1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073
|
/* ------------------------------------------------------------------------
_codecs -- Provides access to the codec registry and the builtin
codecs.
This module should never be imported directly. The standard library
module "codecs" wraps this builtin module for use within Python.
The codec registry is accessible via:
register(search_function) -> None
lookup(encoding) -> CodecInfo object
The builtin Unicode codecs use the following interface:
<encoding>_encode(Unicode_object[,errors='strict']) ->
(string object, bytes consumed)
<encoding>_decode(char_buffer_obj[,errors='strict']) ->
(Unicode object, bytes consumed)
These <encoding>s are available: utf_8, unicode_escape,
raw_unicode_escape, latin_1, ascii (7-bit), mbcs (on win32).
Written by Marc-Andre Lemburg (mal@lemburg.com).
Copyright (c) Corporation for National Research Initiatives.
------------------------------------------------------------------------ */
#include "Python.h"
#include "pycore_codecs.h" // _PyCodec_Lookup()
#ifdef MS_WINDOWS
#include <windows.h>
#endif
/*[clinic input]
module _codecs
[clinic start generated code]*/
/*[clinic end generated code: output=da39a3ee5e6b4b0d input=e1390e3da3cb9deb]*/
#include "pycore_runtime.h"
#include "clinic/_codecsmodule.c.h"
/* --- Registry ----------------------------------------------------------- */
/*[clinic input]
_codecs.register
search_function: object
/
Register a codec search function.
Search functions are expected to take one argument, the encoding name in
all lower case letters, and either return None, or a tuple of functions
(encoder, decoder, stream_reader, stream_writer) (or a CodecInfo object).
[clinic start generated code]*/
static PyObject *
_codecs_register(PyObject *module, PyObject *search_function)
/*[clinic end generated code: output=d1bf21e99db7d6d3 input=369578467955cae4]*/
{
if (PyCodec_Register(search_function))
return NULL;
Py_RETURN_NONE;
}
/*[clinic input]
_codecs.unregister
search_function: object
/
Unregister a codec search function and clear the registry's cache.
If the search function is not registered, do nothing.
[clinic start generated code]*/
static PyObject *
_codecs_unregister(PyObject *module, PyObject *search_function)
/*[clinic end generated code: output=1f0edee9cf246399 input=dd7c004c652d345e]*/
{
if (PyCodec_Unregister(search_function) < 0) {
return NULL;
}
Py_RETURN_NONE;
}
/*[clinic input]
_codecs.lookup
encoding: str
/
Looks up a codec tuple in the Python codec registry and returns a CodecInfo object.
[clinic start generated code]*/
static PyObject *
_codecs_lookup_impl(PyObject *module, const char *encoding)
/*[clinic end generated code: output=9f0afa572080c36d input=3c572c0db3febe9c]*/
{
return _PyCodec_Lookup(encoding);
}
/*[clinic input]
_codecs.encode
obj: object
encoding: str(c_default="NULL") = "utf-8"
errors: str(c_default="NULL") = "strict"
Encodes obj using the codec registered for encoding.
The default encoding is 'utf-8'. errors may be given to set a
different error handling scheme. Default is 'strict' meaning that encoding
errors raise a ValueError. Other possible values are 'ignore', 'replace'
and 'backslashreplace' as well as any other name registered with
codecs.register_error that can handle ValueErrors.
[clinic start generated code]*/
static PyObject *
_codecs_encode_impl(PyObject *module, PyObject *obj, const char *encoding,
const char *errors)
/*[clinic end generated code: output=385148eb9a067c86 input=cd5b685040ff61f0]*/
{
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
/* Encode via the codec registry */
return PyCodec_Encode(obj, encoding, errors);
}
/*[clinic input]
_codecs.decode
obj: object
encoding: str(c_default="NULL") = "utf-8"
errors: str(c_default="NULL") = "strict"
Decodes obj using the codec registered for encoding.
Default encoding is 'utf-8'. errors may be given to set a
different error handling scheme. Default is 'strict' meaning that encoding
errors raise a ValueError. Other possible values are 'ignore', 'replace'
and 'backslashreplace' as well as any other name registered with
codecs.register_error that can handle ValueErrors.
[clinic start generated code]*/
static PyObject *
_codecs_decode_impl(PyObject *module, PyObject *obj, const char *encoding,
const char *errors)
/*[clinic end generated code: output=679882417dc3a0bd input=7702c0cc2fa1add6]*/
{
if (encoding == NULL)
encoding = PyUnicode_GetDefaultEncoding();
/* Decode via the codec registry */
return PyCodec_Decode(obj, encoding, errors);
}
/* --- Helpers ------------------------------------------------------------ */
static
PyObject *codec_tuple(PyObject *decoded,
Py_ssize_t len)
{
if (decoded == NULL)
return NULL;
return Py_BuildValue("Nn", decoded, len);
}
/* --- String codecs ------------------------------------------------------ */
/*[clinic input]
_codecs.escape_decode
data: Py_buffer(accept={str, buffer})
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_escape_decode_impl(PyObject *module, Py_buffer *data,
const char *errors)
/*[clinic end generated code: output=505200ba8056979a input=77298a561c90bd82]*/
{
PyObject *decoded = PyBytes_DecodeEscape(data->buf, data->len,
errors, 0, NULL);
return codec_tuple(decoded, data->len);
}
/*[clinic input]
_codecs.escape_encode
data: object(subclass_of='&PyBytes_Type')
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_escape_encode_impl(PyObject *module, PyObject *data,
const char *errors)
/*[clinic end generated code: output=4af1d477834bab34 input=8f4b144799a94245]*/
{
Py_ssize_t size;
Py_ssize_t newsize;
PyObject *v;
size = PyBytes_GET_SIZE(data);
if (size > PY_SSIZE_T_MAX / 4) {
PyErr_SetString(PyExc_OverflowError,
"string is too large to encode");
return NULL;
}
newsize = 4*size;
v = PyBytes_FromStringAndSize(NULL, newsize);
if (v == NULL) {
return NULL;
}
else {
Py_ssize_t i;
char c;
char *p = PyBytes_AS_STRING(v);
for (i = 0; i < size; i++) {
/* There's at least enough room for a hex escape */
assert(newsize - (p - PyBytes_AS_STRING(v)) >= 4);
c = PyBytes_AS_STRING(data)[i];
if (c == '\'' || c == '\\')
*p++ = '\\', *p++ = c;
else if (c == '\t')
*p++ = '\\', *p++ = 't';
else if (c == '\n')
*p++ = '\\', *p++ = 'n';
else if (c == '\r')
*p++ = '\\', *p++ = 'r';
else if (c < ' ' || c >= 0x7f) {
*p++ = '\\';
*p++ = 'x';
*p++ = Py_hexdigits[(c & 0xf0) >> 4];
*p++ = Py_hexdigits[c & 0xf];
}
else
*p++ = c;
}
*p = '\0';
if (_PyBytes_Resize(&v, (p - PyBytes_AS_STRING(v)))) {
return NULL;
}
}
return codec_tuple(v, size);
}
/* --- Decoder ------------------------------------------------------------ */
/*[clinic input]
_codecs.utf_7_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_7_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=0cd3a944a32a4089 input=dbf8c8998102dc7d]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF7Stateful(data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_8_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_8_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=10f74dec8d9bb8bf input=ca06bc8a9c970e25]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF8Stateful(data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_16_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=783b442abcbcc2d0 input=5b0f52071ba6cadc]*/
{
int byteorder = 0;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF16Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_16_le_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_le_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=899b9e6364379dcd input=115bd8c7b783d0bf]*/
{
int byteorder = -1;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF16Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_16_be_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_be_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=49f6465ea07669c8 input=63131422b01f9cb4]*/
{
int byteorder = 1;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF16Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/* This non-standard version also provides access to the byteorder
parameter of the builtin UTF-16 codec.
It returns a tuple (unicode, bytesread, byteorder) with byteorder
being the value in effect at the end of data.
*/
/*[clinic input]
_codecs.utf_16_ex_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
byteorder: int = 0
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_ex_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int byteorder, int final)
/*[clinic end generated code: output=0f385f251ecc1988 input=f368a51cf384bf4c]*/
{
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF16Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
if (decoded == NULL)
return NULL;
return Py_BuildValue("Nni", decoded, consumed, byteorder);
}
/*[clinic input]
_codecs.utf_32_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=2fc961807f7b145f input=fcdf3658c5e9b5f3]*/
{
int byteorder = 0;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF32Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_32_le_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_le_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=ec8f46b67a94f3e6 input=12220556e885f817]*/
{
int byteorder = -1;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF32Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.utf_32_be_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_be_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=ff82bae862c92c4e input=2bc669b4781598db]*/
{
int byteorder = 1;
/* This is overwritten unless final is true. */
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF32Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/* This non-standard version also provides access to the byteorder
parameter of the builtin UTF-32 codec.
It returns a tuple (unicode, bytesread, byteorder) with byteorder
being the value in effect at the end of data.
*/
/*[clinic input]
_codecs.utf_32_ex_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
byteorder: int = 0
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_ex_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int byteorder, int final)
/*[clinic end generated code: output=6bfb177dceaf4848 input=4a2323d0013620df]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeUTF32Stateful(data->buf, data->len,
errors, &byteorder,
final ? NULL : &consumed);
if (decoded == NULL)
return NULL;
return Py_BuildValue("Nni", decoded, consumed, byteorder);
}
/*[clinic input]
_codecs.unicode_escape_decode
data: Py_buffer(accept={str, buffer})
errors: str(accept={str, NoneType}) = None
final: bool = True
/
[clinic start generated code]*/
static PyObject *
_codecs_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=b284f97b12c635ee input=15019f081ffe272b]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = _PyUnicode_DecodeUnicodeEscapeStateful(data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.raw_unicode_escape_decode
data: Py_buffer(accept={str, buffer})
errors: str(accept={str, NoneType}) = None
final: bool = True
/
[clinic start generated code]*/
static PyObject *
_codecs_raw_unicode_escape_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=11dbd96301e2879e input=b93f823aa8c343ad]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = _PyUnicode_DecodeRawUnicodeEscapeStateful(data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.latin_1_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_latin_1_decode_impl(PyObject *module, Py_buffer *data,
const char *errors)
/*[clinic end generated code: output=07f3dfa3f72c7d8f input=76ca58fd6dcd08c7]*/
{
PyObject *decoded = PyUnicode_DecodeLatin1(data->buf, data->len, errors);
return codec_tuple(decoded, data->len);
}
/*[clinic input]
_codecs.ascii_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_ascii_decode_impl(PyObject *module, Py_buffer *data,
const char *errors)
/*[clinic end generated code: output=2627d72058d42429 input=e428a267a04b4481]*/
{
PyObject *decoded = PyUnicode_DecodeASCII(data->buf, data->len, errors);
return codec_tuple(decoded, data->len);
}
/*[clinic input]
_codecs.charmap_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
mapping: object = None
/
[clinic start generated code]*/
static PyObject *
_codecs_charmap_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, PyObject *mapping)
/*[clinic end generated code: output=2c335b09778cf895 input=15b69df43458eb40]*/
{
PyObject *decoded;
if (mapping == Py_None)
mapping = NULL;
decoded = PyUnicode_DecodeCharmap(data->buf, data->len, mapping, errors);
return codec_tuple(decoded, data->len);
}
#ifdef MS_WINDOWS
/*[clinic input]
_codecs.mbcs_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_mbcs_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=39b65b8598938c4b input=f144ad1ed6d8f5a6]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeMBCSStateful(data->buf, data->len,
errors, final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.oem_decode
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_oem_decode_impl(PyObject *module, Py_buffer *data,
const char *errors, int final)
/*[clinic end generated code: output=da1617612f3fcad8 input=629bf87376d211b4]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeCodePageStateful(CP_OEMCP,
data->buf, data->len, errors, final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
/*[clinic input]
_codecs.code_page_decode
codepage: int
data: Py_buffer
errors: str(accept={str, NoneType}) = None
final: bool = False
/
[clinic start generated code]*/
static PyObject *
_codecs_code_page_decode_impl(PyObject *module, int codepage,
Py_buffer *data, const char *errors, int final)
/*[clinic end generated code: output=53008ea967da3fff input=6a32589b0658c277]*/
{
Py_ssize_t consumed = data->len;
PyObject *decoded = PyUnicode_DecodeCodePageStateful(codepage,
data->buf, data->len,
errors,
final ? NULL : &consumed);
return codec_tuple(decoded, consumed);
}
#endif /* MS_WINDOWS */
/* --- Encoder ------------------------------------------------------------ */
/*[clinic input]
_codecs.readbuffer_encode
data: Py_buffer(accept={str, buffer})
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_readbuffer_encode_impl(PyObject *module, Py_buffer *data,
const char *errors)
/*[clinic end generated code: output=c645ea7cdb3d6e86 input=aa10cfdf252455c5]*/
{
PyObject *result = PyBytes_FromStringAndSize(data->buf, data->len);
return codec_tuple(result, data->len);
}
/*[clinic input]
_codecs.utf_7_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_7_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=0feda21ffc921bc8 input=2546dbbb3fa53114]*/
{
return codec_tuple(_PyUnicode_EncodeUTF7(str, 0, 0, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.utf_8_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_8_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=02bf47332b9c796c input=a3e71ae01c3f93f3]*/
{
return codec_tuple(_PyUnicode_AsUTF8String(str, errors),
PyUnicode_GET_LENGTH(str));
}
/* This version provides access to the byteorder parameter of the
builtin UTF-16 codecs as optional third argument. It defaults to 0
which means: use the native byte order and prepend the data with a
BOM mark.
*/
/*[clinic input]
_codecs.utf_16_encode
str: unicode
errors: str(accept={str, NoneType}) = None
byteorder: int = 0
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_encode_impl(PyObject *module, PyObject *str,
const char *errors, int byteorder)
/*[clinic end generated code: output=c654e13efa2e64e4 input=68cdc2eb8338555d]*/
{
return codec_tuple(_PyUnicode_EncodeUTF16(str, errors, byteorder),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.utf_16_le_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_le_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=431b01e55f2d4995 input=83d042706eed6798]*/
{
return codec_tuple(_PyUnicode_EncodeUTF16(str, errors, -1),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.utf_16_be_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_16_be_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=96886a6fd54dcae3 input=6f1e9e623b03071b]*/
{
return codec_tuple(_PyUnicode_EncodeUTF16(str, errors, +1),
PyUnicode_GET_LENGTH(str));
}
/* This version provides access to the byteorder parameter of the
builtin UTF-32 codecs as optional third argument. It defaults to 0
which means: use the native byte order and prepend the data with a
BOM mark.
*/
/*[clinic input]
_codecs.utf_32_encode
str: unicode
errors: str(accept={str, NoneType}) = None
byteorder: int = 0
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_encode_impl(PyObject *module, PyObject *str,
const char *errors, int byteorder)
/*[clinic end generated code: output=5c760da0c09a8b83 input=8ec4c64d983bc52b]*/
{
return codec_tuple(_PyUnicode_EncodeUTF32(str, errors, byteorder),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.utf_32_le_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_le_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=b65cd176de8e36d6 input=f0918d41de3eb1b1]*/
{
return codec_tuple(_PyUnicode_EncodeUTF32(str, errors, -1),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.utf_32_be_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_utf_32_be_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=1d9e71a9358709e9 input=967a99a95748b557]*/
{
return codec_tuple(_PyUnicode_EncodeUTF32(str, errors, +1),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.unicode_escape_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_unicode_escape_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=66271b30bc4f7a3c input=8c4de07597054e33]*/
{
return codec_tuple(PyUnicode_AsUnicodeEscapeString(str),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.raw_unicode_escape_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_raw_unicode_escape_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=a66a806ed01c830a input=4aa6f280d78e4574]*/
{
return codec_tuple(PyUnicode_AsRawUnicodeEscapeString(str),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.latin_1_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_latin_1_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=2c28c83a27884e08 input=ec3ef74bf85c5c5d]*/
{
return codec_tuple(_PyUnicode_AsLatin1String(str, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.ascii_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_ascii_encode_impl(PyObject *module, PyObject *str,
const char *errors)
/*[clinic end generated code: output=b5e035182d33befc input=93e6e602838bd3de]*/
{
return codec_tuple(_PyUnicode_AsASCIIString(str, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.charmap_encode
str: unicode
errors: str(accept={str, NoneType}) = None
mapping: object = None
/
[clinic start generated code]*/
static PyObject *
_codecs_charmap_encode_impl(PyObject *module, PyObject *str,
const char *errors, PyObject *mapping)
/*[clinic end generated code: output=047476f48495a9e9 input=2a98feae73dadce8]*/
{
if (mapping == Py_None)
mapping = NULL;
return codec_tuple(_PyUnicode_EncodeCharmap(str, mapping, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.charmap_build
map: unicode
/
[clinic start generated code]*/
static PyObject *
_codecs_charmap_build_impl(PyObject *module, PyObject *map)
/*[clinic end generated code: output=bb073c27031db9ac input=d91a91d1717dbc6d]*/
{
return PyUnicode_BuildEncodingMap(map);
}
#ifdef MS_WINDOWS
/*[clinic input]
_codecs.mbcs_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_mbcs_encode_impl(PyObject *module, PyObject *str, const char *errors)
/*[clinic end generated code: output=76e2e170c966c080 input=2e932fc289ea5a5b]*/
{
return codec_tuple(PyUnicode_EncodeCodePage(CP_ACP, str, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.oem_encode
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_oem_encode_impl(PyObject *module, PyObject *str, const char *errors)
/*[clinic end generated code: output=65d5982c737de649 input=9eac86dc21eb14f2]*/
{
return codec_tuple(PyUnicode_EncodeCodePage(CP_OEMCP, str, errors),
PyUnicode_GET_LENGTH(str));
}
/*[clinic input]
_codecs.code_page_encode
code_page: int
str: unicode
errors: str(accept={str, NoneType}) = None
/
[clinic start generated code]*/
static PyObject *
_codecs_code_page_encode_impl(PyObject *module, int code_page, PyObject *str,
const char *errors)
/*[clinic end generated code: output=45673f6085657a9e input=7d18a33bc8cd0f94]*/
{
return codec_tuple(PyUnicode_EncodeCodePage(code_page, str, errors),
PyUnicode_GET_LENGTH(str));
}
#endif /* MS_WINDOWS */
/* --- Error handler registry --------------------------------------------- */
/*[clinic input]
_codecs.register_error
errors: str
handler: object
/
Register the specified error handler under the name errors.
handler must be a callable object, that will be called with an exception
instance containing information about the location of the encoding/decoding
error and must return a (replacement, new position) tuple.
[clinic start generated code]*/
static PyObject *
_codecs_register_error_impl(PyObject *module, const char *errors,
PyObject *handler)
/*[clinic end generated code: output=fa2f7d1879b3067d input=5e6709203c2e33fe]*/
{
if (PyCodec_RegisterError(errors, handler))
return NULL;
Py_RETURN_NONE;
}
/*[clinic input]
_codecs.lookup_error
name: str
/
lookup_error(errors) -> handler
Return the error handler for the specified error handling name or raise a
LookupError, if no handler exists under this name.
[clinic start generated code]*/
static PyObject *
_codecs_lookup_error_impl(PyObject *module, const char *name)
/*[clinic end generated code: output=087f05dc0c9a98cc input=4775dd65e6235aba]*/
{
return PyCodec_LookupError(name);
}
/* --- Module API --------------------------------------------------------- */
static PyMethodDef _codecs_functions[] = {
_CODECS_REGISTER_METHODDEF
_CODECS_UNREGISTER_METHODDEF
_CODECS_LOOKUP_METHODDEF
_CODECS_ENCODE_METHODDEF
_CODECS_DECODE_METHODDEF
_CODECS_ESCAPE_ENCODE_METHODDEF
_CODECS_ESCAPE_DECODE_METHODDEF
_CODECS_UTF_8_ENCODE_METHODDEF
_CODECS_UTF_8_DECODE_METHODDEF
_CODECS_UTF_7_ENCODE_METHODDEF
_CODECS_UTF_7_DECODE_METHODDEF
_CODECS_UTF_16_ENCODE_METHODDEF
_CODECS_UTF_16_LE_ENCODE_METHODDEF
_CODECS_UTF_16_BE_ENCODE_METHODDEF
_CODECS_UTF_16_DECODE_METHODDEF
_CODECS_UTF_16_LE_DECODE_METHODDEF
_CODECS_UTF_16_BE_DECODE_METHODDEF
_CODECS_UTF_16_EX_DECODE_METHODDEF
_CODECS_UTF_32_ENCODE_METHODDEF
_CODECS_UTF_32_LE_ENCODE_METHODDEF
_CODECS_UTF_32_BE_ENCODE_METHODDEF
_CODECS_UTF_32_DECODE_METHODDEF
_CODECS_UTF_32_LE_DECODE_METHODDEF
_CODECS_UTF_32_BE_DECODE_METHODDEF
_CODECS_UTF_32_EX_DECODE_METHODDEF
_CODECS_UNICODE_ESCAPE_ENCODE_METHODDEF
_CODECS_UNICODE_ESCAPE_DECODE_METHODDEF
_CODECS_RAW_UNICODE_ESCAPE_ENCODE_METHODDEF
_CODECS_RAW_UNICODE_ESCAPE_DECODE_METHODDEF
_CODECS_LATIN_1_ENCODE_METHODDEF
_CODECS_LATIN_1_DECODE_METHODDEF
_CODECS_ASCII_ENCODE_METHODDEF
_CODECS_ASCII_DECODE_METHODDEF
_CODECS_CHARMAP_ENCODE_METHODDEF
_CODECS_CHARMAP_DECODE_METHODDEF
_CODECS_CHARMAP_BUILD_METHODDEF
_CODECS_READBUFFER_ENCODE_METHODDEF
_CODECS_MBCS_ENCODE_METHODDEF
_CODECS_MBCS_DECODE_METHODDEF
_CODECS_OEM_ENCODE_METHODDEF
_CODECS_OEM_DECODE_METHODDEF
_CODECS_CODE_PAGE_ENCODE_METHODDEF
_CODECS_CODE_PAGE_DECODE_METHODDEF
_CODECS_REGISTER_ERROR_METHODDEF
_CODECS_LOOKUP_ERROR_METHODDEF
{NULL, NULL} /* sentinel */
};
static PyModuleDef_Slot _codecs_slots[] = {
{Py_mod_multiple_interpreters, Py_MOD_PER_INTERPRETER_GIL_SUPPORTED},
{Py_mod_gil, Py_MOD_GIL_NOT_USED},
{0, NULL}
};
static struct PyModuleDef codecsmodule = {
PyModuleDef_HEAD_INIT,
"_codecs",
NULL,
0,
_codecs_functions,
_codecs_slots,
NULL,
NULL,
NULL
};
PyMODINIT_FUNC
PyInit__codecs(void)
{
return PyModuleDef_Init(&codecsmodule);
}
|