aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/icu/common/unistr_cnv.cpp
blob: 2d649b2d511d6a0f7abd89b85a49279c5c7463d6 (plain) (blame)
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
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 1999-2014, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  unistr_cnv.cpp
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:2
*
*   created on: 2004aug19
*   created by: Markus W. Scherer
*
*   Character conversion functions moved here from unistr.cpp
*/

#include "unicode/utypes.h"

#if !UCONFIG_NO_CONVERSION

#include "unicode/putil.h"
#include "cstring.h"
#include "cmemory.h"
#include "unicode/ustring.h"
#include "unicode/unistr.h"
#include "unicode/ucnv.h"
#include "ucnv_imp.h"
#include "putilimp.h"
#include "ustr_cnv.h"
#include "ustr_imp.h"

U_NAMESPACE_BEGIN

//========================================
// Constructors
//========================================

#if !U_CHARSET_IS_UTF8

UnicodeString::UnicodeString(const char *codepageData) {
    fUnion.fFields.fLengthAndFlags = kShortString;
    if(codepageData != 0) {
        doCodepageCreate(codepageData, (int32_t)uprv_strlen(codepageData), 0);
    }
}

UnicodeString::UnicodeString(const char *codepageData,
                             int32_t dataLength) {
    fUnion.fFields.fLengthAndFlags = kShortString;
    if(codepageData != 0) {
        doCodepageCreate(codepageData, dataLength, 0);
    }
}

// else see unistr.cpp
#endif

UnicodeString::UnicodeString(const char *codepageData,
                             const char *codepage) {
    fUnion.fFields.fLengthAndFlags = kShortString;
    if(codepageData != 0) {
        doCodepageCreate(codepageData, (int32_t)uprv_strlen(codepageData), codepage);
    }
}

UnicodeString::UnicodeString(const char *codepageData,
                             int32_t dataLength,
                             const char *codepage) {
    fUnion.fFields.fLengthAndFlags = kShortString;
    if(codepageData != 0) {
        doCodepageCreate(codepageData, dataLength, codepage);
    }
}

UnicodeString::UnicodeString(const char *src, int32_t srcLength,
                             UConverter *cnv,
                             UErrorCode &errorCode) {
    fUnion.fFields.fLengthAndFlags = kShortString;
    if(U_SUCCESS(errorCode)) {
        // check arguments
        if(src==nullptr) {
            // treat as an empty string, do nothing more
        } else if(srcLength<-1) {
            errorCode=U_ILLEGAL_ARGUMENT_ERROR;
        } else {
            // get input length
            if(srcLength==-1) {
                srcLength=(int32_t)uprv_strlen(src);
            }
            if(srcLength>0) {
                if(cnv!=0) {
                    // use the provided converter
                    ucnv_resetToUnicode(cnv);
                    doCodepageCreate(src, srcLength, cnv, errorCode);
                } else {
                    // use the default converter
                    cnv=u_getDefaultConverter(&errorCode);
                    doCodepageCreate(src, srcLength, cnv, errorCode);
                    u_releaseDefaultConverter(cnv);
                }
            }
        }

        if(U_FAILURE(errorCode)) {
            setToBogus();
        }
    }
}

//========================================
// Codeset conversion
//========================================

#if !U_CHARSET_IS_UTF8

int32_t
UnicodeString::extract(int32_t start,
                       int32_t length,
                       char *target,
                       uint32_t dstSize) const {
    return extract(start, length, target, dstSize, 0);
}

// else see unistr.cpp
#endif

int32_t
UnicodeString::extract(int32_t start,
                       int32_t length,
                       char *target,
                       uint32_t dstSize,
                       const char *codepage) const
{
    // if the arguments are illegal, then do nothing
    if(/*dstSize < 0 || */(dstSize > 0 && target == 0)) {
        return 0;
    }

    // pin the indices to legal values
    pinIndices(start, length);

