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 — python-rapidjson/rapidjson.cpp at master · python-rapidjson/python-rapidjson Expand file tree/ Copy pathrapidjson.cppMore file actions 4156 lines (3537 loc) · 141 KB / Copy pathrapidjson.cppFile metadata and controls4156 lines (3537 loc) · 141 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 // -*- coding: utf-8 -*- // :Project: python-rapidjson -- Python extension module // :Author: Ken Robbins <[email protected]> // :License: MIT License // :Copyright: © 2015 Ken Robbins // :Copyright: © 2015-2026 Lele Gaifax // #include <Python.h> #include <datetime.h> #include <structmember.h> #include <algorithm> #include <cmath> #include <string> #include <vector> #include "rapidjson/reader.h" #include "rapidjson/schema.h" #include "rapidjson/stringbuffer.h" #include "rapidjson/writer.h" #include "rapidjson/prettywriter.h" #include "rapidjson/error/en.h" using namespace rapidjson; /* On some MacOS combo, using Py_IS_XXX() macros does not work (see https://github.com/python-rapidjson/python-rapidjson/issues/78). OTOH, MSVC < 2015 does not have std::isxxx() (see https://stackoverflow.com/questions/38441740/where-is-isnan-in-msvc-2010). Oh well... */ #if defined (_MSC_VER) && (_MSC_VER < 1900) #define IS_NAN(x) Py_IS_NAN(x) #define IS_INF(x) Py_IS_INFINITY(x) #else #define IS_NAN(x) std::isnan(x) #define IS_INF(x) std::isinf(x) #endif static PyObject* decimal_type = NULL; static PyObject* timezone_type = NULL; static PyObject* timezone_utc = NULL; static PyObject* uuid_type = NULL; static PyObject* validation_error = NULL; static PyObject* decode_error = NULL; /* These are the names of often used methods or literal values, interned in the module initialization function, to avoid repeated creation/destruction of PyUnicode values from plain C strings. We cannot use _Py_IDENTIFIER() because that upsets the GNU C++ compiler in -pedantic mode. */ static PyObject* astimezone_name = NULL; static PyObject* hex_name = NULL; static PyObject* timestamp_name = NULL; static PyObject* total_seconds_name = NULL; static PyObject* utcoffset_name = NULL; static PyObject* is_infinite_name = NULL; static PyObject* is_nan_name = NULL; static PyObject* start_object_name = NULL; static PyObject* end_object_name = NULL; static PyObject* default_name = NULL; static PyObject* end_array_name = NULL; static PyObject* string_name = NULL; static PyObject* read_name = NULL; static PyObject* write_name = NULL; static PyObject* encoding_name = NULL; static PyObject* minus_inf_string_value = NULL; static PyObject* nan_string_value = NULL; static PyObject* plus_inf_string_value = NULL; struct HandlerContext { PyObject* object; const char* key; SizeType keyLength; bool isObject; bool keyValuePairs; bool copiedKey; }; enum DatetimeMode { DM_NONE = 0, // Formats DM_ISO8601 = 1<<0, // Bidirectional ISO8601 for datetimes, dates and times DM_UNIX_TIME = 1<<1, // Serialization only, "Unix epoch"-based number of seconds // Options DM_ONLY_SECONDS = 1<<4, // Truncate values to the whole second, ignoring micro seconds DM_IGNORE_TZ = 1<<5, // Ignore timezones DM_NAIVE_IS_UTC = 1<<6, // Assume naive datetime are in UTC timezone DM_SHIFT_TO_UTC = 1<<7, // Shift to/from UTC DM_MAX = 1<<8 }; #define DATETIME_MODE_FORMATS_MASK 0x0f // 0b00001111 in C++14 static inline int datetime_mode_format(unsigned mode) { return mode & DATETIME_MODE_FORMATS_MASK; } static inline bool valid_datetime_mode(long mode) { int format = datetime_mode_format(mode); return (mode >= 0 && mode < DM_MAX && (format <= DM_UNIX_TIME) && (mode == 0 || format > 0)); } static int days_per_month(int year, int month) { assert(month >= 1); assert(month <= 12); if (month == 1 || month == 3 || month == 5 || month == 7 || month == 8 || month == 10 || month == 12) { return 31; } else if (month == 4 || month == 6 || month == 9 || month == 11) { return 30; } else if (year % 4 == 0 && (year % 100 != 0 || year % 400 == 0)) { return 29; } else { return 28; } } enum UuidMode { UM_NONE = 0, UM_CANONICAL = 1<<0, // 4-dashed 32 hex chars: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx UM_HEX = 1<<1, // canonical OR 32 hex chars in a row UM_MAX = 1<<2 }; enum NumberMode { NM_NONE = 0, NM_NAN = 1<<0, // allow "not-a-number" values NM_DECIMAL = 1<<1, // serialize Decimal instances, deserialize floats as Decimal NM_NATIVE = 1<<2, // use faster native C library number handling NM_MAX = 1<<3 }; enum BytesMode { BM_NONE = 0, BM_UTF8 = 1<<0, // try to convert to UTF-8 BM_MAX = 1<<1 }; enum ParseMode { PM_NONE = 0, PM_COMMENTS = 1<<0, // Allow one-line // ... and multi-line /* ... */ comments PM_TRAILING_COMMAS = 1<<1, // allow trailing commas at the end of objects and arrays PM_MAX = 1<<2 }; enum WriteMode { WM_COMPACT = 0, WM_PRETTY = 1<<0, // Use PrettyWriter WM_SINGLE_LINE_ARRAY = 1<<1, // Format arrays on a single line WM_MAX = 1<<2 }; enum IterableMode { IM_ANY_ITERABLE = 0, // Default, any iterable is dumped as JSON array IM_ONLY_LISTS = 1<<0, // Only list instances are dumped as JSON arrays IM_MAX = 1<<1 }; enum MappingMode { MM_ANY_MAPPING = 0, // Default, any mapping is dumped as JSON object MM_ONLY_DICTS = 1<<0, // Only dict instances are dumped as JSON objects MM_COERCE_KEYS_TO_STRINGS = 1<<1, // Convert keys to strings MM_SKIP_NON_STRING_KEYS = 1<<2, // Ignore non-string keys MM_SORT_KEYS = 1<<3, // Sort keys MM_MAX = 1<<4 }; ////////////////////////// // Forward declarations // ////////////////////////// static PyObject* do_decode(PyObject* decoder, const char* jsonStr, Py_ssize_t jsonStrlen, PyObject* jsonStream, size_t chunkSize, PyObject* objectHook, unsigned numberMode, unsigned datetimeMode, unsigned uuidMode, unsigned parseMode); static PyObject* decoder_call(PyObject* self, PyObject* args, PyObject* kwargs); static PyObject* decoder_new(PyTypeObject* type, PyObject* args, PyObject* kwargs); static PyObject* do_encode(PyObject* value, PyObject* defaultFn, bool ensureAscii, unsigned writeMode, char indentChar, unsigned indentCount, unsigned numberMode, unsigned datetimeMode, unsigned uuidMode, unsigned bytesMode, unsigned iterableMode, unsigned mappingMode); static PyObject* do_stream_encode(PyObject* value, PyObject* stream, size_t chunkSize, PyObject* defaultFn, bool ensureAscii, unsigned writeMode, char indentChar, unsigned indentCount, unsigned numberMode, unsigned datetimeMode, unsigned uuidMode, unsigned bytesMode, unsigned iterableMode, unsigned mappingMode); static PyObject* encoder_call(PyObject* self, PyObject* args, PyObject* kwargs); static PyObject* encoder_new(PyTypeObject* type, PyObject* args, PyObject* kwargs); static PyObject* validator_call(PyObject* self, PyObject* args, PyObject* kwargs); static void validator_dealloc(PyObject* self); static PyObject* validator_new(PyTypeObject* type, PyObject* args, PyObject* kwargs); /////////////////////////////////////////////////// // Stream wrapper around Python file-like object // /////////////////////////////////////////////////// class PyReadStreamWrapper { public: typedef char Ch; PyReadStreamWrapper(PyObject* stream, size_t size) : stream(stream) { Py_INCREF(stream); chunkSize = PyLong_FromUnsignedLong(size); buffer = NULL; chunk = NULL; chunkLen = 0; pos = 0; offset = 0; eof = false; } ~PyReadStreamWrapper() { Py_CLEAR(stream); Py_CLEAR(chunkSize); Py_CLEAR(chunk); } Ch Peek() { if (!eof && pos == chunkLen) { Read(); } return eof ? '\0' : buffer[pos]; } Ch Take() { if (!eof && pos == chunkLen) { Read(); } return eof ? '\0' : buffer[pos++]; } size_t Tell() const { return offset + pos; } bool IsEnd() const { return eof; } void Flush() { assert(false); } void Put(Ch c) { assert(false); } Ch* PutBegin() { assert(false); return 0; } size_t PutEnd(Ch* begin) { assert(false); return 0; } private: void Read() { Py_CLEAR(chunk); chunk = PyObject_CallMethodObjArgs(stream, read_name, chunkSize, NULL); if (chunk == NULL) { eof = true; } else { Py_ssize_t len; if (PyBytes_Check(chunk)) { len = PyBytes_GET_SIZE(chunk); buffer = PyBytes_AS_STRING(chunk); } else { buffer = PyUnicode_AsUTF8AndSize(chunk, &len); if (buffer == NULL) { len = 0; } } if (len == 0) { eof = true; } else { offset += chunkLen; chunkLen = len; pos = 0; } } } PyObject* stream; PyObject* chunkSize; PyObject* chunk; const Ch* buffer; size_t chunkLen; size_t pos; size_t offset; bool eof; }; class PyWriteStreamWrapper { public: typedef char Ch; PyWriteStreamWrapper(PyObject* stream, size_t size) : stream(stream) { Py_INCREF(stream); buffer = (char*) PyMem_Malloc(size); assert(buffer); bufferEnd = buffer + size; cursor = buffer; multiByteChar = NULL; isBinary = !PyObject_HasAttr(stream, encoding_name); } ~PyWriteStreamWrapper() { Py_CLEAR(stream); PyMem_Free(buffer); } Ch Peek() { assert(false); return 0; } Ch Take() { assert(false); return 0; } size_t Tell() const { assert(false); return 0; } void Flush() { PyObject* c; if (isBinary) { c = PyBytes_FromStringAndSize(buffer, (size_t)(cursor - buffer)); cursor = buffer; } else { if (multiByteChar == NULL) { c = PyUnicode_FromStringAndSize(buffer, (size_t)(cursor - buffer)); cursor = buffer; } else { size_t complete = (size_t)(multiByteChar - buffer); c = PyUnicode_FromStringAndSize(buffer, complete); size_t remaining = (size_t)(cursor - multiByteChar); if (RAPIDJSON_LIKELY(remaining < complete)) memcpy(buffer, multiByteChar, remaining); else std::memmove(buffer, multiByteChar, remaining); cursor = buffer + remaining; multiByteChar = NULL; } } if (c == NULL) { // Propagate the error state, it will be caught by dumps_internal() } else { PyObject* res = PyObject_CallMethodObjArgs(stream, write_name, c, NULL); if (res == NULL) { // Likewise } else { Py_DECREF(res); } Py_DECREF(c); } } void Put(Ch c) { if (cursor == bufferEnd) Flush(); if (!isBinary) { if ((c & 0x80) == 0) { multiByteChar = NULL; } else if (c & 0x40) { multiByteChar = cursor; } } *cursor++ = c; } Ch* PutBegin() { assert(false); return 0; } size_t PutEnd(Ch* begin) { assert(false); return 0; } private: PyObject* stream; Ch* buffer; Ch* bufferEnd; Ch* cursor; Ch* multiByteChar; bool isBinary; }; inline void PutUnsafe(PyWriteStreamWrapper& stream, char c) { stream.Put(c); } ///////////// // RawJSON // ///////////// typedef struct { PyObject_HEAD PyObject* value; } RawJSON; static void RawJSON_dealloc(RawJSON* self) { Py_XDECREF(self->value); Py_TYPE(self)->tp_free((PyObject*) self); } static PyObject* RawJSON_new(PyTypeObject* type, PyObject* args, PyObject* kwds) { static char const* kwlist[] = { "value", NULL }; PyObject* value = NULL; if (!PyArg_ParseTupleAndKeywords(args, kwds, "U", (char**) kwlist, &value)) return NULL; PyObject* self = type->tp_alloc(type, 0); if (self == NULL) return NULL; ((RawJSON*) self)->value = value; Py_INCREF(value); return self; } static PyMemberDef RawJSON_members[] = { {"value", T_OBJECT_EX, offsetof(RawJSON, value), READONLY, "string representing a serialized JSON object"}, {NULL} /* Sentinel */ }; PyDoc_STRVAR(rawjson_doc, "Raw (preserialized) JSON object\n" "\n" "When rapidjson tries to serialize instances of this class, it will" " use their literal `value`. For instance:\n" ">>> rapidjson.dumps(RawJSON('{\"already\": \"serialized\"}'))\n" "'{\"already\": \"serialized\"}'"); static PyTypeObject RawJSON_Type = { PyVarObject_HEAD_INIT(NULL, 0) "rapidjson.RawJSON", /* tp_name */ sizeof(RawJSON), /* tp_basicsize */ 0, /* tp_itemsize */ (destructor) RawJSON_dealloc, /* tp_dealloc */ 0, /* tp_print */ 0, /* tp_getattr */ 0, /* tp_setattr */ 0, /* tp_compare */ 0, /* tp_repr */ 0, /* tp_as_number */ 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ 0, /* tp_hash */ 0, /* tp_call */ 0, /* tp_str */ 0, /* tp_getattro */ 0, /* tp_setattro */ 0, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT, /* tp_flags */ rawjson_doc, /* tp_doc */ 0, /* tp_traverse */ 0, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ 0, /* tp_methods */ RawJSON_members, /* tp_members */ 0, /* tp_getset */ 0, /* tp_base */ 0, /* tp_dict */ 0, /* tp_descr_get */ 0, /* tp_descr_set */ 0, /* tp_dictoffset */ 0, /* tp_init */ 0, /* tp_alloc */ RawJSON_new, /* tp_new */ }; static bool accept_indent_arg(PyObject* arg, unsigned &write_mode, unsigned &indent_count, char &indent_char) { if (arg != NULL && arg != Py_None) { write_mode = WM_PRETTY; if (PyLong_Check(arg) && PyLong_AsLong(arg) >= 0) { indent_count = PyLong_AsUnsignedLong(arg); } else if (PyUnicode_Check(arg)) { Py_ssize_t len; const char* indentStr = PyUnicode_AsUTF8AndSize(arg, &len); indent_count = len; if (indent_count) { indent_char = '\0'; while (len--) { char ch = indentStr[len]; if (ch == '\n' || ch == ' ' || ch == '\t' || ch == '\r') { if (indent_char == '\0') { indent_char = ch; } else if (indent_char != ch) { PyErr_SetString( PyExc_TypeError, "indent string cannot contains different chars"); return false; } } else { PyErr_SetString(PyExc_TypeError, "non-whitespace char in indent string"); return false; } } } } else { PyErr_SetString(PyExc_TypeError, "indent must be a non-negative int or a string"); return false; } } return true; } static bool accept_write_mode_arg(PyObject* arg, unsigned &write_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= WM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid write_mode"); return false; } write_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "write_mode must be a non-negative int"); return false; } } return true; } static bool accept_number_mode_arg(PyObject* arg, int allow_nan, unsigned &number_mode) { if (arg != NULL) { if (arg == Py_None) number_mode = NM_NONE; else if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= NM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid number_mode, out of range"); return false; } number_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "number_mode must be a non-negative int"); return false; } } if (allow_nan != -1) { if (allow_nan) number_mode |= NM_NAN; else number_mode &= ~NM_NAN; } return true; } static bool accept_datetime_mode_arg(PyObject* arg, unsigned &datetime_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (!valid_datetime_mode(mode)) { PyErr_SetString(PyExc_ValueError, "Invalid datetime_mode, out of range"); return false; } datetime_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "datetime_mode must be a non-negative int"); return false; } } return true; } static bool accept_uuid_mode_arg(PyObject* arg, unsigned &uuid_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= UM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid uuid_mode, out of range"); return false; } uuid_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "uuid_mode must be a non-negative int"); return false; } } return true; } static bool accept_bytes_mode_arg(PyObject* arg, unsigned &bytes_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= BM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid bytes_mode, out of range"); return false; } bytes_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "bytes_mode must be a non-negative int"); return false; } } return true; } static bool accept_iterable_mode_arg(PyObject* arg, unsigned &iterable_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= IM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid iterable_mode, out of range"); return false; } iterable_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "iterable_mode must be a non-negative int"); return false; } } return true; } static bool accept_mapping_mode_arg(PyObject* arg, unsigned &mapping_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= MM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid mapping_mode, out of range"); return false; } mapping_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "mapping_mode must be a non-negative int"); return false; } } return true; } static bool accept_chunk_size_arg(PyObject* arg, size_t &chunk_size) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { Py_ssize_t size = PyNumber_AsSsize_t(arg, PyExc_ValueError); if (PyErr_Occurred() || size < 4 || size > UINT_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid chunk_size, out of range"); return false; } chunk_size = (size_t) size; } else { PyErr_SetString(PyExc_TypeError, "chunk_size must be a non-negative int"); return false; } } return true; } static bool accept_parse_mode_arg(PyObject* arg, unsigned &parse_mode) { if (arg != NULL && arg != Py_None) { if (PyLong_Check(arg)) { long mode = PyLong_AsLong(arg); if (mode < 0 || mode >= PM_MAX) { PyErr_SetString(PyExc_ValueError, "Invalid parse_mode, out of range"); return false; } parse_mode = (unsigned) mode; } else { PyErr_SetString(PyExc_TypeError, "parse_mode must be a non-negative int"); return false; } } return true; } ///////////// // Decoder // ///////////// /* Adapted from CPython's Objects/floatobject.c::float_from_string_inner() */ static PyObject* float_from_string(const char* s, Py_ssize_t len) { double x; const char* end; /* We don't care about overflow or underflow. If the platform * supports them, infinities and signed zeroes (on underflow) are * fine. */ x = PyOS_string_to_double(s, (char **) &end, NULL); if (end != s + len) { return NULL; } else if (x == -1.0 && PyErr_Occurred()) { return NULL; } else { return PyFloat_FromDouble(x); } } struct PyHandler { PyObject* decoderStartObject; PyObject* decoderEndObject; PyObject* decoderEndArray; PyObject* decoderString; PyObject* sharedKeys; PyObject* root; PyObject* objectHook; unsigned datetimeMode; unsigned uuidMode; unsigned numberMode; unsigned recursionLimit; std::vector<HandlerContext> stack; PyHandler(PyObject* decoder, PyObject* hook, unsigned dm, unsigned um, unsigned nm) : decoderStartObject(NULL), decoderEndObject(NULL), decoderEndArray(NULL), decoderString(NULL), root(NULL), objectHook(hook), datetimeMode(dm), uuidMode(um), numberMode(nm) { stack.reserve(128); if (decoder != NULL) { assert(!objectHook); if (PyObject_HasAttr(decoder, start_object_name)) { decoderStartObject = PyObject_GetAttr(decoder, start_object_name); } if (PyObject_HasAttr(decoder, end_object_name)) { decoderEndObject = PyObject_GetAttr(decoder, end_object_name); } if (PyObject_HasAttr(decoder, end_array_name)) { decoderEndArray = PyObject_GetAttr(decoder, end_array_name); } if (PyObject_HasAttr(decoder, string_name)) { decoderString = PyObject_GetAttr(decoder, string_name); } } sharedKeys = PyDict_New(); recursionLimit = Py_GetRecursionLimit(); } ~PyHandler() { while (!stack.empty()) { const HandlerContext& ctx = stack.back(); if (ctx.copiedKey) PyMem_Free((void*) ctx.key); if (ctx.object != NULL) Py_DECREF(ctx.object); stack.pop_back(); } Py_CLEAR(decoderStartObject); Py_CLEAR(decoderEndObject); Py_CLEAR(decoderEndArray); Py_CLEAR(decoderString); Py_CLEAR(sharedKeys); } bool Handle(PyObject* value) { if (root) { const HandlerContext& current = stack.back(); if (current.isObject) { PyObject* key = PyUnicode_FromStringAndSize(current.key, current.keyLength); if (key == NULL) { Py_DECREF(value); return false; } PyObject* shared_key = PyDict_SetDefault(sharedKeys, key, key); if (shared_key == NULL) { Py_DECREF(key); Py_DECREF(value); return false; } Py_INCREF(shared_key); Py_DECREF(key); key = shared_key; int rc; if (current.keyValuePairs) { PyObject* pair = PyTuple_Pack(2, key, value); Py_DECREF(key); Py_DECREF(value); if (pair == NULL) { return false; } rc = PyList_Append(current.object, pair); Py_DECREF(pair); } else { if (PyDict_CheckExact(current.object)) // If it's a standard dictionary, this is +20% faster rc = PyDict_SetItem(current.object, key, value); else rc = PyObject_SetItem(current.object, key, value); Py_DECREF(key); Py_DECREF(value); } if (rc == -1) { return false; } } else { int rc = PyList_Append(current.object, value); Py_DECREF(value); if (rc == -1) { return false; } } } else { root = value; } return true; } bool Key(const char* str, SizeType length, bool copy) { HandlerContext& current = stack.back(); // This happens when operating in stream mode and kParseInsituFlag is not set: we // must copy the incoming string in the context, and destroy the duplicate when // the context gets reused for the next dictionary key if (current.key && current.copiedKey) { PyMem_Free((void*) current.key); current.key = NULL; } if (copy) { char* copied_str = (char*) PyMem_Malloc(length+1); if (copied_str == NULL) return false; memcpy(copied_str, str, length+1); str = copied_str; assert(!current.key); } current.key = str; current.keyLength = length; current.copiedKey = copy; return true; } bool StartObject() { if (recursionLimit-- == 0) { PyErr_SetString(PyExc_RecursionError, "Maximum parse recursion depth exceeded"); return false; } PyObject* mapping; bool key_value_pairs; if (decoderStartObject != NULL) { mapping = PyObject_CallFunctionObjArgs(decoderStartObject, NULL); if (mapping == NULL) return false; key_value_pairs = PyList_Check(mapping); if (!PyMapping_Check(mapping) && !key_value_pairs) { Py_DECREF(mapping); PyErr_SetString(PyExc_ValueError, "start_object() must return a mapping or a list instance"); return false; } } else { mapping = PyDict_New(); if (mapping == NULL) { return false; } key_value_pairs = false; } if (!Handle(mapping)) { return false; } HandlerContext ctx; ctx.isObject = true; ctx.keyValuePairs = key_value_pairs; ctx.object = mapping; ctx.key = NULL; ctx.copiedKey = false; Py_INCREF(mapping); stack.push_back(ctx); return true; |
| You are visitor 01402503 — 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. |