cpython.git - https://github.com/python/cpython.git

diff options

author	Jason R. Coombs <jaraco@jaraco.com>	2019-09-10 14:58:29 (GMT)
committer	GitHub <noreply@github.com>	2019-09-10 14:58:29 (GMT)
commit	97c2f68a4c0bf4e69a1e769928d7928fab73a666 (patch)
tree	deec87892efb21a3f44f270df94c94500d907a85 /Python/pythonrun.c
parent	313f80192a7396ea3e5ab107175afe4c5a017ab8 (diff)
download	cpython-97c2f68a4c0bf4e69a1e769928d7928fab73a666.zip cpython-97c2f68a4c0bf4e69a1e769928d7928fab73a666.tar.gz cpython-97c2f68a4c0bf4e69a1e769928d7928fab73a666.tar.bz2

[3.8] bpo-38086: Sync importlib.metadata with importlib_metadata 0.21. (GH-15840) (#15861)

https://gitlab.com/python-devs/importlib_metadata/-/tags/0.21. (cherry picked from commit 17499d82702432955d8e442a1871ff276ca64bc5) Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>

Diffstat (limited to 'Python/pythonrun.c')

0 files changed, 0 insertions, 0 deletions

id='n127' href='#n127'>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 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554

/* ------------------------------------------------------------------------

   Python Codec Registry and support functions

Written by Marc-Andre Lemburg (mal@lemburg.com).

Copyright (c) Corporation for National Research Initiatives.

   ------------------------------------------------------------------------ */

#include "Python.h"
#include "ucnhash.h"
#include <ctype.h>

const char *Py_hexdigits = "0123456789abcdef";

/* --- Codec Registry ----------------------------------------------------- */

/* Import the standard encodings package which will register the first
   codec search function.

   This is done in a lazy way so that the Unicode implementation does
   not downgrade startup time of scripts not needing it.

   ImportErrors are silently ignored by this function. Only one try is
   made.

*/

static int _PyCodecRegistry_Init(void); /* Forward */

int PyCodec_Register(PyObject *search_function)
{
    PyInterpreterState *interp = PyThreadState_GET()->interp;
    if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
        goto onError;
    if (search_function == NULL) {
        PyErr_BadArgument();
        goto onError;
    }
    if (!PyCallable_Check(search_function)) {
        PyErr_SetString(PyExc_TypeError, "argument must be callable");
        goto onError;
    }
    return PyList_Append(interp->codec_search_path, search_function);

 onError:
    return -1;
}

/* Convert a string to a normalized Python string: all characters are
   converted to lower case, spaces are replaced with underscores. */

static
PyObject *normalizestring(const char *string)
{
    size_t i;
    size_t len = strlen(string);
    char *p;
    PyObject *v;

    if (len > PY_SSIZE_T_MAX) {
        PyErr_SetString(PyExc_OverflowError, "string is too large");
        return NULL;
    }

    p = PyMem_Malloc(len + 1);
    if (p == NULL)
        return PyErr_NoMemory();
    for (i = 0; i < len; i++) {
        char ch = string[i];
        if (ch == ' ')
            ch = '-';
        else
            ch = Py_TOLOWER(Py_CHARMASK(ch));
        p[i] = ch;
    }
    p[i] = '\0';
    v = PyUnicode_FromString(p);
    if (v == NULL)
        return NULL;
    PyMem_Free(p);
    return v;
}

/* Lookup the given encoding and return a tuple providing the codec
   facilities.

   The encoding string is looked up converted to all lower-case
   characters. This makes encodings looked up through this mechanism
   effectively case-insensitive.

   If no codec is found, a LookupError is set and NULL returned.

   As side effect, this tries to load the encodings package, if not
   yet done. This is part of the lazy load strategy for the encodings
   package.

*/

PyObject *_PyCodec_Lookup(const char *encoding)
{
    PyInterpreterState *interp;
    PyObject *result, *args = NULL, *v;
    Py_ssize_t i, len;

    if (encoding == NULL) {
        PyErr_BadArgument();
        goto onError;
    }

    interp = PyThreadState_GET()->interp;
    if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
        goto onError;

    /* Convert the encoding to a normalized Python string: all
       characters are converted to lower case, spaces and hyphens are
       replaced with underscores. */
    v = normalizestring(encoding);
    if (v == NULL)
        goto onError;
    PyUnicode_InternInPlace(&v);

    /* First, try to lookup the name in the registry dictionary */
    result = PyDict_GetItem(interp->codec_search_cache, v);
    if (result != NULL) {
        Py_INCREF(result);
        Py_DECREF(v);
        return result;
    }

