1/*[clinic input]
2preserve
3[clinic start generated code]*/
4
5PyDoc_STRVAR(_io_open__doc__,
6"open($module, /, file, mode=\'r\', buffering=-1, encoding=None,\n"
7" errors=None, newline=None, closefd=True, opener=None)\n"
8"--\n"
9"\n"
10"Open file and return a stream. Raise OSError upon failure.\n"
11"\n"
12"file is either a text or byte string giving the name (and the path\n"
13"if the file isn\'t in the current working directory) of the file to\n"
14"be opened or an integer file descriptor of the file to be\n"
15"wrapped. (If a file descriptor is given, it is closed when the\n"
16"returned I/O object is closed, unless closefd is set to False.)\n"
17"\n"
18"mode is an optional string that specifies the mode in which the file\n"
19"is opened. It defaults to \'r\' which means open for reading in text\n"
20"mode. Other common values are \'w\' for writing (truncating the file if\n"
21"it already exists), \'x\' for creating and writing to a new file, and\n"
22"\'a\' for appending (which on some Unix systems, means that all writes\n"
23"append to the end of the file regardless of the current seek position).\n"
24"In text mode, if encoding is not specified the encoding used is platform\n"
25"dependent: locale.getpreferredencoding(False) is called to get the\n"
26"current locale encoding. (For reading and writing raw bytes use binary\n"
27"mode and leave encoding unspecified.) The available modes are:\n"
28"\n"
29"========= ===============================================================\n"
30"Character Meaning\n"
31"--------- ---------------------------------------------------------------\n"
32"\'r\' open for reading (default)\n"
33"\'w\' open for writing, truncating the file first\n"
34"\'x\' create a new file and open it for writing\n"
35"\'a\' open for writing, appending to the end of the file if it exists\n"
36"\'b\' binary mode\n"
37"\'t\' text mode (default)\n"
38"\'+\' open a disk file for updating (reading and writing)\n"
39"\'U\' universal newline mode (deprecated)\n"
40"========= ===============================================================\n"
41"\n"
42"The default mode is \'rt\' (open for reading text). For binary random\n"
43"access, the mode \'w+b\' opens and truncates the file to 0 bytes, while\n"
44"\'r+b\' opens the file without truncation. The \'x\' mode implies \'w\' and\n"
45"raises an `FileExistsError` if the file already exists.\n"
46"\n"
47"Python distinguishes between files opened in binary and text modes,\n"
48"even when the underlying operating system doesn\'t. Files opened in\n"
49"binary mode (appending \'b\' to the mode argument) return contents as\n"
50"bytes objects without any decoding. In text mode (the default, or when\n"
51"\'t\' is appended to the mode argument), the contents of the file are\n"
52"returned as strings, the bytes having been first decoded using a\n"
53"platform-dependent encoding or using the specified encoding if given.\n"
54"\n"
55"\'U\' mode is deprecated and will raise an exception in future versions\n"
56"of Python. It has no effect in Python 3. Use newline to control\n"
57"universal newlines mode.\n"
58"\n"
59"buffering is an optional integer used to set the buffering policy.\n"
60"Pass 0 to switch buffering off (only allowed in binary mode), 1 to select\n"
61"line buffering (only usable in text mode), and an integer > 1 to indicate\n"
62"the size of a fixed-size chunk buffer. When no buffering argument is\n"
63"given, the default buffering policy works as follows:\n"
64"\n"
65"* Binary files are buffered in fixed-size chunks; the size of the buffer\n"
66" is chosen using a heuristic trying to determine the underlying device\'s\n"
67" \"block size\" and falling back on `io.DEFAULT_BUFFER_SIZE`.\n"
68" On many systems, the buffer will typically be 4096 or 8192 bytes long.\n"
69"\n"
70"* \"Interactive\" text files (files for which isatty() returns True)\n"
71" use line buffering. Other text files use the policy described above\n"
72" for binary files.\n"
73"\n"
74"encoding is the name of the encoding used to decode or encode the\n"
75"file. This should only be used in text mode. The default encoding is\n"
76"platform dependent, but any encoding supported by Python can be\n"
77"passed. See the codecs module for the list of supported encodings.\n"
78"\n"
79"errors is an optional string that specifies how encoding errors are to\n"
80"be handled---this argument should not be used in binary mode. Pass\n"
81"\'strict\' to raise a ValueError exception if there is an encoding error\n"
82"(the default of None has the same effect), or pass \'ignore\' to ignore\n"
83"errors. (Note that ignoring encoding errors can lead to data loss.)\n"