    // We need to cast dstSize to int32_t for all subsequent code.
    // I don't know why the API was defined with uint32_t but we are stuck with it.
    // Also, dstSize==0xffffffff means "unlimited" but if we use target+dstSize
    // as a limit in some functions, it may wrap around and yield a pointer
    // that compares less-than target.
    int32_t capacity;
    if(dstSize < 0x7fffffff) {
        // Assume that the capacity is real and a limit pointer won't wrap around.
        capacity = (int32_t)dstSize;
    } else {
        // Pin the capacity so that a limit pointer does not wrap around.
        char *targetLimit = (char *)U_MAX_PTR(target);
        // U_MAX_PTR(target) returns a targetLimit that is at most 0x7fffffff
        // greater than target and does not wrap around the top of the address space.
        capacity = (int32_t)(targetLimit - target);
    }

    // create the converter
    UConverter *converter;
    UErrorCode status = U_ZERO_ERROR;

    // just write the NUL if the string length is 0
    if(length == 0) {
        return u_terminateChars(target, capacity, 0, &status);
    }

    // if the codepage is the default, use our cache
    // if it is an empty string, then use the "invariant character" conversion
    if (codepage == 0) {
        const char *defaultName = ucnv_getDefaultName();
        if(UCNV_FAST_IS_UTF8(defaultName)) {
            return toUTF8(start, length, target, capacity);
        }
        converter = u_getDefaultConverter(&status);
    } else if (*codepage == 0) {
        // use the "invariant characters" conversion
        int32_t destLength;
        if(length <= capacity) {
            destLength = length;
        } else {
            destLength = capacity;
        }
        u_UCharsToChars(getArrayStart() + start, target, destLength);
        return u_terminateChars(target, capacity, length, &status);
    } else {
        converter = ucnv_open(codepage, &status);
    }

    length = doExtract(start, length, target, capacity, converter, status);

    // close the converter
    if (codepage == 0) {
        u_releaseDefaultConverter(converter);
    } else {
        ucnv_close(converter);
    }

    return length;
}

int32_t
UnicodeString::extract(char *dest, int32_t destCapacity,
                       UConverter *cnv,
                       UErrorCode &errorCode) const
{
    if(U_FAILURE(errorCode)) {
        return 0;
    }

    if(isBogus() || destCapacity<0 || (destCapacity>0 && dest==0)) {
        errorCode=U_ILLEGAL_ARGUMENT_ERROR;
        return 0;
    }

    // nothing to do?
    if(isEmpty()) {
        return u_terminateChars(dest, destCapacity, 0, &errorCode);
    }

    // get the converter
    UBool isDefaultConverter;
    if(cnv==0) {
        isDefaultConverter=true;
        cnv=u_getDefaultConverter(&errorCode);
        if(U_FAILURE(errorCode)) {
            return 0;
        }
    } else {
        isDefaultConverter=false;
        ucnv_resetFromUnicode(cnv);
    }

    // convert
    int32_t len=doExtract(0, length(), dest, destCapacity, cnv, errorCode);

    // release the converter
    if(isDefaultConverter) {
        u_releaseDefaultConverter(cnv);
    }

    return len;
}

int32_t
UnicodeString::doExtract(int32_t start, int32_t length,
                         char *dest, int32_t destCapacity,
                         UConverter *cnv,
                         UErrorCode &errorCode) const
{
    if(U_FAILURE(errorCode)) {
        if(destCapacity!=0) {
            *dest=0;
        }
        return 0;
    }

    const char16_t *src=getArrayStart()+start, *srcLimit=src+length;
    char *originalDest=dest;
    const char *destLimit;

    if(destCapacity==0) {
        destLimit=dest=0;
    } else if(destCapacity==-1) {
        // Pin the limit to U_MAX_PTR if the "magic" destCapacity is used.
        destLimit=(char*)U_MAX_PTR(dest);
        // for NUL-termination, translate into highest int32_t
        destCapacity=0x7fffffff;
    } else {
        destLimit=dest+destCapacity;
    }

    // perform the conversion
    ucnv_fromUnicode(cnv, &dest, destLimit, &src, srcLimit, 0, true, &errorCode);
    length=(int32_t)(dest-originalDest);

