset;
swapper->readUInt16= inIsBigEndian==U_IS_BIG_ENDIAN ? uprv_readDirectUInt16 : uprv_readSwapUInt16;
swapper->readUInt32= inIsBigEndian==U_IS_BIG_ENDIAN ? uprv_readDirectUInt32 : uprv_readSwapUInt32;
swapper->writeUInt16= outIsBigEndian==U_IS_BIG_ENDIAN ? uprv_writeDirectUInt16 : uprv_writeSwapUInt16;
swapper->writeUInt32= outIsBigEndian==U_IS_BIG_ENDIAN ? uprv_writeDirectUInt32 : uprv_writeSwapUInt32;
swapper->compareInvChars= outCharset==U_ASCII_FAMILY ? uprv_compareInvAscii : uprv_compareInvEbcdic;
if(inIsBigEndian==outIsBigEndian) {
swapper->swapArray16=uprv_copyArray16;
swapper->swapArray32=uprv_copyArray32;
swapper->swapArray64=uprv_copyArray64;
} else {
swapper->swapArray16=uprv_swapArray16;
swapper->swapArray32=uprv_swapArray32;
swapper->swapArray64=uprv_swapArray64;
}
if(inCharset==U_ASCII_FAMILY) {
swapper->swapInvChars= outCharset==U_ASCII_FAMILY ? uprv_copyAscii : uprv_ebcdicFromAscii;
} else /* U_EBCDIC_FAMILY */ {
swapper->swapInvChars= outCharset==U_EBCDIC_FAMILY ? uprv_copyEbcdic : uprv_asciiFromEbcdic;
}
return swapper;
}
U_CAPI UDataSwapper * U_EXPORT2
udata_openSwapperForInputData(const void *data, int32_t length,
UBool outIsBigEndian, uint8_t outCharset,
UErrorCode *pErrorCode) {
const DataHeader *pHeader;
uint16_t headerSize, infoSize;
UBool inIsBigEndian;
int8_t inCharset;
if(pErrorCode==nullptr || U_FAILURE(*pErrorCode)) {
return nullptr;
}
if( data==nullptr ||
(length>=0 && length<(int32_t)sizeof(DataHeader)) ||
outCharset>U_EBCDIC_FAMILY
) {
*pErrorCode=U_ILLEGAL_ARGUMENT_ERROR;
return nullptr;
}
pHeader=(const DataHeader *)data;
if( (length>=0 && length<(int32_t)sizeof(DataHeader)) ||
pHeader->dataHeader.magic1!=0xda ||
pHeader->dataHeader.magic2!=0x27 ||
pHeader->info.sizeofUChar!=2
) {
*pErrorCode=U_UNSUPPORTED_ERROR;
return nullptr;
}
inIsBigEndian=(UBool)pHeader->info.isBigEndian;
inCharset=pHeader->info.charsetFamily;
if(inIsBigEndian==U_IS_BIG_ENDIAN) {
headerSize=pHeader->dataHeader.headerSize;
infoSize=pHeader->info.size;
} else {
headerSize=uprv_readSwapUInt16(pHeader->dataHeader.headerSize);
infoSize=uprv_readSwapUInt16(pHeader->info.size);
}
if( headerSize<sizeof(DataHeader) ||
infoSize<sizeof(UDataInfo) ||
headerSize<(sizeof(pHeader->dataHeader)+infoSize) ||
(length>=0 && length<headerSize)
) {
*pErrorCode=U_UNSUPPORTED_ERROR;
return nullptr;
}
return udata_openSwapper(inIsBigEndian, inCharset, outIsBigEndian, outCharset, pErrorCode);
}
U_CAPI void U_EXPORT2
udata_closeSwapper(UDataSwapper *ds) {
uprv_free(ds);
}
|