GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — cpython/Modules/_json.c at 3.14 · python/cpython Expand file tree/ Copy path_json.cMore file actions 1974 lines (1788 loc) · 61.4 KB / Copy path_json.cFile metadata and controls1974 lines (1788 loc) · 61.4 KB 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 /* JSON accelerator C extensor: _json module. * * It is built as a built-in module (Py_BUILD_CORE_BUILTIN define) on Windows * and as an extension module (Py_BUILD_CORE_MODULE define) on other * platforms. */ #ifndef Py_BUILD_CORE_BUILTIN # define Py_BUILD_CORE_MODULE 1 #endif #include "Python.h" #include "pycore_ceval.h" // _Py_EnterRecursiveCall() #include "pycore_global_strings.h" // _Py_ID() #include "pycore_pyerrors.h" // _PyErr_FormatNote #include "pycore_runtime.h" // _PyRuntime #include "pycore_unicodeobject.h" // _PyUnicode_CheckConsistency() #include <stdbool.h> // bool typedef struct _PyScannerObject { PyObject_HEAD signed char strict; PyObject *object_hook; PyObject *object_pairs_hook; PyObject *parse_float; PyObject *parse_int; PyObject *parse_constant; } PyScannerObject; #define PyScannerObject_CAST(op) ((PyScannerObject *)(op)) static PyMemberDef scanner_members[] = { {"strict", Py_T_BOOL, offsetof(PyScannerObject, strict), Py_READONLY, "strict"}, {"object_hook", _Py_T_OBJECT, offsetof(PyScannerObject, object_hook), Py_READONLY, "object_hook"}, {"object_pairs_hook", _Py_T_OBJECT, offsetof(PyScannerObject, object_pairs_hook), Py_READONLY}, {"parse_float", _Py_T_OBJECT, offsetof(PyScannerObject, parse_float), Py_READONLY, "parse_float"}, {"parse_int", _Py_T_OBJECT, offsetof(PyScannerObject, parse_int), Py_READONLY, "parse_int"}, {"parse_constant", _Py_T_OBJECT, offsetof(PyScannerObject, parse_constant), Py_READONLY, "parse_constant"}, {NULL} }; typedef struct _PyEncoderObject { PyObject_HEAD PyObject *markers; PyObject *defaultfn; PyObject *encoder; PyObject *indent; PyObject *key_separator; PyObject *item_separator; char sort_keys; char skipkeys; int allow_nan; PyCFunction fast_encode; } PyEncoderObject; #define PyEncoderObject_CAST(op) ((PyEncoderObject *)(op)) static PyMemberDef encoder_members[] = { {"markers", _Py_T_OBJECT, offsetof(PyEncoderObject, markers), Py_READONLY, "markers"}, {"default", _Py_T_OBJECT, offsetof(PyEncoderObject, defaultfn), Py_READONLY, "default"}, {"encoder", _Py_T_OBJECT, offsetof(PyEncoderObject, encoder), Py_READONLY, "encoder"}, {"indent", _Py_T_OBJECT, offsetof(PyEncoderObject, indent), Py_READONLY, "indent"}, {"key_separator", _Py_T_OBJECT, offsetof(PyEncoderObject, key_separator), Py_READONLY, "key_separator"}, {"item_separator", _Py_T_OBJECT, offsetof(PyEncoderObject, item_separator), Py_READONLY, "item_separator"}, {"sort_keys", Py_T_BOOL, offsetof(PyEncoderObject, sort_keys), Py_READONLY, "sort_keys"}, {"skipkeys", Py_T_BOOL, offsetof(PyEncoderObject, skipkeys), Py_READONLY, "skipkeys"}, {NULL} }; /* Forward decls */ static PyObject * ascii_escape_unicode(PyObject *pystr); static PyObject * py_encode_basestring_ascii(PyObject* Py_UNUSED(self), PyObject *pystr); static PyObject * scan_once_unicode(PyScannerObject *s, PyObject *memo, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr); static PyObject * _build_rval_index_tuple(PyObject *rval, Py_ssize_t idx); static PyObject * scanner_new(PyTypeObject *type, PyObject *args, PyObject *kwds); static void scanner_dealloc(PyObject *self); static int scanner_clear(PyObject *self); static PyObject * encoder_new(PyTypeObject *type, PyObject *args, PyObject *kwds); static void encoder_dealloc(PyObject *self); static int encoder_clear(PyObject *self); static int encoder_listencode_list(PyEncoderObject *s, PyUnicodeWriter *writer, PyObject *seq, Py_ssize_t