Mercurial > repos > rliterman > csp2

comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/include/python3.8/cpython/unicodeobject.h @ 69:33d812a61356

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author jpayne
date Tue, 18 Mar 2025 17:55:14 -0400
parents
children
comparison
equal deleted inserted replaced
67:0e9998148a16 69:33d812a61356
1 #ifndef Py_CPYTHON_UNICODEOBJECT_H
2 # error "this header file must not be included directly"
3 #endif
4
5 #ifdef __cplusplus
6 extern "C" {
7 #endif
8
9 /* Py_UNICODE was the native Unicode storage format (code unit) used by
10 Python and represents a single Unicode element in the Unicode type.
11 With PEP 393, Py_UNICODE is deprecated and replaced with a
12 typedef to wchar_t. */
13 #define PY_UNICODE_TYPE wchar_t
14 /* Py_DEPRECATED(3.3) */ typedef wchar_t Py_UNICODE;
15
16 /* --- Internal Unicode Operations ---------------------------------------- */
17
18 /* Since splitting on whitespace is an important use case, and
19 whitespace in most situations is solely ASCII whitespace, we
20 optimize for the common case by using a quick look-up table
21 _Py_ascii_whitespace (see below) with an inlined check.
22
23 */
24 #define Py_UNICODE_ISSPACE(ch) \
25 ((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))
26
27 #define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
28 #define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
29 #define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
30 #define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
31
32 #define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
33 #define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
34 #define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
35
36 #define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
37 #define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
38 #define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
39 #define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
40
41 #define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
42 #define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
43 #define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
44
45 #define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
46
47 #define Py_UNICODE_ISALNUM(ch) \
48 (Py_UNICODE_ISALPHA(ch) || \
49 Py_UNICODE_ISDECIMAL(ch) || \
50 Py_UNICODE_ISDIGIT(ch) || \
51 Py_UNICODE_ISNUMERIC(ch))
52
53 #define Py_UNICODE_COPY(target, source, length) \
54 memcpy((target), (source), (length)*sizeof(Py_UNICODE))
55
56 #define Py_UNICODE_FILL(target, value, length) \
57 do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
58 for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
59 } while (0)
60
61 /* macros to work with surrogates */
62 #define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDFFF)
63 #define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDBFF)
64 #define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= (ch) && (ch) <= 0xDFFF)
65 /* Join two surrogate characters and return a single Py_UCS4 value. */
66 #define Py_UNICODE_JOIN_SURROGATES(high, low) \
67 (((((Py_UCS4)(high) & 0x03FF) << 10) | \
68 ((Py_UCS4)(low) & 0x03FF)) + 0x10000)
69 /* high surrogate = top 10 bits added to D800 */
70 #define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 - (0x10000 >> 10) + ((ch) >> 10))
71 /* low surrogate = bottom 10 bits added to DC00 */
72 #define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 + ((ch) & 0x3FF))
73
74 /* Check if substring matches at given offset. The offset must be
75 valid, and the substring must not be empty. */
76
77 #define Py_UNICODE_MATCH(string, offset, substring) \
78 ((*((string)->wstr + (offset)) == *((substring)->wstr)) && \
79 ((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
80 !memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))
81
82 /* --- Unicode Type ------------------------------------------------------- */
83
84 /* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
85 structure. state.ascii and state.compact are set, and the data
86 immediately follow the structure. utf8_length and wstr_length can be found
87 in the length field; the utf8 pointer is equal to the data pointer. */
88 typedef struct {
89 /* There are 4 forms of Unicode strings:
90
91 - compact ascii:
92
93 * structure = PyASCIIObject
94 * test: PyUnicode_IS_COMPACT_ASCII(op)
95 * kind = PyUnicode_1BYTE_KIND
96 * compact = 1
97 * ascii = 1
98 * ready = 1
99 * (length is the length of the utf8 and wstr strings)
100 * (data starts just after the structure)
101 * (since ASCII is decoded from UTF-8, the utf8 string are the data)
102
103 - compact:
104
105 * structure = PyCompactUnicodeObject
106 * test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
107 * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
108 PyUnicode_4BYTE_KIND
109 * compact = 1
110 * ready = 1
111 * ascii = 0
112 * utf8 is not shared with data
113 * utf8_length = 0 if utf8 is NULL
114 * wstr is shared with data and wstr_length=length
115 if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
116 or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
117 * wstr_length = 0 if wstr is NULL
118 * (data starts just after the structure)
119
120 - legacy string, not ready:
121
122 * structure = PyUnicodeObject
123 * test: kind == PyUnicode_WCHAR_KIND
124 * length = 0 (use wstr_length)
125 * hash = -1
126 * kind = PyUnicode_WCHAR_KIND
127 * compact = 0
128 * ascii = 0
129 * ready = 0
130 * interned = SSTATE_NOT_INTERNED
131 * wstr is not NULL
132 * data.any is NULL
133 * utf8 is NULL
134 * utf8_length = 0
135
136 - legacy string, ready:
137
138 * structure = PyUnicodeObject structure
139 * test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
140 * kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
141 PyUnicode_4BYTE_KIND
142 * compact = 0
143 * ready = 1
144 * data.any is not NULL
145 * utf8 is shared and utf8_length = length with data.any if ascii = 1
146 * utf8_length = 0 if utf8 is NULL
147 * wstr is shared with data.any and wstr_length = length
148 if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
149 or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
150 * wstr_length = 0 if wstr is NULL
151
152 Compact strings use only one memory block (structure + characters),
153 whereas legacy strings use one block for the structure and one block
154 for characters.
155
156 Legacy strings are created by PyUnicode_FromUnicode() and
157 PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
158 when PyUnicode_READY() is called.
159
160 See also _PyUnicode_CheckConsistency().
161 */
162 PyObject_HEAD
163 Py_ssize_t length; /* Number of code points in the string */
164 Py_hash_t hash; /* Hash value; -1 if not set */
165 struct {
166 /*
167 SSTATE_NOT_INTERNED (0)
168 SSTATE_INTERNED_MORTAL (1)
169 SSTATE_INTERNED_IMMORTAL (2)
170
171 If interned != SSTATE_NOT_INTERNED, the two references from the
172 dictionary to this object are *not* counted in ob_refcnt.
173 */
174 unsigned int interned:2;
175 /* Character size:
176
177 - PyUnicode_WCHAR_KIND (0):
178
179 * character type = wchar_t (16 or 32 bits, depending on the
180 platform)
181
182 - PyUnicode_1BYTE_KIND (1):
183
184 * character type = Py_UCS1 (8 bits, unsigned)
185 * all characters are in the range U+0000-U+00FF (latin1)
186 * if ascii is set, all characters are in the range U+0000-U+007F
187 (ASCII), otherwise at least one character is in the range
188 U+0080-U+00FF
189
190 - PyUnicode_2BYTE_KIND (2):
191
192 * character type = Py_UCS2 (16 bits, unsigned)
193 * all characters are in the range U+0000-U+FFFF (BMP)
194 * at least one character is in the range U+0100-U+FFFF
195
196 - PyUnicode_4BYTE_KIND (4):
197
198 * character type = Py_UCS4 (32 bits, unsigned)
199 * all characters are in the range U+0000-U+10FFFF
200 * at least one character is in the range U+10000-U+10FFFF
201 */
202 unsigned int kind:3;
203 /* Compact is with respect to the allocation scheme. Compact unicode
204 objects only require one memory block while non-compact objects use
205 one block for the PyUnicodeObject struct and another for its data
206 buffer. */
207 unsigned int compact:1;
208 /* The string only contains characters in the range U+0000-U+007F (ASCII)
209 and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
210 set, use the PyASCIIObject structure. */
211 unsigned int ascii:1;
212 /* The ready flag indicates whether the object layout is initialized
213 completely. This means that this is either a compact object, or
214 the data pointer is filled out. The bit is redundant, and helps
215 to minimize the test in PyUnicode_IS_READY(). */
216 unsigned int ready:1;
217 /* Padding to ensure that PyUnicode_DATA() is always aligned to
218 4 bytes (see issue #19537 on m68k). */
219 unsigned int :24;
220 } state;
221 wchar_t *wstr; /* wchar_t representation (null-terminated) */
222 } PyASCIIObject;
223
224 /* Non-ASCII strings allocated through PyUnicode_New use the
225 PyCompactUnicodeObject structure. state.compact is set, and the data
226 immediately follow the structure. */
227 typedef struct {
228 PyASCIIObject _base;
229 Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
230 * terminating \0. */
231 char *utf8; /* UTF-8 representation (null-terminated) */
232 Py_ssize_t wstr_length; /* Number of code points in wstr, possible
233 * surrogates count as two code points. */
234 } PyCompactUnicodeObject;
235
236 /* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
237 PyUnicodeObject structure. The actual string data is initially in the wstr
238 block, and copied into the data block using _PyUnicode_Ready. */
239 typedef struct {
240 PyCompactUnicodeObject _base;
241 union {
242 void *any;
243 Py_UCS1 *latin1;
244 Py_UCS2 *ucs2;
245 Py_UCS4 *ucs4;
246 } data; /* Canonical, smallest-form Unicode buffer */
247 } PyUnicodeObject;
248
249 PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
250 PyObject *op,
251 int check_content);
252
253 /* Fast access macros */
254 #define PyUnicode_WSTR_LENGTH(op) \
255 (PyUnicode_IS_COMPACT_ASCII(op) ? \
256 ((PyASCIIObject*)op)->length : \
257 ((PyCompactUnicodeObject*)op)->wstr_length)
258
259 /* Returns the deprecated Py_UNICODE representation's size in code units
260 (this includes surrogate pairs as 2 units).
261 If the Py_UNICODE representation is not available, it will be computed
262 on request. Use PyUnicode_GET_LENGTH() for the length in code points. */
263
264 /* Py_DEPRECATED(3.3) */
265 #define PyUnicode_GET_SIZE(op) \
266 (assert(PyUnicode_Check(op)), \
267 (((PyASCIIObject *)(op))->wstr) ? \
268 PyUnicode_WSTR_LENGTH(op) : \
269 ((void)PyUnicode_AsUnicode(_PyObject_CAST(op)),\
270 assert(((PyASCIIObject *)(op))->wstr), \
271 PyUnicode_WSTR_LENGTH(op)))
272
273 /* Py_DEPRECATED(3.3) */
274 #define PyUnicode_GET_DATA_SIZE(op) \
275 (PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
276
277 /* Alias for PyUnicode_AsUnicode(). This will create a wchar_t/Py_UNICODE
278 representation on demand. Using this macro is very inefficient now,
279 try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
280 use PyUnicode_WRITE() and PyUnicode_READ(). */
281
282 /* Py_DEPRECATED(3.3) */
283 #define PyUnicode_AS_UNICODE(op) \
284 (assert(PyUnicode_Check(op)), \
285 (((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
286 PyUnicode_AsUnicode(_PyObject_CAST(op)))
287
288 /* Py_DEPRECATED(3.3) */
289 #define PyUnicode_AS_DATA(op) \
290 ((const char *)(PyUnicode_AS_UNICODE(op)))
291
292
293 /* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
294
295 /* Values for PyASCIIObject.state: */
296
297 /* Interning state. */
298 #define SSTATE_NOT_INTERNED 0
299 #define SSTATE_INTERNED_MORTAL 1
300 #define SSTATE_INTERNED_IMMORTAL 2
301
302 /* Return true if the string contains only ASCII characters, or 0 if not. The
303 string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
304 ready. */
305 #define PyUnicode_IS_ASCII(op) \
306 (assert(PyUnicode_Check(op)), \
307 assert(PyUnicode_IS_READY(op)), \
308 ((PyASCIIObject*)op)->state.ascii)
309
310 /* Return true if the string is compact or 0 if not.
311 No type checks or Ready calls are performed. */
312 #define PyUnicode_IS_COMPACT(op) \
313 (((PyASCIIObject*)(op))->state.compact)
314
315 /* Return true if the string is a compact ASCII string (use PyASCIIObject
316 structure), or 0 if not. No type checks or Ready calls are performed. */
317 #define PyUnicode_IS_COMPACT_ASCII(op) \
318 (((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
319
320 enum PyUnicode_Kind {
321 /* String contains only wstr byte characters. This is only possible
322 when the string was created with a legacy API and _PyUnicode_Ready()
323 has not been called yet. */
324 PyUnicode_WCHAR_KIND = 0,
325 /* Return values of the PyUnicode_KIND() macro: */
326 PyUnicode_1BYTE_KIND = 1,
327 PyUnicode_2BYTE_KIND = 2,
328 PyUnicode_4BYTE_KIND = 4
329 };
330
331 /* Return pointers to the canonical representation cast to unsigned char,
332 Py_UCS2, or Py_UCS4 for direct character access.
333 No checks are performed, use PyUnicode_KIND() before to ensure
334 these will work correctly. */
335
336 #define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
337 #define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
338 #define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
339
340 /* Return one of the PyUnicode_*_KIND values defined above. */
341 #define PyUnicode_KIND(op) \
342 (assert(PyUnicode_Check(op)), \
343 assert(PyUnicode_IS_READY(op)), \
344 ((PyASCIIObject *)(op))->state.kind)
345
346 /* Return a void pointer to the raw unicode buffer. */
347 #define _PyUnicode_COMPACT_DATA(op) \
348 (PyUnicode_IS_ASCII(op) ? \
349 ((void*)((PyASCIIObject*)(op) + 1)) : \
350 ((void*)((PyCompactUnicodeObject*)(op) + 1)))
351
352 #define _PyUnicode_NONCOMPACT_DATA(op) \
353 (assert(((PyUnicodeObject*)(op))->data.any), \
354 ((((PyUnicodeObject *)(op))->data.any)))
355
356 #define PyUnicode_DATA(op) \
357 (assert(PyUnicode_Check(op)), \
358 PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
359 _PyUnicode_NONCOMPACT_DATA(op))
360
361 /* In the access macros below, "kind" may be evaluated more than once.
362 All other macro parameters are evaluated exactly once, so it is safe
363 to put side effects into them (such as increasing the index). */
364
365 /* Write into the canonical representation, this macro does not do any sanity
366 checks and is intended for usage in loops. The caller should cache the
367 kind and data pointers obtained from other macro calls.
368 index is the index in the string (starts at 0) and value is the new
369 code point value which should be written to that location. */
370 #define PyUnicode_WRITE(kind, data, index, value) \
371 do { \
372 switch ((kind)) { \
373 case PyUnicode_1BYTE_KIND: { \
374 ((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
375 break; \
376 } \
377 case PyUnicode_2BYTE_KIND: { \
378 ((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
379 break; \
380 } \
381 default: { \
382 assert((kind) == PyUnicode_4BYTE_KIND); \
383 ((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
384 } \
385 } \
386 } while (0)
387
388 /* Read a code point from the string's canonical representation. No checks
389 or ready calls are performed. */
390 #define PyUnicode_READ(kind, data, index) \
391 ((Py_UCS4) \
392 ((kind) == PyUnicode_1BYTE_KIND ? \
393 ((const Py_UCS1 *)(data))[(index)] : \
394 ((kind) == PyUnicode_2BYTE_KIND ? \
395 ((const Py_UCS2 *)(data))[(index)] : \
396 ((const Py_UCS4 *)(data))[(index)] \
397 ) \
398 ))
399
400 /* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it
401 calls PyUnicode_KIND() and might call it twice. For single reads, use
402 PyUnicode_READ_CHAR, for multiple consecutive reads callers should
403 cache kind and use PyUnicode_READ instead. */
404 #define PyUnicode_READ_CHAR(unicode, index) \
405 (assert(PyUnicode_Check(unicode)), \
406 assert(PyUnicode_IS_READY(unicode)), \
407 (Py_UCS4) \
408 (PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
409 ((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
410 (PyUnicode_KIND((unicode)) == PyUnicode_2BYTE_KIND ? \
411 ((const Py_UCS2 *)(PyUnicode_DATA((unicode))))[(index)] : \
412 ((const Py_UCS4 *)(PyUnicode_DATA((unicode))))[(index)] \
413 ) \
414 ))
415
416 /* Returns the length of the unicode string. The caller has to make sure that
417 the string has it's canonical representation set before calling
418 this macro. Call PyUnicode_(FAST_)Ready to ensure that. */
419 #define PyUnicode_GET_LENGTH(op) \
420 (assert(PyUnicode_Check(op)), \
421 assert(PyUnicode_IS_READY(op)), \
422 ((PyASCIIObject *)(op))->length)
423
424
425 /* Fast check to determine whether an object is ready. Equivalent to
426 PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any) */
427
428 #define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)
429
430 /* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
431 case. If the canonical representation is not yet set, it will still call
432 _PyUnicode_Ready().
433 Returns 0 on success and -1 on errors. */
434 #define PyUnicode_READY(op) \
435 (assert(PyUnicode_Check(op)), \
436 (PyUnicode_IS_READY(op) ? \
437 0 : _PyUnicode_Ready(_PyObject_CAST(op))))
438
439 /* Return a maximum character value which is suitable for creating another
440 string based on op. This is always an approximation but more efficient
441 than iterating over the string. */
442 #define PyUnicode_MAX_CHAR_VALUE(op) \
443 (assert(PyUnicode_IS_READY(op)), \
444 (PyUnicode_IS_ASCII(op) ? \
445 (0x7f) : \
446 (PyUnicode_KIND(op) == PyUnicode_1BYTE_KIND ? \
447 (0xffU) : \
448 (PyUnicode_KIND(op) == PyUnicode_2BYTE_KIND ? \
449 (0xffffU) : \
450 (0x10ffffU)))))
451
452 /* === Public API ========================================================= */
453
454 /* --- Plain Py_UNICODE --------------------------------------------------- */
455
456 /* With PEP 393, this is the recommended way to allocate a new unicode object.
457 This function will allocate the object and its buffer in a single memory
458 block. Objects created using this function are not resizable. */
459 PyAPI_FUNC(PyObject*) PyUnicode_New(
460 Py_ssize_t size, /* Number of code points in the new string */
461 Py_UCS4 maxchar /* maximum code point value in the string */
462 );
463
464 /* Initializes the canonical string representation from the deprecated
465 wstr/Py_UNICODE representation. This function is used to convert Unicode
466 objects which were created using the old API to the new flexible format
467 introduced with PEP 393.
468
469 Don't call this function directly, use the public PyUnicode_READY() macro
470 instead. */
471 PyAPI_FUNC(int) _PyUnicode_Ready(
472 PyObject *unicode /* Unicode object */
473 );
474
475 /* Get a copy of a Unicode string. */
476 PyAPI_FUNC(PyObject*) _PyUnicode_Copy(
477 PyObject *unicode
478 );
479
480 /* Copy character from one unicode object into another, this function performs
481 character conversion when necessary and falls back to memcpy() if possible.
482
483 Fail if to is too small (smaller than *how_many* or smaller than
484 len(from)-from_start), or if kind(from[from_start:from_start+how_many]) >
485 kind(to), or if *to* has more than 1 reference.
486
487 Return the number of written character, or return -1 and raise an exception
488 on error.
489
490 Pseudo-code:
491
492 how_many = min(how_many, len(from) - from_start)
493 to[to_start:to_start+how_many] = from[from_start:from_start+how_many]
494 return how_many
495
496 Note: The function doesn't write a terminating null character.
497 */
498 PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters(
499 PyObject *to,
500 Py_ssize_t to_start,
501 PyObject *from,
502 Py_ssize_t from_start,
503 Py_ssize_t how_many
504 );
505
506 /* Unsafe version of PyUnicode_CopyCharacters(): don't check arguments and so
507 may crash if parameters are invalid (e.g. if the output string
508 is too short). */
509 PyAPI_FUNC(void) _PyUnicode_FastCopyCharacters(
510 PyObject *to,
511 Py_ssize_t to_start,
512 PyObject *from,
513 Py_ssize_t from_start,
514 Py_ssize_t how_many
515 );
516
517 /* Fill a string with a character: write fill_char into
518 unicode[start:start+length].
519
520 Fail if fill_char is bigger than the string maximum character, or if the
521 string has more than 1 reference.
522
523 Return the number of written character, or return -1 and raise an exception
524 on error. */
525 PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill(
526 PyObject *unicode,
527 Py_ssize_t start,
528 Py_ssize_t length,
529 Py_UCS4 fill_char
530 );
531
532 /* Unsafe version of PyUnicode_Fill(): don't check arguments and so may crash
533 if parameters are invalid (e.g. if length is longer than the string). */
534 PyAPI_FUNC(void) _PyUnicode_FastFill(
535 PyObject *unicode,
536 Py_ssize_t start,
537 Py_ssize_t length,
538 Py_UCS4 fill_char
539 );
540
541 /* Create a Unicode Object from the Py_UNICODE buffer u of the given
542 size.
543
544 u may be NULL which causes the contents to be undefined. It is the
545 user's responsibility to fill in the needed data afterwards. Note
546 that modifying the Unicode object contents after construction is
547 only allowed if u was set to NULL.
548
549 The buffer is copied into the new object. */
550 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
551 const Py_UNICODE *u, /* Unicode buffer */
552 Py_ssize_t size /* size of buffer */
553 );
554
555 /* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters.
556 Scan the string to find the maximum character. */
557 PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
558 int kind,
559 const void *buffer,
560 Py_ssize_t size);
561
562 /* Create a new string from a buffer of ASCII characters.
563 WARNING: Don't check if the string contains any non-ASCII character. */
564 PyAPI_FUNC(PyObject*) _PyUnicode_FromASCII(
565 const char *buffer,
566 Py_ssize_t size);
567
568 /* Compute the maximum character of the substring unicode[start:end].
569 Return 127 for an empty string. */
570 PyAPI_FUNC(Py_UCS4) _PyUnicode_FindMaxChar (
571 PyObject *unicode,
572 Py_ssize_t start,
573 Py_ssize_t end);
574
575 /* Return a read-only pointer to the Unicode object's internal
576 Py_UNICODE buffer.
577 If the wchar_t/Py_UNICODE representation is not yet available, this
578 function will calculate it. */
579 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
580 PyObject *unicode /* Unicode object */
581 );
582
583 /* Similar to PyUnicode_AsUnicode(), but raises a ValueError if the string
584 contains null characters. */
585 PyAPI_FUNC(const Py_UNICODE *) _PyUnicode_AsUnicode(
586 PyObject *unicode /* Unicode object */
587 );
588
589 /* Return a read-only pointer to the Unicode object's internal
590 Py_UNICODE buffer and save the length at size.
591 If the wchar_t/Py_UNICODE representation is not yet available, this
592 function will calculate it. */
593
594 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicodeAndSize(
595 PyObject *unicode, /* Unicode object */
596 Py_ssize_t *size /* location where to save the length */
597 );
598
599 /* Get the maximum ordinal for a Unicode character. */
600 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
601
602
603 /* --- _PyUnicodeWriter API ----------------------------------------------- */
604
605 typedef struct {
606 PyObject *buffer;
607 void *data;
608 enum PyUnicode_Kind kind;
609 Py_UCS4 maxchar;
610 Py_ssize_t size;
611 Py_ssize_t pos;
612
613 /* minimum number of allocated characters (default: 0) */
614 Py_ssize_t min_length;
615
616 /* minimum character (default: 127, ASCII) */
617 Py_UCS4 min_char;
618
619 /* If non-zero, overallocate the buffer (default: 0). */
620 unsigned char overallocate;
621
622 /* If readonly is 1, buffer is a shared string (cannot be modified)
623 and size is set to 0. */
624 unsigned char readonly;
625 } _PyUnicodeWriter ;
626
627 /* Initialize a Unicode writer.
628 *
629 * By default, the minimum buffer size is 0 character and overallocation is
630 * disabled. Set min_length, min_char and overallocate attributes to control
631 * the allocation of the buffer. */
632 PyAPI_FUNC(void)
633 _PyUnicodeWriter_Init(_PyUnicodeWriter *writer);
634
635 /* Prepare the buffer to write 'length' characters
636 with the specified maximum character.
637
638 Return 0 on success, raise an exception and return -1 on error. */
639 #define _PyUnicodeWriter_Prepare(WRITER, LENGTH, MAXCHAR) \
640 (((MAXCHAR) <= (WRITER)->maxchar \
641 && (LENGTH) <= (WRITER)->size - (WRITER)->pos) \
642 ? 0 \
643 : (((LENGTH) == 0) \
644 ? 0 \
645 : _PyUnicodeWriter_PrepareInternal((WRITER), (LENGTH), (MAXCHAR))))
646
647 /* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro
648 instead. */
649 PyAPI_FUNC(int)
650 _PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
651 Py_ssize_t length, Py_UCS4 maxchar);
652
653 /* Prepare the buffer to have at least the kind KIND.
654 For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will
655 support characters in range U+000-U+FFFF.
656
657 Return 0 on success, raise an exception and return -1 on error. */
658 #define _PyUnicodeWriter_PrepareKind(WRITER, KIND) \
659 (assert((KIND) != PyUnicode_WCHAR_KIND), \
660 (KIND) <= (WRITER)->kind \
661 ? 0 \
662 : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))
663
664 /* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
665 macro instead. */
666 PyAPI_FUNC(int)
667 _PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
668 enum PyUnicode_Kind kind);
669
670 /* Append a Unicode character.
671 Return 0 on success, raise an exception and return -1 on error. */
672 PyAPI_FUNC(int)
673 _PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer,
674 Py_UCS4 ch
675 );
676
677 /* Append a Unicode string.
678 Return 0 on success, raise an exception and return -1 on error. */
679 PyAPI_FUNC(int)
680 _PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer,
681 PyObject *str /* Unicode string */
682 );
683
684 /* Append a substring of a Unicode string.
685 Return 0 on success, raise an exception and return -1 on error. */
686 PyAPI_FUNC(int)
687 _PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer,
688 PyObject *str, /* Unicode string */
689 Py_ssize_t start,
690 Py_ssize_t end
691 );
692
693 /* Append an ASCII-encoded byte string.
694 Return 0 on success, raise an exception and return -1 on error. */
695 PyAPI_FUNC(int)
696 _PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer,
697 const char *str, /* ASCII-encoded byte string */
698 Py_ssize_t len /* number of bytes, or -1 if unknown */
699 );
700
701 /* Append a latin1-encoded byte string.
702 Return 0 on success, raise an exception and return -1 on error. */
703 PyAPI_FUNC(int)
704 _PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
705 const char *str, /* latin1-encoded byte string */
706 Py_ssize_t len /* length in bytes */
707 );
708
709 /* Get the value of the writer as a Unicode string. Clear the
710 buffer of the writer. Raise an exception and return NULL
711 on error. */
712 PyAPI_FUNC(PyObject *)
713 _PyUnicodeWriter_Finish(_PyUnicodeWriter *writer);
714
715 /* Deallocate memory of a writer (clear its internal buffer). */
716 PyAPI_FUNC(void)
717 _PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer);
718
719
720 /* Format the object based on the format_spec, as defined in PEP 3101
721 (Advanced String Formatting). */
722 PyAPI_FUNC(int) _PyUnicode_FormatAdvancedWriter(
723 _PyUnicodeWriter *writer,
724 PyObject *obj,
725 PyObject *format_spec,
726 Py_ssize_t start,
727 Py_ssize_t end);
728
729 /* --- wchar_t support for platforms which support it --------------------- */
730
731 #ifdef HAVE_WCHAR_H
732 PyAPI_FUNC(void*) _PyUnicode_AsKind(PyObject *s, unsigned int kind);
733 #endif
734
735 /* --- Manage the default encoding ---------------------------------------- */
736
737 /* Returns a pointer to the default encoding (UTF-8) of the
738 Unicode object unicode and the size of the encoded representation
739 in bytes stored in *size.
740
741 In case of an error, no *size is set.
742
743 This function caches the UTF-8 encoded string in the unicodeobject
744 and subsequent calls will return the same string. The memory is released
745 when the unicodeobject is deallocated.
746
747 _PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
748 support the previous internal function with the same behaviour.
749
750 *** This API is for interpreter INTERNAL USE ONLY and will likely
751 *** be removed or changed in the future.
752
753 *** If you need to access the Unicode object as UTF-8 bytes string,
754 *** please use PyUnicode_AsUTF8String() instead.
755 */
756
757 PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
758 PyObject *unicode,
759 Py_ssize_t *size);
760
761 #define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
762
763 /* Returns a pointer to the default encoding (UTF-8) of the
764 Unicode object unicode.
765
766 Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation
767 in the unicodeobject.
768
769 _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to
770 support the previous internal function with the same behaviour.
771
772 Use of this API is DEPRECATED since no size information can be
773 extracted from the returned data.
774
775 *** This API is for interpreter INTERNAL USE ONLY and will likely
776 *** be removed or changed for Python 3.1.
777
778 *** If you need to access the Unicode object as UTF-8 bytes string,
779 *** please use PyUnicode_AsUTF8String() instead.
780
781 */
782
783 PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
784
785 #define _PyUnicode_AsString PyUnicode_AsUTF8
786
787 /* --- Generic Codecs ----------------------------------------------------- */
788
789 /* Encodes a Py_UNICODE buffer of the given size and returns a
790 Python string object. */
791 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_Encode(
792 const Py_UNICODE *s, /* Unicode char buffer */
793 Py_ssize_t size, /* number of Py_UNICODE chars to encode */
794 const char *encoding, /* encoding */
795 const char *errors /* error handling */
796 );
797
798 /* --- UTF-7 Codecs ------------------------------------------------------- */
799
800 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
801 const Py_UNICODE *data, /* Unicode char buffer */
802 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
803 int base64SetO, /* Encode RFC2152 Set O characters in base64 */
804 int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
805 const char *errors /* error handling */
806 );
807
808 PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF7(
809 PyObject *unicode, /* Unicode object */
810 int base64SetO, /* Encode RFC2152 Set O characters in base64 */
811 int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
812 const char *errors /* error handling */
813 );
814
815 /* --- UTF-8 Codecs ------------------------------------------------------- */
816
817 PyAPI_FUNC(PyObject*) _PyUnicode_AsUTF8String(
818 PyObject *unicode,
819 const char *errors);
820
821 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
822 const Py_UNICODE *data, /* Unicode char buffer */
823 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
824 const char *errors /* error handling */
825 );
826
827 /* --- UTF-32 Codecs ------------------------------------------------------ */
828
829 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF32(
830 const Py_UNICODE *data, /* Unicode char buffer */
831 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
832 const char *errors, /* error handling */
833 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
834 );
835
836 PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF32(
837 PyObject *object, /* Unicode object */
838 const char *errors, /* error handling */
839 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
840 );
841
842 /* --- UTF-16 Codecs ------------------------------------------------------ */
843
844 /* Returns a Python string object holding the UTF-16 encoded value of
845 the Unicode data.
846
847 If byteorder is not 0, output is written according to the following
848 byte order:
849
850 byteorder == -1: little endian
851 byteorder == 0: native byte order (writes a BOM mark)
852 byteorder == 1: big endian
853
854 If byteorder is 0, the output string will always start with the
855 Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
856 prepended.
857
858 Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
859 UCS-2. This trick makes it possible to add full UTF-16 capabilities
860 at a later point without compromising the APIs.
861
862 */
863 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
864 const Py_UNICODE *data, /* Unicode char buffer */
865 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
866 const char *errors, /* error handling */
867 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
868 );
869
870 PyAPI_FUNC(PyObject*) _PyUnicode_EncodeUTF16(
871 PyObject* unicode, /* Unicode object */
872 const char *errors, /* error handling */
873 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
874 );
875
876 /* --- Unicode-Escape Codecs ---------------------------------------------- */
877
878 /* Helper for PyUnicode_DecodeUnicodeEscape that detects invalid escape
879 chars. */
880 PyAPI_FUNC(PyObject*) _PyUnicode_DecodeUnicodeEscape(
881 const char *string, /* Unicode-Escape encoded string */
882 Py_ssize_t length, /* size of string */
883 const char *errors, /* error handling */
884 const char **first_invalid_escape /* on return, points to first
885 invalid escaped char in
886 string. */
887 );
888
889 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
890 const Py_UNICODE *data, /* Unicode char buffer */
891 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
892 );
893
894 /* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
895
896 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
897 const Py_UNICODE *data, /* Unicode char buffer */
898 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
899 );
900
901 /* --- Latin-1 Codecs ----------------------------------------------------- */
902
903 PyAPI_FUNC(PyObject*) _PyUnicode_AsLatin1String(
904 PyObject* unicode,
905 const char* errors);
906
907 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
908 const Py_UNICODE *data, /* Unicode char buffer */
909 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
910 const char *errors /* error handling */
911 );
912
913 /* --- ASCII Codecs ------------------------------------------------------- */
914
915 PyAPI_FUNC(PyObject*) _PyUnicode_AsASCIIString(
916 PyObject* unicode,
917 const char* errors);
918
919 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
920 const Py_UNICODE *data, /* Unicode char buffer */
921 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
922 const char *errors /* error handling */
923 );
924
925 /* --- Character Map Codecs ----------------------------------------------- */
926
927 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
928 const Py_UNICODE *data, /* Unicode char buffer */
929 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
930 PyObject *mapping, /* encoding mapping */
931 const char *errors /* error handling */
932 );
933
934 PyAPI_FUNC(PyObject*) _PyUnicode_EncodeCharmap(
935 PyObject *unicode, /* Unicode object */
936 PyObject *mapping, /* encoding mapping */
937 const char *errors /* error handling */
938 );
939
940 /* Translate a Py_UNICODE buffer of the given length by applying a
941 character mapping table to it and return the resulting Unicode
942 object.
943
944 The mapping table must map Unicode ordinal integers to Unicode strings,
945 Unicode ordinal integers or None (causing deletion of the character).
946
947 Mapping tables may be dictionaries or sequences. Unmapped character
948 ordinals (ones which cause a LookupError) are left untouched and
949 are copied as-is.
950
951 */
952 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
953 const Py_UNICODE *data, /* Unicode char buffer */
954 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
955 PyObject *table, /* Translate table */
956 const char *errors /* error handling */
957 );
958
959 /* --- MBCS codecs for Windows -------------------------------------------- */
960
961 #ifdef MS_WINDOWS
962 Py_DEPRECATED(3.3) PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
963 const Py_UNICODE *data, /* Unicode char buffer */
964 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
965 const char *errors /* error handling */
966 );
967 #endif
968
969 /* --- Decimal Encoder ---------------------------------------------------- */
970
971 /* Takes a Unicode string holding a decimal value and writes it into
972 an output buffer using standard ASCII digit codes.
973
974 The output buffer has to provide at least length+1 bytes of storage
975 area. The output string is 0-terminated.
976
977 The encoder converts whitespace to ' ', decimal characters to their
978 corresponding ASCII digit and all other Latin-1 characters except
979 \0 as-is. Characters outside this range (Unicode ordinals 1-256)
980 are treated as errors. This includes embedded NULL bytes.
981
982 Error handling is defined by the errors argument:
983
984 NULL or "strict": raise a ValueError
985 "ignore": ignore the wrong characters (these are not copied to the
986 output buffer)
987 "replace": replaces illegal characters with '?'
988
989 Returns 0 on success, -1 on failure.
990
991 */
992
993 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
994 Py_UNICODE *s, /* Unicode buffer */
995 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
996 char *output, /* Output buffer; must have size >= length */
997 const char *errors /* error handling */
998 );
999
1000 /* Transforms code points that have decimal digit property to the
1001 corresponding ASCII digit code points.
1002
1003 Returns a new Unicode string on success, NULL on failure.
1004 */
1005
1006 /* Py_DEPRECATED(3.3) */
1007 PyAPI_FUNC(PyObject*) PyUnicode_TransformDecimalToASCII(
1008 Py_UNICODE *s, /* Unicode buffer */
1009 Py_ssize_t length /* Number of Py_UNICODE chars to transform */
1010 );
1011
1012 /* Coverts a Unicode object holding a decimal value to an ASCII string
1013 for using in int, float and complex parsers.
1014 Transforms code points that have decimal digit property to the
1015 corresponding ASCII digit code points. Transforms spaces to ASCII.
1016 Transforms code points starting from the first non-ASCII code point that
1017 is neither a decimal digit nor a space to the end into '?'. */
1018
1019 PyAPI_FUNC(PyObject*) _PyUnicode_TransformDecimalAndSpaceToASCII(
1020 PyObject *unicode /* Unicode object */
1021 );
1022
1023 /* --- Methods & Slots ---------------------------------------------------- */
1024
1025 PyAPI_FUNC(PyObject *) _PyUnicode_JoinArray(
1026 PyObject *separator,
1027 PyObject *const *items,
1028 Py_ssize_t seqlen
1029 );
1030
1031 /* Test whether a unicode is equal to ASCII identifier. Return 1 if true,
1032 0 otherwise. The right argument must be ASCII identifier.
1033 Any error occurs inside will be cleared before return. */
1034 PyAPI_FUNC(int) _PyUnicode_EqualToASCIIId(
1035 PyObject *left, /* Left string */
1036 _Py_Identifier *right /* Right identifier */
1037 );
1038
1039 /* Test whether a unicode is equal to ASCII string. Return 1 if true,
1040 0 otherwise. The right argument must be ASCII-encoded string.
1041 Any error occurs inside will be cleared before return. */
1042 PyAPI_FUNC(int) _PyUnicode_EqualToASCIIString(
1043 PyObject *left,
1044 const char *right /* ASCII-encoded string */
1045 );
1046
1047 /* Externally visible for str.strip(unicode) */
1048 PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
1049 PyObject *self,
1050 int striptype,
1051 PyObject *sepobj
1052 );
1053
1054 /* Using explicit passed-in values, insert the thousands grouping
1055 into the string pointed to by buffer. For the argument descriptions,
1056 see Objects/stringlib/localeutil.h */
1057 PyAPI_FUNC(Py_ssize_t) _PyUnicode_InsertThousandsGrouping(
1058 _PyUnicodeWriter *writer,
1059 Py_ssize_t n_buffer,
1060 PyObject *digits,
1061 Py_ssize_t d_pos,
1062 Py_ssize_t n_digits,
1063 Py_ssize_t min_width,
1064 const char *grouping,
1065 PyObject *thousands_sep,
1066 Py_UCS4 *maxchar);
1067
1068 /* === Characters Type APIs =============================================== */
1069
1070 /* Helper array used by Py_UNICODE_ISSPACE(). */
1071
1072 PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[];
1073
1074 /* These should not be used directly. Use the Py_UNICODE_IS* and
1075 Py_UNICODE_TO* macros instead.
1076
1077 These APIs are implemented in Objects/unicodectype.c.
1078
1079 */
1080
1081 PyAPI_FUNC(int) _PyUnicode_IsLowercase(
1082 Py_UCS4 ch /* Unicode character */
1083 );
1084
1085 PyAPI_FUNC(int) _PyUnicode_IsUppercase(
1086 Py_UCS4 ch /* Unicode character */
1087 );
1088
1089 PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
1090 Py_UCS4 ch /* Unicode character */
1091 );
1092
1093 PyAPI_FUNC(int) _PyUnicode_IsXidStart(
1094 Py_UCS4 ch /* Unicode character */
1095 );
1096
1097 PyAPI_FUNC(int) _PyUnicode_IsXidContinue(
1098 Py_UCS4 ch /* Unicode character */
1099 );
1100
1101 PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
1102 const Py_UCS4 ch /* Unicode character */
1103 );
1104
1105 PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
1106 const Py_UCS4 ch /* Unicode character */
1107 );
1108
1109 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase(
1110 Py_UCS4 ch /* Unicode character */
1111 );
1112
1113 /* Py_DEPRECATED(3.3) */ PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase(
1114 Py_UCS4 ch /* Unicode character */
1115 );
1116
1117 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase(
1118 Py_UCS4 ch /* Unicode character */
1119 );
1120
1121 PyAPI_FUNC(int) _PyUnicode_ToLowerFull(
1122 Py_UCS4 ch, /* Unicode character */
1123 Py_UCS4 *res
1124 );
1125
1126 PyAPI_FUNC(int) _PyUnicode_ToTitleFull(
1127 Py_UCS4 ch, /* Unicode character */
1128 Py_UCS4 *res
1129 );
1130
1131 PyAPI_FUNC(int) _PyUnicode_ToUpperFull(
1132 Py_UCS4 ch, /* Unicode character */
1133 Py_UCS4 *res
1134 );
1135
1136 PyAPI_FUNC(int) _PyUnicode_ToFoldedFull(
1137 Py_UCS4 ch, /* Unicode character */
1138 Py_UCS4 *res
1139 );
1140
1141 PyAPI_FUNC(int) _PyUnicode_IsCaseIgnorable(
1142 Py_UCS4 ch /* Unicode character */
1143 );
1144
1145 PyAPI_FUNC(int) _PyUnicode_IsCased(
1146 Py_UCS4 ch /* Unicode character */
1147 );
1148
1149 PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
1150 Py_UCS4 ch /* Unicode character */
1151 );
1152
1153 PyAPI_FUNC(int) _PyUnicode_ToDigit(
1154 Py_UCS4 ch /* Unicode character */
1155 );
1156
1157 PyAPI_FUNC(double) _PyUnicode_ToNumeric(
1158 Py_UCS4 ch /* Unicode character */
1159 );
1160
1161 PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
1162 Py_UCS4 ch /* Unicode character */
1163 );
1164
1165 PyAPI_FUNC(int) _PyUnicode_IsDigit(
1166 Py_UCS4 ch /* Unicode character */
1167 );
1168
1169 PyAPI_FUNC(int) _PyUnicode_IsNumeric(
1170 Py_UCS4 ch /* Unicode character */
1171 );
1172
1173 PyAPI_FUNC(int) _PyUnicode_IsPrintable(
1174 Py_UCS4 ch /* Unicode character */
1175 );
1176
1177 PyAPI_FUNC(int) _PyUnicode_IsAlpha(
1178 Py_UCS4 ch /* Unicode character */
1179 );
1180
1181 Py_DEPRECATED(3.3) PyAPI_FUNC(size_t) Py_UNICODE_strlen(
1182 const Py_UNICODE *u
1183 );
1184
1185 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
1186 Py_UNICODE *s1,
1187 const Py_UNICODE *s2);
1188
1189 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcat(
1190 Py_UNICODE *s1, const Py_UNICODE *s2);
1191
1192 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
1193 Py_UNICODE *s1,
1194 const Py_UNICODE *s2,
1195 size_t n);
1196
1197 Py_DEPRECATED(3.3) PyAPI_FUNC(int) Py_UNICODE_strcmp(
1198 const Py_UNICODE *s1,
1199 const Py_UNICODE *s2
1200 );
1201
1202 Py_DEPRECATED(3.3) PyAPI_FUNC(int) Py_UNICODE_strncmp(
1203 const Py_UNICODE *s1,
1204 const Py_UNICODE *s2,
1205 size_t n
1206 );
1207
1208 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
1209 const Py_UNICODE *s,
1210 Py_UNICODE c
1211 );
1212
1213 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strrchr(
1214 const Py_UNICODE *s,
1215 Py_UNICODE c
1216 );
1217
1218 PyAPI_FUNC(PyObject*) _PyUnicode_FormatLong(PyObject *, int, int, int);
1219
1220 /* Create a copy of a unicode string ending with a nul character. Return NULL
1221 and raise a MemoryError exception on memory allocation failure, otherwise
1222 return a new allocated buffer (use PyMem_Free() to free the buffer). */
1223
1224 Py_DEPRECATED(3.3) PyAPI_FUNC(Py_UNICODE*) PyUnicode_AsUnicodeCopy(
1225 PyObject *unicode
1226 );
1227
1228 /* Return an interned Unicode object for an Identifier; may fail if there is no memory.*/
1229 PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
1230 /* Clear all static strings. */
1231 PyAPI_FUNC(void) _PyUnicode_ClearStaticStrings(void);
1232
1233 /* Fast equality check when the inputs are known to be exact unicode types
1234 and where the hash values are equal (i.e. a very probable match) */
1235 PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);
1236
1237 #ifdef __cplusplus
1238 }
1239 #endif