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
10
11 PyDoc_STRVAR(_io_open__doc__,
12 "open($module, /, file, mode=\'r\', buffering=-1, encoding=None,\n"
13 " errors=None, newline=None, closefd=True, opener=None)\n"
14 "--\n"
15 "\n"
16 "Open file and return a stream. Raise OSError upon failure.\n"
17 "\n"
18 "file is either a text or byte string giving the name (and the path\n"
19 "if the file isn\'t in the current working directory) of the file to\n"
20 "be opened or an integer file descriptor of the file to be\n"
21 "wrapped. (If a file descriptor is given, it is closed when the\n"
22 "returned I/O object is closed, unless closefd is set to False.)\n"
23 "\n"
24 "mode is an optional string that specifies the mode in which the file\n"
25 "is opened. It defaults to \'r\' which means open for reading in text\n"
26 "mode. Other common values are \'w\' for writing (truncating the file if\n"
27 "it already exists), \'x\' for creating and writing to a new file, and\n"
28 "\'a\' for appending (which on some Unix systems, means that all writes\n"
29 "append to the end of the file regardless of the current seek position).\n"
30 "In text mode, if encoding is not specified the encoding used is platform\n"
31 "dependent: locale.getencoding() is called to get the current locale encoding.\n"
32 "(For reading and writing raw bytes use binary mode and leave encoding\n"
33 "unspecified.) The available modes are:\n"
34 "\n"
35 "========= ===============================================================\n"
36 "Character Meaning\n"
37 "--------- ---------------------------------------------------------------\n"
38 "\'r\' open for reading (default)\n"
39 "\'w\' open for writing, truncating the file first\n"
40 "\'x\' create a new file and open it for writing\n"
41 "\'a\' open for writing, appending to the end of the file if it exists\n"
42 "\'b\' binary mode\n"
43 "\'t\' text mode (default)\n"
44 "\'+\' open a disk file for updating (reading and writing)\n"
45 "========= ===============================================================\n"
46 "\n"
47 "The default mode is \'rt\' (open for reading text). For binary random\n"
48 "access, the mode \'w+b\' opens and truncates the file to 0 bytes, while\n"
49 "\'r+b\' opens the file without truncation. The \'x\' mode implies \'w\' and\n"
50 "raises an `FileExistsError` if the file already exists.\n"
51 "\n"
52 "Python distinguishes between files opened in binary and text modes,\n"
53 "even when the underlying operating system doesn\'t. Files opened in\n"
54 "binary mode (appending \'b\' to the mode argument) return contents as\n"
55 "bytes objects without any decoding. In text mode (the default, or when\n"
56 "\'t\' is appended to the mode argument), the contents of the file are\n"
57 "returned as strings, the bytes having been first decoded using a\n"
58 "platform-dependent encoding or using the specified encoding if given.\n"
59 "\n"
60 "buffering is an optional integer used to set the buffering policy.\n"
61 "Pass 0 to switch buffering off (only allowed in binary mode), 1 to select\n"
62 "line buffering (only usable in text mode), and an integer > 1 to indicate\n"
63 "the size of a fixed-size chunk buffer. When no buffering argument is\n"
64 "given, the default buffering policy works as follows:\n"
65 "\n"
66 "* Binary files are buffered in fixed-size chunks; the size of the buffer\n"
67 " is chosen using a heuristic trying to determine the underlying device\'s\n"
68 " \"block size\" and falling back on `io.DEFAULT_BUFFER_SIZE`.\n"
69 " On many systems, the buffer will typically be 4096 or 8192 bytes long.\n"
70 "\n"
71 "* \"Interactive\" text files (files for which isatty() returns True)\n"
72 " use line buffering. Other text files use the policy described above\n"
73 " for binary files.\n"