indent_level, PyObject *indent_cache); static int encoder_listencode_obj(PyEncoderObject *s, PyUnicodeWriter *writer, PyObject *obj, Py_ssize_t indent_level, PyObject *indent_cache); static int encoder_listencode_dict(PyEncoderObject *s, PyUnicodeWriter *writer, PyObject *dct, Py_ssize_t indent_level, PyObject *indent_cache); static PyObject * _encoded_const(PyObject *obj); static void raise_errmsg(const char *msg, PyObject *s, Py_ssize_t end); static PyObject * encoder_encode_string(PyEncoderObject *s, PyObject *obj); static PyObject * encoder_encode_float(PyEncoderObject *s, PyObject *obj); #define S_CHAR(c) (c >= ' ' && c <= '~' && c != '\\' && c != '"') #define IS_WHITESPACE(c) (((c) == ' ') || ((c) == '\t') || ((c) == '\n') || ((c) == '\r')) static Py_ssize_t ascii_escape_unichar(Py_UCS4 c, unsigned char *output, Py_ssize_t chars) { /* Escape unicode code point c to ASCII escape sequences in char *output. output must have at least 12 bytes unused to accommodate an escaped surrogate pair "\uXXXX\uXXXX" */ output[chars++] = '\\'; switch (c) { case '\\': output[chars++] = c; break; case '"': output[chars++] = c; break; case '\b': output[chars++] = 'b'; break; case '\f': output[chars++] = 'f'; break; case '\n': output[chars++] = 'n'; break; case '\r': output[chars++] = 'r'; break; case '\t': output[chars++] = 't'; break; default: if (c >= 0x10000) { /* UTF-16 surrogate pair */ Py_UCS4 v = Py_UNICODE_HIGH_SURROGATE(c); output[chars++] = 'u'; output[chars++] = Py_hexdigits[(v >> 12) & 0xf]; output[chars++] = Py_hexdigits[(v >> 8) & 0xf]; output[chars++] = Py_hexdigits[(v >> 4) & 0xf]; output[chars++] = Py_hexdigits[(v ) & 0xf]; c = Py_UNICODE_LOW_SURROGATE(c); output[chars++] = '\\'; } output[chars++] = 'u'; output[chars++] = Py_hexdigits[(c >> 12) & 0xf]; output[chars++] = Py_hexdigits[(c >> 8) & 0xf]; output[chars++] = Py_hexdigits[(c >> 4) & 0xf]; output[chars++] = Py_hexdigits[(c ) & 0xf]; } return chars; } static PyObject * ascii_escape_unicode(PyObject *pystr) { /* Take a PyUnicode pystr and return a new ASCII-only escaped PyUnicode */ Py_ssize_t i; Py_ssize_t input_chars; Py_ssize_t output_size; Py_ssize_t chars; PyObject *rval; const void *input; Py_UCS1 *output; int kind; input_chars = PyUnicode_GET_LENGTH(pystr); input = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); /* Compute the output size */ for (i = 0, output_size = 2; i < input_chars; i++) { Py_UCS4 c = PyUnicode_READ(kind, input, i); Py_ssize_t d; if (S_CHAR(c)) { d = 1; } else { switch(c) { case '\\': case '"': case '\b': case '\f': case '\n': case '\r': case '\t': d = 2; break; default: d = c >= 0x10000 ? 12 : 6; } } if (output_size > PY_SSIZE_T_MAX - d) { PyErr_SetString(PyExc_OverflowError, "string is too long to escape"); return NULL; } output_size += d; } rval = PyUnicode_New(output_size, 127); if (rval == NULL) { return NULL; } output = PyUnicode_1BYTE_DATA(rval); chars = 0; output[chars++] = '"'; for (i = 0; i < input_chars; i++) { Py_UCS4 c = PyUnicode_READ(kind, input, i); if (S_CHAR(c)) { output[chars++] = c; } else { chars = ascii_escape_unichar(c, output, chars); } } output[chars++] = '"'; #ifdef Py_DEBUG assert(_PyUnicode_CheckConsistency(rval, 1)); #endif return rval; } static PyObject * escape_unicode(PyObject *pystr) { /* Take a PyUnicode pystr and return a new escaped PyUnicode */ Py_ssize_t i; Py_ssize_t input_chars; Py_ssize_t output_size; Py_ssize_t chars; PyObject *rval; const void *input; int kind; Py_UCS4 maxchar; maxchar = PyUnicode_MAX_CHAR_VALUE(pystr); input_chars = PyUnicode_GET_LENGTH(pystr); input = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); /* Compute the output size */ for (i = 0, output_size = 2; i < input_chars; i++) { Py_UCS4 