/usr/include/glibmm-2.4/glibmm/regex.h is in libglibmm-2.4-dev 2.42.0-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 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 | // -*- c++ -*-
// Generated by gmmproc 2.42.0 -- DO NOT MODIFY!
#ifndef _GLIBMM_REGEX_H
#define _GLIBMM_REGEX_H
/* Copyright (C) 2007 The glibmm Development Team
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <glibmmconfig.h>
#include <glibmm/refptr.h>
#include <glibmm/ustring.h>
#include <glibmm/error.h>
#include <glibmm/arrayhandle.h>
#include <glib.h>
#ifndef DOXYGEN_SHOULD_SKIP_THIS
typedef struct _GRegex GRegex;
#endif
namespace Glib
{
/** @addtogroup glibmmEnums glibmm Enums and Flags */
/**
* @var RegexCompileFlags REGEX_CASELESS
* Letters in the pattern match both upper- and lowercase letters. This option can be changed within a pattern by a "(?i)" option setting.
*
* @var RegexCompileFlags REGEX_MULTILINE
* By default, GRegex treats the strings as consisting of a single line of characters (even if it actually contains newlines). The "start of line" metacharacter ("^") matches only at the start of the string, while the "end of line" metacharacter ("$") matches only at the end of the string, or before a terminating newline (unless REGEX_DOLLAR_ENDONLY is set). When REGEX_MULTILINE is set, the "start of line" and "end of line" constructs match immediately following or immediately before any newline in the string, respectively, as well as at the very start and end. This can be changed within a pattern by a "(?m)" option setting.
*
* @var RegexCompileFlags REGEX_DOTALL
* A dot metacharater (".") in the pattern matches all characters, including newlines. Without it, newlines are excluded. This option can be changed within a pattern by a ("?s") option setting.
*
* @var RegexCompileFlags REGEX_EXTENDED
* Whitespace data characters in the pattern are totally ignored except when escaped or inside a character class. Whitespace does not include the VT character (code 11). In addition, characters between an unescaped "#" outside a character class and the next newline character, inclusive, are also ignored. This can be changed within a pattern by a "(?x)" option setting.
*
* @var RegexCompileFlags REGEX_ANCHORED
* The pattern is forced to be "anchored", that is, it is constrained to match only at the first matching point in the string that is being searched. This effect can also be achieved by appropriate constructs in the pattern itself such as the "^" metacharater.
*
* @var RegexCompileFlags REGEX_DOLLAR_ENDONLY
* A dollar metacharacter ("$") in the pattern matches only at the end of the string. Without this option, a dollar also matches immediately before the final character if it is a newline (but not before any other newlines). This option is ignored if REGEX_MULTILINE is set.
*
* @var RegexCompileFlags REGEX_UNGREEDY
* Inverts the "greediness" of the quantifiers so that they are not greedy by default, but become greedy if followed by "?". It can also be set by a "(?U)" option setting within the pattern.
*
* @var RegexCompileFlags REGEX_RAW
* Usually strings must be valid UTF-8 strings, using this flag they are considered as a raw sequence of bytes.
*
* @var RegexCompileFlags REGEX_NO_AUTO_CAPTURE
* Disables the use of numbered capturing parentheses in the pattern. Any opening parenthesis that is not followed by "?" behaves as if it were followed by "?:" but named parentheses can still be used for capturing (and they acquire numbers in the usual way).
*
* @var RegexCompileFlags REGEX_OPTIMIZE
* Optimize the regular expression. If the pattern will be used many times, then it may be worth the effort to optimize it to improve the speed of matches.
*
* @var RegexCompileFlags REGEX_FIRSTLINE
* Limits an unanchored pattern to match before (or at) the first newline. @newin{2,34}
*
* @var RegexCompileFlags REGEX_DUPNAMES
* Names used to identify capturing subpatterns need not be unique. This can be helpful for certain types of pattern when it is known that only one instance of the named subpattern can ever be matched.
*
* @var RegexCompileFlags REGEX_NEWLINE_CR
* Usually any newline character or character sequence is recognized. If this option is set, the only recognized newline character is '\\r'.
*
* @var RegexCompileFlags REGEX_NEWLINE_LF
* Usually any newline character or character sequence is recognized. If this option is set, the only recognized newline character is '\\n'.
*
* @var RegexCompileFlags REGEX_NEWLINE_CRLF
* Usually any newline character or character sequence is recognized. If this option is set, the only recognized newline character sequence is '\\r\\n'.
*
* @var RegexCompileFlags REGEX_NEWLINE_ANYCRLF
* Usually any newline character or character sequence is recognized. If this option is set, the only recognized newline character sequences are '\\r', '\\n', and '\\r\\n'. @newin{2,34}
*
* @var RegexCompileFlags REGEX_BSR_ANYCRLF
* Usually any newline character or character sequence is recognised. If this option is set, then "\\R" only recognizes the newline characters '\\r', '\\n' and '\\r\\n'. @newin{2,34}
*
* @var RegexCompileFlags REGEX_JAVASCRIPT_COMPAT
* Changes behaviour so that it is compatible with JavaScript rather than PCRE. @newin{2,34}
*
* @enum RegexCompileFlags
*
* Flags specifying compile-time options.
