{{ message }}
-
-
Notifications
You must be signed in to change notification settings - Fork 35.4k
Expand file tree
/
Copy pathunicode_writer.c
More file actions
647 lines (530 loc) · 17.5 KB
/
Copy pathunicode_writer.c
File metadata and controls
647 lines (530 loc) · 17.5 KB
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
/*
Unicode implementation based on original code by Fredrik Lundh,
modified by Marc-Andre Lemburg <mal@lemburg.com>.
Major speed upgrades to the method implementations at the Reykjavik
NeedForSpeed sprint, by Fredrik Lundh and Andrew Dalke.
Copyright (c) Corporation for National Research Initiatives.
--------------------------------------------------------------------
The original string type implementation is:
Copyright (c) 1999 by Secret Labs AB
Copyright (c) 1999 by Fredrik Lundh
By obtaining, using, and/or copying this software and/or its
associated documentation, you agree that you have read, understood,
and will comply with the following terms and conditions:
Permission to use, copy, modify, and distribute this software and its
associated documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appears in all
copies, and that both that copyright notice and this permission notice
appear in supporting documentation, and that the name of Secret Labs
AB or the author not be used in advertising or publicity pertaining to
distribution of the software without specific, written prior
permission.
SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
--------------------------------------------------------------------
*/
#include "Python.h"
#include "pycore_freelist.h" // _Py_FREELIST_FREE()
#include "pycore_long.h" // _PyLong_FormatWriter()
#include "pycore_unicodeobject.h" // _PyUnicode_Result()
#ifdef MS_WINDOWS
/* On Windows, overallocate by 50% is the best factor */
# define OVERALLOCATE_FACTOR 2
#else
/* On Linux, overallocate by 25% is the best factor */
# define OVERALLOCATE_FACTOR 4
#endif
/* Compilation of templated routines */
#define STRINGLIB_GET_EMPTY() _PyUnicode_GetEmpty()
#include "stringlib/ucs1lib.h"
#include "stringlib/find_max_char.h"
#include "stringlib/undef.h"
/* Copy an ASCII or latin1 char* string into a Python Unicode string.
WARNING: The function doesn't copy the terminating null character and
doesn't check the maximum character (may write a latin1 character in an
ASCII string). */
static void
unicode_write_cstr(PyObject *unicode, Py_ssize_t index,
const char *str, Py_ssize_t len)
{
int kind = PyUnicode_KIND(unicode);
const void *data = PyUnicode_DATA(unicode);
const char *end = str + len;
assert(index + len <= PyUnicode_GET_LENGTH(unicode));
switch (kind) {
case PyUnicode_1BYTE_KIND: {
#ifdef Py_DEBUG
if (PyUnicode_IS_ASCII(unicode)) {
Py_UCS4 maxchar = ucs1lib_find_max_char(
(const Py_UCS1*)str,
(const Py_UCS1*)str + len);
assert(maxchar < 128);
}
#endif
memcpy((char *) data + index, str, len);
break;
}
case PyUnicode_2BYTE_KIND: {
Py_UCS2 *start = (Py_UCS2 *)data + index;
Py_UCS2 *ucs2 = start;
for (; str < end; ++ucs2, ++str)
*ucs2 = (Py_UCS2)*str;
assert((ucs2 - start) <= PyUnicode_GET_LENGTH(unicode));
break;
}
case PyUnicode_4BYTE_KIND: {
Py_UCS4 *start = (Py_UCS4 *)data + index;
Py_UCS4 *ucs4 = start;
for (; str < end; ++ucs4, ++str)
*ucs4 = (Py_UCS4)*str;
assert((ucs4 - start) <= PyUnicode_GET_LENGTH(unicode));
break;
}
default:
Py_UNREACHABLE();
}
}
static inline void
_PyUnicodeWriter_Update(_PyUnicodeWriter *writer)
{
writer->maxchar = PyUnicode_MAX_CHAR_VALUE(writer->buffer);
writer->data = PyUnicode_DATA(writer->buffer);
if (!writer->readonly) {
writer->kind = PyUnicode_KIND(writer->buffer);
writer->size = PyUnicode_GET_LENGTH(writer->buffer);