c = PyUnicode_READ(kind, input, i); Py_ssize_t d; switch (c) { case '\\': case '"': case '\b': case '\f': case '\n': case '\r': case '\t': d = 2; break; default: if (c <= 0x1f) d = 6; else d = 1; } if (output_size > PY_SSIZE_T_MAX - d) { PyErr_SetString(PyExc_OverflowError, "string is too long to escape"); return NULL; } output_size += d; } rval = PyUnicode_New(output_size, maxchar); if (rval == NULL) return NULL; kind = PyUnicode_KIND(rval); #define ENCODE_OUTPUT do { \ chars = 0; \ output[chars++] = '"'; \ for (i = 0; i < input_chars; i++) { \ Py_UCS4 c = PyUnicode_READ(kind, input, i); \ switch (c) { \ case '\\': output[chars++] = '\\'; output[chars++] = c; break; \ case '"': output[chars++] = '\\'; output[chars++] = c; break; \ case '\b': output[chars++] = '\\'; output[chars++] = 'b'; break; \ case '\f': output[chars++] = '\\'; output[chars++] = 'f'; break; \ case '\n': output[chars++] = '\\'; output[chars++] = 'n'; break; \ case '\r': output[chars++] = '\\'; output[chars++] = 'r'; break; \ case '\t': output[chars++] = '\\'; output[chars++] = 't'; break; \ default: \ if (c <= 0x1f) { \ output[chars++] = '\\'; \ output[chars++] = 'u'; \ output[chars++] = '0'; \ output[chars++] = '0'; \ output[chars++] = Py_hexdigits[(c >> 4) & 0xf]; \ output[chars++] = Py_hexdigits[(c ) & 0xf]; \ } else { \ output[chars++] = c; \ } \ } \ } \ output[chars++] = '"'; \ } while (0) if (kind == PyUnicode_1BYTE_KIND) { Py_UCS1 *output = PyUnicode_1BYTE_DATA(rval); ENCODE_OUTPUT; } else if (kind == PyUnicode_2BYTE_KIND) { Py_UCS2 *output = PyUnicode_2BYTE_DATA(rval); ENCODE_OUTPUT; } else { Py_UCS4 *output = PyUnicode_4BYTE_DATA(rval); assert(kind == PyUnicode_4BYTE_KIND); ENCODE_OUTPUT; } #undef ENCODE_OUTPUT #ifdef Py_DEBUG assert(_PyUnicode_CheckConsistency(rval, 1)); #endif return rval; } static void raise_errmsg(const char *msg, PyObject *s, Py_ssize_t end) { /* Use JSONDecodeError exception to raise a nice looking ValueError subclass */ _Py_DECLARE_STR(json_decoder, "json.decoder"); PyObject *JSONDecodeError = PyImport_ImportModuleAttr(&_Py_STR(json_decoder), &_Py_ID(JSONDecodeError)); if (JSONDecodeError == NULL) { return; } PyObject *exc; exc = PyObject_CallFunction(JSONDecodeError, "zOn", msg, s, end); if (exc) { PyErr_SetObject(JSONDecodeError, exc); Py_DECREF(exc); } Py_DECREF(JSONDecodeError); } static void raise_stop_iteration(Py_ssize_t idx) { PyObject *value = PyLong_FromSsize_t(idx); if (value != NULL) { PyErr_SetObject(PyExc_StopIteration, value); Py_DECREF(value); } } static PyObject * _build_rval_index_tuple(PyObject *rval, Py_ssize_t idx) { /* return (rval, idx) tuple, stealing reference to rval */ PyObject *tpl; PyObject *pyidx; /* steal a reference to rval, returns (rval, idx) */ if (rval == NULL) { return NULL; } pyidx = PyLong_FromSsize_t(idx); if (pyidx == NULL) { Py_DECREF(rval); return NULL; } tpl = PyTuple_New(2); if (tpl == NULL) { Py_DECREF(pyidx); Py_DECREF(rval); return NULL; } PyTuple_SET_ITEM(tpl, 0, rval); PyTuple_SET_ITEM(tpl, 1, pyidx); return tpl; } static inline int _PyUnicodeWriter_IsEmpty(PyUnicodeWriter *writer_pub) { _PyUnicodeWriter *writer = (_PyUnicodeWriter*)writer_pub; return (writer->pos == 0); } static PyObject * scanstring_unicode(PyObject *pystr, Py_ssize_t end, int strict, Py_ssize_t *next_end_ptr) { /* Read the JSON string from PyUnicode pystr. end is the index of the first character after the quote. if strict is zero then literal control characters are allowed *next_end_ptr is a return-by-reference index of the character after the end quote Return value is a new PyUnicode */ PyObject *rval = NULL; Py_ssize_t len; Py_ssize_t begin = end - 1; Py_ssize_t next /* = begin */; const void *buf; int kind; PyUnicodeWriter *writer = PyUnicodeWriter_Create(0); if (writer == NULL) { goto bail; } len = PyUnicode_GET_LENGTH(pystr); buf = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); if (end < 0 || len < end) { PyErr_SetString(PyExc_ValueError, "end is out of bounds"); goto bail; } while (1) { /* Find the end of the string or the next escape */ Py_UCS4 c; { // Use tight scope variable to help register allocation. Py_UCS4 d = 0; for (next = end; next < len; next++) { d = PyUnicode_READ(kind, buf, next); if (d == '"' || d == '\\') { break; } if (d <= 0x1f && strict) { raise_errmsg("Invalid control character at", pystr, next); goto bail; } } c = d; } if (c == '"') { // Fast path for simple case. if (_PyUnicodeWriter_IsEmpty(writer)) { PyObject *ret = PyUnicode_Substring(pystr, end, next); if (ret == NULL) { goto bail; } PyUnicodeWriter_Discard(writer); *next_end_ptr = next + 1;; return ret; } } else if (c != '\\') { raise_errmsg("Unterminated string starting at", pystr, begin); goto bail; } /* Pick up this chunk if it's not zero length */ if (next != end) { if (PyUnicodeWriter_WriteSubstring(writer, pystr, end, next) < 0) { goto bail; } } next++; if (c == '"') { end = next; break; } if (next == len) { raise_errmsg("Unterminated string starting at", pystr, begin); goto bail; } c = PyUnicode_READ(kind, buf, next); if (c != 'u') { /* Non-unicode backslash escapes */ end = next + 1; switch (c) { case '"': break; case '\\': break; case '/': break; case 'b': c = '\b'; break; case 'f': c = '\f'; break; case 'n': c = '\n'; break; case 'r': c = '\r'; break; case 't': c = '\t'; break; default: c = 0; } if (c == 0) { raise_errmsg("Invalid \\escape", pystr, end - 2); goto bail; } } else { c = 0; next++; end = next + 4; if (end > len) { raise_errmsg("Invalid \\uXXXX escape", pystr, next - 1); goto bail; } /* Decode 4 hex digits */ for (; next < end; next++) { Py_UCS4 digit = PyUnicode_READ(kind, buf, next); c <<= 4; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c |= (digit - 'A' + 10); break; default: raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5); goto bail; } } /* Surrogate pair */ if (Py_UNICODE_IS_HIGH_SURROGATE(c) && end + 6 < len && PyUnicode_READ(kind, buf, next++) == '\\' && PyUnicode_READ(kind, buf, next++) == 'u') { Py_UCS4 c2 = 0; end += 6; /* Decode 4 hex digits */ for (; next < end; next++) { Py_UCS4 digit = PyUnicode_READ(kind, buf, next); c2 <<= 4; switch (digit) { case '0': case '1': case '2': case '3': case '4': case '5': case '6': case '7': case '8': case '9': c2 |= (digit - '0'); break; case 'a': case 'b': case 'c': case 'd': case 'e': case 'f': c2 |= (digit - 'a' + 10); break; case 'A': case 'B': case 'C': case 'D': case 'E': case 'F': c2 |= (digit - 'A' + 10); break; default: raise_errmsg("Invalid \\uXXXX escape", pystr, end - 5); goto bail; } } if (Py_UNICODE_IS_LOW_SURROGATE(c2)) c = Py_UNICODE_JOIN_SURROGATES(c, c2); else end -= 6; } } if (PyUnicodeWriter_WriteChar(writer, c) < 0) { goto bail; } } rval = PyUnicodeWriter_Finish(writer); *next_end_ptr = end; return rval; bail: *next_end_ptr = -1; PyUnicodeWriter_Discard(writer); return NULL; } PyDoc_STRVAR(pydoc_scanstring, "scanstring(string, end, strict=True) -> (string, end)\n" "\n" "Scan the string s for a JSON string. End is the index of the\n" "character in s after the quote that started the JSON string.\n" "Unescapes all valid JSON string escape sequences and raises ValueError\n" "on attempt to decode an invalid string. If strict is False then literal\n" "control characters are allowed in the string.\n" "\n" "Returns a tuple of the decoded string and the index of the character in s\n" "after the end quote." ); static PyObject * py_scanstring(PyObject* Py_UNUSED(self), PyObject *args) { PyObject *pystr; PyObject *rval; Py_ssize_t end; Py_ssize_t next_end = -1; int strict = 1; if (!PyArg_ParseTuple(args, "On|p:scanstring", &pystr, &end, &strict)) { return NULL; } if (PyUnicode_Check(pystr)) { rval = scanstring_unicode(pystr, end, strict, &next_end); } else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } return _build_rval_index_tuple(rval, next_end); } PyDoc_STRVAR(pydoc_encode_basestring_ascii, "encode_basestring_ascii(string) -> string\n" "\n" "Return an ASCII-only JSON representation of a Python string" ); static PyObject * py_encode_basestring_ascii(PyObject* Py_UNUSED(self), PyObject *pystr) { PyObject *rval; /* Return an ASCII-only JSON representation of a Python string */ /* METH_O */ if (PyUnicode_Check(pystr)) { rval = ascii_escape_unicode(pystr); } else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } return rval; } PyDoc_STRVAR(pydoc_encode_basestring, "encode_basestring(string) -> string\n" "\n" "Return a JSON representation of a Python string" ); static PyObject * py_encode_basestring(PyObject* Py_UNUSED(self), PyObject *pystr) { PyObject *rval; /* Return a JSON representation of a Python string */ /* METH_O */ if (PyUnicode_Check(pystr)) { rval = escape_unicode(pystr); } else { PyErr_Format(PyExc_TypeError, "first argument must be a string, not %.80s", Py_TYPE(pystr)->tp_name); return NULL; } return rval; } static void scanner_dealloc(PyObject *self) { PyTypeObject *tp = Py_TYPE(self); /* bpo-31095: UnTrack is needed before calling any callbacks */ PyObject_GC_UnTrack(self); (void)scanner_clear(self); tp->tp_free(self); Py_DECREF(tp); } static int scanner_traverse(PyObject *op, visitproc visit, void *arg) { PyScannerObject *self = PyScannerObject_CAST(op); Py_VISIT(Py_TYPE(self)); Py_VISIT(self->object_hook); Py_VISIT(self->object_pairs_hook); Py_VISIT(self->parse_float); Py_VISIT(self->parse_int); Py_VISIT(self->parse_constant); return 0; } static int scanner_clear(PyObject *op) { PyScannerObject *self = PyScannerObject_CAST(op); Py_CLEAR(self->object_hook); Py_CLEAR(self->object_pairs_hook); Py_CLEAR(self->parse_float); Py_CLEAR(self->parse_int); Py_CLEAR(self->parse_constant); return 0; } static PyObject * _parse_object_unicode(PyScannerObject *s, PyObject *memo, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON object from PyUnicode pystr. idx is the index of the first character after the opening curly brace. *next_idx_ptr is a return-by-reference index to the first character after the closing curly brace. Returns a new PyObject (usually a dict, but object_hook can change that) */ const void *str; int kind; Py_ssize_t end_idx; PyObject *val = NULL; PyObject *rval = NULL; PyObject *key = NULL; int has_pairs_hook = (s->object_pairs_hook != Py_None); Py_ssize_t next_idx; Py_ssize_t comma_idx; str = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); end_idx = PyUnicode_GET_LENGTH(pystr) - 1; if (has_pairs_hook) rval = PyList_New(0); else rval = PyDict_New(); if (rval == NULL) return NULL; /* skip whitespace after { */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind,str, idx))) idx++; /* only loop if the object is non-empty */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != '}') { while (1) { PyObject *memokey; /* read key */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != '"') { raise_errmsg("Expecting property name enclosed in double quotes", pystr, idx); goto bail; } key = scanstring_unicode(pystr, idx + 1, s->strict, &next_idx); if (key == NULL) goto bail; if (PyDict_SetDefaultRef(memo, key, key, &memokey) < 0) { goto bail; } Py_SETREF(key, memokey); idx = next_idx; /* skip whitespace between key and : delimiter, read :, skip whitespace */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ':') { raise_errmsg("Expecting ':' delimiter", pystr, idx); goto bail; } idx++; while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* read any JSON term */ val = scan_once_unicode(s, memo, pystr, idx, &next_idx); if (val == NULL) goto bail; if (has_pairs_hook) { PyObject *item = PyTuple_Pack(2, key, val); if (item == NULL) goto bail; Py_CLEAR(key); Py_CLEAR(val); if (PyList_Append(rval, item) == -1) { Py_DECREF(item); goto bail; } Py_DECREF(item); } else { if (PyDict_SetItem(rval, key, val) < 0) goto bail; Py_CLEAR(key); Py_CLEAR(val); } idx = next_idx; /* skip whitespace before } or , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* bail if the object is closed or we didn't get the , delimiter */ if (idx <= end_idx && PyUnicode_READ(kind, str, idx) == '}') break; if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ',') { raise_errmsg("Expecting ',' delimiter", pystr, idx); goto bail; } comma_idx = idx; idx++; /* skip whitespace after , delimiter */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; if (idx <= end_idx && PyUnicode_READ(kind, str, idx) == '}') { raise_errmsg("Illegal trailing comma before end of object", pystr, comma_idx); goto bail; } } } *next_idx_ptr = idx + 1; if (has_pairs_hook) { val = PyObject_CallOneArg(s->object_pairs_hook, rval); Py_DECREF(rval); return val; } /* if object_hook is not None: rval = object_hook(rval) */ if (s->object_hook != Py_None) { val = PyObject_CallOneArg(s->object_hook, rval); Py_DECREF(rval); return val; } return rval; bail: Py_XDECREF(key); Py_XDECREF(val); Py_XDECREF(rval); return NULL; } static PyObject * _parse_array_unicode(PyScannerObject *s, PyObject *memo, PyObject *pystr, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON array from PyUnicode pystr. idx is the index of the first character after the opening brace. *next_idx_ptr is a return-by-reference index to the first character after the closing brace. Returns a new PyList */ const void *str; int kind; Py_ssize_t end_idx; PyObject *val = NULL; PyObject *rval; Py_ssize_t next_idx; Py_ssize_t comma_idx; rval = PyList_New(0); if (rval == NULL) return NULL; str = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); end_idx = PyUnicode_GET_LENGTH(pystr) - 1; /* skip whitespace after [ */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* only loop if the array is non-empty */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ']') { while (1) { /* read any JSON term */ val = scan_once_unicode(s, memo, pystr, idx, &next_idx); if (val == NULL) goto bail; if (PyList_Append(rval, val) == -1) goto bail; Py_CLEAR(val); idx = next_idx; /* skip whitespace between term and , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; /* bail if the array is closed or we didn't get the , delimiter */ if (idx <= end_idx && PyUnicode_READ(kind, str, idx) == ']') break; if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ',') { raise_errmsg("Expecting ',' delimiter", pystr, idx); goto bail; } comma_idx = idx; idx++; /* skip whitespace after , */ while (idx <= end_idx && IS_WHITESPACE(PyUnicode_READ(kind, str, idx))) idx++; if (idx <= end_idx && PyUnicode_READ(kind, str, idx) == ']') { raise_errmsg("Illegal trailing comma before end of array", pystr, comma_idx); goto bail; } } } /* verify that idx < end_idx, PyUnicode_READ(kind, str, idx) should be ']' */ if (idx > end_idx || PyUnicode_READ(kind, str, idx) != ']') { raise_errmsg("Expecting value", pystr, end_idx); goto bail; } *next_idx_ptr = idx + 1; return rval; bail: Py_XDECREF(val); Py_DECREF(rval); return NULL; } static PyObject * _parse_constant(PyScannerObject *s, const char *constant, Py_ssize_t idx, Py_ssize_t *next_idx_ptr) { /* Read a JSON constant. constant is the constant string that was found ("NaN", "Infinity", "-Infinity"). idx is the index of the first character of the constant *next_idx_ptr is a return-by-reference index to the first character after the constant. Returns the result of parse_constant */ PyObject *cstr; PyObject *rval; /* constant is "NaN", "Infinity", or "-Infinity" */ cstr = PyUnicode_InternFromString(constant); if (cstr == NULL) return NULL; /* rval = parse_constant(constant) */ rval = PyObject_CallOneArg(s->parse_constant, cstr); idx += PyUnicode_GET_LENGTH(cstr); Py_DECREF(cstr); *next_idx_ptr = idx; return rval; } static PyObject * _match_number_unicode(PyScannerObject *s, PyObject *pystr, Py_ssize_t start, Py_ssize_t *next_idx_ptr) { /* Read a JSON number from PyUnicode pystr. idx is the index of the first character of the number *next_idx_ptr is a return-by-reference index to the first character after the number. Returns a new PyObject representation of that number: PyLong, or PyFloat. May return other types if parse_int or parse_float are set */ const void *str; int kind; Py_ssize_t end_idx; Py_ssize_t idx = start; int is_float = 0; PyObject *rval; PyObject *numstr = NULL; PyObject *custom_func; str = PyUnicode_DATA(pystr); kind = PyUnicode_KIND(pystr); end_idx = PyUnicode_GET_LENGTH(pystr) - 1; /* read a sign if it's there, make sure it's not the end of the string */ if (PyUnicode_READ(kind, str, idx) == '-') { idx++; if (idx > end_idx) { raise_stop_iteration(start); return NULL; } } /* read as many integer digits as we find as long as it doesn't start with 0 */ if (PyUnicode_READ(kind, str, idx) >= '1' && PyUnicode_READ(kind, str, idx) <= '9') { idx++; while (idx <= end_idx && PyUnicode_READ(kind, str, idx) >= '0' && PyUnicode_READ(kind, str, idx) <= '9') idx++; } /* if it starts with 0 we only expect one integer digit */ else if (PyUnicode_READ(kind, str, idx) == '0') { idx++; } /* no integer digits, error */ else { raise_stop_iteration(start); return NULL; } /* if the next char is '.' followed by a digit then read all float digits */ if (idx < end_idx && PyUnicode_READ(kind, str, idx) == '.' && PyUnicode_READ(kind, str, idx + 1) >= '0' && PyUnicode_READ(kind, str, idx + 1) <= '9') { is_float = 1; idx += 2; while (idx <= end_idx && PyUnicode_READ(kind, str, idx) >= '0' && PyUnicode_READ(kind, str, idx) <= '9') idx++; } /* if the next char is 'e' or 'E' then maybe read the exponent (or backtrack) */ if (idx < end_idx && (PyUnicode_READ(kind, str, idx) == 'e' || PyUnicode_READ(kind, str, idx) == 'E')) { Py_ssize_t e_start = idx; idx++; /* read an exponent sign if present */ if (idx < end_idx && (PyUnicode_READ(kind, str, idx) == '-' || PyUnicode_READ(kind, str, idx) == '+')) idx++; /* read all digits */ while (idx <= end_idx && PyUnicode_READ(kind, str, idx) >= '0' && PyUnicode_READ(kind, str, idx) <= '9') idx++; /* if we got a digit, then parse as float. if not, backtrack */ if (PyUnicode_READ(kind, str, idx - 1) >= '0' && PyUnicode_READ(kind, str, idx - 1) <= '9') { is_float = 1; } else { idx = e_start; } } if (is_float && s->parse_float != (PyObject *)&PyFloat_Type) custom_func = s->parse_float; else if (!is_float && s->parse_int != (PyObject *) &PyLong_Type) custom_func = s->parse_int; else custom_func = NULL; if (custom_func) { /* copy the section we determined to be a number */ numstr = PyUnicode_FromKindAndData(kind, (char*)str + kind * start, idx - start); if (numstr == NULL) return NULL; rval = PyObject_CallOneArg(custom_func, numstr); } else { Py_ssize_t i, n; char *buf; /* Straight conversion to ASCII, to avoid costly conversion of decimal unicode digits (which cannot appear here) */ n = idx - start; |
| You are visitor 01402520 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |