/src/cpython/Objects/clinic/unicodeobject.c.h
Line | Count | Source (jump to first uncovered line) |
1 | | /*[clinic input] |
2 | | preserve |
3 | | [clinic start generated code]*/ |
4 | | |
5 | | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
6 | | # include "pycore_gc.h" // PyGC_Head |
7 | | # include "pycore_runtime.h" // _Py_ID() |
8 | | #endif |
9 | | #include "pycore_abstract.h" // _PyNumber_Index() |
10 | | #include "pycore_modsupport.h" // _PyArg_CheckPositional() |
11 | | |
12 | | PyDoc_STRVAR(EncodingMap_size__doc__, |
13 | | "size($self, /)\n" |
14 | | "--\n" |
15 | | "\n" |
16 | | "Return the size (in bytes) of this object."); |
17 | | |
18 | | #define ENCODINGMAP_SIZE_METHODDEF \ |
19 | | {"size", (PyCFunction)EncodingMap_size, METH_NOARGS, EncodingMap_size__doc__}, |
20 | | |
21 | | static PyObject * |
22 | | EncodingMap_size_impl(struct encoding_map *self); |
23 | | |
24 | | static PyObject * |
25 | | EncodingMap_size(PyObject *self, PyObject *Py_UNUSED(ignored)) |
26 | 0 | { |
27 | 0 | return EncodingMap_size_impl((struct encoding_map *)self); |
28 | 0 | } |
29 | | |
30 | | PyDoc_STRVAR(unicode_title__doc__, |
31 | | "title($self, /)\n" |
32 | | "--\n" |
33 | | "\n" |
34 | | "Return a version of the string where each word is titlecased.\n" |
35 | | "\n" |
36 | | "More specifically, words start with uppercased characters and all remaining\n" |
37 | | "cased characters have lower case."); |
38 | | |
39 | | #define UNICODE_TITLE_METHODDEF \ |
40 | | {"title", (PyCFunction)unicode_title, METH_NOARGS, unicode_title__doc__}, |
41 | | |
42 | | static PyObject * |
43 | | unicode_title_impl(PyObject *self); |
44 | | |
45 | | static PyObject * |
46 | | unicode_title(PyObject *self, PyObject *Py_UNUSED(ignored)) |
47 | 0 | { |
48 | 0 | return unicode_title_impl(self); |
49 | 0 | } |
50 | | |
51 | | PyDoc_STRVAR(unicode_capitalize__doc__, |
52 | | "capitalize($self, /)\n" |
53 | | "--\n" |
54 | | "\n" |
55 | | "Return a capitalized version of the string.\n" |
56 | | "\n" |
57 | | "More specifically, make the first character have upper case and the rest lower\n" |
58 | | "case."); |
59 | | |
60 | | #define UNICODE_CAPITALIZE_METHODDEF \ |
61 | | {"capitalize", (PyCFunction)unicode_capitalize, METH_NOARGS, unicode_capitalize__doc__}, |
62 | | |
63 | | static PyObject * |
64 | | unicode_capitalize_impl(PyObject *self); |
65 | | |
66 | | static PyObject * |
67 | | unicode_capitalize(PyObject *self, PyObject *Py_UNUSED(ignored)) |
68 | 0 | { |
69 | 0 | return unicode_capitalize_impl(self); |
70 | 0 | } |
71 | | |
72 | | PyDoc_STRVAR(unicode_casefold__doc__, |
73 | | "casefold($self, /)\n" |
74 | | "--\n" |
75 | | "\n" |
76 | | "Return a version of the string suitable for caseless comparisons."); |
77 | | |
78 | | #define UNICODE_CASEFOLD_METHODDEF \ |
79 | | {"casefold", (PyCFunction)unicode_casefold, METH_NOARGS, unicode_casefold__doc__}, |
80 | | |
81 | | static PyObject * |
82 | | unicode_casefold_impl(PyObject *self); |
83 | | |
84 | | static PyObject * |
85 | | unicode_casefold(PyObject *self, PyObject *Py_UNUSED(ignored)) |
86 | 0 | { |
87 | 0 | return unicode_casefold_impl(self); |
88 | 0 | } |
89 | | |
90 | | PyDoc_STRVAR(unicode_center__doc__, |
91 | | "center($self, width, fillchar=\' \', /)\n" |
92 | | "--\n" |
93 | | "\n" |
94 | | "Return a centered string of length width.\n" |
95 | | "\n" |
96 | | "Padding is done using the specified fill character (default is a space)."); |
97 | | |
98 | | #define UNICODE_CENTER_METHODDEF \ |
99 | | {"center", _PyCFunction_CAST(unicode_center), METH_FASTCALL, unicode_center__doc__}, |
100 | | |
101 | | static PyObject * |
102 | | unicode_center_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar); |
103 | | |
104 | | static PyObject * |
105 | | unicode_center(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
106 | 0 | { |
107 | 0 | PyObject *return_value = NULL; |
108 | 0 | Py_ssize_t width; |
109 | 0 | Py_UCS4 fillchar = ' '; |
110 | |
|
111 | 0 | if (!_PyArg_CheckPositional("center", nargs, 1, 2)) { |
112 | 0 | goto exit; |
113 | 0 | } |
114 | 0 | { |
115 | 0 | Py_ssize_t ival = -1; |
116 | 0 | PyObject *iobj = _PyNumber_Index(args[0]); |
117 | 0 | if (iobj != NULL) { |
118 | 0 | ival = PyLong_AsSsize_t(iobj); |
119 | 0 | Py_DECREF(iobj); |
120 | 0 | } |
121 | 0 | if (ival == -1 && PyErr_Occurred()) { |
122 | 0 | goto exit; |
123 | 0 | } |
124 | 0 | width = ival; |
125 | 0 | } |
126 | 0 | if (nargs < 2) { |
127 | 0 | goto skip_optional; |
128 | 0 | } |
129 | 0 | if (!convert_uc(args[1], &fillchar)) { |
130 | 0 | goto exit; |
131 | 0 | } |
132 | 0 | skip_optional: |
133 | 0 | return_value = unicode_center_impl(self, width, fillchar); |
134 | |
|
135 | 0 | exit: |
136 | 0 | return return_value; |
137 | 0 | } |
138 | | |
139 | | PyDoc_STRVAR(unicode_count__doc__, |
140 | | "count($self, sub[, start[, end]], /)\n" |
141 | | "--\n" |
142 | | "\n" |
143 | | "Return the number of non-overlapping occurrences of substring sub in string S[start:end].\n" |
144 | | "\n" |
145 | | "Optional arguments start and end are interpreted as in slice notation."); |
146 | | |
147 | | #define UNICODE_COUNT_METHODDEF \ |
148 | | {"count", _PyCFunction_CAST(unicode_count), METH_FASTCALL, unicode_count__doc__}, |
149 | | |
150 | | static Py_ssize_t |
151 | | unicode_count_impl(PyObject *str, PyObject *substr, Py_ssize_t start, |
152 | | Py_ssize_t end); |
153 | | |
154 | | static PyObject * |
155 | | unicode_count(PyObject *str, PyObject *const *args, Py_ssize_t nargs) |
156 | 19.0M | { |
157 | 19.0M | PyObject *return_value = NULL; |
158 | 19.0M | PyObject *substr; |
159 | 19.0M | Py_ssize_t start = 0; |
160 | 19.0M | Py_ssize_t end = PY_SSIZE_T_MAX; |
161 | 19.0M | Py_ssize_t _return_value; |
162 | | |
163 | 19.0M | if (!_PyArg_CheckPositional("count", nargs, 1, 3)) { |
164 | 0 | goto exit; |
165 | 0 | } |
166 | 19.0M | if (!PyUnicode_Check(args[0])) { |
167 | 0 | _PyArg_BadArgument("count", "argument 1", "str", args[0]); |
168 | 0 | goto exit; |
169 | 0 | } |
170 | 19.0M | substr = args[0]; |
171 | 19.0M | if (nargs < 2) { |
172 | 7.45M | goto skip_optional; |
173 | 7.45M | } |
174 | 11.6M | if (!_PyEval_SliceIndex(args[1], &start)) { |
175 | 0 | goto exit; |
176 | 0 | } |
177 | 11.6M | if (nargs < 3) { |
178 | 0 | goto skip_optional; |
179 | 0 | } |
180 | 11.6M | if (!_PyEval_SliceIndex(args[2], &end)) { |
181 | 0 | goto exit; |
182 | 0 | } |
183 | 19.0M | skip_optional: |
184 | 19.0M | _return_value = unicode_count_impl(str, substr, start, end); |
185 | 19.0M | if ((_return_value == -1) && PyErr_Occurred()) { |
186 | 0 | goto exit; |
187 | 0 | } |
188 | 19.0M | return_value = PyLong_FromSsize_t(_return_value); |
189 | | |
190 | 19.0M | exit: |
191 | 19.0M | return return_value; |
192 | 19.0M | } |
193 | | |
194 | | PyDoc_STRVAR(unicode_encode__doc__, |
195 | | "encode($self, /, encoding=\'utf-8\', errors=\'strict\')\n" |
196 | | "--\n" |
197 | | "\n" |
198 | | "Encode the string using the codec registered for encoding.\n" |
199 | | "\n" |
200 | | " encoding\n" |
201 | | " The encoding in which to encode the string.\n" |
202 | | " errors\n" |
203 | | " The error handling scheme to use for encoding errors.\n" |
204 | | " The default is \'strict\' meaning that encoding errors raise a\n" |
205 | | " UnicodeEncodeError. Other possible values are \'ignore\', \'replace\' and\n" |
206 | | " \'xmlcharrefreplace\' as well as any other name registered with\n" |
207 | | " codecs.register_error that can handle UnicodeEncodeErrors."); |
208 | | |
209 | | #define UNICODE_ENCODE_METHODDEF \ |
210 | | {"encode", _PyCFunction_CAST(unicode_encode), METH_FASTCALL|METH_KEYWORDS, unicode_encode__doc__}, |
211 | | |
212 | | static PyObject * |
213 | | unicode_encode_impl(PyObject *self, const char *encoding, const char *errors); |
214 | | |
215 | | static PyObject * |
216 | | unicode_encode(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
217 | 15.6M | { |
218 | 15.6M | PyObject *return_value = NULL; |
219 | 15.6M | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
220 | | |
221 | 15.6M | #define NUM_KEYWORDS 2 |
222 | 15.6M | static struct { |
223 | 15.6M | PyGC_Head _this_is_not_used; |
224 | 15.6M | PyObject_VAR_HEAD |
225 | 15.6M | Py_hash_t ob_hash; |
226 | 15.6M | PyObject *ob_item[NUM_KEYWORDS]; |
227 | 15.6M | } _kwtuple = { |
228 | 15.6M | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
229 | 15.6M | .ob_hash = -1, |
230 | 15.6M | .ob_item = { &_Py_ID(encoding), &_Py_ID(errors), }, |
231 | 15.6M | }; |
232 | 15.6M | #undef NUM_KEYWORDS |
233 | 15.6M | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
234 | | |
235 | | #else // !Py_BUILD_CORE |
236 | | # define KWTUPLE NULL |
237 | | #endif // !Py_BUILD_CORE |
238 | | |
239 | 15.6M | static const char * const _keywords[] = {"encoding", "errors", NULL}; |
240 | 15.6M | static _PyArg_Parser _parser = { |
241 | 15.6M | .keywords = _keywords, |
242 | 15.6M | .fname = "encode", |
243 | 15.6M | .kwtuple = KWTUPLE, |
244 | 15.6M | }; |
245 | 15.6M | #undef KWTUPLE |
246 | 15.6M | PyObject *argsbuf[2]; |
247 | 15.6M | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; |
248 | 15.6M | const char *encoding = NULL; |
249 | 15.6M | const char *errors = NULL; |
250 | | |
251 | 15.6M | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
252 | 15.6M | /*minpos*/ 0, /*maxpos*/ 2, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
253 | 15.6M | if (!args) { |
254 | 0 | goto exit; |
255 | 0 | } |
256 | 15.6M | if (!noptargs) { |
257 | 11.7M | goto skip_optional_pos; |
258 | 11.7M | } |
259 | 3.83M | if (args[0]) { |
260 | 3.83M | if (!PyUnicode_Check(args[0])) { |
261 | 0 | _PyArg_BadArgument("encode", "argument 'encoding'", "str", args[0]); |
262 | 0 | goto exit; |
263 | 0 | } |
264 | 3.83M | Py_ssize_t encoding_length; |
265 | 3.83M | encoding = PyUnicode_AsUTF8AndSize(args[0], &encoding_length); |
266 | 3.83M | if (encoding == NULL) { |
267 | 0 | goto exit; |
268 | 0 | } |
269 | 3.83M | if (strlen(encoding) != (size_t)encoding_length) { |
270 | 0 | PyErr_SetString(PyExc_ValueError, "embedded null character"); |
271 | 0 | goto exit; |
272 | 0 | } |
273 | 3.83M | if (!--noptargs) { |
274 | 3.01M | goto skip_optional_pos; |
275 | 3.01M | } |
276 | 3.83M | } |
277 | 821k | if (!PyUnicode_Check(args[1])) { |
278 | 0 | _PyArg_BadArgument("encode", "argument 'errors'", "str", args[1]); |
279 | 0 | goto exit; |
280 | 0 | } |
281 | 821k | Py_ssize_t errors_length; |
282 | 821k | errors = PyUnicode_AsUTF8AndSize(args[1], &errors_length); |
283 | 821k | if (errors == NULL) { |
284 | 0 | goto exit; |
285 | 0 | } |
286 | 821k | if (strlen(errors) != (size_t)errors_length) { |
287 | 0 | PyErr_SetString(PyExc_ValueError, "embedded null character"); |
288 | 0 | goto exit; |
289 | 0 | } |
290 | 15.6M | skip_optional_pos: |
291 | 15.6M | return_value = unicode_encode_impl(self, encoding, errors); |
292 | | |
293 | 15.6M | exit: |
294 | 15.6M | return return_value; |
295 | 15.6M | } |
296 | | |
297 | | PyDoc_STRVAR(unicode_expandtabs__doc__, |
298 | | "expandtabs($self, /, tabsize=8)\n" |
299 | | "--\n" |
300 | | "\n" |
301 | | "Return a copy where all tab characters are expanded using spaces.\n" |
302 | | "\n" |
303 | | "If tabsize is not given, a tab size of 8 characters is assumed."); |
304 | | |
305 | | #define UNICODE_EXPANDTABS_METHODDEF \ |
306 | | {"expandtabs", _PyCFunction_CAST(unicode_expandtabs), METH_FASTCALL|METH_KEYWORDS, unicode_expandtabs__doc__}, |
307 | | |
308 | | static PyObject * |
309 | | unicode_expandtabs_impl(PyObject *self, int tabsize); |
310 | | |
311 | | static PyObject * |
312 | | unicode_expandtabs(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
313 | 8.61M | { |
314 | 8.61M | PyObject *return_value = NULL; |
315 | 8.61M | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
316 | | |
317 | 8.61M | #define NUM_KEYWORDS 1 |
318 | 8.61M | static struct { |
319 | 8.61M | PyGC_Head _this_is_not_used; |
320 | 8.61M | PyObject_VAR_HEAD |
321 | 8.61M | Py_hash_t ob_hash; |
322 | 8.61M | PyObject *ob_item[NUM_KEYWORDS]; |
323 | 8.61M | } _kwtuple = { |
324 | 8.61M | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
325 | 8.61M | .ob_hash = -1, |
326 | 8.61M | .ob_item = { &_Py_ID(tabsize), }, |
327 | 8.61M | }; |
328 | 8.61M | #undef NUM_KEYWORDS |
329 | 8.61M | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
330 | | |
331 | | #else // !Py_BUILD_CORE |
332 | | # define KWTUPLE NULL |
333 | | #endif // !Py_BUILD_CORE |
334 | | |
335 | 8.61M | static const char * const _keywords[] = {"tabsize", NULL}; |
336 | 8.61M | static _PyArg_Parser _parser = { |
337 | 8.61M | .keywords = _keywords, |
338 | 8.61M | .fname = "expandtabs", |
339 | 8.61M | .kwtuple = KWTUPLE, |
340 | 8.61M | }; |
341 | 8.61M | #undef KWTUPLE |
342 | 8.61M | PyObject *argsbuf[1]; |
343 | 8.61M | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; |
344 | 8.61M | int tabsize = 8; |
345 | | |
346 | 8.61M | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
347 | 8.61M | /*minpos*/ 0, /*maxpos*/ 1, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
348 | 8.61M | if (!args) { |
349 | 0 | goto exit; |
350 | 0 | } |
351 | 8.61M | if (!noptargs) { |
352 | 1.88k | goto skip_optional_pos; |
353 | 1.88k | } |
354 | 8.61M | tabsize = PyLong_AsInt(args[0]); |
355 | 8.61M | if (tabsize == -1 && PyErr_Occurred()) { |
356 | 0 | goto exit; |
357 | 0 | } |
358 | 8.61M | skip_optional_pos: |
359 | 8.61M | return_value = unicode_expandtabs_impl(self, tabsize); |
360 | | |
361 | 8.61M | exit: |
362 | 8.61M | return return_value; |
363 | 8.61M | } |
364 | | |
365 | | PyDoc_STRVAR(unicode_find__doc__, |
366 | | "find($self, sub[, start[, end]], /)\n" |
367 | | "--\n" |
368 | | "\n" |
369 | | "Return the lowest index in S where substring sub is found, such that sub is contained within S[start:end].\n" |
370 | | "\n" |
371 | | "Optional arguments start and end are interpreted as in slice notation.\n" |
372 | | "Return -1 on failure."); |
373 | | |
374 | | #define UNICODE_FIND_METHODDEF \ |
375 | | {"find", _PyCFunction_CAST(unicode_find), METH_FASTCALL, unicode_find__doc__}, |
376 | | |
377 | | static Py_ssize_t |
378 | | unicode_find_impl(PyObject *str, PyObject *substr, Py_ssize_t start, |
379 | | Py_ssize_t end); |
380 | | |
381 | | static PyObject * |
382 | | unicode_find(PyObject *str, PyObject *const *args, Py_ssize_t nargs) |
383 | 14.4M | { |
384 | 14.4M | PyObject *return_value = NULL; |
385 | 14.4M | PyObject *substr; |
386 | 14.4M | Py_ssize_t start = 0; |
387 | 14.4M | Py_ssize_t end = PY_SSIZE_T_MAX; |
388 | 14.4M | Py_ssize_t _return_value; |
389 | | |
390 | 14.4M | if (!_PyArg_CheckPositional("find", nargs, 1, 3)) { |
391 | 0 | goto exit; |
392 | 0 | } |
393 | 14.4M | if (!PyUnicode_Check(args[0])) { |
394 | 0 | _PyArg_BadArgument("find", "argument 1", "str", args[0]); |
395 | 0 | goto exit; |
396 | 0 | } |
397 | 14.4M | substr = args[0]; |
398 | 14.4M | if (nargs < 2) { |
399 | 10.6M | goto skip_optional; |
400 | 10.6M | } |
401 | 3.84M | if (!_PyEval_SliceIndex(args[1], &start)) { |
402 | 0 | goto exit; |
403 | 0 | } |
404 | 3.84M | if (nargs < 3) { |
405 | 3.84M | goto skip_optional; |
406 | 3.84M | } |
407 | 0 | if (!_PyEval_SliceIndex(args[2], &end)) { |
408 | 0 | goto exit; |
409 | 0 | } |
410 | 14.4M | skip_optional: |
411 | 14.4M | _return_value = unicode_find_impl(str, substr, start, end); |
412 | 14.4M | if ((_return_value == -1) && PyErr_Occurred()) { |
413 | 0 | goto exit; |
414 | 0 | } |
415 | 14.4M | return_value = PyLong_FromSsize_t(_return_value); |
416 | | |
417 | 14.4M | exit: |
418 | 14.4M | return return_value; |
419 | 14.4M | } |
420 | | |
421 | | PyDoc_STRVAR(unicode_index__doc__, |
422 | | "index($self, sub[, start[, end]], /)\n" |
423 | | "--\n" |
424 | | "\n" |
425 | | "Return the lowest index in S where substring sub is found, such that sub is contained within S[start:end].\n" |
426 | | "\n" |
427 | | "Optional arguments start and end are interpreted as in slice notation.\n" |
428 | | "Raises ValueError when the substring is not found."); |
429 | | |
430 | | #define UNICODE_INDEX_METHODDEF \ |
431 | | {"index", _PyCFunction_CAST(unicode_index), METH_FASTCALL, unicode_index__doc__}, |
432 | | |
433 | | static Py_ssize_t |
434 | | unicode_index_impl(PyObject *str, PyObject *substr, Py_ssize_t start, |
435 | | Py_ssize_t end); |
436 | | |
437 | | static PyObject * |
438 | | unicode_index(PyObject *str, PyObject *const *args, Py_ssize_t nargs) |
439 | 528k | { |
440 | 528k | PyObject *return_value = NULL; |
441 | 528k | PyObject *substr; |
442 | 528k | Py_ssize_t start = 0; |
443 | 528k | Py_ssize_t end = PY_SSIZE_T_MAX; |
444 | 528k | Py_ssize_t _return_value; |
445 | | |
446 | 528k | if (!_PyArg_CheckPositional("index", nargs, 1, 3)) { |
447 | 0 | goto exit; |
448 | 0 | } |
449 | 528k | if (!PyUnicode_Check(args[0])) { |
450 | 0 | _PyArg_BadArgument("index", "argument 1", "str", args[0]); |
451 | 0 | goto exit; |
452 | 0 | } |
453 | 528k | substr = args[0]; |
454 | 528k | if (nargs < 2) { |
455 | 528k | goto skip_optional; |
456 | 528k | } |
457 | 0 | if (!_PyEval_SliceIndex(args[1], &start)) { |
458 | 0 | goto exit; |
459 | 0 | } |
460 | 0 | if (nargs < 3) { |
461 | 0 | goto skip_optional; |
462 | 0 | } |
463 | 0 | if (!_PyEval_SliceIndex(args[2], &end)) { |
464 | 0 | goto exit; |
465 | 0 | } |
466 | 528k | skip_optional: |
467 | 528k | _return_value = unicode_index_impl(str, substr, start, end); |
468 | 528k | if ((_return_value == -1) && PyErr_Occurred()) { |
469 | 0 | goto exit; |
470 | 0 | } |
471 | 528k | return_value = PyLong_FromSsize_t(_return_value); |
472 | | |
473 | 528k | exit: |
474 | 528k | return return_value; |
475 | 528k | } |
476 | | |
477 | | PyDoc_STRVAR(unicode_isascii__doc__, |
478 | | "isascii($self, /)\n" |
479 | | "--\n" |
480 | | "\n" |
481 | | "Return True if all characters in the string are ASCII, False otherwise.\n" |
482 | | "\n" |
483 | | "ASCII characters have code points in the range U+0000-U+007F.\n" |
484 | | "Empty string is ASCII too."); |
485 | | |
486 | | #define UNICODE_ISASCII_METHODDEF \ |
487 | | {"isascii", (PyCFunction)unicode_isascii, METH_NOARGS, unicode_isascii__doc__}, |
488 | | |
489 | | static PyObject * |
490 | | unicode_isascii_impl(PyObject *self); |
491 | | |
492 | | static PyObject * |
493 | | unicode_isascii(PyObject *self, PyObject *Py_UNUSED(ignored)) |
494 | 13.6M | { |
495 | 13.6M | return unicode_isascii_impl(self); |
496 | 13.6M | } |
497 | | |
498 | | PyDoc_STRVAR(unicode_islower__doc__, |
499 | | "islower($self, /)\n" |
500 | | "--\n" |
501 | | "\n" |
502 | | "Return True if the string is a lowercase string, False otherwise.\n" |
503 | | "\n" |
504 | | "A string is lowercase if all cased characters in the string are lowercase and\n" |
505 | | "there is at least one cased character in the string."); |
506 | | |
507 | | #define UNICODE_ISLOWER_METHODDEF \ |
508 | | {"islower", (PyCFunction)unicode_islower, METH_NOARGS, unicode_islower__doc__}, |
509 | | |
510 | | static PyObject * |
511 | | unicode_islower_impl(PyObject *self); |
512 | | |
513 | | static PyObject * |
514 | | unicode_islower(PyObject *self, PyObject *Py_UNUSED(ignored)) |
515 | 0 | { |
516 | 0 | return unicode_islower_impl(self); |
517 | 0 | } |
518 | | |
519 | | PyDoc_STRVAR(unicode_isupper__doc__, |
520 | | "isupper($self, /)\n" |
521 | | "--\n" |
522 | | "\n" |
523 | | "Return True if the string is an uppercase string, False otherwise.\n" |
524 | | "\n" |
525 | | "A string is uppercase if all cased characters in the string are uppercase and\n" |
526 | | "there is at least one cased character in the string."); |
527 | | |
528 | | #define UNICODE_ISUPPER_METHODDEF \ |
529 | | {"isupper", (PyCFunction)unicode_isupper, METH_NOARGS, unicode_isupper__doc__}, |
530 | | |
531 | | static PyObject * |
532 | | unicode_isupper_impl(PyObject *self); |
533 | | |
534 | | static PyObject * |
535 | | unicode_isupper(PyObject *self, PyObject *Py_UNUSED(ignored)) |
536 | 6.96k | { |
537 | 6.96k | return unicode_isupper_impl(self); |
538 | 6.96k | } |
539 | | |
540 | | PyDoc_STRVAR(unicode_istitle__doc__, |
541 | | "istitle($self, /)\n" |
542 | | "--\n" |
543 | | "\n" |
544 | | "Return True if the string is a title-cased string, False otherwise.\n" |
545 | | "\n" |
546 | | "In a title-cased string, upper- and title-case characters may only\n" |
547 | | "follow uncased characters and lowercase characters only cased ones."); |
548 | | |
549 | | #define UNICODE_ISTITLE_METHODDEF \ |
550 | | {"istitle", (PyCFunction)unicode_istitle, METH_NOARGS, unicode_istitle__doc__}, |
551 | | |
552 | | static PyObject * |
553 | | unicode_istitle_impl(PyObject *self); |
554 | | |
555 | | static PyObject * |
556 | | unicode_istitle(PyObject *self, PyObject *Py_UNUSED(ignored)) |
557 | 0 | { |
558 | 0 | return unicode_istitle_impl(self); |
559 | 0 | } |
560 | | |
561 | | PyDoc_STRVAR(unicode_isspace__doc__, |
562 | | "isspace($self, /)\n" |
563 | | "--\n" |
564 | | "\n" |
565 | | "Return True if the string is a whitespace string, False otherwise.\n" |
566 | | "\n" |
567 | | "A string is whitespace if all characters in the string are whitespace and there\n" |
568 | | "is at least one character in the string."); |
569 | | |
570 | | #define UNICODE_ISSPACE_METHODDEF \ |
571 | | {"isspace", (PyCFunction)unicode_isspace, METH_NOARGS, unicode_isspace__doc__}, |
572 | | |
573 | | static PyObject * |
574 | | unicode_isspace_impl(PyObject *self); |
575 | | |
576 | | static PyObject * |
577 | | unicode_isspace(PyObject *self, PyObject *Py_UNUSED(ignored)) |
578 | 18.3M | { |
579 | 18.3M | return unicode_isspace_impl(self); |
580 | 18.3M | } |
581 | | |
582 | | PyDoc_STRVAR(unicode_isalpha__doc__, |
583 | | "isalpha($self, /)\n" |
584 | | "--\n" |
585 | | "\n" |
586 | | "Return True if the string is an alphabetic string, False otherwise.\n" |
587 | | "\n" |
588 | | "A string is alphabetic if all characters in the string are alphabetic and there\n" |
589 | | "is at least one character in the string."); |
590 | | |
591 | | #define UNICODE_ISALPHA_METHODDEF \ |
592 | | {"isalpha", (PyCFunction)unicode_isalpha, METH_NOARGS, unicode_isalpha__doc__}, |
593 | | |
594 | | static PyObject * |
595 | | unicode_isalpha_impl(PyObject *self); |
596 | | |
597 | | static PyObject * |
598 | | unicode_isalpha(PyObject *self, PyObject *Py_UNUSED(ignored)) |
599 | 0 | { |
600 | 0 | return unicode_isalpha_impl(self); |
601 | 0 | } |
602 | | |
603 | | PyDoc_STRVAR(unicode_isalnum__doc__, |
604 | | "isalnum($self, /)\n" |
605 | | "--\n" |
606 | | "\n" |
607 | | "Return True if the string is an alpha-numeric string, False otherwise.\n" |
608 | | "\n" |
609 | | "A string is alpha-numeric if all characters in the string are alpha-numeric and\n" |
610 | | "there is at least one character in the string."); |
611 | | |
612 | | #define UNICODE_ISALNUM_METHODDEF \ |
613 | | {"isalnum", (PyCFunction)unicode_isalnum, METH_NOARGS, unicode_isalnum__doc__}, |
614 | | |
615 | | static PyObject * |
616 | | unicode_isalnum_impl(PyObject *self); |
617 | | |
618 | | static PyObject * |
619 | | unicode_isalnum(PyObject *self, PyObject *Py_UNUSED(ignored)) |
620 | 13.7M | { |
621 | 13.7M | return unicode_isalnum_impl(self); |
622 | 13.7M | } |
623 | | |
624 | | PyDoc_STRVAR(unicode_isdecimal__doc__, |
625 | | "isdecimal($self, /)\n" |
626 | | "--\n" |
627 | | "\n" |
628 | | "Return True if the string is a decimal string, False otherwise.\n" |
629 | | "\n" |
630 | | "A string is a decimal string if all characters in the string are decimal and\n" |
631 | | "there is at least one character in the string."); |
632 | | |
633 | | #define UNICODE_ISDECIMAL_METHODDEF \ |
634 | | {"isdecimal", (PyCFunction)unicode_isdecimal, METH_NOARGS, unicode_isdecimal__doc__}, |
635 | | |
636 | | static PyObject * |
637 | | unicode_isdecimal_impl(PyObject *self); |
638 | | |
639 | | static PyObject * |
640 | | unicode_isdecimal(PyObject *self, PyObject *Py_UNUSED(ignored)) |
641 | 0 | { |
642 | 0 | return unicode_isdecimal_impl(self); |
643 | 0 | } |
644 | | |
645 | | PyDoc_STRVAR(unicode_isdigit__doc__, |
646 | | "isdigit($self, /)\n" |
647 | | "--\n" |
648 | | "\n" |
649 | | "Return True if the string is a digit string, False otherwise.\n" |
650 | | "\n" |
651 | | "A string is a digit string if all characters in the string are digits and there\n" |
652 | | "is at least one character in the string."); |
653 | | |
654 | | #define UNICODE_ISDIGIT_METHODDEF \ |
655 | | {"isdigit", (PyCFunction)unicode_isdigit, METH_NOARGS, unicode_isdigit__doc__}, |
656 | | |
657 | | static PyObject * |
658 | | unicode_isdigit_impl(PyObject *self); |
659 | | |
660 | | static PyObject * |
661 | | unicode_isdigit(PyObject *self, PyObject *Py_UNUSED(ignored)) |
662 | 1.56M | { |
663 | 1.56M | return unicode_isdigit_impl(self); |
664 | 1.56M | } |
665 | | |
666 | | PyDoc_STRVAR(unicode_isnumeric__doc__, |
667 | | "isnumeric($self, /)\n" |
668 | | "--\n" |
669 | | "\n" |
670 | | "Return True if the string is a numeric string, False otherwise.\n" |
671 | | "\n" |
672 | | "A string is numeric if all characters in the string are numeric and there is at\n" |
673 | | "least one character in the string."); |
674 | | |
675 | | #define UNICODE_ISNUMERIC_METHODDEF \ |
676 | | {"isnumeric", (PyCFunction)unicode_isnumeric, METH_NOARGS, unicode_isnumeric__doc__}, |
677 | | |
678 | | static PyObject * |
679 | | unicode_isnumeric_impl(PyObject *self); |
680 | | |
681 | | static PyObject * |
682 | | unicode_isnumeric(PyObject *self, PyObject *Py_UNUSED(ignored)) |
683 | 0 | { |
684 | 0 | return unicode_isnumeric_impl(self); |
685 | 0 | } |
686 | | |
687 | | PyDoc_STRVAR(unicode_isidentifier__doc__, |
688 | | "isidentifier($self, /)\n" |
689 | | "--\n" |
690 | | "\n" |
691 | | "Return True if the string is a valid Python identifier, False otherwise.\n" |
692 | | "\n" |
693 | | "Call keyword.iskeyword(s) to test whether string s is a reserved identifier,\n" |
694 | | "such as \"def\" or \"class\"."); |
695 | | |
696 | | #define UNICODE_ISIDENTIFIER_METHODDEF \ |
697 | | {"isidentifier", (PyCFunction)unicode_isidentifier, METH_NOARGS, unicode_isidentifier__doc__}, |
698 | | |
699 | | static PyObject * |
700 | | unicode_isidentifier_impl(PyObject *self); |
701 | | |
702 | | static PyObject * |
703 | | unicode_isidentifier(PyObject *self, PyObject *Py_UNUSED(ignored)) |
704 | 269 | { |
705 | 269 | return unicode_isidentifier_impl(self); |
706 | 269 | } |
707 | | |
708 | | PyDoc_STRVAR(unicode_isprintable__doc__, |
709 | | "isprintable($self, /)\n" |
710 | | "--\n" |
711 | | "\n" |
712 | | "Return True if all characters in the string are printable, False otherwise.\n" |
713 | | "\n" |
714 | | "A character is printable if repr() may use it in its output."); |
715 | | |
716 | | #define UNICODE_ISPRINTABLE_METHODDEF \ |
717 | | {"isprintable", (PyCFunction)unicode_isprintable, METH_NOARGS, unicode_isprintable__doc__}, |
718 | | |
719 | | static PyObject * |
720 | | unicode_isprintable_impl(PyObject *self); |
721 | | |
722 | | static PyObject * |
723 | | unicode_isprintable(PyObject *self, PyObject *Py_UNUSED(ignored)) |
724 | 1.30M | { |
725 | 1.30M | return unicode_isprintable_impl(self); |
726 | 1.30M | } |
727 | | |
728 | | PyDoc_STRVAR(unicode_join__doc__, |
729 | | "join($self, iterable, /)\n" |
730 | | "--\n" |
731 | | "\n" |
732 | | "Concatenate any number of strings.\n" |
733 | | "\n" |
734 | | "The string whose method is called is inserted in between each given string.\n" |
735 | | "The result is returned as a new string.\n" |
736 | | "\n" |
737 | | "Example: \'.\'.join([\'ab\', \'pq\', \'rs\']) -> \'ab.pq.rs\'"); |
738 | | |
739 | | #define UNICODE_JOIN_METHODDEF \ |
740 | | {"join", (PyCFunction)unicode_join, METH_O, unicode_join__doc__}, |
741 | | |
742 | | PyDoc_STRVAR(unicode_ljust__doc__, |
743 | | "ljust($self, width, fillchar=\' \', /)\n" |
744 | | "--\n" |
745 | | "\n" |
746 | | "Return a left-justified string of length width.\n" |
747 | | "\n" |
748 | | "Padding is done using the specified fill character (default is a space)."); |
749 | | |
750 | | #define UNICODE_LJUST_METHODDEF \ |
751 | | {"ljust", _PyCFunction_CAST(unicode_ljust), METH_FASTCALL, unicode_ljust__doc__}, |
752 | | |
753 | | static PyObject * |
754 | | unicode_ljust_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar); |
755 | | |
756 | | static PyObject * |
757 | | unicode_ljust(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
758 | 0 | { |
759 | 0 | PyObject *return_value = NULL; |
760 | 0 | Py_ssize_t width; |
761 | 0 | Py_UCS4 fillchar = ' '; |
762 | |
|
763 | 0 | if (!_PyArg_CheckPositional("ljust", nargs, 1, 2)) { |
764 | 0 | goto exit; |
765 | 0 | } |
766 | 0 | { |
767 | 0 | Py_ssize_t ival = -1; |
768 | 0 | PyObject *iobj = _PyNumber_Index(args[0]); |
769 | 0 | if (iobj != NULL) { |
770 | 0 | ival = PyLong_AsSsize_t(iobj); |
771 | 0 | Py_DECREF(iobj); |
772 | 0 | } |
773 | 0 | if (ival == -1 && PyErr_Occurred()) { |
774 | 0 | goto exit; |
775 | 0 | } |
776 | 0 | width = ival; |
777 | 0 | } |
778 | 0 | if (nargs < 2) { |
779 | 0 | goto skip_optional; |
780 | 0 | } |
781 | 0 | if (!convert_uc(args[1], &fillchar)) { |
782 | 0 | goto exit; |
783 | 0 | } |
784 | 0 | skip_optional: |
785 | 0 | return_value = unicode_ljust_impl(self, width, fillchar); |
786 | |
|
787 | 0 | exit: |
788 | 0 | return return_value; |
789 | 0 | } |
790 | | |
791 | | PyDoc_STRVAR(unicode_lower__doc__, |
792 | | "lower($self, /)\n" |
793 | | "--\n" |
794 | | "\n" |
795 | | "Return a copy of the string converted to lowercase."); |
796 | | |
797 | | #define UNICODE_LOWER_METHODDEF \ |
798 | | {"lower", (PyCFunction)unicode_lower, METH_NOARGS, unicode_lower__doc__}, |
799 | | |
800 | | static PyObject * |
801 | | unicode_lower_impl(PyObject *self); |
802 | | |
803 | | static PyObject * |
804 | | unicode_lower(PyObject *self, PyObject *Py_UNUSED(ignored)) |
805 | 116M | { |
806 | 116M | return unicode_lower_impl(self); |
807 | 116M | } |
808 | | |
809 | | PyDoc_STRVAR(unicode_strip__doc__, |
810 | | "strip($self, chars=None, /)\n" |
811 | | "--\n" |
812 | | "\n" |
813 | | "Return a copy of the string with leading and trailing whitespace removed.\n" |
814 | | "\n" |
815 | | "If chars is given and not None, remove characters in chars instead."); |
816 | | |
817 | | #define UNICODE_STRIP_METHODDEF \ |
818 | | {"strip", _PyCFunction_CAST(unicode_strip), METH_FASTCALL, unicode_strip__doc__}, |
819 | | |
820 | | static PyObject * |
821 | | unicode_strip_impl(PyObject *self, PyObject *chars); |
822 | | |
823 | | static PyObject * |
824 | | unicode_strip(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
825 | 37.5M | { |
826 | 37.5M | PyObject *return_value = NULL; |
827 | 37.5M | PyObject *chars = Py_None; |
828 | | |
829 | 37.5M | if (!_PyArg_CheckPositional("strip", nargs, 0, 1)) { |
830 | 0 | goto exit; |
831 | 0 | } |
832 | 37.5M | if (nargs < 1) { |
833 | 37.5M | goto skip_optional; |
834 | 37.5M | } |
835 | 0 | chars = args[0]; |
836 | 37.5M | skip_optional: |
837 | 37.5M | return_value = unicode_strip_impl(self, chars); |
838 | | |
839 | 37.5M | exit: |
840 | 37.5M | return return_value; |
841 | 37.5M | } |
842 | | |
843 | | PyDoc_STRVAR(unicode_lstrip__doc__, |
844 | | "lstrip($self, chars=None, /)\n" |
845 | | "--\n" |
846 | | "\n" |
847 | | "Return a copy of the string with leading whitespace removed.\n" |
848 | | "\n" |
849 | | "If chars is given and not None, remove characters in chars instead."); |
850 | | |
851 | | #define UNICODE_LSTRIP_METHODDEF \ |
852 | | {"lstrip", _PyCFunction_CAST(unicode_lstrip), METH_FASTCALL, unicode_lstrip__doc__}, |
853 | | |
854 | | static PyObject * |
855 | | unicode_lstrip_impl(PyObject *self, PyObject *chars); |
856 | | |
857 | | static PyObject * |
858 | | unicode_lstrip(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
859 | 1.49M | { |
860 | 1.49M | PyObject *return_value = NULL; |
861 | 1.49M | PyObject *chars = Py_None; |
862 | | |
863 | 1.49M | if (!_PyArg_CheckPositional("lstrip", nargs, 0, 1)) { |
864 | 0 | goto exit; |
865 | 0 | } |
866 | 1.49M | if (nargs < 1) { |
867 | 1.08M | goto skip_optional; |
868 | 1.08M | } |
869 | 407k | chars = args[0]; |
870 | 1.49M | skip_optional: |
871 | 1.49M | return_value = unicode_lstrip_impl(self, chars); |
872 | | |
873 | 1.49M | exit: |
874 | 1.49M | return return_value; |
875 | 1.49M | } |
876 | | |
877 | | PyDoc_STRVAR(unicode_rstrip__doc__, |
878 | | "rstrip($self, chars=None, /)\n" |
879 | | "--\n" |
880 | | "\n" |
881 | | "Return a copy of the string with trailing whitespace removed.\n" |
882 | | "\n" |
883 | | "If chars is given and not None, remove characters in chars instead."); |
884 | | |
885 | | #define UNICODE_RSTRIP_METHODDEF \ |
886 | | {"rstrip", _PyCFunction_CAST(unicode_rstrip), METH_FASTCALL, unicode_rstrip__doc__}, |
887 | | |
888 | | static PyObject * |
889 | | unicode_rstrip_impl(PyObject *self, PyObject *chars); |
890 | | |
891 | | static PyObject * |
892 | | unicode_rstrip(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
893 | 24.3M | { |
894 | 24.3M | PyObject *return_value = NULL; |
895 | 24.3M | PyObject *chars = Py_None; |
896 | | |
897 | 24.3M | if (!_PyArg_CheckPositional("rstrip", nargs, 0, 1)) { |
898 | 0 | goto exit; |
899 | 0 | } |
900 | 24.3M | if (nargs < 1) { |
901 | 14.8M | goto skip_optional; |
902 | 14.8M | } |
903 | 9.48M | chars = args[0]; |
904 | 24.3M | skip_optional: |
905 | 24.3M | return_value = unicode_rstrip_impl(self, chars); |
906 | | |
907 | 24.3M | exit: |
908 | 24.3M | return return_value; |
909 | 24.3M | } |
910 | | |
911 | | PyDoc_STRVAR(unicode_replace__doc__, |
912 | | "replace($self, old, new, /, count=-1)\n" |
913 | | "--\n" |
914 | | "\n" |
915 | | "Return a copy with all occurrences of substring old replaced by new.\n" |
916 | | "\n" |
917 | | " count\n" |
918 | | " Maximum number of occurrences to replace.\n" |
919 | | " -1 (the default value) means replace all occurrences.\n" |
920 | | "\n" |
921 | | "If the optional argument count is given, only the first count occurrences are\n" |
922 | | "replaced."); |
923 | | |
924 | | #define UNICODE_REPLACE_METHODDEF \ |
925 | | {"replace", _PyCFunction_CAST(unicode_replace), METH_FASTCALL|METH_KEYWORDS, unicode_replace__doc__}, |
926 | | |
927 | | static PyObject * |
928 | | unicode_replace_impl(PyObject *self, PyObject *old, PyObject *new, |
929 | | Py_ssize_t count); |
930 | | |
931 | | static PyObject * |
932 | | unicode_replace(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
933 | 99.0M | { |
934 | 99.0M | PyObject *return_value = NULL; |
935 | 99.0M | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
936 | | |
937 | 99.0M | #define NUM_KEYWORDS 1 |
938 | 99.0M | static struct { |
939 | 99.0M | PyGC_Head _this_is_not_used; |
940 | 99.0M | PyObject_VAR_HEAD |
941 | 99.0M | Py_hash_t ob_hash; |
942 | 99.0M | PyObject *ob_item[NUM_KEYWORDS]; |
943 | 99.0M | } _kwtuple = { |
944 | 99.0M | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
945 | 99.0M | .ob_hash = -1, |
946 | 99.0M | .ob_item = { &_Py_ID(count), }, |
947 | 99.0M | }; |
948 | 99.0M | #undef NUM_KEYWORDS |
949 | 99.0M | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
950 | | |
951 | | #else // !Py_BUILD_CORE |
952 | | # define KWTUPLE NULL |
953 | | #endif // !Py_BUILD_CORE |
954 | | |
955 | 99.0M | static const char * const _keywords[] = {"", "", "count", NULL}; |
956 | 99.0M | static _PyArg_Parser _parser = { |
957 | 99.0M | .keywords = _keywords, |
958 | 99.0M | .fname = "replace", |
959 | 99.0M | .kwtuple = KWTUPLE, |
960 | 99.0M | }; |
961 | 99.0M | #undef KWTUPLE |
962 | 99.0M | PyObject *argsbuf[3]; |
963 | 99.0M | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 2; |
964 | 99.0M | PyObject *old; |
965 | 99.0M | PyObject *new; |
966 | 99.0M | Py_ssize_t count = -1; |
967 | | |
968 | 99.0M | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
969 | 99.0M | /*minpos*/ 2, /*maxpos*/ 3, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
970 | 99.0M | if (!args) { |
971 | 0 | goto exit; |
972 | 0 | } |
973 | 99.0M | if (!PyUnicode_Check(args[0])) { |
974 | 0 | _PyArg_BadArgument("replace", "argument 1", "str", args[0]); |
975 | 0 | goto exit; |
976 | 0 | } |
977 | 99.0M | old = args[0]; |
978 | 99.0M | if (!PyUnicode_Check(args[1])) { |
979 | 0 | _PyArg_BadArgument("replace", "argument 2", "str", args[1]); |
980 | 0 | goto exit; |
981 | 0 | } |
982 | 99.0M | new = args[1]; |
983 | 99.0M | if (!noptargs) { |
984 | 99.0M | goto skip_optional_pos; |
985 | 99.0M | } |
986 | 0 | { |
987 | 0 | Py_ssize_t ival = -1; |
988 | 0 | PyObject *iobj = _PyNumber_Index(args[2]); |
989 | 0 | if (iobj != NULL) { |
990 | 0 | ival = PyLong_AsSsize_t(iobj); |
991 | 0 | Py_DECREF(iobj); |
992 | 0 | } |
993 | 0 | if (ival == -1 && PyErr_Occurred()) { |
994 | 0 | goto exit; |
995 | 0 | } |
996 | 0 | count = ival; |
997 | 0 | } |
998 | 99.0M | skip_optional_pos: |
999 | 99.0M | return_value = unicode_replace_impl(self, old, new, count); |
1000 | | |
1001 | 99.0M | exit: |
1002 | 99.0M | return return_value; |
1003 | 99.0M | } |
1004 | | |
1005 | | PyDoc_STRVAR(unicode_removeprefix__doc__, |
1006 | | "removeprefix($self, prefix, /)\n" |
1007 | | "--\n" |
1008 | | "\n" |
1009 | | "Return a str with the given prefix string removed if present.\n" |
1010 | | "\n" |
1011 | | "If the string starts with the prefix string, return string[len(prefix):].\n" |
1012 | | "Otherwise, return a copy of the original string."); |
1013 | | |
1014 | | #define UNICODE_REMOVEPREFIX_METHODDEF \ |
1015 | | {"removeprefix", (PyCFunction)unicode_removeprefix, METH_O, unicode_removeprefix__doc__}, |
1016 | | |
1017 | | static PyObject * |
1018 | | unicode_removeprefix_impl(PyObject *self, PyObject *prefix); |
1019 | | |
1020 | | static PyObject * |
1021 | | unicode_removeprefix(PyObject *self, PyObject *arg) |
1022 | 0 | { |
1023 | 0 | PyObject *return_value = NULL; |
1024 | 0 | PyObject *prefix; |
1025 | |
|
1026 | 0 | if (!PyUnicode_Check(arg)) { |
1027 | 0 | _PyArg_BadArgument("removeprefix", "argument", "str", arg); |
1028 | 0 | goto exit; |
1029 | 0 | } |
1030 | 0 | prefix = arg; |
1031 | 0 | return_value = unicode_removeprefix_impl(self, prefix); |
1032 | |
|
1033 | 0 | exit: |
1034 | 0 | return return_value; |
1035 | 0 | } |
1036 | | |
1037 | | PyDoc_STRVAR(unicode_removesuffix__doc__, |
1038 | | "removesuffix($self, suffix, /)\n" |
1039 | | "--\n" |
1040 | | "\n" |
1041 | | "Return a str with the given suffix string removed if present.\n" |
1042 | | "\n" |
1043 | | "If the string ends with the suffix string and that suffix is not empty,\n" |
1044 | | "return string[:-len(suffix)]. Otherwise, return a copy of the original\n" |
1045 | | "string."); |
1046 | | |
1047 | | #define UNICODE_REMOVESUFFIX_METHODDEF \ |
1048 | | {"removesuffix", (PyCFunction)unicode_removesuffix, METH_O, unicode_removesuffix__doc__}, |
1049 | | |
1050 | | static PyObject * |
1051 | | unicode_removesuffix_impl(PyObject *self, PyObject *suffix); |
1052 | | |
1053 | | static PyObject * |
1054 | | unicode_removesuffix(PyObject *self, PyObject *arg) |
1055 | 0 | { |
1056 | 0 | PyObject *return_value = NULL; |
1057 | 0 | PyObject *suffix; |
1058 | |
|
1059 | 0 | if (!PyUnicode_Check(arg)) { |
1060 | 0 | _PyArg_BadArgument("removesuffix", "argument", "str", arg); |
1061 | 0 | goto exit; |
1062 | 0 | } |
1063 | 0 | suffix = arg; |
1064 | 0 | return_value = unicode_removesuffix_impl(self, suffix); |
1065 | |
|
1066 | 0 | exit: |
1067 | 0 | return return_value; |
1068 | 0 | } |
1069 | | |
1070 | | PyDoc_STRVAR(unicode_rfind__doc__, |
1071 | | "rfind($self, sub[, start[, end]], /)\n" |
1072 | | "--\n" |
1073 | | "\n" |
1074 | | "Return the highest index in S where substring sub is found, such that sub is contained within S[start:end].\n" |
1075 | | "\n" |
1076 | | "Optional arguments start and end are interpreted as in slice notation.\n" |
1077 | | "Return -1 on failure."); |
1078 | | |
1079 | | #define UNICODE_RFIND_METHODDEF \ |
1080 | | {"rfind", _PyCFunction_CAST(unicode_rfind), METH_FASTCALL, unicode_rfind__doc__}, |
1081 | | |
1082 | | static Py_ssize_t |
1083 | | unicode_rfind_impl(PyObject *str, PyObject *substr, Py_ssize_t start, |
1084 | | Py_ssize_t end); |
1085 | | |
1086 | | static PyObject * |
1087 | | unicode_rfind(PyObject *str, PyObject *const *args, Py_ssize_t nargs) |
1088 | 10.2k | { |
1089 | 10.2k | PyObject *return_value = NULL; |
1090 | 10.2k | PyObject *substr; |
1091 | 10.2k | Py_ssize_t start = 0; |
1092 | 10.2k | Py_ssize_t end = PY_SSIZE_T_MAX; |
1093 | 10.2k | Py_ssize_t _return_value; |
1094 | | |
1095 | 10.2k | if (!_PyArg_CheckPositional("rfind", nargs, 1, 3)) { |
1096 | 0 | goto exit; |
1097 | 0 | } |
1098 | 10.2k | if (!PyUnicode_Check(args[0])) { |
1099 | 0 | _PyArg_BadArgument("rfind", "argument 1", "str", args[0]); |
1100 | 0 | goto exit; |
1101 | 0 | } |
1102 | 10.2k | substr = args[0]; |
1103 | 10.2k | if (nargs < 2) { |
1104 | 1.71k | goto skip_optional; |
1105 | 1.71k | } |
1106 | 8.50k | if (!_PyEval_SliceIndex(args[1], &start)) { |
1107 | 0 | goto exit; |
1108 | 0 | } |
1109 | 8.50k | if (nargs < 3) { |
1110 | 3.77k | goto skip_optional; |
1111 | 3.77k | } |
1112 | 4.72k | if (!_PyEval_SliceIndex(args[2], &end)) { |
1113 | 0 | goto exit; |
1114 | 0 | } |
1115 | 10.2k | skip_optional: |
1116 | 10.2k | _return_value = unicode_rfind_impl(str, substr, start, end); |
1117 | 10.2k | if ((_return_value == -1) && PyErr_Occurred()) { |
1118 | 0 | goto exit; |
1119 | 0 | } |
1120 | 10.2k | return_value = PyLong_FromSsize_t(_return_value); |
1121 | | |
1122 | 10.2k | exit: |
1123 | 10.2k | return return_value; |
1124 | 10.2k | } |
1125 | | |
1126 | | PyDoc_STRVAR(unicode_rindex__doc__, |
1127 | | "rindex($self, sub[, start[, end]], /)\n" |
1128 | | "--\n" |
1129 | | "\n" |
1130 | | "Return the highest index in S where substring sub is found, such that sub is contained within S[start:end].\n" |
1131 | | "\n" |
1132 | | "Optional arguments start and end are interpreted as in slice notation.\n" |
1133 | | "Raises ValueError when the substring is not found."); |
1134 | | |
1135 | | #define UNICODE_RINDEX_METHODDEF \ |
1136 | | {"rindex", _PyCFunction_CAST(unicode_rindex), METH_FASTCALL, unicode_rindex__doc__}, |
1137 | | |
1138 | | static Py_ssize_t |
1139 | | unicode_rindex_impl(PyObject *str, PyObject *substr, Py_ssize_t start, |
1140 | | Py_ssize_t end); |
1141 | | |
1142 | | static PyObject * |
1143 | | unicode_rindex(PyObject *str, PyObject *const *args, Py_ssize_t nargs) |
1144 | 271k | { |
1145 | 271k | PyObject *return_value = NULL; |
1146 | 271k | PyObject *substr; |
1147 | 271k | Py_ssize_t start = 0; |
1148 | 271k | Py_ssize_t end = PY_SSIZE_T_MAX; |
1149 | 271k | Py_ssize_t _return_value; |
1150 | | |
1151 | 271k | if (!_PyArg_CheckPositional("rindex", nargs, 1, 3)) { |
1152 | 0 | goto exit; |
1153 | 0 | } |
1154 | 271k | if (!PyUnicode_Check(args[0])) { |
1155 | 0 | _PyArg_BadArgument("rindex", "argument 1", "str", args[0]); |
1156 | 0 | goto exit; |
1157 | 0 | } |
1158 | 271k | substr = args[0]; |
1159 | 271k | if (nargs < 2) { |
1160 | 0 | goto skip_optional; |
1161 | 0 | } |
1162 | 271k | if (!_PyEval_SliceIndex(args[1], &start)) { |
1163 | 0 | goto exit; |
1164 | 0 | } |
1165 | 271k | if (nargs < 3) { |
1166 | 0 | goto skip_optional; |
1167 | 0 | } |
1168 | 271k | if (!_PyEval_SliceIndex(args[2], &end)) { |
1169 | 0 | goto exit; |
1170 | 0 | } |
1171 | 271k | skip_optional: |
1172 | 271k | _return_value = unicode_rindex_impl(str, substr, start, end); |
1173 | 271k | if ((_return_value == -1) && PyErr_Occurred()) { |
1174 | 0 | goto exit; |
1175 | 0 | } |
1176 | 271k | return_value = PyLong_FromSsize_t(_return_value); |
1177 | | |
1178 | 271k | exit: |
1179 | 271k | return return_value; |
1180 | 271k | } |
1181 | | |
1182 | | PyDoc_STRVAR(unicode_rjust__doc__, |
1183 | | "rjust($self, width, fillchar=\' \', /)\n" |
1184 | | "--\n" |
1185 | | "\n" |
1186 | | "Return a right-justified string of length width.\n" |
1187 | | "\n" |
1188 | | "Padding is done using the specified fill character (default is a space)."); |
1189 | | |
1190 | | #define UNICODE_RJUST_METHODDEF \ |
1191 | | {"rjust", _PyCFunction_CAST(unicode_rjust), METH_FASTCALL, unicode_rjust__doc__}, |
1192 | | |
1193 | | static PyObject * |
1194 | | unicode_rjust_impl(PyObject *self, Py_ssize_t width, Py_UCS4 fillchar); |
1195 | | |
1196 | | static PyObject * |
1197 | | unicode_rjust(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
1198 | 0 | { |
1199 | 0 | PyObject *return_value = NULL; |
1200 | 0 | Py_ssize_t width; |
1201 | 0 | Py_UCS4 fillchar = ' '; |
1202 | |
|
1203 | 0 | if (!_PyArg_CheckPositional("rjust", nargs, 1, 2)) { |
1204 | 0 | goto exit; |
1205 | 0 | } |
1206 | 0 | { |
1207 | 0 | Py_ssize_t ival = -1; |
1208 | 0 | PyObject *iobj = _PyNumber_Index(args[0]); |
1209 | 0 | if (iobj != NULL) { |
1210 | 0 | ival = PyLong_AsSsize_t(iobj); |
1211 | 0 | Py_DECREF(iobj); |
1212 | 0 | } |
1213 | 0 | if (ival == -1 && PyErr_Occurred()) { |
1214 | 0 | goto exit; |
1215 | 0 | } |
1216 | 0 | width = ival; |
1217 | 0 | } |
1218 | 0 | if (nargs < 2) { |
1219 | 0 | goto skip_optional; |
1220 | 0 | } |
1221 | 0 | if (!convert_uc(args[1], &fillchar)) { |
1222 | 0 | goto exit; |
1223 | 0 | } |
1224 | 0 | skip_optional: |
1225 | 0 | return_value = unicode_rjust_impl(self, width, fillchar); |
1226 | |
|
1227 | 0 | exit: |
1228 | 0 | return return_value; |
1229 | 0 | } |
1230 | | |
1231 | | PyDoc_STRVAR(unicode_split__doc__, |
1232 | | "split($self, /, sep=None, maxsplit=-1)\n" |
1233 | | "--\n" |
1234 | | "\n" |
1235 | | "Return a list of the substrings in the string, using sep as the separator string.\n" |
1236 | | "\n" |
1237 | | " sep\n" |
1238 | | " The separator used to split the string.\n" |
1239 | | "\n" |
1240 | | " When set to None (the default value), will split on any whitespace\n" |
1241 | | " character (including \\n \\r \\t \\f and spaces) and will discard\n" |
1242 | | " empty strings from the result.\n" |
1243 | | " maxsplit\n" |
1244 | | " Maximum number of splits.\n" |
1245 | | " -1 (the default value) means no limit.\n" |
1246 | | "\n" |
1247 | | "Splitting starts at the front of the string and works to the end.\n" |
1248 | | "\n" |
1249 | | "Note, str.split() is mainly useful for data that has been intentionally\n" |
1250 | | "delimited. With natural text that includes punctuation, consider using\n" |
1251 | | "the regular expression module."); |
1252 | | |
1253 | | #define UNICODE_SPLIT_METHODDEF \ |
1254 | | {"split", _PyCFunction_CAST(unicode_split), METH_FASTCALL|METH_KEYWORDS, unicode_split__doc__}, |
1255 | | |
1256 | | static PyObject * |
1257 | | unicode_split_impl(PyObject *self, PyObject *sep, Py_ssize_t maxsplit); |
1258 | | |
1259 | | static PyObject * |
1260 | | unicode_split(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
1261 | 23.8M | { |
1262 | 23.8M | PyObject *return_value = NULL; |
1263 | 23.8M | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
1264 | | |
1265 | 23.8M | #define NUM_KEYWORDS 2 |
1266 | 23.8M | static struct { |
1267 | 23.8M | PyGC_Head _this_is_not_used; |
1268 | 23.8M | PyObject_VAR_HEAD |
1269 | 23.8M | Py_hash_t ob_hash; |
1270 | 23.8M | PyObject *ob_item[NUM_KEYWORDS]; |
1271 | 23.8M | } _kwtuple = { |
1272 | 23.8M | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
1273 | 23.8M | .ob_hash = -1, |
1274 | 23.8M | .ob_item = { &_Py_ID(sep), &_Py_ID(maxsplit), }, |
1275 | 23.8M | }; |
1276 | 23.8M | #undef NUM_KEYWORDS |
1277 | 23.8M | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
1278 | | |
1279 | | #else // !Py_BUILD_CORE |
1280 | | # define KWTUPLE NULL |
1281 | | #endif // !Py_BUILD_CORE |
1282 | | |
1283 | 23.8M | static const char * const _keywords[] = {"sep", "maxsplit", NULL}; |
1284 | 23.8M | static _PyArg_Parser _parser = { |
1285 | 23.8M | .keywords = _keywords, |
1286 | 23.8M | .fname = "split", |
1287 | 23.8M | .kwtuple = KWTUPLE, |
1288 | 23.8M | }; |
1289 | 23.8M | #undef KWTUPLE |
1290 | 23.8M | PyObject *argsbuf[2]; |
1291 | 23.8M | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; |
1292 | 23.8M | PyObject *sep = Py_None; |
1293 | 23.8M | Py_ssize_t maxsplit = -1; |
1294 | | |
1295 | 23.8M | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
1296 | 23.8M | /*minpos*/ 0, /*maxpos*/ 2, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
1297 | 23.8M | if (!args) { |
1298 | 0 | goto exit; |
1299 | 0 | } |
1300 | 23.8M | if (!noptargs) { |
1301 | 115k | goto skip_optional_pos; |
1302 | 115k | } |
1303 | 23.7M | if (args[0]) { |
1304 | 23.7M | sep = args[0]; |
1305 | 23.7M | if (!--noptargs) { |
1306 | 13.4M | goto skip_optional_pos; |
1307 | 13.4M | } |
1308 | 23.7M | } |
1309 | 10.2M | { |
1310 | 10.2M | Py_ssize_t ival = -1; |
1311 | 10.2M | PyObject *iobj = _PyNumber_Index(args[1]); |
1312 | 10.2M | if (iobj != NULL) { |
1313 | 10.2M | ival = PyLong_AsSsize_t(iobj); |
1314 | 10.2M | Py_DECREF(iobj); |
1315 | 10.2M | } |
1316 | 10.2M | if (ival == -1 && PyErr_Occurred()) { |
1317 | 0 | goto exit; |
1318 | 0 | } |
1319 | 10.2M | maxsplit = ival; |
1320 | 10.2M | } |
1321 | 23.8M | skip_optional_pos: |
1322 | 23.8M | return_value = unicode_split_impl(self, sep, maxsplit); |
1323 | | |
1324 | 23.8M | exit: |
1325 | 23.8M | return return_value; |
1326 | 23.8M | } |
1327 | | |
1328 | | PyDoc_STRVAR(unicode_partition__doc__, |
1329 | | "partition($self, sep, /)\n" |
1330 | | "--\n" |
1331 | | "\n" |
1332 | | "Partition the string into three parts using the given separator.\n" |
1333 | | "\n" |
1334 | | "This will search for the separator in the string. If the separator is found,\n" |
1335 | | "returns a 3-tuple containing the part before the separator, the separator\n" |
1336 | | "itself, and the part after it.\n" |
1337 | | "\n" |
1338 | | "If the separator is not found, returns a 3-tuple containing the original string\n" |
1339 | | "and two empty strings."); |
1340 | | |
1341 | | #define UNICODE_PARTITION_METHODDEF \ |
1342 | | {"partition", (PyCFunction)unicode_partition, METH_O, unicode_partition__doc__}, |
1343 | | |
1344 | | PyDoc_STRVAR(unicode_rpartition__doc__, |
1345 | | "rpartition($self, sep, /)\n" |
1346 | | "--\n" |
1347 | | "\n" |
1348 | | "Partition the string into three parts using the given separator.\n" |
1349 | | "\n" |
1350 | | "This will search for the separator in the string, starting at the end. If\n" |
1351 | | "the separator is found, returns a 3-tuple containing the part before the\n" |
1352 | | "separator, the separator itself, and the part after it.\n" |
1353 | | "\n" |
1354 | | "If the separator is not found, returns a 3-tuple containing two empty strings\n" |
1355 | | "and the original string."); |
1356 | | |
1357 | | #define UNICODE_RPARTITION_METHODDEF \ |
1358 | | {"rpartition", (PyCFunction)unicode_rpartition, METH_O, unicode_rpartition__doc__}, |
1359 | | |
1360 | | PyDoc_STRVAR(unicode_rsplit__doc__, |
1361 | | "rsplit($self, /, sep=None, maxsplit=-1)\n" |
1362 | | "--\n" |
1363 | | "\n" |
1364 | | "Return a list of the substrings in the string, using sep as the separator string.\n" |
1365 | | "\n" |
1366 | | " sep\n" |
1367 | | " The separator used to split the string.\n" |
1368 | | "\n" |
1369 | | " When set to None (the default value), will split on any whitespace\n" |
1370 | | " character (including \\n \\r \\t \\f and spaces) and will discard\n" |
1371 | | " empty strings from the result.\n" |
1372 | | " maxsplit\n" |
1373 | | " Maximum number of splits.\n" |
1374 | | " -1 (the default value) means no limit.\n" |
1375 | | "\n" |
1376 | | "Splitting starts at the end of the string and works to the front."); |
1377 | | |
1378 | | #define UNICODE_RSPLIT_METHODDEF \ |
1379 | | {"rsplit", _PyCFunction_CAST(unicode_rsplit), METH_FASTCALL|METH_KEYWORDS, unicode_rsplit__doc__}, |
1380 | | |
1381 | | static PyObject * |
1382 | | unicode_rsplit_impl(PyObject *self, PyObject *sep, Py_ssize_t maxsplit); |
1383 | | |
1384 | | static PyObject * |
1385 | | unicode_rsplit(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
1386 | 50 | { |
1387 | 50 | PyObject *return_value = NULL; |
1388 | 50 | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
1389 | | |
1390 | 50 | #define NUM_KEYWORDS 2 |
1391 | 50 | static struct { |
1392 | 50 | PyGC_Head _this_is_not_used; |
1393 | 50 | PyObject_VAR_HEAD |
1394 | 50 | Py_hash_t ob_hash; |
1395 | 50 | PyObject *ob_item[NUM_KEYWORDS]; |
1396 | 50 | } _kwtuple = { |
1397 | 50 | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
1398 | 50 | .ob_hash = -1, |
1399 | 50 | .ob_item = { &_Py_ID(sep), &_Py_ID(maxsplit), }, |
1400 | 50 | }; |
1401 | 50 | #undef NUM_KEYWORDS |
1402 | 50 | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
1403 | | |
1404 | | #else // !Py_BUILD_CORE |
1405 | | # define KWTUPLE NULL |
1406 | | #endif // !Py_BUILD_CORE |
1407 | | |
1408 | 50 | static const char * const _keywords[] = {"sep", "maxsplit", NULL}; |
1409 | 50 | static _PyArg_Parser _parser = { |
1410 | 50 | .keywords = _keywords, |
1411 | 50 | .fname = "rsplit", |
1412 | 50 | .kwtuple = KWTUPLE, |
1413 | 50 | }; |
1414 | 50 | #undef KWTUPLE |
1415 | 50 | PyObject *argsbuf[2]; |
1416 | 50 | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; |
1417 | 50 | PyObject *sep = Py_None; |
1418 | 50 | Py_ssize_t maxsplit = -1; |
1419 | | |
1420 | 50 | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
1421 | 50 | /*minpos*/ 0, /*maxpos*/ 2, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
1422 | 50 | if (!args) { |
1423 | 0 | goto exit; |
1424 | 0 | } |
1425 | 50 | if (!noptargs) { |
1426 | 0 | goto skip_optional_pos; |
1427 | 0 | } |
1428 | 50 | if (args[0]) { |
1429 | 50 | sep = args[0]; |
1430 | 50 | if (!--noptargs) { |
1431 | 0 | goto skip_optional_pos; |
1432 | 0 | } |
1433 | 50 | } |
1434 | 50 | { |
1435 | 50 | Py_ssize_t ival = -1; |
1436 | 50 | PyObject *iobj = _PyNumber_Index(args[1]); |
1437 | 50 | if (iobj != NULL) { |
1438 | 50 | ival = PyLong_AsSsize_t(iobj); |
1439 | 50 | Py_DECREF(iobj); |
1440 | 50 | } |
1441 | 50 | if (ival == -1 && PyErr_Occurred()) { |
1442 | 0 | goto exit; |
1443 | 0 | } |
1444 | 50 | maxsplit = ival; |
1445 | 50 | } |
1446 | 50 | skip_optional_pos: |
1447 | 50 | return_value = unicode_rsplit_impl(self, sep, maxsplit); |
1448 | | |
1449 | 50 | exit: |
1450 | 50 | return return_value; |
1451 | 50 | } |
1452 | | |
1453 | | PyDoc_STRVAR(unicode_splitlines__doc__, |
1454 | | "splitlines($self, /, keepends=False)\n" |
1455 | | "--\n" |
1456 | | "\n" |
1457 | | "Return a list of the lines in the string, breaking at line boundaries.\n" |
1458 | | "\n" |
1459 | | "Line breaks are not included in the resulting list unless keepends is given and\n" |
1460 | | "true."); |
1461 | | |
1462 | | #define UNICODE_SPLITLINES_METHODDEF \ |
1463 | | {"splitlines", _PyCFunction_CAST(unicode_splitlines), METH_FASTCALL|METH_KEYWORDS, unicode_splitlines__doc__}, |
1464 | | |
1465 | | static PyObject * |
1466 | | unicode_splitlines_impl(PyObject *self, int keepends); |
1467 | | |
1468 | | static PyObject * |
1469 | | unicode_splitlines(PyObject *self, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames) |
1470 | 14.3k | { |
1471 | 14.3k | PyObject *return_value = NULL; |
1472 | 14.3k | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
1473 | | |
1474 | 14.3k | #define NUM_KEYWORDS 1 |
1475 | 14.3k | static struct { |
1476 | 14.3k | PyGC_Head _this_is_not_used; |
1477 | 14.3k | PyObject_VAR_HEAD |
1478 | 14.3k | Py_hash_t ob_hash; |
1479 | 14.3k | PyObject *ob_item[NUM_KEYWORDS]; |
1480 | 14.3k | } _kwtuple = { |
1481 | 14.3k | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
1482 | 14.3k | .ob_hash = -1, |
1483 | 14.3k | .ob_item = { &_Py_ID(keepends), }, |
1484 | 14.3k | }; |
1485 | 14.3k | #undef NUM_KEYWORDS |
1486 | 14.3k | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
1487 | | |
1488 | | #else // !Py_BUILD_CORE |
1489 | | # define KWTUPLE NULL |
1490 | | #endif // !Py_BUILD_CORE |
1491 | | |
1492 | 14.3k | static const char * const _keywords[] = {"keepends", NULL}; |
1493 | 14.3k | static _PyArg_Parser _parser = { |
1494 | 14.3k | .keywords = _keywords, |
1495 | 14.3k | .fname = "splitlines", |
1496 | 14.3k | .kwtuple = KWTUPLE, |
1497 | 14.3k | }; |
1498 | 14.3k | #undef KWTUPLE |
1499 | 14.3k | PyObject *argsbuf[1]; |
1500 | 14.3k | Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 0; |
1501 | 14.3k | int keepends = 0; |
1502 | | |
1503 | 14.3k | args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, |
1504 | 14.3k | /*minpos*/ 0, /*maxpos*/ 1, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
1505 | 14.3k | if (!args) { |
1506 | 0 | goto exit; |
1507 | 0 | } |
1508 | 14.3k | if (!noptargs) { |
1509 | 14.3k | goto skip_optional_pos; |
1510 | 14.3k | } |
1511 | 0 | keepends = PyObject_IsTrue(args[0]); |
1512 | 0 | if (keepends < 0) { |
1513 | 0 | goto exit; |
1514 | 0 | } |
1515 | 14.3k | skip_optional_pos: |
1516 | 14.3k | return_value = unicode_splitlines_impl(self, keepends); |
1517 | | |
1518 | 14.3k | exit: |
1519 | 14.3k | return return_value; |
1520 | 14.3k | } |
1521 | | |
1522 | | PyDoc_STRVAR(unicode_swapcase__doc__, |
1523 | | "swapcase($self, /)\n" |
1524 | | "--\n" |
1525 | | "\n" |
1526 | | "Convert uppercase characters to lowercase and lowercase characters to uppercase."); |
1527 | | |
1528 | | #define UNICODE_SWAPCASE_METHODDEF \ |
1529 | | {"swapcase", (PyCFunction)unicode_swapcase, METH_NOARGS, unicode_swapcase__doc__}, |
1530 | | |
1531 | | static PyObject * |
1532 | | unicode_swapcase_impl(PyObject *self); |
1533 | | |
1534 | | static PyObject * |
1535 | | unicode_swapcase(PyObject *self, PyObject *Py_UNUSED(ignored)) |
1536 | 0 | { |
1537 | 0 | return unicode_swapcase_impl(self); |
1538 | 0 | } |
1539 | | |
1540 | | PyDoc_STRVAR(unicode_maketrans__doc__, |
1541 | | "maketrans(x, y=<unrepresentable>, z=<unrepresentable>, /)\n" |
1542 | | "--\n" |
1543 | | "\n" |
1544 | | "Return a translation table usable for str.translate().\n" |
1545 | | "\n" |
1546 | | "If there is only one argument, it must be a dictionary mapping Unicode\n" |
1547 | | "ordinals (integers) or characters to Unicode ordinals, strings or None.\n" |
1548 | | "Character keys will be then converted to ordinals.\n" |
1549 | | "If there are two arguments, they must be strings of equal length, and\n" |
1550 | | "in the resulting dictionary, each character in x will be mapped to the\n" |
1551 | | "character at the same position in y. If there is a third argument, it\n" |
1552 | | "must be a string, whose characters will be mapped to None in the result."); |
1553 | | |
1554 | | #define UNICODE_MAKETRANS_METHODDEF \ |
1555 | | {"maketrans", _PyCFunction_CAST(unicode_maketrans), METH_FASTCALL|METH_STATIC, unicode_maketrans__doc__}, |
1556 | | |
1557 | | static PyObject * |
1558 | | unicode_maketrans_impl(PyObject *x, PyObject *y, PyObject *z); |
1559 | | |
1560 | | static PyObject * |
1561 | | unicode_maketrans(PyObject *null, PyObject *const *args, Py_ssize_t nargs) |
1562 | 0 | { |
1563 | 0 | PyObject *return_value = NULL; |
1564 | 0 | PyObject *x; |
1565 | 0 | PyObject *y = NULL; |
1566 | 0 | PyObject *z = NULL; |
1567 | |
|
1568 | 0 | if (!_PyArg_CheckPositional("maketrans", nargs, 1, 3)) { |
1569 | 0 | goto exit; |
1570 | 0 | } |
1571 | 0 | x = args[0]; |
1572 | 0 | if (nargs < 2) { |
1573 | 0 | goto skip_optional; |
1574 | 0 | } |
1575 | 0 | if (!PyUnicode_Check(args[1])) { |
1576 | 0 | _PyArg_BadArgument("maketrans", "argument 2", "str", args[1]); |
1577 | 0 | goto exit; |
1578 | 0 | } |
1579 | 0 | y = args[1]; |
1580 | 0 | if (nargs < 3) { |
1581 | 0 | goto skip_optional; |
1582 | 0 | } |
1583 | 0 | if (!PyUnicode_Check(args[2])) { |
1584 | 0 | _PyArg_BadArgument("maketrans", "argument 3", "str", args[2]); |
1585 | 0 | goto exit; |
1586 | 0 | } |
1587 | 0 | z = args[2]; |
1588 | 0 | skip_optional: |
1589 | 0 | return_value = unicode_maketrans_impl(x, y, z); |
1590 | |
|
1591 | 0 | exit: |
1592 | 0 | return return_value; |
1593 | 0 | } |
1594 | | |
1595 | | PyDoc_STRVAR(unicode_translate__doc__, |
1596 | | "translate($self, table, /)\n" |
1597 | | "--\n" |
1598 | | "\n" |
1599 | | "Replace each character in the string using the given translation table.\n" |
1600 | | "\n" |
1601 | | " table\n" |
1602 | | " Translation table, which must be a mapping of Unicode ordinals to\n" |
1603 | | " Unicode ordinals, strings, or None.\n" |
1604 | | "\n" |
1605 | | "The table must implement lookup/indexing via __getitem__, for instance a\n" |
1606 | | "dictionary or list. If this operation raises LookupError, the character is\n" |
1607 | | "left untouched. Characters mapped to None are deleted."); |
1608 | | |
1609 | | #define UNICODE_TRANSLATE_METHODDEF \ |
1610 | | {"translate", (PyCFunction)unicode_translate, METH_O, unicode_translate__doc__}, |
1611 | | |
1612 | | PyDoc_STRVAR(unicode_upper__doc__, |
1613 | | "upper($self, /)\n" |
1614 | | "--\n" |
1615 | | "\n" |
1616 | | "Return a copy of the string converted to uppercase."); |
1617 | | |
1618 | | #define UNICODE_UPPER_METHODDEF \ |
1619 | | {"upper", (PyCFunction)unicode_upper, METH_NOARGS, unicode_upper__doc__}, |
1620 | | |
1621 | | static PyObject * |
1622 | | unicode_upper_impl(PyObject *self); |
1623 | | |
1624 | | static PyObject * |
1625 | | unicode_upper(PyObject *self, PyObject *Py_UNUSED(ignored)) |
1626 | 0 | { |
1627 | 0 | return unicode_upper_impl(self); |
1628 | 0 | } |
1629 | | |
1630 | | PyDoc_STRVAR(unicode_zfill__doc__, |
1631 | | "zfill($self, width, /)\n" |
1632 | | "--\n" |
1633 | | "\n" |
1634 | | "Pad a numeric string with zeros on the left, to fill a field of the given width.\n" |
1635 | | "\n" |
1636 | | "The string is never truncated."); |
1637 | | |
1638 | | #define UNICODE_ZFILL_METHODDEF \ |
1639 | | {"zfill", (PyCFunction)unicode_zfill, METH_O, unicode_zfill__doc__}, |
1640 | | |
1641 | | static PyObject * |
1642 | | unicode_zfill_impl(PyObject *self, Py_ssize_t width); |
1643 | | |
1644 | | static PyObject * |
1645 | | unicode_zfill(PyObject *self, PyObject *arg) |
1646 | 0 | { |
1647 | 0 | PyObject *return_value = NULL; |
1648 | 0 | Py_ssize_t width; |
1649 | |
|
1650 | 0 | { |
1651 | 0 | Py_ssize_t ival = -1; |
1652 | 0 | PyObject *iobj = _PyNumber_Index(arg); |
1653 | 0 | if (iobj != NULL) { |
1654 | 0 | ival = PyLong_AsSsize_t(iobj); |
1655 | 0 | Py_DECREF(iobj); |
1656 | 0 | } |
1657 | 0 | if (ival == -1 && PyErr_Occurred()) { |
1658 | 0 | goto exit; |
1659 | 0 | } |
1660 | 0 | width = ival; |
1661 | 0 | } |
1662 | 0 | return_value = unicode_zfill_impl(self, width); |
1663 | |
|
1664 | 0 | exit: |
1665 | 0 | return return_value; |
1666 | 0 | } |
1667 | | |
1668 | | PyDoc_STRVAR(unicode_startswith__doc__, |
1669 | | "startswith($self, prefix[, start[, end]], /)\n" |
1670 | | "--\n" |
1671 | | "\n" |
1672 | | "Return True if the string starts with the specified prefix, False otherwise.\n" |
1673 | | "\n" |
1674 | | " prefix\n" |
1675 | | " A string or a tuple of strings to try.\n" |
1676 | | " start\n" |
1677 | | " Optional start position. Default: start of the string.\n" |
1678 | | " end\n" |
1679 | | " Optional stop position. Default: end of the string."); |
1680 | | |
1681 | | #define UNICODE_STARTSWITH_METHODDEF \ |
1682 | | {"startswith", _PyCFunction_CAST(unicode_startswith), METH_FASTCALL, unicode_startswith__doc__}, |
1683 | | |
1684 | | static PyObject * |
1685 | | unicode_startswith_impl(PyObject *self, PyObject *subobj, Py_ssize_t start, |
1686 | | Py_ssize_t end); |
1687 | | |
1688 | | static PyObject * |
1689 | | unicode_startswith(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
1690 | 82.1M | { |
1691 | 82.1M | PyObject *return_value = NULL; |
1692 | 82.1M | PyObject *subobj; |
1693 | 82.1M | Py_ssize_t start = 0; |
1694 | 82.1M | Py_ssize_t end = PY_SSIZE_T_MAX; |
1695 | | |
1696 | 82.1M | if (!_PyArg_CheckPositional("startswith", nargs, 1, 3)) { |
1697 | 0 | goto exit; |
1698 | 0 | } |
1699 | 82.1M | subobj = args[0]; |
1700 | 82.1M | if (nargs < 2) { |
1701 | 72.8M | goto skip_optional; |
1702 | 72.8M | } |
1703 | 9.23M | if (!_PyEval_SliceIndex(args[1], &start)) { |
1704 | 0 | goto exit; |
1705 | 0 | } |
1706 | 9.23M | if (nargs < 3) { |
1707 | 9.23M | goto skip_optional; |
1708 | 9.23M | } |
1709 | 0 | if (!_PyEval_SliceIndex(args[2], &end)) { |
1710 | 0 | goto exit; |
1711 | 0 | } |
1712 | 82.1M | skip_optional: |
1713 | 82.1M | return_value = unicode_startswith_impl(self, subobj, start, end); |
1714 | | |
1715 | 82.1M | exit: |
1716 | 82.1M | return return_value; |
1717 | 82.1M | } |
1718 | | |
1719 | | PyDoc_STRVAR(unicode_endswith__doc__, |
1720 | | "endswith($self, suffix[, start[, end]], /)\n" |
1721 | | "--\n" |
1722 | | "\n" |
1723 | | "Return True if the string ends with the specified suffix, False otherwise.\n" |
1724 | | "\n" |
1725 | | " suffix\n" |
1726 | | " A string or a tuple of strings to try.\n" |
1727 | | " start\n" |
1728 | | " Optional start position. Default: start of the string.\n" |
1729 | | " end\n" |
1730 | | " Optional stop position. Default: end of the string."); |
1731 | | |
1732 | | #define UNICODE_ENDSWITH_METHODDEF \ |
1733 | | {"endswith", _PyCFunction_CAST(unicode_endswith), METH_FASTCALL, unicode_endswith__doc__}, |
1734 | | |
1735 | | static PyObject * |
1736 | | unicode_endswith_impl(PyObject *self, PyObject *subobj, Py_ssize_t start, |
1737 | | Py_ssize_t end); |
1738 | | |
1739 | | static PyObject * |
1740 | | unicode_endswith(PyObject *self, PyObject *const *args, Py_ssize_t nargs) |
1741 | 14.4M | { |
1742 | 14.4M | PyObject *return_value = NULL; |
1743 | 14.4M | PyObject *subobj; |
1744 | 14.4M | Py_ssize_t start = 0; |
1745 | 14.4M | Py_ssize_t end = PY_SSIZE_T_MAX; |
1746 | | |
1747 | 14.4M | if (!_PyArg_CheckPositional("endswith", nargs, 1, 3)) { |
1748 | 0 | goto exit; |
1749 | 0 | } |
1750 | 14.4M | subobj = args[0]; |
1751 | 14.4M | if (nargs < 2) { |
1752 | 14.4M | goto skip_optional; |
1753 | 14.4M | } |
1754 | 0 | if (!_PyEval_SliceIndex(args[1], &start)) { |
1755 | 0 | goto exit; |
1756 | 0 | } |
1757 | 0 | if (nargs < 3) { |
1758 | 0 | goto skip_optional; |
1759 | 0 | } |
1760 | 0 | if (!_PyEval_SliceIndex(args[2], &end)) { |
1761 | 0 | goto exit; |
1762 | 0 | } |
1763 | 14.4M | skip_optional: |
1764 | 14.4M | return_value = unicode_endswith_impl(self, subobj, start, end); |
1765 | | |
1766 | 14.4M | exit: |
1767 | 14.4M | return return_value; |
1768 | 14.4M | } |
1769 | | |
1770 | | PyDoc_STRVAR(unicode___format____doc__, |
1771 | | "__format__($self, format_spec, /)\n" |
1772 | | "--\n" |
1773 | | "\n" |
1774 | | "Return a formatted version of the string as described by format_spec."); |
1775 | | |
1776 | | #define UNICODE___FORMAT___METHODDEF \ |
1777 | | {"__format__", (PyCFunction)unicode___format__, METH_O, unicode___format____doc__}, |
1778 | | |
1779 | | static PyObject * |
1780 | | unicode___format___impl(PyObject *self, PyObject *format_spec); |
1781 | | |
1782 | | static PyObject * |
1783 | | unicode___format__(PyObject *self, PyObject *arg) |
1784 | 0 | { |
1785 | 0 | PyObject *return_value = NULL; |
1786 | 0 | PyObject *format_spec; |
1787 | |
|
1788 | 0 | if (!PyUnicode_Check(arg)) { |
1789 | 0 | _PyArg_BadArgument("__format__", "argument", "str", arg); |
1790 | 0 | goto exit; |
1791 | 0 | } |
1792 | 0 | format_spec = arg; |
1793 | 0 | return_value = unicode___format___impl(self, format_spec); |
1794 | |
|
1795 | 0 | exit: |
1796 | 0 | return return_value; |
1797 | 0 | } |
1798 | | |
1799 | | PyDoc_STRVAR(unicode_sizeof__doc__, |
1800 | | "__sizeof__($self, /)\n" |
1801 | | "--\n" |
1802 | | "\n" |
1803 | | "Return the size of the string in memory, in bytes."); |
1804 | | |
1805 | | #define UNICODE_SIZEOF_METHODDEF \ |
1806 | | {"__sizeof__", (PyCFunction)unicode_sizeof, METH_NOARGS, unicode_sizeof__doc__}, |
1807 | | |
1808 | | static PyObject * |
1809 | | unicode_sizeof_impl(PyObject *self); |
1810 | | |
1811 | | static PyObject * |
1812 | | unicode_sizeof(PyObject *self, PyObject *Py_UNUSED(ignored)) |
1813 | 0 | { |
1814 | 0 | return unicode_sizeof_impl(self); |
1815 | 0 | } |
1816 | | |
1817 | | static PyObject * |
1818 | | unicode_new_impl(PyTypeObject *type, PyObject *x, const char *encoding, |
1819 | | const char *errors); |
1820 | | |
1821 | | static PyObject * |
1822 | | unicode_new(PyTypeObject *type, PyObject *args, PyObject *kwargs) |
1823 | 10.1M | { |
1824 | 10.1M | PyObject *return_value = NULL; |
1825 | 10.1M | #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE) |
1826 | | |
1827 | 10.1M | #define NUM_KEYWORDS 3 |
1828 | 10.1M | static struct { |
1829 | 10.1M | PyGC_Head _this_is_not_used; |
1830 | 10.1M | PyObject_VAR_HEAD |
1831 | 10.1M | Py_hash_t ob_hash; |
1832 | 10.1M | PyObject *ob_item[NUM_KEYWORDS]; |
1833 | 10.1M | } _kwtuple = { |
1834 | 10.1M | .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS) |
1835 | 10.1M | .ob_hash = -1, |
1836 | 10.1M | .ob_item = { &_Py_ID(object), &_Py_ID(encoding), &_Py_ID(errors), }, |
1837 | 10.1M | }; |
1838 | 10.1M | #undef NUM_KEYWORDS |
1839 | 10.1M | #define KWTUPLE (&_kwtuple.ob_base.ob_base) |
1840 | | |
1841 | | #else // !Py_BUILD_CORE |
1842 | | # define KWTUPLE NULL |
1843 | | #endif // !Py_BUILD_CORE |
1844 | | |
1845 | 10.1M | static const char * const _keywords[] = {"object", "encoding", "errors", NULL}; |
1846 | 10.1M | static _PyArg_Parser _parser = { |
1847 | 10.1M | .keywords = _keywords, |
1848 | 10.1M | .fname = "str", |
1849 | 10.1M | .kwtuple = KWTUPLE, |
1850 | 10.1M | }; |
1851 | 10.1M | #undef KWTUPLE |
1852 | 10.1M | PyObject *argsbuf[3]; |
1853 | 10.1M | PyObject * const *fastargs; |
1854 | 10.1M | Py_ssize_t nargs = PyTuple_GET_SIZE(args); |
1855 | 10.1M | Py_ssize_t noptargs = nargs + (kwargs ? PyDict_GET_SIZE(kwargs) : 0) - 0; |
1856 | 10.1M | PyObject *x = NULL; |
1857 | 10.1M | const char *encoding = NULL; |
1858 | 10.1M | const char *errors = NULL; |
1859 | | |
1860 | 10.1M | fastargs = _PyArg_UnpackKeywords(_PyTuple_CAST(args)->ob_item, nargs, kwargs, NULL, &_parser, |
1861 | 10.1M | /*minpos*/ 0, /*maxpos*/ 3, /*minkw*/ 0, /*varpos*/ 0, argsbuf); |
1862 | 10.1M | if (!fastargs) { |
1863 | 0 | goto exit; |
1864 | 0 | } |
1865 | 10.1M | if (!noptargs) { |
1866 | 0 | goto skip_optional_pos; |
1867 | 0 | } |
1868 | 10.1M | if (fastargs[0]) { |
1869 | 10.1M | x = fastargs[0]; |
1870 | 10.1M | if (!--noptargs) { |
1871 | 10.1M | goto skip_optional_pos; |
1872 | 10.1M | } |
1873 | 10.1M | } |
1874 | 0 | if (fastargs[1]) { |
1875 | 0 | if (!PyUnicode_Check(fastargs[1])) { |
1876 | 0 | _PyArg_BadArgument("str", "argument 'encoding'", "str", fastargs[1]); |
1877 | 0 | goto exit; |
1878 | 0 | } |
1879 | 0 | Py_ssize_t encoding_length; |
1880 | 0 | encoding = PyUnicode_AsUTF8AndSize(fastargs[1], &encoding_length); |
1881 | 0 | if (encoding == NULL) { |
1882 | 0 | goto exit; |
1883 | 0 | } |
1884 | 0 | if (strlen(encoding) != (size_t)encoding_length) { |
1885 | 0 | PyErr_SetString(PyExc_ValueError, "embedded null character"); |
1886 | 0 | goto exit; |
1887 | 0 | } |
1888 | 0 | if (!--noptargs) { |
1889 | 0 | goto skip_optional_pos; |
1890 | 0 | } |
1891 | 0 | } |
1892 | 0 | if (!PyUnicode_Check(fastargs[2])) { |
1893 | 0 | _PyArg_BadArgument("str", "argument 'errors'", "str", fastargs[2]); |
1894 | 0 | goto exit; |
1895 | 0 | } |
1896 | 0 | Py_ssize_t errors_length; |
1897 | 0 | errors = PyUnicode_AsUTF8AndSize(fastargs[2], &errors_length); |
1898 | 0 | if (errors == NULL) { |
1899 | 0 | goto exit; |
1900 | 0 | } |
1901 | 0 | if (strlen(errors) != (size_t)errors_length) { |
1902 | 0 | PyErr_SetString(PyExc_ValueError, "embedded null character"); |
1903 | 0 | goto exit; |
1904 | 0 | } |
1905 | 10.1M | skip_optional_pos: |
1906 | 10.1M | return_value = unicode_new_impl(type, x, encoding, errors); |
1907 | | |
1908 | 10.1M | exit: |
1909 | 10.1M | return return_value; |
1910 | 10.1M | } |
1911 | | /*[clinic end generated code: output=238917fe66120bde input=a9049054013a1b77]*/ |