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/_csv.c at master · rbu/cpython Expand file tree/ Copy path_csv.cMore file actions 1691 lines (1511 loc) · 49.8 KB / Copy path_csv.cFile metadata and controls1691 lines (1511 loc) · 49.8 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 /* csv module */ /* This module provides the low-level underpinnings of a CSV reading/writing module. Users should not use this module directly, but import the csv.py module instead. */ #define MODULE_VERSION "1.0" #include "Python.h" #include "structmember.h" typedef struct { PyObject *error_obj; /* CSV exception */ PyObject *dialects; /* Dialect registry */ long field_limit; /* max parsed field size */ } _csvstate; #define _csvstate(o) ((_csvstate *)PyModule_GetState(o)) static int _csv_clear(PyObject *m) { Py_CLEAR(_csvstate(m)->error_obj); Py_CLEAR(_csvstate(m)->dialects); return 0; } static int _csv_traverse(PyObject *m, visitproc visit, void *arg) { Py_VISIT(_csvstate(m)->error_obj); Py_VISIT(_csvstate(m)->dialects); return 0; } static void _csv_free(void *m) { _csv_clear((PyObject *)m); } static struct PyModuleDef _csvmodule; #define _csvstate_global ((_csvstate *)PyModule_GetState(PyState_FindModule(&_csvmodule))) typedef enum { START_RECORD, START_FIELD, ESCAPED_CHAR, IN_FIELD, IN_QUOTED_FIELD, ESCAPE_IN_QUOTED_FIELD, QUOTE_IN_QUOTED_FIELD, EAT_CRNL,AFTER_ESCAPED_CRNL } ParserState; typedef enum { QUOTE_MINIMAL, QUOTE_ALL, QUOTE_NONNUMERIC, QUOTE_NONE } QuoteStyle; typedef struct { QuoteStyle style; const char *name; } StyleDesc; static const StyleDesc quote_styles[] = { { QUOTE_MINIMAL, "QUOTE_MINIMAL" }, { QUOTE_ALL, "QUOTE_ALL" }, { QUOTE_NONNUMERIC, "QUOTE_NONNUMERIC" }, { QUOTE_NONE, "QUOTE_NONE" }, { 0 } }; typedef struct { PyObject_HEAD int doublequote; /* is " represented by ""? */ Py_UCS4 delimiter; /* field separator */ Py_UCS4 quotechar; /* quote character */ Py_UCS4 escapechar; /* escape character */ int skipinitialspace; /* ignore spaces following delimiter? */ PyObject *lineterminator; /* string to write between records */ int quoting; /* style of quoting to write */ int strict; /* raise exception on bad CSV */ } DialectObj; static PyTypeObject Dialect_Type; typedef struct { PyObject_HEAD PyObject *input_iter; /* iterate over this for input lines */ DialectObj *dialect; /* parsing dialect */ PyObject *fields; /* field list for current record */ ParserState state; /* current CSV parse state */ Py_UCS4 *field; /* temporary buffer */ Py_ssize_t field_size; /* size of allocated buffer */ Py_ssize_t field_len; /* length of current field */ int numeric_field; /* treat field as numeric */ unsigned long line_num; /* Source-file line number */ } ReaderObj; static PyTypeObject Reader_Type; #define ReaderObject_Check(v) (Py_TYPE(v) == &Reader_Type) typedef struct { PyObject_HEAD PyObject *writeline; /* write output lines to this file */ DialectObj *dialect; /* parsing dialect */ Py_UCS4 *rec; /* buffer for parser.join */ Py_ssize_t rec_size; /* size of allocated record */ Py_ssize_t rec_len; /* length of record */ int num_fields; /* number of fields in record */ } WriterObj; static PyTypeObject Writer_Type; /* * DIALECT class */ static PyObject * get_dialect_from_registry(PyObject * name_obj) { PyObject *dialect_obj; dialect_obj = PyDict_GetItem(_csvstate_global->dialects, name_obj); if (dialect_obj == NULL) { if (!PyErr_Occurred()) PyErr_Format(_csvstate_global->error_obj, "unknown dialect"); } else Py_INCREF(dialect_obj); return dialect_obj; } static PyObject * get_string(PyObject *str) { Py_XINCREF(str); return str; } static PyObject * get_nullchar_as_None(Py_UCS4 c) { if (c == '\0') { Py_RETURN_NONE; } else return PyUnicode_FromOrdinal(c); } static PyObject * Dialect_get_lineterminator(DialectObj *self) { return get_string(self->lineterminator); } static PyObject * Dialect_get_delimiter(DialectObj *self) { return get_nullchar_as_None(self->delimiter); } static PyObject * Dialect_get_escapechar(DialectObj *self) { return get_nullchar_as_None(self->escapechar); } static PyObject * Dialect_get_quotechar(DialectObj *self) { return get_nullchar_as_None(self->quotechar); } static PyObject * Dialect_get_quoting(DialectObj *self) { return PyLong_FromLong(self->quoting); } static int _set_bool(const char *name, int *target, PyObject *src, int dflt) { if (src == NULL) *target = dflt; else { int b = PyObject_IsTrue(src); if (b < 0) return -1; *target = b; } return 0; } static int _set_int(const char *name, int *target, PyObject *src, int dflt) { if (src == NULL) *target = dflt; else { int value; if (!PyLong_CheckExact(src)) { PyErr_Format(PyExc_TypeError, "\"%s\" must be an integer", name); return -1; } value = _PyLong_AsInt(src); if (value == -1 && PyErr_Occurred()) { return -1; } *target = value; } return 0; } static int _set_char(const char *name, Py_UCS4 *target, PyObject *src, Py_UCS4 dflt) { if (src == NULL) *target = dflt; else { *target = '\0'; if (src != Py_None) { Py_ssize_t len; if (!PyUnicode_Check(src)) { PyErr_Format(PyExc_TypeError, "\"%s\" must be string, not %.200s", name, src->ob_type->tp_name); return -1; } len = PyUnicode_GetLength(src); if (len > 1) { PyErr_Format(PyExc_TypeError, "\"%s\" must be a 1-character string", name); return -1; } /* PyUnicode_READY() is called in PyUnicode_GetLength() */ if (len > 0) *target = PyUnicode_READ_CHAR(src, 0); } } return 0; } static int _set_str(const char *name, PyObject **target, PyObject *src, const char *dflt) { if (src == NULL) *target = PyUnicode_DecodeASCII(dflt, strlen(dflt), NULL); else { if (src == Py_None) *target = NULL; else if (!PyUnicode_Check(src)) { PyErr_Format(PyExc_TypeError, "\"%s\" must be a string", name); return -1; } else { if (PyUnicode_READY(src) == -1) return -1; Py_INCREF(src); Py_XSETREF(*target, src); } } return 0; } static int dialect_check_quoting(int quoting) { const StyleDesc *qs; for (qs = quote_styles; qs->name; qs++) { if ((int)qs->style == quoting) return 0; } PyErr_Format(PyExc_TypeError, "bad \"quoting\" value"); return -1; } #define D_OFF(x) offsetof(DialectObj, x) static struct PyMemberDef Dialect_memberlist[] = { { "skipinitialspace", T_INT, D_OFF(skipinitialspace), READONLY }, { "doublequote", T_INT, D_OFF(doublequote), READONLY }, { "strict", T_INT, D_OFF(strict), READONLY }, { NULL } }; static PyGetSetDef Dialect_getsetlist[] = { { "delimiter", (getter)Dialect_get_delimiter}, { "escapechar", (getter)Dialect_get_escapechar}, { "lineterminator", (getter)Dialect_get_lineterminator}, { "quotechar", (getter)Dialect_get_quotechar}, { "quoting", (getter)Dialect_get_quoting}, {NULL}, }; static void Dialect_dealloc(DialectObj *self) { Py_XDECREF(self->lineterminator); Py_TYPE(self)->tp_free((PyObject *)self); } static char *dialect_kws[] = { "dialect", "delimiter", "doublequote", "escapechar", "lineterminator", "quotechar", "quoting", "skipinitialspace", "strict", NULL }; static PyObject * dialect_new(PyTypeObject *type, PyObject *args, PyObject *kwargs) { DialectObj *self; PyObject *ret = NULL; PyObject *dialect = NULL; PyObject *delimiter = NULL; PyObject *doublequote = NULL; PyObject *escapechar = NULL; PyObject *lineterminator = NULL; PyObject *quotechar = NULL; PyObject *quoting = NULL; PyObject *skipinitialspace = NULL; PyObject *strict = NULL; if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|OOOOOOOOO", dialect_kws, &dialect, &delimiter, &doublequote, &escapechar, &lineterminator, "echar, "ing, &skipinitialspace, &strict)) return NULL; if (dialect != NULL) { if (PyUnicode_Check(dialect)) { dialect = get_dialect_from_registry(dialect); if (dialect == NULL) return NULL; } else Py_INCREF(dialect); /* Can we reuse this instance? */ if (PyObject_TypeCheck(dialect, &Dialect_Type) && delimiter == NULL && doublequote == NULL && escapechar == NULL && lineterminator == NULL && quotechar == NULL && quoting == NULL && skipinitialspace == NULL && strict == NULL) return dialect; } self = (DialectObj *)type->tp_alloc(type, 0); if (self == NULL) { Py_XDECREF(dialect); return NULL; } self->lineterminator = NULL; Py_XINCREF(delimiter); Py_XINCREF(doublequote); Py_XINCREF(escapechar); Py_XINCREF(lineterminator); Py_XINCREF(quotechar); Py_XINCREF(quoting); Py_XINCREF(skipinitialspace); Py_XINCREF(strict); if (dialect != NULL) { #define DIALECT_GETATTR(v, n) \ if (v == NULL) \ v = PyObject_GetAttrString(dialect, n) DIALECT_GETATTR(delimiter, "delimiter"); DIALECT_GETATTR(doublequote, "doublequote"); DIALECT_GETATTR(escapechar, "escapechar"); DIALECT_GETATTR(lineterminator, "lineterminator"); DIALECT_GETATTR(quotechar, "quotechar"); DIALECT_GETATTR(quoting, "quoting"); DIALECT_GETATTR(skipinitialspace, "skipinitialspace"); DIALECT_GETATTR(strict, "strict"); PyErr_Clear(); } /* check types and convert to C values */ #define DIASET(meth, name, target, src, dflt) \ if (meth(name, target, src, dflt)) \ goto err DIASET(_set_char, "delimiter", &self->delimiter, delimiter, ','); DIASET(_set_bool, "doublequote", &self->doublequote, doublequote, 1); DIASET(_set_char, "escapechar", &self->escapechar, escapechar, 0); DIASET(_set_str, "lineterminator", &self->lineterminator, lineterminator, "\r\n"); DIASET(_set_char, "quotechar", &self->quotechar, quotechar, '"'); DIASET(_set_int, "quoting", &self->quoting, quoting, QUOTE_MINIMAL); DIASET(_set_bool, "skipinitialspace", &self->skipinitialspace, skipinitialspace, 0); DIASET(_set_bool, "strict", &self->strict, strict, 0); /* validate options */ if (dialect_check_quoting(self->quoting)) goto err; if (self->delimiter == 0) { PyErr_SetString(PyExc_TypeError, "\"delimiter\" must be a 1-character string"); goto err; } if (quotechar == Py_None && quoting == NULL) self->quoting = QUOTE_NONE; if (self->quoting != QUOTE_NONE && self->quotechar == 0) { PyErr_SetString(PyExc_TypeError, "quotechar must be set if quoting enabled"); goto err; } if (self->lineterminator == 0) { PyErr_SetString(PyExc_TypeError, "lineterminator must be set"); goto err; } ret = (PyObject *)self; Py_INCREF(self); err: Py_XDECREF(self); Py_XDECREF(dialect); Py_XDECREF(delimiter); Py_XDECREF(doublequote); Py_XDECREF(escapechar); Py_XDECREF(lineterminator); Py_XDECREF(quotechar); Py_XDECREF(quoting); Py_XDECREF(skipinitialspace); Py_XDECREF(strict); return ret; } PyDoc_STRVAR(Dialect_Type_doc, "CSV dialect\n" "\n" "The Dialect type records CSV parsing and generation options.\n"); static PyTypeObject Dialect_Type = { PyVarObject_HEAD_INIT(NULL, 0) "_csv.Dialect", /* tp_name */ sizeof(DialectObj), /* tp_basicsize */ 0, /* tp_itemsize */ /* methods */ (destructor)Dialect_dealloc, /* tp_dealloc */ (printfunc)0, /* tp_print */ (getattrfunc)0, /* tp_getattr */ (setattrfunc)0, /* tp_setattr */ 0, /* tp_reserved */ (reprfunc)0, /* tp_repr */ 0, /* tp_as_number */ 0, /* tp_as_sequence */ 0, /* tp_as_mapping */ (hashfunc)0, /* tp_hash */ (ternaryfunc)0, /* tp_call */ (reprfunc)0, /* tp_str */ 0, /* tp_getattro */ 0, /* tp_setattro */ 0, /* tp_as_buffer */ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE, /* tp_flags */ Dialect_Type_doc, /* tp_doc */ 0, /* tp_traverse */ 0, /* tp_clear */ 0, /* tp_richcompare */ 0, /* tp_weaklistoffset */ 0, /* tp_iter */ 0, /* tp_iternext */ 0, /* tp_methods */ Dialect_memberlist, /* tp_members */ Dialect_getsetlist, /* 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 */ dialect_new, /* tp_new */ 0, /* tp_free */ }; /* * Return an instance of the dialect type, given a Python instance or kwarg * description of the dialect */ static PyObject * _call_dialect(PyObject *dialect_inst, PyObject *kwargs) { PyObject *type = (PyObject *)&Dialect_Type; if (dialect_inst) { return _PyObject_FastCallDict(type, &dialect_inst, 1, kwargs); } else { return _PyObject_FastCallDict(type, NULL, 0, kwargs); } } /* * READER */ static int parse_save_field(ReaderObj *self) { PyObject *field; field = PyUnicode_FromKindAndData(PyUnicode_4BYTE_KIND, (void *) self->field, self->field_len); if (field == NULL) return -1; self->field_len = 0; if (self->numeric_field) { PyObject *tmp; self->numeric_field = 0; tmp = PyNumber_Float(field); Py_DECREF(field); if (tmp == NULL) return -1; field = tmp; } if (PyList_Append(self->fields, field) < 0) { Py_DECREF(field); return -1; } Py_DECREF(field); return 0; } static int parse_grow_buff(ReaderObj *self) { if (self->field_size == 0) { self->field_size = 4096; if (self->field != NULL) PyMem_Free(self->field); self->field = PyMem_New(Py_UCS4, self->field_size); } else { Py_UCS4 *field = self->field; if (self->field_size > PY_SSIZE_T_MAX / 2) { PyErr_NoMemory(); return 0; } self->field_size *= 2; self->field = PyMem_Resize(field, Py_UCS4, self->field_size); } if (self->field == NULL) { PyErr_NoMemory(); return 0; } return 1; } static int parse_add_char(ReaderObj *self, Py_UCS4 c) { if (self->field_len >= _csvstate_global->field_limit) { PyErr_Format(_csvstate_global->error_obj, "field larger than field limit (%ld)", _csvstate_global->field_limit); return -1; } if (self->field_len == self->field_size && !parse_grow_buff(self)) return -1; self->field[self->field_len++] = c; return 0; } static int parse_process_char(ReaderObj *self, Py_UCS4 c) { DialectObj *dialect = self->dialect; switch (self->state) { case START_RECORD: /* start of record */ if (c == '\0') /* empty line - return [] */ break; else if (c == '\n' || c == '\r') { self->state = EAT_CRNL; break; } /* normal character - handle as START_FIELD */ self->state = START_FIELD; /* fallthru */ case START_FIELD: /* expecting field */ if (c == '\n' || c == '\r' || c == '\0') { /* save empty field - return [fields] */ if (parse_save_field(self) < 0) return -1; self->state = (c == '\0' ? START_RECORD : EAT_CRNL); } else if (c == dialect->quotechar && dialect->quoting != QUOTE_NONE) { /* start quoted field */ self->state = IN_QUOTED_FIELD; } else if (c == dialect->escapechar) { /* possible escaped character */ self->state = ESCAPED_CHAR; } else if (c == ' ' && dialect->skipinitialspace) /* ignore space at start of field */ ; else if (c == dialect->delimiter) { /* save empty field */ if (parse_save_field(self) < 0) return -1; } else { /* begin new unquoted field */ if (dialect->quoting == QUOTE_NONNUMERIC) self->numeric_field = 1; if (parse_add_char(self, c) < 0) return -1; self->state = IN_FIELD; } break; case ESCAPED_CHAR: if (c == '\n' || c=='\r') { if (parse_add_char(self, c) < 0) return -1; self->state = AFTER_ESCAPED_CRNL; break; } if (c == '\0') c = '\n'; if (parse_add_char(self, c) < 0) return -1; self->state = IN_FIELD; break; case AFTER_ESCAPED_CRNL: if (c == '\0') break; /*fallthru*/ case IN_FIELD: /* in unquoted field */ if (c == '\n' || c == '\r' || c == '\0') { /* end of line - return [fields] */ if (parse_save_field(self) < 0) return -1; self->state = (c == '\0' ? START_RECORD : EAT_CRNL); } else if (c == dialect->escapechar) { /* possible escaped character */ self->state = ESCAPED_CHAR; } else if (c == dialect->delimiter) { /* save field - wait for new field */ if (parse_save_field(self) < 0) return -1; self->state = START_FIELD; } else { /* normal character - save in field */ if (parse_add_char(self, c) < 0) return -1; } break; case IN_QUOTED_FIELD: /* in quoted field */ if (c == '\0') ; else if (c == dialect->escapechar) { /* Possible escape character */ self->state = ESCAPE_IN_QUOTED_FIELD; } else if (c == dialect->quotechar && dialect->quoting != QUOTE_NONE) { if (dialect->doublequote) { /* doublequote; " represented by "" */ self->state = QUOTE_IN_QUOTED_FIELD; } else { /* end of quote part of field */ self->state = IN_FIELD; } } else { /* normal character - save in field */ if (parse_add_char(self, c) < 0) return -1; } break; case ESCAPE_IN_QUOTED_FIELD: if (c == '\0') c = '\n'; if (parse_add_char(self, c) < 0) return -1; self->state = IN_QUOTED_FIELD; break; case QUOTE_IN_QUOTED_FIELD: /* doublequote - seen a quote in a quoted field */ if (dialect->quoting != QUOTE_NONE && c == dialect->quotechar) { /* save "" as " */ if (parse_add_char(self, c) < 0) return -1; self->state = IN_QUOTED_FIELD; } else if (c == dialect->delimiter) { /* save field - wait for new field */ if (parse_save_field(self) < 0) return -1; self->state = START_FIELD; } else if (c == '\n' || c == '\r' || c == '\0') { /* end of line - return [fields] */ if (parse_save_field(self) < 0) return -1; self->state = (c == '\0' ? START_RECORD : EAT_CRNL); } else if (!dialect->strict) { if (parse_add_char(self, c) < 0) return -1; self->state = IN_FIELD; } else { /* illegal */ PyErr_Format(_csvstate_global->error_obj, "'%c' expected after '%c'", dialect->delimiter, dialect->quotechar); return -1; } break; case EAT_CRNL: if (c == '\n' || c == '\r') ; else if (c == '\0') self->state = START_RECORD; else { PyErr_Format(_csvstate_global->error_obj, "new-line character seen in unquoted field - do you need to open the file in universal-newline mode?"); return -1; } break; } return 0; } static int parse_reset(ReaderObj *self) { Py_XSETREF(self->fields, PyList_New(0)); if (self->fields == NULL) return -1; self->field_len = 0; self->state = START_RECORD; self->numeric_field = 0; return 0; } static PyObject * Reader_iternext(ReaderObj *self) { PyObject *fields = NULL; Py_UCS4 c; Py_ssize_t pos, linelen; unsigned int kind; void *data; PyObject *lineobj; if (parse_reset(self) < 0) return NULL; do { lineobj = PyIter_Next(self->input_iter); if (lineobj == NULL) { /* End of input OR exception */ if (!PyErr_Occurred() && (self->field_len != 0 || self->state == IN_QUOTED_FIELD)) { if (self->dialect->strict) PyErr_SetString(_csvstate_global->error_obj, "unexpected end of data"); else if (parse_save_field(self) >= 0) break; } return NULL; } if (!PyUnicode_Check(lineobj)) { PyErr_Format(_csvstate_global->error_obj, "iterator should return strings, " "not %.200s " "(did you open the file in text mode?)", lineobj->ob_type->tp_name ); Py_DECREF(lineobj); return NULL; } if (PyUnicode_READY(lineobj) == -1) { Py_DECREF(lineobj); return NULL; } ++self->line_num; kind = PyUnicode_KIND(lineobj); data = PyUnicode_DATA(lineobj); pos = 0; linelen = PyUnicode_GET_LENGTH(lineobj); while (linelen--) { c = PyUnicode_READ(kind, data, pos); if (c == '\0') { Py_DECREF(lineobj); PyErr_Format(_csvstate_global->error_obj, "line contains NULL byte"); goto err; } if (parse_process_char(self, c) < 0) { Py_DECREF(lineobj); goto err; } pos++; } Py_DECREF(lineobj); if (parse_process_char(self, 0) < 0) goto err; } while (self->state != START_RECORD); fields = self->fields; self->fields = NULL; err: return fields; } static void Reader_dealloc(ReaderObj *self) { PyObject_GC_UnTrack(self); Py_XDECREF(self->dialect); Py_XDECREF(self->input_iter); Py_XDECREF(self->fields); if (self->field != NULL) PyMem_Free(self->field); PyObject_GC_Del(self); } static int Reader_traverse(ReaderObj *self, visitproc visit, void *arg) { Py_VISIT(self->dialect); Py_VISIT(self->input_iter); Py_VISIT(self->fields); return 0; } static int Reader_clear(ReaderObj *self) { Py_CLEAR(self->dialect); Py_CLEAR(self->input_iter); Py_CLEAR(self->fields); return 0; } PyDoc_STRVAR(Reader_Type_doc, "CSV reader\n" "\n" "Reader objects are responsible for reading and parsing tabular data\n" "in CSV format.\n" ); static struct PyMethodDef Reader_methods[] = { { NULL, NULL } }; #define R_OFF(x) offsetof(ReaderObj, x) static struct PyMemberDef Reader_memberlist[] = { { "dialect", T_OBJECT, R_OFF(dialect), READONLY }, { "line_num", T_ULONG, R_OFF(line_num), READONLY }, { NULL } }; static PyTypeObject Reader_Type = { PyVarObject_HEAD_INIT(NULL, 0) "_csv.reader", /*tp_name*/ sizeof(ReaderObj), /*tp_basicsize*/ 0, /*tp_itemsize*/ /* methods */ (destructor)Reader_dealloc, /*tp_dealloc*/ (printfunc)0, /*tp_print*/ (getattrfunc)0, /*tp_getattr*/ (setattrfunc)0, /*tp_setattr*/ 0, /*tp_reserved*/ (reprfunc)0, /*tp_repr*/ 0, /*tp_as_number*/ 0, /*tp_as_sequence*/ 0, /*tp_as_mapping*/ (hashfunc)0, /*tp_hash*/ (ternaryfunc)0, /*tp_call*/ (reprfunc)0, /*tp_str*/ 0, /*tp_getattro*/ 0, /*tp_setattro*/ 0, /*tp_as_buffer*/ Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE | Py_TPFLAGS_HAVE_GC, /*tp_flags*/ Reader_Type_doc, /*tp_doc*/ (traverseproc)Reader_traverse, /*tp_traverse*/ (inquiry)Reader_clear, /*tp_clear*/ 0, /*tp_richcompare*/ 0, /*tp_weaklistoffset*/ PyObject_SelfIter, /*tp_iter*/ (getiterfunc)Reader_iternext, /*tp_iternext*/ Reader_methods, /*tp_methods*/ Reader_memberlist, /*tp_members*/ 0, /*tp_getset*/ }; static PyObject * csv_reader(PyObject *module, PyObject *args, PyObject *keyword_args) { PyObject * iterator, * dialect = NULL; ReaderObj * self = PyObject_GC_New(ReaderObj, &Reader_Type); if (!self) return NULL; self->dialect = NULL; self->fields = NULL; self->input_iter = NULL; self->field = NULL; self->field_size = 0; self->line_num = 0; if (parse_reset(self) < 0) { Py_DECREF(self); return NULL; } if (!PyArg_UnpackTuple(args, "", 1, 2, &iterator, &dialect)) { Py_DECREF(self); return NULL; } self->input_iter = PyObject_GetIter(iterator); if (self->input_iter == NULL) { PyErr_SetString(PyExc_TypeError, "argument 1 must be an iterator"); Py_DECREF(self); return NULL; } self->dialect = (DialectObj *)_call_dialect(dialect, keyword_args); if (self->dialect == NULL) { Py_DECREF(self); return NULL; } PyObject_GC_Track(self); return (PyObject *)self; } /* * WRITER */ /* ---------------------------------------------------------------- */ static void join_reset(WriterObj *self) { self->rec_len = 0; self->num_fields = 0; } #define MEM_INCR 32768 /* Calculate new record length or append field to record. Return new * record length. */ static Py_ssize_t join_append_data(WriterObj *self, unsigned int field_kind, void *field_data, |
| 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. |