}
else {
/* use a value smaller than PyUnicode_1BYTE_KIND() so
_PyUnicodeWriter_PrepareKind() will copy the buffer. */
writer->kind = 0;
assert(writer->kind <= PyUnicode_1BYTE_KIND);
/* Copy-on-write mode: set buffer size to 0 so
* _PyUnicodeWriter_Prepare() will copy (and enlarge) the buffer on
* next write. */
writer->size = 0;
}
}
void
_PyUnicodeWriter_Init(_PyUnicodeWriter *writer)
{
memset(writer, 0, sizeof(*writer));
/* ASCII is the bare minimum */
writer->min_char = 127;
/* use a kind value smaller than PyUnicode_1BYTE_KIND so
_PyUnicodeWriter_PrepareKind() will copy the buffer. */
assert(writer->kind == 0);
assert(writer->kind < PyUnicode_1BYTE_KIND);
}
PyUnicodeWriter*
PyUnicodeWriter_Create(Py_ssize_t length)
{
if (length < 0) {
PyErr_SetString(PyExc_ValueError,
"length must be positive");
return NULL;
}
const size_t size = sizeof(_PyUnicodeWriter);
PyUnicodeWriter *pub_writer;
pub_writer = _Py_FREELIST_POP_MEM(unicode_writers);
if (pub_writer == NULL) {
pub_writer = (PyUnicodeWriter *)PyMem_Malloc(size);
if (pub_writer == NULL) {
return (PyUnicodeWriter *)PyErr_NoMemory();
}
}
_PyUnicodeWriter *writer = (_PyUnicodeWriter *)pub_writer;
_PyUnicodeWriter_Init(writer);
if (_PyUnicodeWriter_Prepare(writer, length, 127) < 0) {
PyUnicodeWriter_Discard(pub_writer);
return NULL;
}
writer->overallocate = 1;
return pub_writer;
}
void PyUnicodeWriter_Discard(PyUnicodeWriter *writer)
{
if (writer == NULL) {
return;
}
_PyUnicodeWriter_Dealloc((_PyUnicodeWriter*)writer);
_Py_FREELIST_FREE(unicode_writers, writer, PyMem_Free);
}
// Initialize _PyUnicodeWriter with initial buffer
void
_PyUnicodeWriter_InitWithBuffer(_PyUnicodeWriter *writer, PyObject *buffer)
{
memset(writer, 0, sizeof(*writer));
writer->buffer = buffer;
_PyUnicodeWriter_Update(writer);
writer->min_length = writer->size;
}
int
_PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
Py_ssize_t length, Py_UCS4 maxchar)
{
Py_ssize_t newlen;
PyObject *newbuffer;
assert(length >= 0);
assert(maxchar <= _Py_MAX_UNICODE);
/* ensure that the _PyUnicodeWriter_Prepare macro was used */
assert((maxchar > writer->maxchar && length >= 0)
|| length > 0);
if (length > PY_SSIZE_T_MAX - writer->pos) {
PyErr_NoMemory();
return -1;
}
newlen = writer->pos + length;
maxchar = Py_MAX(maxchar, writer->min_char);
if (writer->buffer == NULL) {
assert(!writer->readonly);
if (writer->overallocate
&& newlen <= (PY_SSIZE_T_MAX - newlen / OVERALLOCATE_FACTOR)) {
/* overallocate to limit the number of realloc() */
newlen += newlen / OVERALLOCATE_FACTOR;
}
if (newlen < writer->min_length)
newlen = writer->min_length;
writer->buffer = PyUnicode_New(newlen, maxchar);
if (writer->buffer == NULL)
return -1;
}
else if (newlen > writer->size) {
if (writer->overallocate
&& newlen <= (PY_SSIZE_T_MAX - newlen / OVERALLOCATE_FACTOR)) {
/* overallocate to limit the number of realloc() */
newlen += newlen / OVERALLOCATE_FACTOR;
}
if (newlen < writer->min_length)
newlen = writer->min_length;
if (maxchar > writer->maxchar || writer->readonly) {
/* resize + widen */
maxchar = Py_MAX(maxchar, writer->maxchar);
newbuffer = PyUnicode_New(newlen, maxchar);
if (newbuffer == NULL)
return -1;
_PyUnicode_FastCopyCharacters(newbuffer, 0,
writer->buffer, 0, writer->pos);
Py_DECREF(writer->buffer);
writer->readonly = 0;
}
else {
newbuffer = _PyUnicode_ResizeCompact(writer->buffer, newlen);
if (newbuffer == NULL)
return -1;
}
writer->buffer = newbuffer;
}
else if (maxchar > writer->maxchar) {
assert(!writer->readonly);
newbuffer = PyUnicode_New(writer->size, maxchar);
if (newbuffer == NULL)
return -1;
_PyUnicode_FastCopyCharacters(newbuffer, 0,