    // if an overflow occurs, then get the preflighting length
    if(errorCode==U_BUFFER_OVERFLOW_ERROR) {
        char buffer[1024];

        destLimit=buffer+sizeof(buffer);
        do {
            dest=buffer;
            errorCode=U_ZERO_ERROR;
            ucnv_fromUnicode(cnv, &dest, destLimit, &src, srcLimit, 0, true, &errorCode);
            length+=(int32_t)(dest-buffer);
        } while(errorCode==U_BUFFER_OVERFLOW_ERROR);
    }

    return u_terminateChars(originalDest, destCapacity, length, &errorCode);
}

void
UnicodeString::doCodepageCreate(const char *codepageData,
                                int32_t dataLength,
                                const char *codepage)
{
    // if there's nothing to convert, do nothing
    if(codepageData == 0 || dataLength == 0 || dataLength < -1) {
        return;
    }
    if(dataLength == -1) {
        dataLength = (int32_t)uprv_strlen(codepageData);
    }

    UErrorCode status = U_ZERO_ERROR;

    // create the converter
    // if the codepage is the default, use our cache
    // if it is an empty string, then use the "invariant character" conversion
    UConverter *converter;
    if (codepage == 0) {
        const char *defaultName = ucnv_getDefaultName();
        if(UCNV_FAST_IS_UTF8(defaultName)) {
            setToUTF8(StringPiece(codepageData, dataLength));
            return;
        }
        converter = u_getDefaultConverter(&status);
    } else if(*codepage == 0) {
        // use the "invariant characters" conversion
        if(cloneArrayIfNeeded(dataLength, dataLength, false)) {
            u_charsToUChars(codepageData, getArrayStart(), dataLength);
            setLength(dataLength);
        } else {
            setToBogus();
        }
        return;
    } else {
        converter = ucnv_open(codepage, &status);
    }

    // if we failed, set the appropriate flags and return
    if(U_FAILURE(status)) {
        setToBogus();
        return;
    }

    // perform the conversion
    doCodepageCreate(codepageData, dataLength, converter, status);
    if(U_FAILURE(status)) {
        setToBogus();
    }

    // close the converter
    if(codepage == 0) {
        u_releaseDefaultConverter(converter);
    } else {
        ucnv_close(converter);
    }
}

void
UnicodeString::doCodepageCreate(const char *codepageData,
                                int32_t dataLength,
                                UConverter *converter,
                                UErrorCode &status)
{
    if(U_FAILURE(status)) {
        return;
    }

    // set up the conversion parameters
    const char *mySource     = codepageData;
    const char *mySourceEnd  = mySource + dataLength;
    char16_t *array, *myTarget;

    // estimate the size needed:
    int32_t arraySize;
    if(dataLength <= US_STACKBUF_SIZE) {
        // try to use the stack buffer
        arraySize = US_STACKBUF_SIZE;
    } else {
        // 1.25 char16_t's per source byte should cover most cases
        arraySize = dataLength + (dataLength >> 2);
    }

    // we do not care about the current contents
    UBool doCopyArray = false;
    for(;;) {
        if(!cloneArrayIfNeeded(arraySize, arraySize, doCopyArray)) {
            setToBogus();
            break;
        }

        // perform the conversion
        array = getArrayStart();
        myTarget = array + length();
        ucnv_toUnicode(converter, &myTarget,  array + getCapacity(),
            &mySource, mySourceEnd, 0, true, &status);

        // update the conversion parameters
        setLength((int32_t)(myTarget - array));

        // allocate more space and copy data, if needed
        if(status == U_BUFFER_OVERFLOW_ERROR) {
            // reset the error code
            status = U_ZERO_ERROR;

            // keep the previous conversion results
            doCopyArray = true;

            // estimate the new size needed, larger than before
            // try 2 char16_t's per remaining source byte
            arraySize = (int32_t)(length() + 2 * (mySourceEnd - mySource));
        } else {
            break;
        }
    }
}

U_NAMESPACE_END

#endif