84"See the documentation for codecs.register or run \'help(codecs.Codec)\'\n"
85"for a list of the permitted encoding error strings.\n"
86"\n"
87"newline controls how universal newlines works (it only applies to text\n"
88"mode). It can be None, \'\', \'\\n\', \'\\r\', and \'\\r\\n\'. It works as\n"
89"follows:\n"
90"\n"
91"* On input, if newline is None, universal newlines mode is\n"
92" enabled. Lines in the input can end in \'\\n\', \'\\r\', or \'\\r\\n\', and\n"
93" these are translated into \'\\n\' before being returned to the\n"
94" caller. If it is \'\', universal newline mode is enabled, but line\n"
95" endings are returned to the caller untranslated. If it has any of\n"
96" the other legal values, input lines are only terminated by the given\n"
97" string, and the line ending is returned to the caller untranslated.\n"
98"\n"
99"* On output, if newline is None, any \'\\n\' characters written are\n"
100" translated to the system default line separator, os.linesep. If\n"
101" newline is \'\' or \'\\n\', no translation takes place. If newline is any\n"
102" of the other legal values, any \'\\n\' characters written are translated\n"
103" to the given string.\n"
104"\n"
105"If closefd is False, the underlying file descriptor will be kept open\n"
106"when the file is closed. This does not work when a file name is given\n"
107"and must be True in that case.\n"
108"\n"
109"A custom opener can be used by passing a callable as *opener*. The\n"
110"underlying file descriptor for the file object is then obtained by\n"
111"calling *opener* with (*file*, *flags*). *opener* must return an open\n"
112"file descriptor (passing os.open as *opener* results in functionality\n"
113"similar to passing None).\n"
114"\n"
115"open() returns a file object whose type depends on the mode, and\n"
116"through which the standard file operations such as reading and writing\n"
117"are performed. When open() is used to open a file in a text mode (\'w\',\n"
118"\'r\', \'wt\', \'rt\', etc.), it returns a TextIOWrapper. When used to open\n"
119"a file in a binary mode, the returned class varies: in read binary\n"
120"mode, it returns a BufferedReader; in write binary and append binary\n"
121"modes, it returns a BufferedWriter, and in read/write mode, it returns\n"
122"a BufferedRandom.\n"
123"\n"
124"It is also possible to use a string or bytearray as a file for both\n"
125"reading and writing. For strings StringIO can be used like a file\n"
126"opened in a text mode, and for bytes a BytesIO can be used like a file\n"
127"opened in a binary mode.");
128
129#define _IO_OPEN_METHODDEF \
130 {"open", (PyCFunction)(void(*)(void))_io_open, METH_FASTCALL|METH_KEYWORDS, _io_open__doc__},
131
132static PyObject *
133_io_open_impl(PyObject *module, PyObject *file, const char *mode,
134 int buffering, const char *encoding, const char *errors,
135 const char *newline, int closefd, PyObject *opener);
136
137static PyObject *
138_io_open(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
139{
140 PyObject *return_value = NULL;
141 static const char * const _keywords[] = {"file", "mode", "buffering", "encoding", "errors", "newline", "closefd", "opener", NULL};
142 static _PyArg_Parser _parser = {NULL, _keywords, "open", 0};
143 PyObject *argsbuf[8];
144 Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1;
145 PyObject *file;
146 const char *mode = "r";
147 int buffering = -1;
148 const char *encoding = NULL;
149 const char *errors = NULL;
150 const char *newline = NULL;
151 int closefd = 1;
152 PyObject *opener = Py_None;
153
154 args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 8, 0, argsbuf);
155 if (!args) {
156 goto exit;
157 }
158 file = args[0];
159 if (!noptargs) {
160 goto skip_optional_pos;
161 }
162 if (args[1]) {
163 if (!PyUnicode_Check(args[1])) {
164 _PyArg_BadArgument("open", "argument 'mode'", "str", args[1]);
165 goto exit;
166 }
167 Py_ssize_t mode_length;
168 mode = PyUnicode_AsUTF8AndSize(args[1], &mode_length);
169 if (mode == NULL) {
170 goto exit;
171 }
172 if (strlen(mode) != (size_t)mode_length) {
173 PyErr_SetString(PyExc_ValueError, "embedded null character");
174 goto exit;
175 }
176 if (!--noptargs) {
177 goto skip_optional_pos;
178 }
179 }
180 if (args[2]) {
181 buffering = _PyLong_AsInt(args[2]);
182 if (buffering == -1 && PyErr_Occurred()) {
183 goto exit;
184 }
185 if (!--noptargs) {
186 goto skip_optional_pos;
187 }
188 }
189 if (args[3]) {
190 if (args[3] == Py_None) {
191 encoding = NULL;
192 }
193 else if (PyUnicode_Check(args[3])) {
194 Py_ssize_t encoding_length;
195 encoding = PyUnicode_AsUTF8AndSize(args[3], &encoding_length);
196 if (encoding == NULL) {
197 goto exit;
198 }
199 if (strlen(encoding) != (size_t)encoding_length) {
200 PyErr_SetString(PyExc_ValueError, "embedded null character");
201 goto exit;
202 }
203 }
204 else {
205 _PyArg_BadArgument("open", "argument 'encoding'", "str or None", args[3]);
206 goto exit;
207 }
208 if (!--noptargs) {
209 goto skip_optional_pos;
210 }
211 }
212 if (args[4]) {
213 if (args[4] == Py_None) {
214 errors = NULL;
215 }
216 else if (PyUnicode_Check(args[4])) {
217 Py_ssize_t errors_length;
218 errors = PyUnicode_AsUTF8AndSize(args[4], &errors_length);
219 if (errors == NULL) {
220 goto exit;
221 }
222 if (strlen(errors) != (size_t)errors_length) {
223 PyErr_SetString(PyExc_ValueError, "embedded null character");
224 goto exit;
225 }
226 }
227 else {
228 _PyArg_BadArgument("open", "argument 'errors'", "str or None", args[4]);
229 goto exit;
230 }
231 if (!--noptargs) {
232 goto skip_optional_pos;
233 }
234 }
235 if (args[5]) {
236 if (args[5] == Py_None) {
237 newline = NULL;
238 }
239 else if (PyUnicode_Check(args[5])) {
240 Py_ssize_t newline_length;
241 newline = PyUnicode_AsUTF8AndSize(args[5], &newline_length);
242 if (newline == NULL) {
243 goto exit;
244 }
245 if (strlen(newline) != (size_t)newline_length) {
246 PyErr_SetString(PyExc_ValueError, "embedded null character");
247 goto exit;
248 }
249 }
250 else {
251 _PyArg_BadArgument("open", "argument 'newline'", "str or None", args[5]);
252 goto exit;
253 }
254 if (!--noptargs) {
255 goto skip_optional_pos;
256 }
257 }
258 if (args[6]) {
259 closefd = _PyLong_AsInt(args[6]);
260 if (closefd == -1 && PyErr_Occurred()) {
261 goto exit;
262 }
263 if (!--noptargs) {
264 goto skip_optional_pos;
265 }
266 }
267 opener = args[7];
268skip_optional_pos:
269 return_value = _io_open_impl(module, file, mode, buffering, encoding, errors, newline, closefd, opener);
270
271exit:
272 return return_value;
273}
274
275PyDoc_STRVAR(_io_text_encoding__doc__,
276"text_encoding($module, encoding, stacklevel=2, /)\n"
277"--\n"
278"\n"
279"A helper function to choose the text encoding.\n"
280"\n"
281"When encoding is not None, just return it.\n"
282"Otherwise, return the default text encoding (i.e. \"locale\").\n"
283"\n"
284"This function emits an EncodingWarning if encoding is None and\n"
285"sys.flags.warn_default_encoding is true.\n"
286"\n"
287"This can be used in APIs with an encoding=None parameter.\n"
288"However, please consider using encoding=\"utf-8\" for new APIs.");
289
290#define _IO_TEXT_ENCODING_METHODDEF \
291 {"text_encoding", (PyCFunction)(void(*)(void))_io_text_encoding, METH_FASTCALL, _io_text_encoding__doc__},
292
293static PyObject *
294_io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel);
295
296static PyObject *
297_io_text_encoding(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
298{
299 PyObject *return_value = NULL;
300 PyObject *encoding;
301 int stacklevel = 2;
302
303 if (!_PyArg_CheckPositional("text_encoding", nargs, 1, 2)) {
304 goto exit;
305 }
306 encoding = args[0];
307 if (nargs < 2) {
308 goto skip_optional;
309 }
310 stacklevel = _PyLong_AsInt(args[1]);
311 if (stacklevel == -1 && PyErr_Occurred()) {
312 goto exit;
313 }
314skip_optional:
315 return_value = _io_text_encoding_impl(module, encoding, stacklevel);
316
317exit:
318 return return_value;
319}
320
321PyDoc_STRVAR(_io_open_code__doc__,
322"open_code($module, /, path)\n"
323"--\n"
324"\n"
325"Opens the provided file with the intent to import the contents.\n"
326"\n"
327"This may perform extra validation beyond open(), but is otherwise interchangeable\n"
328"with calling open(path, \'rb\').");
329
330#define _IO_OPEN_CODE_METHODDEF \
331 {"open_code", (PyCFunction)(void(*)(void))_io_open_code, METH_FASTCALL|METH_KEYWORDS, _io_open_code__doc__},
332
333static PyObject *
334_io_open_code_impl(PyObject *module, PyObject *path);
335
336static PyObject *
337_io_open_code(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
338{
339 PyObject *return_value = NULL;
340 static const char * const _keywords[] = {"path", NULL};
341 static _PyArg_Parser _parser = {NULL, _keywords, "open_code", 0};
342 PyObject *argsbuf[1];
343 PyObject *path;
344
345 args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser, 1, 1, 0, argsbuf);
346 if (!args) {
347 goto exit;
348 }
349 if (!PyUnicode_Check(args[0])) {
350 _PyArg_BadArgument("open_code", "argument 'path'", "str", args[0]);
351 goto exit;
352 }
353 if (PyUnicode_READY(args[0]) == -1) {
354 goto exit;
355 }
356 path = args[0];
357 return_value = _io_open_code_impl(module, path);
358
359exit:
360 return return_value;
361}
362/*[clinic end generated code: output=06e055d1d80b835d input=a9049054013a1b77]*/
363