    /* Next, scan the search functions in order of registration */
    args = PyTuple_New(1);
    if (args == NULL)
        goto onError;
    PyTuple_SET_ITEM(args,0,v);

    len = PyList_Size(interp->codec_search_path);
    if (len < 0)
        goto onError;
    if (len == 0) {
        PyErr_SetString(PyExc_LookupError,
                        "no codec search functions registered: "
                        "can't find encoding");
        goto onError;
    }

    for (i = 0; i < len; i++) {
        PyObject *func;

        func = PyList_GetItem(interp->codec_search_path, i);
        if (func == NULL)
            goto onError;
        result = PyEval_CallObject(func, args);
        if (result == NULL)
            goto onError;
        if (result == Py_None) {
            Py_DECREF(result);
            continue;
        }
        if (!PyTuple_Check(result) || PyTuple_GET_SIZE(result) != 4) {
            PyErr_SetString(PyExc_TypeError,
                            "codec search functions must return 4-tuples");
            Py_DECREF(result);
            goto onError;
        }
        break;
    }
    if (i == len) {
        /* XXX Perhaps we should cache misses too ? */
        PyErr_Format(PyExc_LookupError,
                     "unknown encoding: %s", encoding);
        goto onError;
    }

    /* Cache and return the result */
    if (PyDict_SetItem(interp->codec_search_cache, v, result) < 0) {
        Py_DECREF(result);
        goto onError;
    }
    Py_DECREF(args);
    return result;

 onError:
    Py_XDECREF(args);
    return NULL;
}

int _PyCodec_Forget(const char *encoding)
{
    PyInterpreterState *interp;
    PyObject *v;
    int result;

    interp = PyThreadState_GET()->interp;
    if (interp->codec_search_path == NULL) {
        return -1;
    }

    /* Convert the encoding to a normalized Python string: all
       characters are converted to lower case, spaces and hyphens are
       replaced with underscores. */
    v = normalizestring(encoding);
    if (v == NULL) {
        return -1;
    }

    /* Drop the named codec from the internal cache */
    result = PyDict_DelItem(interp->codec_search_cache, v);
    Py_DECREF(v);

    return result;
}

/* Codec registry encoding check API. */

int PyCodec_KnownEncoding(const char *encoding)
{
    PyObject *codecs;

    codecs = _PyCodec_Lookup(encoding);
    if (!codecs) {
        PyErr_Clear();
        return 0;
    }
    else {
        Py_DECREF(codecs);
        return 1;
    }
}

static
PyObject *args_tuple(PyObject *object,
                     const char *errors)
{
    PyObject *args;

    args = PyTuple_New(1 + (errors != NULL));
    if (args == NULL)
        return NULL;
    Py_INCREF(object);
    PyTuple_SET_ITEM(args,0,object);
    if (errors) {
        PyObject *v;

        v = PyUnicode_FromString(errors);
        if (v == NULL) {
            Py_DECREF(args);
            return NULL;
        }
        PyTuple_SET_ITEM(args, 1, v);
    }
    return args;
}

/* Helper function to get a codec item */

static
PyObject *codec_getitem(const char *encoding, int index)
{
    PyObject *codecs;
    PyObject *v;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
        return NULL;
    v = PyTuple_GET_ITEM(codecs, index);
    Py_DECREF(codecs);
    Py_INCREF(v);
    return v;
}

/* Helper functions to create an incremental codec. */
static
PyObject *codec_makeincrementalcodec(PyObject *codec_info,
                                     const char *errors,
                                     const char *attrname)
{
    PyObject *ret, *inccodec;

    inccodec = PyObject_GetAttrString(codec_info, attrname);
    if (inccodec == NULL)
        return NULL;
    if (errors)
        ret = PyObject_CallFunction(inccodec, "s", errors);
    else
        ret = PyObject_CallFunction(inccodec, NULL);
    Py_DECREF(inccodec);
    return ret;
}

static
PyObject *codec_getincrementalcodec(const char *encoding,
                                    const char *errors,
                                    const char *attrname)
{
    PyObject *codec_info, *ret;

    codec_info = _PyCodec_Lookup(encoding);
    if (codec_info == NULL)
        return NULL;
    ret = codec_makeincrementalcodec(codec_info, errors, attrname);
    Py_DECREF(codec_info);
    return ret;
}

/* Helper function to create a stream codec. */

static
PyObject *codec_getstreamcodec(const char *encoding,
                               PyObject *stream,
                               const char *errors,
                               const int index)
{
    PyObject *codecs, *streamcodec, *codeccls;

    codecs = _PyCodec_Lookup(encoding);
    if (codecs == NULL)
        return NULL;

    codeccls = PyTuple_GET_ITEM(codecs, index);
    if (errors != NULL)
        streamcodec = PyObject_CallFunction(codeccls, "Os", stream, errors);
    else
        streamcodec = PyObject_CallFunction(codeccls, "O", stream);
    Py_DECREF(codecs);
    return streamcodec;
}

/* Helpers to work with the result of _PyCodec_Lookup

 */
PyObject *_PyCodecInfo_GetIncrementalDecoder(PyObject *codec_info,
                                             const char *errors)
{
    return codec_makeincrementalcodec(codec_info, errors,
                                      "incrementaldecoder");
}

PyObject *_PyCodecInfo_GetIncrementalEncoder(PyObject *codec_info,
                                             const char *errors)
{
    return codec_makeincrementalcodec(codec_info, errors,
                                      "incrementalencoder");
}


/* Convenience APIs to query the Codec registry.

   All APIs return a codec object with incremented refcount.

 */

PyObject *PyCodec_Encoder(const char *encoding)
{
    return codec_getitem(encoding, 0);
}

PyObject *PyCodec_Decoder(const char *encoding)
{
    return codec_getitem(encoding, 1);
}

PyObject *PyCodec_IncrementalEncoder(const char *encoding,
                                     const char *errors)
{
    return codec_getincrementalcodec(encoding, errors, "incrementalencoder");
}

PyObject *PyCodec_IncrementalDecoder(const char *encoding,
                                     const char *errors)
{
    return codec_getincrementalcodec(encoding, errors, "incrementaldecoder");
}

PyObject *PyCodec_StreamReader(const char *encoding,
                               PyObject *stream,
                               const char *errors)
{
    return codec_getstreamcodec(encoding, stream, errors, 2);
}

PyObject *PyCodec_StreamWriter(const char *encoding,
                               PyObject *stream,
                               const char *errors)
{
    return codec_getstreamcodec(encoding, stream, errors, 3);
}

/* Helper that tries to ensure the reported exception chain indicates the
 * codec that was invoked to trigger the failure without changing the type
 * of the exception raised.
 */
static void
wrap_codec_error(const char *operation,
                 const char *encoding)
{
    /* TrySetFromCause will replace the active exception with a suitably
     * updated clone if it can, otherwise it will leave the original
     * exception alone.
     */
    _PyErr_TrySetFromCause("%s with '%s' codec failed",
                           operation, encoding);
}

/* Encode an object (e.g. an Unicode object) using the given encoding
   and return the resulting encoded object (usually a Python string).

   errors is passed to the encoder factory as argument if non-NULL. */

static PyObject *
_PyCodec_EncodeInternal(PyObject *object,
                        PyObject *encoder,
                        const char *encoding,
                        const char *errors)
{
    PyObject *args = NULL, *result = NULL;
    PyObject *v = NULL;

    args = args_tuple(object, errors);
    if (args == NULL)
        goto onError;

    result = PyEval_CallObject(encoder, args);
    if (result == NULL) {
        wrap_codec_error("encoding", encoding);
        goto onError;
    }

    if (!PyTuple_Check(result) ||
        PyTuple_GET_SIZE(result) != 2) {
        PyErr_SetString(PyExc_TypeError,
                        "encoder must return a tuple (object, integer)");
        goto onError;
    }
    v = PyTuple_GET_ITEM(result,0);
    Py_INCREF(v);
    /* We don't check or use the second (integer) entry. */

    Py_DECREF(args);
    Py_DECREF(encoder);
    Py_DECREF(result);
    return v;

 onError:
    Py_XDECREF(result);
    Py_XDECREF(args);
    Py_XDECREF(encoder);
    return NULL;
}

/* Decode an object (usually a Python string) using the given encoding
   and return an equivalent object (e.g. an Unicode object).

   errors is passed to the decoder factory as argument if non-NULL. */

static PyObject *
_PyCodec_DecodeInternal(PyObject *object,
                        PyObject *decoder,
                        const char *encoding,
                        const char *errors)
{
    PyObject *args = NULL, *result = NULL;
    PyObject *v;

    args = args_tuple(object, errors);
    if (args == NULL)
        goto onError;

    result = PyEval_CallObject(decoder,args);
    if (result == NULL) {
        wrap_codec_error("decoding", encoding);
        goto onError;
    }
    if (!PyTuple_Check(result) ||
        PyTuple_GET_SIZE(result) != 2) {
        PyErr_SetString(PyExc_TypeError,
                        "decoder must return a tuple (object,integer)");
        goto onError;
    }
    v = PyTuple_GET_ITEM(result,0);
    Py_INCREF(v);
    /* We don't check or use the second (integer) entry. */

    Py_DECREF(args);
    Py_DECREF(decoder);
    Py_DECREF(result);
    return v;

 onError:
    Py_XDECREF(args);
    Py_XDECREF(decoder);
    Py_XDECREF(result);
    return NULL;
}

/* Generic encoding/decoding API */
PyObject *PyCodec_Encode(PyObject *object,
                         const char *encoding,
                         const char *errors)
{
    PyObject *encoder;

    encoder = PyCodec_Encoder(encoding);
    if (encoder == NULL)
        return NULL;

    return _PyCodec_EncodeInternal(object, encoder, encoding, errors);
}

PyObject *PyCodec_Decode(PyObject *object,
                         const char *encoding,
                         const char *errors)
{
    PyObject *decoder;

    decoder = PyCodec_Decoder(encoding);
    if (decoder == NULL)
        return NULL;

    return _PyCodec_DecodeInternal(object, decoder, encoding, errors);
}

/* Text encoding/decoding API */
PyObject * _PyCodec_LookupTextEncoding(const char *encoding,
                                       const char *alternate_command)
{
    _Py_IDENTIFIER(_is_text_encoding);
    PyObject *codec;
    PyObject *attr;
    int is_text_codec;

    codec = _PyCodec_Lookup(encoding);
    if (codec == NULL)
        return NULL;

    /* Backwards compatibility: assume any raw tuple describes a text
     * encoding, and the same for anything lacking the private
     * attribute.
     */
    if (!PyTuple_CheckExact(codec)) {
        attr = _PyObject_GetAttrId(codec, &PyId__is_text_encoding);
        if (attr == NULL) {
            if (PyErr_ExceptionMatches(PyExc_AttributeError)) {
                PyErr_Clear();
            } else {
                Py_DECREF(codec);
                return NULL;
            }
        } else {
            is_text_codec = PyObject_IsTrue(attr);
            Py_DECREF(attr);
            if (!is_text_codec) {
                Py_DECREF(codec);
                PyErr_Format(PyExc_LookupError,
                             "'%.400s' is not a text encoding; "
                             "use %s to handle arbitrary codecs",
                             encoding, alternate_command);
                return NULL;
            }
        }
    }

    /* This appears to be a valid text encoding */
    return codec;
}


static
PyObject *codec_getitem_checked(const char *encoding,
                                const char *alternate_command,
                                int index)
{
    PyObject *codec;
    PyObject *v;

    codec = _PyCodec_LookupTextEncoding(encoding, alternate_command);
    if (codec == NULL)
        return NULL;

    v = PyTuple_GET_ITEM(codec, index);
    Py_INCREF(v);
    Py_DECREF(codec);
    return v;
}

static PyObject * _PyCodec_TextEncoder(const char *encoding)
{
    return codec_getitem_checked(encoding, "codecs.encode()", 0);
}

static PyObject * _PyCodec_TextDecoder(const char *encoding)
{
    return codec_getitem_checked(encoding, "codecs.decode()", 1);
}

PyObject *_PyCodec_EncodeText(PyObject *object,
                              const char *encoding,
                              const char *errors)
{
    PyObject *encoder;

    encoder = _PyCodec_TextEncoder(encoding);
    if (encoder == NULL)
        return NULL;

    return _PyCodec_EncodeInternal(object, encoder, encoding, errors);
}

PyObject *_PyCodec_DecodeText(PyObject *object,
                              const char *encoding,
                              const char *errors)
{
    PyObject *decoder;

    decoder = _PyCodec_TextDecoder(encoding);
    if (decoder == NULL)
        return NULL;

    return _PyCodec_DecodeInternal(object, decoder, encoding, errors);
}

/* Register the error handling callback function error under the name
   name. This function will be called by the codec when it encounters
   an unencodable characters/undecodable bytes and doesn't know the
   callback name, when name is specified as the error parameter
   in the call to the encode/decode function.
   Return 0 on success, -1 on error */
int PyCodec_RegisterError(const char *name, PyObject *error)
{
    PyInterpreterState *interp = PyThreadState_GET()->interp;
    if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
        return -1;
    if (!PyCallable_Check(error)) {
        PyErr_SetString(PyExc_TypeError, "handler must be callable");
        return -1;
    }
    return PyDict_SetItemString(interp->codec_error_registry,
                                name, error);
}

/* Lookup the error handling callback function registered under the
   name error. As a special case NULL can be passed, in which case
   the error handling callback for strict encoding will be returned. */
PyObject *PyCodec_LookupError(const char *name)
{
    PyObject *handler = NULL;

    PyInterpreterState *interp = PyThreadState_GET()->interp;
    if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
        return NULL;

    if (name==NULL)
        name = "strict";
    handler = PyDict_GetItemString(interp->codec_error_registry, name);
    if (!handler)
        PyErr_Format(PyExc_LookupError, "unknown error handler name '%.400s'", name);
    else
        Py_INCREF(handler);
    return handler;
}

static void wrong_exception_type(PyObject *exc)
{
    _Py_IDENTIFIER(__class__);
    _Py_IDENTIFIER(__name__);
    PyObject *type = _PyObject_GetAttrId(exc, &PyId___class__);
    if (type != NULL) {
        PyObject *name = _PyObject_GetAttrId(type, &PyId___name__);
        Py_DECREF(type);
        if (name != NULL) {
            PyErr_Format(PyExc_TypeError,
                         "don't know how to handle %S in error callback", name);
            Py_DECREF(name);
        }
    }
}

PyObject *PyCodec_StrictErrors(PyObject *exc)
{
    if (PyExceptionInstance_Check(exc))
        PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
    else
        PyErr_SetString(PyExc_TypeError, "codec must pass exception instance");
    return NULL;
}


PyObject *PyCodec_IgnoreErrors(PyObject *exc)
{
    Py_ssize_t end;
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
        if (PyUnicodeDecodeError_GetEnd(exc, &end))
            return NULL;
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
        if (PyUnicodeTranslateError_GetEnd(exc, &end))
            return NULL;
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }
    return Py_BuildValue("(Nn)", PyUnicode_New(0, 0), end);
}


PyObject *PyCodec_ReplaceErrors(PyObject *exc)
{
    Py_ssize_t start, end, i, len;

    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        PyObject *res;
        int kind;
        void *data;
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        len = end - start;
        res = PyUnicode_New(len, '?');
        if (res == NULL)
            return NULL;
        kind = PyUnicode_KIND(res);
        data = PyUnicode_DATA(res);
        for (i = 0; i < len; ++i)
            PyUnicode_WRITE(kind, data, i, '?');
        assert(_PyUnicode_CheckConsistency(res, 1));
        return Py_BuildValue("(Nn)", res, end);
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
        if (PyUnicodeDecodeError_GetEnd(exc, &end))
            return NULL;
        return Py_BuildValue("(Cn)",
                             (int)Py_UNICODE_REPLACEMENT_CHARACTER,
                             end);
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
        PyObject *res;
        int kind;
        void *data;
        if (PyUnicodeTranslateError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeTranslateError_GetEnd(exc, &end))
            return NULL;
        len = end - start;
        res = PyUnicode_New(len, Py_UNICODE_REPLACEMENT_CHARACTER);
        if (res == NULL)
            return NULL;
        kind = PyUnicode_KIND(res);
        data = PyUnicode_DATA(res);
        for (i=0; i < len; i++)
            PyUnicode_WRITE(kind, data, i, Py_UNICODE_REPLACEMENT_CHARACTER);
        assert(_PyUnicode_CheckConsistency(res, 1));
        return Py_BuildValue("(Nn)", res, end);
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }
}

PyObject *PyCodec_XMLCharRefReplaceErrors(PyObject *exc)
{
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        PyObject *restuple;
        PyObject *object;
        Py_ssize_t i;
        Py_ssize_t start;
        Py_ssize_t end;
        PyObject *res;
        unsigned char *outp;
        Py_ssize_t ressize;
        Py_UCS4 ch;
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeEncodeError_GetObject(exc)))
            return NULL;
        if (end - start > PY_SSIZE_T_MAX / (2+7+1))
            end = start + PY_SSIZE_T_MAX / (2+7+1);
        for (i = start, ressize = 0; i < end; ++i) {
            /* object is guaranteed to be "ready" */
            ch = PyUnicode_READ_CHAR(object, i);
            if (ch<10)
                ressize += 2+1+1;
            else if (ch<100)
                ressize += 2+2+1;
            else if (ch<1000)
                ressize += 2+3+1;
            else if (ch<10000)
                ressize += 2+4+1;
            else if (ch<100000)
                ressize += 2+5+1;
            else if (ch<1000000)
                ressize += 2+6+1;
            else
                ressize += 2+7+1;
        }
        /* allocate replacement */
        res = PyUnicode_New(ressize, 127);
        if (res == NULL) {
            Py_DECREF(object);
            return NULL;
        }
        outp = PyUnicode_1BYTE_DATA(res);
        /* generate replacement */
        for (i = start; i < end; ++i) {
            int digits;
            int base;
            ch = PyUnicode_READ_CHAR(object, i);
            *outp++ = '&';
            *outp++ = '#';
            if (ch<10) {
                digits = 1;
                base = 1;
            }
            else if (ch<100) {
                digits = 2;
                base = 10;
            }
            else if (ch<1000) {
                digits = 3;
                base = 100;
            }
            else if (ch<10000) {
                digits = 4;
                base = 1000;
            }
            else if (ch<100000) {
                digits = 5;
                base = 10000;
            }
            else if (ch<1000000) {
                digits = 6;
                base = 100000;
            }
            else {
                digits = 7;
                base = 1000000;
            }
            while (digits-->0) {
                *outp++ = '0' + ch/base;
                ch %= base;
                base /= 10;
            }
            *outp++ = ';';
        }
        assert(_PyUnicode_CheckConsistency(res, 1));
        restuple = Py_BuildValue("(Nn)", res, end);
        Py_DECREF(object);
        return restuple;
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }
}

PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
{
    PyObject *object;
    Py_ssize_t i;
    Py_ssize_t start;
    Py_ssize_t end;
    PyObject *res;
    unsigned char *outp;
    int ressize;
    Py_UCS4 c;

    if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
        unsigned char *p;
        if (PyUnicodeDecodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeDecodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeDecodeError_GetObject(exc)))
            return NULL;
        if (!(p = (unsigned char*)PyBytes_AsString(object))) {
            Py_DECREF(object);
            return NULL;
        }
        res = PyUnicode_New(4 * (end - start), 127);
        if (res == NULL) {
            Py_DECREF(object);
            return NULL;
        }
        outp = PyUnicode_1BYTE_DATA(res);
        for (i = start; i < end; i++, outp += 4) {
            unsigned char c = p[i];
            outp[0] = '\\';
            outp[1] = 'x';
            outp[2] = Py_hexdigits[(c>>4)&0xf];
            outp[3] = Py_hexdigits[c&0xf];
        }

        assert(_PyUnicode_CheckConsistency(res, 1));
        Py_DECREF(object);
        return Py_BuildValue("(Nn)", res, end);
    }
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeEncodeError_GetObject(exc)))
            return NULL;
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
        if (PyUnicodeTranslateError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeTranslateError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeTranslateError_GetObject(exc)))
            return NULL;
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }

    if (end - start > PY_SSIZE_T_MAX / (1+1+8))
        end = start + PY_SSIZE_T_MAX / (1+1+8);
    for (i = start, ressize = 0; i < end; ++i) {
        /* object is guaranteed to be "ready" */
        c = PyUnicode_READ_CHAR(object, i);
        if (c >= 0x10000) {
            ressize += 1+1+8;
        }
        else if (c >= 0x100) {
            ressize += 1+1+4;
        }
        else
            ressize += 1+1+2;
    }
    res = PyUnicode_New(ressize, 127);
    if (res == NULL) {
        Py_DECREF(object);
        return NULL;
    }
    outp = PyUnicode_1BYTE_DATA(res);
    for (i = start; i < end; ++i) {
        c = PyUnicode_READ_CHAR(object, i);
        *outp++ = '\\';
        if (c >= 0x00010000) {
            *outp++ = 'U';
            *outp++ = Py_hexdigits[(c>>28)&0xf];
            *outp++ = Py_hexdigits[(c>>24)&0xf];
            *outp++ = Py_hexdigits[(c>>20)&0xf];
            *outp++ = Py_hexdigits[(c>>16)&0xf];
            *outp++ = Py_hexdigits[(c>>12)&0xf];
            *outp++ = Py_hexdigits[(c>>8)&0xf];
        }
        else if (c >= 0x100) {
            *outp++ = 'u';
            *outp++ = Py_hexdigits[(c>>12)&0xf];
            *outp++ = Py_hexdigits[(c>>8)&0xf];
        }
        else
            *outp++ = 'x';
        *outp++ = Py_hexdigits[(c>>4)&0xf];
        *outp++ = Py_hexdigits[c&0xf];
    }

    assert(_PyUnicode_CheckConsistency(res, 1));
    Py_DECREF(object);
    return Py_BuildValue("(Nn)", res, end);
}

static _PyUnicode_Name_CAPI *ucnhash_CAPI = NULL;
static int ucnhash_initialized = 0;

PyObject *PyCodec_NameReplaceErrors(PyObject *exc)
{
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        PyObject *restuple;
        PyObject *object;
        Py_ssize_t i;
        Py_ssize_t start;
        Py_ssize_t end;
        PyObject *res;
        unsigned char *outp;
        Py_ssize_t ressize;
        int replsize;
        Py_UCS4 c;
        char buffer[256]; /* NAME_MAXLEN */
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeEncodeError_GetObject(exc)))
            return NULL;
        if (!ucnhash_initialized) {
            /* load the unicode data module */
            ucnhash_CAPI = (_PyUnicode_Name_CAPI *)PyCapsule_Import(
                                            PyUnicodeData_CAPSULE_NAME, 1);
            ucnhash_initialized = 1;
        }
        for (i = start, ressize = 0; i < end; ++i) {
            /* object is guaranteed to be "ready" */
            c = PyUnicode_READ_CHAR(object, i);
            if (ucnhash_CAPI &&
                ucnhash_CAPI->getname(NULL, c, buffer, sizeof(buffer), 1)) {
                replsize = 1+1+1+(int)strlen(buffer)+1;
            }
            else if (c >= 0x10000) {
                replsize = 1+1+8;
            }
            else if (c >= 0x100) {
                replsize = 1+1+4;
            }
            else
                replsize = 1+1+2;
            if (ressize > PY_SSIZE_T_MAX - replsize)
                break;
            ressize += replsize;
        }
        end = i;
        res = PyUnicode_New(ressize, 127);
        if (res==NULL)
            return NULL;
        for (i = start, outp = PyUnicode_1BYTE_DATA(res);
            i < end; ++i) {
            c = PyUnicode_READ_CHAR(object, i);
            *outp++ = '\\';
            if (ucnhash_CAPI &&
                ucnhash_CAPI->getname(NULL, c, buffer, sizeof(buffer), 1)) {
                *outp++ = 'N';
                *outp++ = '{';
                strcpy((char *)outp, buffer);
                outp += strlen(buffer);
                *outp++ = '}';
                continue;
            }
            if (c >= 0x00010000) {
                *outp++ = 'U';
                *outp++ = Py_hexdigits[(c>>28)&0xf];
                *outp++ = Py_hexdigits[(c>>24)&0xf];
                *outp++ = Py_hexdigits[(c>>20)&0xf];
                *outp++ = Py_hexdigits[(c>>16)&0xf];
                *outp++ = Py_hexdigits[(c>>12)&0xf];
                *outp++ = Py_hexdigits[(c>>8)&0xf];
            }
            else if (c >= 0x100) {
                *outp++ = 'u';
                *outp++ = Py_hexdigits[(c>>12)&0xf];
                *outp++ = Py_hexdigits[(c>>8)&0xf];
            }
            else
                *outp++ = 'x';
            *outp++ = Py_hexdigits[(c>>4)&0xf];
            *outp++ = Py_hexdigits[c&0xf];
        }

        assert(outp == PyUnicode_1BYTE_DATA(res) + ressize);
        assert(_PyUnicode_CheckConsistency(res, 1));
        restuple = Py_BuildValue("(Nn)", res, end);
        Py_DECREF(object);
        return restuple;
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }
}

#define ENC_UNKNOWN     -1
#define ENC_UTF8        0
#define ENC_UTF16BE     1
#define ENC_UTF16LE     2
#define ENC_UTF32BE     3
#define ENC_UTF32LE     4

static int
get_standard_encoding(const char *encoding, int *bytelength)
{
    if (Py_TOLOWER(encoding[0]) == 'u' &&
        Py_TOLOWER(encoding[1]) == 't' &&
        Py_TOLOWER(encoding[2]) == 'f') {
        encoding += 3;
        if (*encoding == '-' || *encoding == '_' )
            encoding++;
        if (encoding[0] == '8' && encoding[1] == '\0') {
            *bytelength = 3;
            return ENC_UTF8;
        }
        else if (encoding[0] == '1' && encoding[1] == '6') {
            encoding += 2;
            *bytelength = 2;
            if (*encoding == '\0') {
#ifdef WORDS_BIGENDIAN
                return ENC_UTF16BE;
#else
                return ENC_UTF16LE;
#endif
            }
            if (*encoding == '-' || *encoding == '_' )
                encoding++;
            if (Py_TOLOWER(encoding[1]) == 'e' && encoding[2] == '\0') {
                if (Py_TOLOWER(encoding[0]) == 'b')
                    return ENC_UTF16BE;
                if (Py_TOLOWER(encoding[0]) == 'l')
                    return ENC_UTF16LE;
            }
        }
        else if (encoding[0] == '3' && encoding[1] == '2') {
            encoding += 2;
            *bytelength = 4;
            if (*encoding == '\0') {
#ifdef WORDS_BIGENDIAN
                return ENC_UTF32BE;
#else
                return ENC_UTF32LE;
#endif
            }
            if (*encoding == '-' || *encoding == '_' )
                encoding++;
            if (Py_TOLOWER(encoding[1]) == 'e' && encoding[2] == '\0') {
                if (Py_TOLOWER(encoding[0]) == 'b')
                    return ENC_UTF32BE;
                if (Py_TOLOWER(encoding[0]) == 'l')
                    return ENC_UTF32LE;
            }
        }
    }
    else if (strcmp(encoding, "CP_UTF8") == 0) {
        *bytelength = 3;
        return ENC_UTF8;
    }
    return ENC_UNKNOWN;
}

/* This handler is declared static until someone demonstrates
   a need to call it directly. */
static PyObject *
PyCodec_SurrogatePassErrors(PyObject *exc)
{
    PyObject *restuple;
    PyObject *object;
    PyObject *encode;
    char *encoding;
    int code;
    int bytelength;
    Py_ssize_t i;
    Py_ssize_t start;
    Py_ssize_t end;
    PyObject *res;
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        unsigned char *outp;
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeEncodeError_GetObject(exc)))
            return NULL;
        if (!(encode = PyUnicodeEncodeError_GetEncoding(exc))) {
            Py_DECREF(object);
            return NULL;
        }
        if (!(encoding = PyUnicode_AsUTF8(encode))) {
            Py_DECREF(object);
            Py_DECREF(encode);
            return NULL;
        }
        code = get_standard_encoding(encoding, &bytelength);
        Py_DECREF(encode);
        if (code == ENC_UNKNOWN) {
            /* Not supported, fail with original exception */
            PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
            Py_DECREF(object);
            return NULL;
        }

        if (end - start > PY_SSIZE_T_MAX / bytelength)
            end = start + PY_SSIZE_T_MAX / bytelength;
        res = PyBytes_FromStringAndSize(NULL, bytelength*(end-start));
        if (!res) {
            Py_DECREF(object);
            return NULL;
        }
        outp = (unsigned char*)PyBytes_AsString(res);
        for (i = start; i < end; i++) {
            /* object is guaranteed to be "ready" */
            Py_UCS4 ch = PyUnicode_READ_CHAR(object, i);
            if (!Py_UNICODE_IS_SURROGATE(ch)) {
                /* Not a surrogate, fail with original exception */
                PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
                Py_DECREF(res);
                Py_DECREF(object);
                return NULL;
            }
            switch (code) {
            case ENC_UTF8:
                *outp++ = (unsigned char)(0xe0 | (ch >> 12));
                *outp++ = (unsigned char)(0x80 | ((ch >> 6) & 0x3f));
                *outp++ = (unsigned char)(0x80 | (ch & 0x3f));
                break;
            case ENC_UTF16LE:
                *outp++ = (unsigned char) ch;
                *outp++ = (unsigned char)(ch >> 8);
                break;
            case ENC_UTF16BE:
                *outp++ = (unsigned char)(ch >> 8);
                *outp++ = (unsigned char) ch;
                break;
            case ENC_UTF32LE:
                *outp++ = (unsigned char) ch;
                *outp++ = (unsigned char)(ch >> 8);
                *outp++ = (unsigned char)(ch >> 16);
                *outp++ = (unsigned char)(ch >> 24);
                break;
            case ENC_UTF32BE:
                *outp++ = (unsigned char)(ch >> 24);
                *outp++ = (unsigned char)(ch >> 16);
                *outp++ = (unsigned char)(ch >> 8);
                *outp++ = (unsigned char) ch;
                break;
            }
        }
        restuple = Py_BuildValue("(On)", res, end);
        Py_DECREF(res);
        Py_DECREF(object);
        return restuple;
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
        unsigned char *p;
        Py_UCS4 ch = 0;
        if (PyUnicodeDecodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeDecodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeDecodeError_GetObject(exc)))
            return NULL;
        if (!(p = (unsigned char*)PyBytes_AsString(object))) {
            Py_DECREF(object);
            return NULL;
        }
        if (!(encode = PyUnicodeDecodeError_GetEncoding(exc))) {
            Py_DECREF(object);
            return NULL;
        }
        if (!(encoding = PyUnicode_AsUTF8(encode))) {
            Py_DECREF(object);
            Py_DECREF(encode);
            return NULL;
        }
        code = get_standard_encoding(encoding, &bytelength);
        Py_DECREF(encode);
        if (code == ENC_UNKNOWN) {
            /* Not supported, fail with original exception */
            PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
            Py_DECREF(object);
            return NULL;
        }

        /* Try decoding a single surrogate character. If
           there are more, let the codec call us again. */
        p += start;
        if (PyBytes_GET_SIZE(object) - start >= bytelength) {
            switch (code) {
            case ENC_UTF8:
                if ((p[0] & 0xf0) == 0xe0 &&
                    (p[1] & 0xc0) == 0x80 &&
                    (p[2] & 0xc0) == 0x80) {
                    /* it's a three-byte code */
                    ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f);
                }
                break;
            case ENC_UTF16LE:
                ch = p[1] << 8 | p[0];
                break;
            case ENC_UTF16BE:
                ch = p[0] << 8 | p[1];
                break;
            case ENC_UTF32LE:
                ch = (p[3] << 24) | (p[2] << 16) | (p[1] << 8) | p[0];
                break;
            case ENC_UTF32BE:
                ch = (p[0] << 24) | (p[1] << 16) | (p[2] << 8) | p[3];
                break;
            }
        }

        Py_DECREF(object);
        if (!Py_UNICODE_IS_SURROGATE(ch)) {
            /* it's not a surrogate - fail */
            PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
            return NULL;
        }
        res = PyUnicode_FromOrdinal(ch);
        if (res == NULL)
            return NULL;
        return Py_BuildValue("(Nn)", res, start + bytelength);
    }
    else {
        wrong_exception_type(exc);
        return NULL;
    }
}

static PyObject *
PyCodec_SurrogateEscapeErrors(PyObject *exc)
{
    PyObject *restuple;
    PyObject *object;
    Py_ssize_t i;
    Py_ssize_t start;
    Py_ssize_t end;
    PyObject *res;
    if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
        char *outp;
        if (PyUnicodeEncodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeEncodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeEncodeError_GetObject(exc)))
            return NULL;
        res = PyBytes_FromStringAndSize(NULL, end-start);
        if (!res) {
            Py_DECREF(object);
            return NULL;
        }
        outp = PyBytes_AsString(res);
        for (i = start; i < end; i++) {
            /* object is guaranteed to be "ready" */
            Py_UCS4 ch = PyUnicode_READ_CHAR(object, i);
            if (ch < 0xdc80 || ch > 0xdcff) {
                /* Not a UTF-8b surrogate, fail with original exception */
                PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
                Py_DECREF(res);
                Py_DECREF(object);
                return NULL;
            }
            *outp++ = ch - 0xdc00;
        }
        restuple = Py_BuildValue("(On)", res, end);
        Py_DECREF(res);
        Py_DECREF(object);
        return restuple;
    }
    else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
        PyObject *str;
        unsigned char *p;
        Py_UCS2 ch[4]; /* decode up to 4 bad bytes. */
        int consumed = 0;
        if (PyUnicodeDecodeError_GetStart(exc, &start))
            return NULL;
        if (PyUnicodeDecodeError_GetEnd(exc, &end))
            return NULL;
        if (!(object = PyUnicodeDecodeError_GetObject(exc)))
            return NULL;
        if (!(p = (unsigned char*)PyBytes_AsString(object))) {
            Py_DECREF(object);
            return NULL;
        }
        while (consumed < 4 && consumed < end-start) {
            /* Refuse to escape ASCII bytes. */
            if (p[start+consumed] < 128)
                break;
            ch[consumed] = 0xdc00 + p[start+consumed];
            consumed++;
        }
        Py_DECREF(object);
        if (!consumed) {


context:
space:
mode: