Coverage Report

Created: 2025-11-11 07:03

next uncovered line (L), next uncovered region (R), next uncovered branch (B)
/src/cpython3/Modules/_io/clinic/_iomodule.c.h
Line
Count
Source
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_modsupport.h"    // _PyArg_UnpackKeywords()
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 max(min(blocksize, 8 MiB), DEFAULT_BUFFER_SIZE)\n"
68
" when the device block size is available.\n"
69
" On most systems, the buffer will typically be 128 kilobytes 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
408
{
141
408
    PyObject *return_value = NULL;
142
408
    #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
143
144
408
    #define NUM_KEYWORDS 8
145
408
    static struct {
146
408
        PyGC_Head _this_is_not_used;
147
408
        PyObject_VAR_HEAD
148
408
        Py_hash_t ob_hash;
149
408
        PyObject *ob_item[NUM_KEYWORDS];
150
408
    } _kwtuple = {
151
408
        .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
152
408
        .ob_hash = -1,
153
408
        .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), },
154
408
    };
155
408
    #undef NUM_KEYWORDS
156
408
    #define KWTUPLE (&_kwtuple.ob_base.ob_base)
157
158
    #else  // !Py_BUILD_CORE
159
    #  define KWTUPLE NULL
160
    #endif  // !Py_BUILD_CORE
161
162
408
    static const char * const _keywords[] = {"file", "mode", "buffering", "encoding", "errors", "newline", "closefd", "opener", NULL};
163
408
    static _PyArg_Parser _parser = {
164
408
        .keywords = _keywords,
165
408
        .fname = "open",
166
408
        .kwtuple = KWTUPLE,
167
408
    };
168
408
    #undef KWTUPLE
169
408
    PyObject *argsbuf[8];
170
408
    Py_ssize_t noptargs = nargs + (kwnames ? PyTuple_GET_SIZE(kwnames) : 0) - 1;
171
408
    PyObject *file;
172
408
    const char *mode = "r";
173
408
    int buffering = -1;
174
408
    const char *encoding = NULL;
175
408
    const char *errors = NULL;
176
408
    const char *newline = NULL;
177
408
    int closefd = 1;
178
408
    PyObject *opener = Py_None;
179
180
408
    args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser,
181
408
            /*minpos*/ 1, /*maxpos*/ 8, /*minkw*/ 0, /*varpos*/ 0, argsbuf);
182
408
    if (!args) {
183
0
        goto exit;
184
0
    }
185
408
    file = args[0];
186
408
    if (!noptargs) {
187
0
        goto skip_optional_pos;
188
0
    }
189
408
    if (args[1]) {
190
408
        if (!PyUnicode_Check(args[1])) {
191
0
            _PyArg_BadArgument("open", "argument 'mode'", "str", args[1]);
192
0
            goto exit;
193
0
        }
194
408
        Py_ssize_t mode_length;
195
408
        mode = PyUnicode_AsUTF8AndSize(args[1], &mode_length);
196
408
        if (mode == NULL) {
197
0
            goto exit;
198
0
        }
199
408
        if (strlen(mode) != (size_t)mode_length) {
200
0
            PyErr_SetString(PyExc_ValueError, "embedded null character");
201
0
            goto exit;
202
0
        }
203
408
        if (!--noptargs) {
204
342
            goto skip_optional_pos;
205
342
        }
206
408
    }
207
66
    if (args[2]) {
208
66
        buffering = PyLong_AsInt(args[2]);
209
66
        if (buffering == -1 && PyErr_Occurred()) {
210
0
            goto exit;
211
0
        }
212
66
        if (!--noptargs) {
213
0
            goto skip_optional_pos;
214
0
        }
215
66
    }
216
66
    if (args[3]) {
217
66
        if (args[3] == Py_None) {
218
66
            encoding = NULL;
219
66
        }
220
0