writer->buffer, 0, writer->pos);
Py_SETREF(writer->buffer, newbuffer);
}
_PyUnicodeWriter_Update(writer);
return 0;
#undef OVERALLOCATE_FACTOR
}
int
_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
int kind)
{
Py_UCS4 maxchar;
/* ensure that the _PyUnicodeWriter_PrepareKind macro was used */
assert(writer->kind < kind);
switch (kind)
{
case PyUnicode_1BYTE_KIND: maxchar = 0xff; break;
case PyUnicode_2BYTE_KIND: maxchar = 0xffff; break;
case PyUnicode_4BYTE_KIND: maxchar = _Py_MAX_UNICODE; break;
default:
Py_UNREACHABLE();
}
return _PyUnicodeWriter_PrepareInternal(writer, 0, maxchar);
}
int
_PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer, Py_UCS4 ch)
{
return _PyUnicodeWriter_WriteCharInline(writer, ch);
}
int
PyUnicodeWriter_WriteChar(PyUnicodeWriter *writer, Py_UCS4 ch)
{
if (ch > _Py_MAX_UNICODE) {
PyErr_SetString(PyExc_ValueError,
"character must be in range(0x110000)");
return -1;
}
return _PyUnicodeWriter_WriteChar((_PyUnicodeWriter*)writer, ch);
}
int
_PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer, PyObject *str)
{
assert(PyUnicode_Check(str));
Py_UCS4 maxchar;
Py_ssize_t len;
len = PyUnicode_GET_LENGTH(str);
if (len == 0)
return 0;
maxchar = PyUnicode_MAX_CHAR_VALUE(str);
if (maxchar > writer->maxchar || len > writer->size - writer->pos) {
if (writer->buffer == NULL && !writer->overallocate) {
assert(_PyUnicode_CheckConsistency(str, 1));
writer->readonly = 1;
writer->buffer = Py_NewRef(str);
_PyUnicodeWriter_Update(writer);
writer->pos += len;
return 0;
}
if (_PyUnicodeWriter_PrepareInternal(writer, len, maxchar) == -1)
return -1;
}
_PyUnicode_FastCopyCharacters(writer->buffer, writer->pos,
str, 0, len);
writer->pos += len;
return 0;
}
int
PyUnicodeWriter_WriteStr(PyUnicodeWriter *writer, PyObject *obj)
{
PyTypeObject *type = Py_TYPE(obj);
if (type == &PyUnicode_Type) {
return _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, obj);
}
if (type == &PyLong_Type) {
return _PyLong_FormatWriter((_PyUnicodeWriter*)writer, obj, 10, 0);
}
PyObject *str = PyObject_Str(obj);
if (str == NULL) {
return -1;
}
int res = _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, str);
Py_DECREF(str);
return res;
}
int
PyUnicodeWriter_WriteRepr(PyUnicodeWriter *writer, PyObject *obj)
{
if (obj == NULL) {
return _PyUnicodeWriter_WriteASCIIString((_PyUnicodeWriter*)writer, "<NULL>", 6);
}
if (Py_TYPE(obj) == &PyLong_Type) {
return _PyLong_FormatWriter((_PyUnicodeWriter*)writer, obj, 10, 0);
}
PyObject *repr = PyObject_Repr(obj);
if (repr == NULL) {
return -1;
}
int res = _PyUnicodeWriter_WriteStr((_PyUnicodeWriter*)writer, repr);
Py_DECREF(repr);
return res;
}
int
_PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer, PyObject *str,
Py_ssize_t start, Py_ssize_t end)
{
assert(0 <= start);
assert(end <= PyUnicode_GET_LENGTH(str));
assert(start <= end);
if (start == 0 && end == PyUnicode_GET_LENGTH(str))
return _PyUnicodeWriter_WriteStr(writer, str);
Py_ssize_t len = end - start;
if (len == 0) {
return 0;
}
Py_UCS4 maxchar;
if (PyUnicode_MAX_CHAR_VALUE(str) > writer->maxchar) {
maxchar = _PyUnicode_FindMaxChar(str, start, end);
}
else {
maxchar = writer->maxchar;
}
if (_PyUnicodeWriter_Prepare(writer, len, maxchar) < 0) {
return -1;
}
_PyUnicode_FastCopyCharacters(writer->buffer, writer->pos,
str, start, len);
writer->pos += len;
return 0;
}
int
PyUnicodeWriter_WriteSubstring(PyUnicodeWriter *writer, PyObject *str,
Py_ssize_t start, Py_ssize_t end)
{
if (!PyUnicode_Check(str)) {
PyErr_Format(PyExc_TypeError, "expect str, not %T", str);
return -1;
}
if (start < 0 || start > end) {
PyErr_Format(PyExc_ValueError, "invalid start argument");
return -1;
}
if (end > PyUnicode_GET_LENGTH(str)) {