74 "\n"
75 "encoding is the name of the encoding used to decode or encode the\n"
76 "file. This should only be used in text mode. The default encoding is\n"
77 "platform dependent, but any encoding supported by Python can be\n"
78 "passed. See the codecs module for the list of supported encodings.\n"
79 "\n"
80 "errors is an optional string that specifies how encoding errors are to\n"
81 "be handled---this argument should not be used in binary mode. Pass\n"
82 "\'strict\' to raise a ValueError exception if there is an encoding error\n"
83 "(the default of None has the same effect), or pass \'ignore\' to ignore\n"
84 "errors. (Note that ignoring encoding errors can lead to data loss.)\n"
85 "See the documentation for codecs.register or run \'help(codecs.Codec)\'\n"
86 "for a list of the permitted encoding error strings.\n"
87 "\n"
88 "newline controls how universal newlines works (it only applies to text\n"
89 "mode). It can be None, \'\', \'\\n\', \'\\r\', and \'\\r\\n\'. It works as\n"
90 "follows:\n"
91 "\n"
92 "* On input, if newline is None, universal newlines mode is\n"
93 " enabled. Lines in the input can end in \'\\n\', \'\\r\', or \'\\r\\n\', and\n"
94 " these are translated into \'\\n\' before being returned to the\n"
95 " caller. If it is \'\', universal newline mode is enabled, but line\n"
96 " endings are returned to the caller untranslated. If it has any of\n"
97 " the other legal values, input lines are only terminated by the given\n"
98 " string, and the line ending is returned to the caller untranslated.\n"
99 "\n"
100 "* On output, if newline is None, any \'\\n\' characters written are\n"
101 " translated to the system default line separator, os.linesep. If\n"
102 " newline is \'\' or \'\\n\', no translation takes place. If newline is any\n"
103 " of the other legal values, any \'\\n\' characters written are translated\n"
104 " to the given string.\n"
105 "\n"
106 "If closefd is False, the underlying file descriptor will be kept open\n"
107 "when the file is closed. This does not work when a file name is given\n"
108 "and must be True in that case.\n"
109 "\n"
110 "A custom opener can be used by passing a callable as *opener*. The\n"
111 "underlying file descriptor for the file object is then obtained by\n"
112 "calling *opener* with (*file*, *flags*). *opener* must return an open\n"
113 "file descriptor (passing os.open as *opener* results in functionality\n"
114 "similar to passing None).\n"
115 "\n"
116 "open() returns a file object whose type depends on the mode, and\n"
117 "through which the standard file operations such as reading and writing\n"
118 "are performed. When open() is used to open a file in a text mode (\'w\',\n"
119 "\'r\', \'wt\', \'rt\', etc.), it returns a TextIOWrapper. When used to open\n"
120 "a file in a binary mode, the returned class varies: in read binary\n"
121 "mode, it returns a BufferedReader; in write binary and append binary\n"
122 "modes, it returns a BufferedWriter, and in read/write mode, it returns\n"
123 "a BufferedRandom.\n"
124 "\n"
125 "It is also possible to use a string or bytearray as a file for both\n"
126 "reading and writing. For strings StringIO can be used like a file\n"
127 "opened in a text mode, and for bytes a BytesIO can be used like a file\n"
128 "opened in a binary mode.");
129
130 #define _IO_OPEN_METHODDEF \
131 {"open", _PyCFunction_CAST(_io_open), METH_FASTCALL|METH_KEYWORDS, _io_open__doc__},
132
133 static PyObject *
134 _io_open_impl(PyObject *module, PyObject *file, const char *mode,
135 int buffering, const char *encoding, const char *errors,
136 const char *newline, int closefd, PyObject *opener);
137
138 static PyObject *
139 _io_open(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
140 {
141 PyObject *return_value = NULL;
142 #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
143
144 #define NUM_KEYWORDS 8
145 static struct {
146 PyGC_Head _this_is_not_used;
147 PyObject_VAR_HEAD
148 PyObject *ob_item[NUM_KEYWORDS];
149 } _kwtuple = {
150 .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
151 .ob_item = { &_Py_ID(file), &_Py_ID(mode), &_Py_ID(buffering), &_Py_ID(encoding), &_Py_ID(errors), &_Py_ID(newline), &_Py_ID(closefd), &_Py_ID(opener), },
152 };
153 #undef NUM_KEYWORDS
154 #define KWTUPLE (&_kwtuple.ob_base.ob_base)
155
156 #else // !Py_BUILD_CORE
157 # define KWTUPLE NULL
158 #endif // !Py_BUILD_CORE
159
160 static const char * const _keywords[] = {"file", "mode", "buffering", "encoding", "errors", "newline", "closefd", "opener", NULL};
161 static _PyArg_Parser _parser = {
162 .keywords = _keywords,
163 .fname = "open",
164 .kwtuple = KWTUPLE,
165 };
166 #undef KWTUPLE
167 PyObject *argsbuf[8];
168 Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1;
169 PyObject *file;
170 const char *mode = "r";
171 int buffering = -1;
172 const char *encoding = NULL;
173 const char *errors = NULL;
174 const char *newline = NULL;
175 int closefd = 1;
176 PyObject *opener = Py_None;
177
178 args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 8, 0, argsbuf);
179 if (!args) {
180 goto exit;
181 }
182 file = args[0];
183 if (!noptargs) {
184 goto skip_optional_pos;
185 }
186 if (args[1]) {
187 if (!PyUnicode_Check(args[1])) {
188 _PyArg_BadArgument("open", "argument 'mode'", "str", args[1]);
189 goto exit;
190 }
191 Py_ssize_t mode_length;
192 mode = PyUnicode_AsUTF8AndSize(args[1], &mode_length);
193 if (mode == NULL) {
194 goto exit;
195 }
196 if (strlen(mode) != (size_t)mode_length) {
197 PyErr_SetString(PyExc_ValueError, "embedded null character");
198 goto exit;
199 }
200 if (!--noptargs) {
201 goto skip_optional_pos;
202 }
203 }
204 if (args[2]) {
205 buffering = _PyLong_AsInt(args[2]);
206 if (buffering == -1 && PyErr_Occurred()) {
207 goto exit;
208 }
209 if (!--noptargs) {
210 goto skip_optional_pos;
211 }
212 }
213 if (args[3]) {
214 if (args[3] == Py_None) {
215 encoding = NULL;
216 }
217 else if (PyUnicode_Check(args[3])) {
218 Py_ssize_t encoding_length;
219 encoding = PyUnicode_AsUTF8AndSize(args[3], &encoding_length);
220 if (encoding == NULL) {
221 goto exit;
222 }
223 if (strlen(encoding) != (size_t)encoding_length) {
224 PyErr_SetString(PyExc_ValueError, "embedded null character");
225 goto exit;
226 }
227 }
228 else {
229 _PyArg_BadArgument("open", "argument 'encoding'", "str or None", args[3]);
230 goto exit;
231 }
232 if (!--noptargs) {
233 goto skip_optional_pos;
234 }
235 }
236 if (args[4]) {
237 if (args[4] == Py_None) {
238 errors = NULL;
239 }
240 else if (PyUnicode_Check(args[4])) {
241 Py_ssize_t errors_length;
242 errors = PyUnicode_AsUTF8AndSize(args[4], &errors_length);
243 if (errors == NULL) {
244 goto exit;
245 }
246 if (strlen(errors) != (size_t)errors_length) {
247 PyErr_SetString(PyExc_ValueError, "embedded null character");
248 goto exit;
249 }
250 }
251 else {
252 _PyArg_BadArgument("open", "argument 'errors'", "str or None", args[4]);
253 goto exit;
254 }
255 if (!--noptargs) {
256 goto skip_optional_pos;
257 }
258 }
259 if (args[5]) {
260 if (args[5] == Py_None) {
261 newline = NULL;
262 }
263 else if (PyUnicode_Check(args[5])) {
264 Py_ssize_t newline_length;
265 newline = PyUnicode_AsUTF8AndSize(args[5], &newline_length);
266 if (newline == NULL) {
267 goto exit;
268 }
269 if (strlen(newline) != (size_t)newline_length) {
270 PyErr_SetString(PyExc_ValueError, "embedded null character");
271 goto exit;
272 }
273 }
274 else {
275 _PyArg_BadArgument("open", "argument 'newline'", "str or None", args[5]);
276 goto exit;
277 }
278 if (!--noptargs) {
279 goto skip_optional_pos;
280 }
281 }
282 if (args[6]) {
283 closefd = PyObject_IsTrue(args[6]);
284 if (closefd < 0) {
285 goto exit;
286 }
287 if (!--noptargs) {
288 goto skip_optional_pos;
289 }
290 }
291 opener = args[7];
292 skip_optional_pos:
293 return_value = _io_open_impl(module, file, mode, buffering, encoding, errors, newline, closefd, opener);
294
295 exit:
296 return return_value;
297 }
298
299 PyDoc_STRVAR(_io_text_encoding__doc__,
300 "text_encoding($module, encoding, stacklevel=2, /)\n"
301 "--\n"
302 "\n"
303 "A helper function to choose the text encoding.\n"
304 "\n"
305 "When encoding is not None, this function returns it.\n"
306 "Otherwise, this function returns the default text encoding\n"
307 "(i.e. \"locale\" or \"utf-8\" depends on UTF-8 mode).\n"
308 "\n"
309 "This function emits an EncodingWarning if encoding is None and\n"
310 "sys.flags.warn_default_encoding is true.\n"
311 "\n"
312 "This can be used in APIs with an encoding=None parameter.\n"
313 "However, please consider using encoding=\"utf-8\" for new APIs.");
314
315 #define _IO_TEXT_ENCODING_METHODDEF \
316 {"text_encoding", _PyCFunction_CAST(_io_text_encoding), METH_FASTCALL, _io_text_encoding__doc__},
317
318 static PyObject *
319 _io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel);
320
321 static PyObject *
322 _io_text_encoding(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
323 {
324 PyObject *return_value = NULL;
325 PyObject *encoding;
326 int stacklevel = 2;
327
328 if (!_PyArg_CheckPositional("text_encoding", nargs, 1, 2)) {
329 goto exit;
330 }
331 encoding = args[0];
332 if (nargs < 2) {
333 goto skip_optional;
334 }
335 stacklevel = _PyLong_AsInt(args[1]);
336 if (stacklevel == -1 && PyErr_Occurred()) {
337 goto exit;
338 }
339 skip_optional:
340 return_value = _io_text_encoding_impl(module, encoding, stacklevel);
341
342 exit:
343 return return_value;
344 }
345
346 PyDoc_STRVAR(_io_open_code__doc__,
347 "open_code($module, /, path)\n"
348 "--\n"
349 "\n"
350 "Opens the provided file with the intent to import the contents.\n"
351 "\n"
352 "This may perform extra validation beyond open(), but is otherwise interchangeable\n"
353 "with calling open(path, \'rb\').");
354
355 #define _IO_OPEN_CODE_METHODDEF \
356 {"open_code", _PyCFunction_CAST(_io_open_code), METH_FASTCALL|METH_KEYWORDS, _io_open_code__doc__},
357
358 static PyObject *
359 _io_open_code_impl(PyObject *module, PyObject *path);
360
361 static PyObject *
362 _io_open_code(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
363 {
364 PyObject *return_value = NULL;
365 #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
366
367 #define NUM_KEYWORDS 1
368 static struct {
369 PyGC_Head _this_is_not_used;
370 PyObject_VAR_HEAD
371 PyObject *ob_item[NUM_KEYWORDS];
372 } _kwtuple = {
373 .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
374 .ob_item = { &_Py_ID(path), },
375 };
376 #undef NUM_KEYWORDS
377 #define KWTUPLE (&_kwtuple.ob_base.ob_base)
378
379 #else // !Py_BUILD_CORE
380 # define KWTUPLE NULL
381 #endif // !Py_BUILD_CORE
382
383 static const char * const _keywords[] = {"path", NULL};
384 static _PyArg_Parser _parser = {
385 .keywords = _keywords,
386 .fname = "open_code",
387 .kwtuple = KWTUPLE,
388 };
389 #undef KWTUPLE
390 PyObject *argsbuf[1];
391 PyObject *path;
392
393 args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf);
394 if (!args) {
395 goto exit;
396 }
397 if (!PyUnicode_Check(args[0])) {
398 _PyArg_BadArgument("open_code", "argument 'path'", "str", args[0]);
399 goto exit;
400 }
401 if (PyUnicode_READY(args[0]) == -1) {
402 goto exit;
403 }
404 path = args[0];
405 return_value = _io_open_code_impl(module, path);
406
407 exit:
408 return return_value;
409 }
410 /*[clinic end generated code: output=f387eba3f4c0254a input=a9049054013a1b77]*/