        else if (PyUnicode_Check(args[3])) {
221
0
            Py_ssize_t encoding_length;
222
0
            encoding = PyUnicode_AsUTF8AndSize(args[3], &encoding_length);
223
0
            if (encoding == NULL) {
224
0
                goto exit;
225
0
            }
226
0
            if (strlen(encoding) != (size_t)encoding_length) {
227
0
                PyErr_SetString(PyExc_ValueError, "embedded null character");
228
0
                goto exit;
229
0
            }
230
0
        }
231
0
        else {
232
0
            _PyArg_BadArgument("open", "argument 'encoding'", "str or None", args[3]);
233
0
            goto exit;
234
0
        }
235
66
        if (!--noptargs) {
236
0
            goto skip_optional_pos;
237
0
        }
238
66
    }
239
66
    if (args[4]) {
240
66
        if (args[4] == Py_None) {
241
66
            errors = NULL;
242
66
        }
243
0
        else if (PyUnicode_Check(args[4])) {
244
0
            Py_ssize_t errors_length;
245
0
            errors = PyUnicode_AsUTF8AndSize(args[4], &errors_length);
246
0
            if (errors == NULL) {
247
0
                goto exit;
248
0
            }
249
0
            if (strlen(errors) != (size_t)errors_length) {
250
0
                PyErr_SetString(PyExc_ValueError, "embedded null character");
251
0
                goto exit;
252
0
            }
253
0
        }
254
0
        else {
255
0
            _PyArg_BadArgument("open", "argument 'errors'", "str or None", args[4]);
256
0
            goto exit;
257
0
        }
258
66
        if (!--noptargs) {
259
0
            goto skip_optional_pos;
260
0
        }
261
66
    }
262
66
    if (args[5]) {
263
66
        if (args[5] == Py_None) {
264
66
            newline = NULL;
265
66
        }
266
0
        else if (PyUnicode_Check(args[5])) {
267
0
            Py_ssize_t newline_length;
268
0
            newline = PyUnicode_AsUTF8AndSize(args[5], &newline_length);
269
0
            if (newline == NULL) {
270
0
                goto exit;
271
0
            }
272
0
            if (strlen(newline) != (size_t)newline_length) {
273
0
                PyErr_SetString(PyExc_ValueError, "embedded null character");
274
0
                goto exit;
275
0
            }
276
0
        }
277
0
        else {
278
0
            _PyArg_BadArgument("open", "argument 'newline'", "str or None", args[5]);
279
0
            goto exit;
280
0
        }
281
66
        if (!--noptargs) {
282
0
            goto skip_optional_pos;
283
0
        }
284
66
    }
285
66
    if (args[6]) {
286
66
        closefd = PyObject_IsTrue(args[6]);
287
66
        if (closefd < 0) {
288
0
            goto exit;
289
0
        }
290
66
        if (!--noptargs) {
291
66
            goto skip_optional_pos;
292
66
        }
293
66
    }
294
0
    opener = args[7];
295
408
skip_optional_pos:
296
408
    return_value = _io_open_impl(module, file, mode, buffering, encoding, errors, newline, closefd, opener);
297
298
408
exit:
299
408
    return return_value;
300
408
}
301
302
PyDoc_STRVAR(_io_text_encoding__doc__,
303
"text_encoding($module, encoding, stacklevel=2, /)\n"
304
"--\n"
305
"\n"
306
"A helper function to choose the text encoding.\n"
307
"\n"
308
"When encoding is not None, this function returns it.\n"
309
"Otherwise, this function returns the default text encoding\n"
310
"(i.e. \"locale\" or \"utf-8\" depends on UTF-8 mode).\n"
311
"\n"
312
"This function emits an EncodingWarning if encoding is None and\n"
313
"sys.flags.warn_default_encoding is true.\n"
314
"\n"
315
"This can be used in APIs with an encoding=None parameter.\n"
316
"However, please consider using encoding=\"utf-8\" for new APIs.");
317
318
#define _IO_TEXT_ENCODING_METHODDEF    \
319
    {"text_encoding", _PyCFunction_CAST(_io_text_encoding), METH_FASTCALL, _io_text_encoding__doc__},
320
321
static PyObject *
322
_io_text_encoding_impl(PyObject *module, PyObject *encoding, int stacklevel);
323
324
static PyObject *
325
_io_text_encoding(PyObject *module, PyObject *const *args, Py_ssize_t nargs)
326
0
{
327
0
    PyObject *return_value = NULL;
328
0
    PyObject *encoding;
329
0
    int stacklevel = 2;
330
331
0
    if (!_PyArg_CheckPositional("text_encoding", nargs, 1, 2)) {
332
0
        goto exit;
333
0
    }
334
0
    encoding = args[0];
335
0
    if (nargs < 2) {
336
0
        goto skip_optional;
337
0
    }
338
0
    stacklevel = PyLong_AsInt(args[1]);
339
0
    if (stacklevel == -1 && PyErr_Occurred()) {
340
0
        goto exit;
341
0
    }
342
0
skip_optional:
343
0
    return_value = _io_text_encoding_impl(module, encoding, stacklevel);
344
345
0
exit:
346
0
    return return_value;
347
0
}
348
349
PyDoc_STRVAR(_io_open_code__doc__,
350
"open_code($module, /, path)\n"
351
"--\n"
352
"\n"
353
"Opens the provided file with the intent to import the contents.\n"
354
"\n"
355
"This may perform extra validation beyond open(), but is otherwise interchangeable\n"
356
"with calling open(path, \'rb\').");
357
358
#define _IO_OPEN_CODE_METHODDEF    \
359
    {"open_code", _PyCFunction_CAST(_io_open_code), METH_FASTCALL|METH_KEYWORDS, _io_open_code__doc__},
360
361
static PyObject *
362
_io_open_code_impl(PyObject *module, PyObject *path);
363
364
static PyObject *
365
_io_open_code(PyObject *module, PyObject *const *args, Py_ssize_t nargs, PyObject *kwnames)
366
342
{
367
342
    PyObject *return_value = NULL;
368
342
    #if defined(Py_BUILD_CORE) && !defined(Py_BUILD_CORE_MODULE)
369
370
342
    #define NUM_KEYWORDS 1
371
342
    static struct {
372
342
        PyGC_Head _this_is_not_used;
373
342
        PyObject_VAR_HEAD
374
342
        Py_hash_t ob_hash;
375
342
        PyObject *ob_item[NUM_KEYWORDS];
376
342
    } _kwtuple = {
377
342
        .ob_base = PyVarObject_HEAD_INIT(&PyTuple_Type, NUM_KEYWORDS)
378
342
        .ob_hash = -1,
379
342
        .ob_item = { &_Py_ID(path), },
380
342
    };
381
342
    #undef NUM_KEYWORDS
382
342
    #define KWTUPLE (&_kwtuple.ob_base.ob_base)
383
384
    #else  // !Py_BUILD_CORE
385
    #  define KWTUPLE NULL
386
    #endif  // !Py_BUILD_CORE
387
388
342
    static const char * const _keywords[] = {"path", NULL};
389
342
    static _PyArg_Parser _parser = {
390
342
        .keywords = _keywords,
391
342
        .fname = "open_code",
392
342
        .kwtuple = KWTUPLE,
393
342
    };
394
342
    #undef KWTUPLE
395
342
    PyObject *argsbuf[1];
396
342
    PyObject *path;
397
398
342
    args = _PyArg_UnpackKeywords(args, nargs, NULL, kwnames, &_parser,
399
342
            /*minpos*/ 1, /*maxpos*/ 1, /*minkw*/ 0, /*varpos*/ 0, argsbuf);
400
342
    if (!args) {
401
0
        goto exit;
402
0
    }
403
342
    if (!PyUnicode_Check(args[0])) {
404
0
        _PyArg_BadArgument("open_code", "argument 'path'", "str", args[0]);
405
0
        goto exit;
406
0
    }
407
342
    path = args[0];
408
342
    return_value = _io_open_code_impl(module, path);
409
410
342
exit:
411
342
    return return_value;
412
342
}
413
/*[clinic end generated code: output=7a8e032c0424bce2 input=a9049054013a1b77]*/