PyErr_Format(PyExc_ValueError, "invalid end argument");
return -1;
}
return _PyUnicodeWriter_WriteSubstring((_PyUnicodeWriter*)writer, str,
start, end);
}
int
_PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer,
const char *ascii, Py_ssize_t len)
{
if (len == -1)
len = strlen(ascii);
if (len == 0) {
return 0;
}
assert(ucs1lib_find_max_char((const Py_UCS1*)ascii, (const Py_UCS1*)ascii + len) < 128);
if (writer->buffer == NULL && !writer->overallocate) {
PyObject *str;
str = _PyUnicode_FromASCII(ascii, len);
if (str == NULL)
return -1;
writer->readonly = 1;
writer->buffer = str;
_PyUnicodeWriter_Update(writer);
writer->pos += len;
return 0;
}
if (_PyUnicodeWriter_Prepare(writer, len, 127) == -1)
return -1;
switch (writer->kind)
{
case PyUnicode_1BYTE_KIND:
{
const Py_UCS1 *str = (const Py_UCS1 *)ascii;
Py_UCS1 *data = writer->data;
memcpy(data + writer->pos, str, len);
break;
}
case PyUnicode_2BYTE_KIND:
{
_PyUnicode_CONVERT_BYTES(
Py_UCS1, Py_UCS2,
ascii, ascii + len,
(Py_UCS2 *)writer->data + writer->pos);
break;
}
case PyUnicode_4BYTE_KIND:
{
_PyUnicode_CONVERT_BYTES(
Py_UCS1, Py_UCS4,
ascii, ascii + len,
(Py_UCS4 *)writer->data + writer->pos);
break;
}
default:
Py_UNREACHABLE();
}
writer->pos += len;
return 0;
}
int
PyUnicodeWriter_WriteASCII(PyUnicodeWriter *writer,
const char *str,
Py_ssize_t size)
{
assert(writer != NULL);
_Py_AssertHoldsTstate();
_PyUnicodeWriter *priv_writer = (_PyUnicodeWriter*)writer;
return _PyUnicodeWriter_WriteASCIIString(priv_writer, str, size);
}
int
PyUnicodeWriter_WriteUTF8(PyUnicodeWriter *writer,
const char *str,
Py_ssize_t size)
{
if (size < 0) {
size = strlen(str);
}
_PyUnicodeWriter *_writer = (_PyUnicodeWriter*)writer;
Py_ssize_t old_pos = _writer->pos;
int res = _PyUnicode_DecodeUTF8Writer(_writer, str, size,
_Py_ERROR_STRICT, NULL, NULL);
if (res < 0) {
_writer->pos = old_pos;
}
return res;
}
int
PyUnicodeWriter_DecodeUTF8Stateful(PyUnicodeWriter *writer,
const char *string,
Py_ssize_t length,
const char *errors,
Py_ssize_t *consumed)
{
if (length < 0) {
length = strlen(string);
}
_PyUnicodeWriter *_writer = (_PyUnicodeWriter*)writer;
Py_ssize_t old_pos = _writer->pos;
int res = _PyUnicode_DecodeUTF8Writer(_writer, string, length,
_Py_ERROR_UNKNOWN, errors,
consumed);
if (res < 0) {
_writer->pos = old_pos;
if (consumed) {
*consumed = 0;
}
}
return res;
}
int
_PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
const char *str, Py_ssize_t len)
{
Py_UCS4 maxchar;
maxchar = ucs1lib_find_max_char((const Py_UCS1*)str, (const Py_UCS1*)str + len);
if (_PyUnicodeWriter_Prepare(writer, len, maxchar) == -1)
return -1;
unicode_write_cstr(writer->buffer, writer->pos, str, len);
writer->pos += len;
return 0;
}
PyObject *
_PyUnicodeWriter_Finish(_PyUnicodeWriter *writer)
{
PyObject *str;
if (writer->pos == 0) {
Py_CLEAR(writer->buffer);
return _PyUnicode_GetEmpty();
}
str = writer->buffer;
writer->buffer = NULL;
if (writer->readonly) {
assert(PyUnicode_GET_LENGTH(str) == writer->pos);
return str;
}
if (PyUnicode_GET_LENGTH(str) != writer->pos) {
PyObject *str2;
str2 = _PyUnicode_ResizeCompact(str, writer->pos);
if (str2 == NULL) {
Py_DECREF(str);
return NULL;
}
str = str2;
}
assert(_PyUnicode_CheckConsistency(str, 1));
return _PyUnicode_Result(str);
}
PyObject*
PyUnicodeWriter_Finish(PyUnicodeWriter *writer)
{
PyObject *str = _PyUnicodeWriter_Finish((_PyUnicodeWriter*)writer);
assert(((_PyUnicodeWriter*)writer)->buffer == NULL);
_Py_FREELIST_FREE(unicode_writers, writer, PyMem_Free);
return str;
}
void
_PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer)
{
Py_CLEAR(writer->buffer);
}
You can’t perform that action at this time.