*
* @newin{2,14}
* @ingroup glibmmEnums
* @par Bitwise operators:
* <tt>%RegexCompileFlags operator|(RegexCompileFlags, RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags operator&(RegexCompileFlags, RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags operator^(RegexCompileFlags, RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags operator~(RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags& operator|=(RegexCompileFlags&, RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags& operator&=(RegexCompileFlags&, RegexCompileFlags)</tt><br>
* <tt>%RegexCompileFlags& operator^=(RegexCompileFlags&, RegexCompileFlags)</tt><br>
*/
enum RegexCompileFlags
{
REGEX_CASELESS = 1 << 0,
REGEX_MULTILINE = 1 << 1,
REGEX_DOTALL = 1 << 2,
REGEX_EXTENDED = 1 << 3,
REGEX_ANCHORED = 1 << 4,
REGEX_DOLLAR_ENDONLY = 1 << 5,
REGEX_UNGREEDY = 1 << 9,
REGEX_RAW = 1 << 11,
REGEX_NO_AUTO_CAPTURE = 1 << 12,
REGEX_OPTIMIZE = 1 << 13,
REGEX_FIRSTLINE = 1 << 18,
REGEX_DUPNAMES = 1 << 19,
REGEX_NEWLINE_CR = 1 << 20,
REGEX_NEWLINE_LF = 1 << 21,
REGEX_NEWLINE_CRLF = 0x300000,
REGEX_NEWLINE_ANYCRLF = 1048576 | 1 << 22,
REGEX_BSR_ANYCRLF = 1 << 23,
REGEX_JAVASCRIPT_COMPAT = 1 << 25
};
/** @ingroup glibmmEnums */
inline RegexCompileFlags operator|(RegexCompileFlags lhs, RegexCompileFlags rhs)
{ return static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags operator&(RegexCompileFlags lhs, RegexCompileFlags rhs)
{ return static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags operator^(RegexCompileFlags lhs, RegexCompileFlags rhs)
{ return static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags operator~(RegexCompileFlags flags)
{ return static_cast<RegexCompileFlags>(~static_cast<unsigned>(flags)); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags& operator|=(RegexCompileFlags& lhs, RegexCompileFlags rhs)
{ return (lhs = static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs))); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags& operator&=(RegexCompileFlags& lhs, RegexCompileFlags rhs)
{ return (lhs = static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs))); }
/** @ingroup glibmmEnums */
inline RegexCompileFlags& operator^=(RegexCompileFlags& lhs, RegexCompileFlags rhs)
{ return (lhs = static_cast<RegexCompileFlags>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs))); }
/**
* @var RegexMatchFlags REGEX_MATCH_ANCHORED
* The pattern is forced to be "anchored", that is, it is constrained to match only at the first matching point in the string that is being searched. This effect can also be achieved by appropriate constructs in the pattern itself such as the "^" metacharater.
*
* @var RegexMatchFlags REGEX_MATCH_NOTBOL
* Specifies that first character of the string is not the beginning of a line, so the circumflex metacharacter should not match before it. Setting this without REGEX_MULTILINE (at compile time) causes circumflex never to match. This option affects only the behaviour of the circumflex metacharacter, it does not affect "\\A".
*
* @var RegexMatchFlags REGEX_MATCH_NOTEOL
* Specifies that the end of the subject string is not the end of a line, so the dollar metacharacter should not match it nor (except in multiline mode) a newline immediately before it. Setting this without REGEX_MULTILINE (at compile time) causes dollar never to match. This option affects only the behaviour of the dollar metacharacter, it does not affect "\\Z" or "\\z".
*
* @var RegexMatchFlags REGEX_MATCH_NOTEMPTY
* An empty string is not considered to be a valid match if this option is set. If there are alternatives in the pattern, they are tried. If all the alternatives match the empty string, the entire match fails. For example, if the pattern "a?b?" is applied to a string not beginning with "a" or "b", it matches the empty string at the start of the string. With this flag set, this match is not valid, so GRegex searches further into the string for occurrences of "a" or "b".
*
* @var RegexMatchFlags REGEX_MATCH_PARTIAL
* Turns on the partial matching feature, for more documentation on partial matching see g_match_info_is_partial_match().
*
* @var RegexMatchFlags REGEX_MATCH_NEWLINE_CR
* Overrides the newline definition set when creating a new Regex, setting the '\\r' character as line terminator.
*
* @var RegexMatchFlags REGEX_MATCH_NEWLINE_LF
* Overrides the newline definition set when creating a new Regex, setting the '\\n' character as line terminator.
*
* @var RegexMatchFlags REGEX_MATCH_NEWLINE_CRLF
* Overrides the newline definition set when creating a new Regex, setting the '\\r\\n' characters sequence as line terminator.
*
* @var RegexMatchFlags REGEX_MATCH_NEWLINE_ANY
* Overrides the newline definition set when creating a new Regex, any Unicode newline sequence is recognised as a newline. These are '\\r', '\\n' and '\\rn', and the single characters U+000B LINE TABULATION, U+000C FORM FEED (FF), U+0085 NEXT LINE (NEL), U+2028 LINE SEPARATOR and U+2029 PARAGRAPH SEPARATOR.
*
* @var RegexMatchFlags REGEX_MATCH_NEWLINE_ANYCRLF
* Overrides the newline definition set when creating a new Regex; any '\\r', '\\n', or '\\r\\n' character sequence is recognized as a newline. @newin{2,34}
*
* @var RegexMatchFlags REGEX_MATCH_BSR_ANYCRLF
* Overrides the newline definition for "\\R" set when creating a new Regex; only '\\r', '\\n', or '\\r\\n' character sequences are recognized as a newline by "\\R". @newin{2,34}
*
* @var RegexMatchFlags REGEX_MATCH_BSR_ANY
* Overrides the newline definition for "\\R" set when creating a new Regex; any Unicode newline character or character sequence are recognized as a newline by "\\R". These are '\\r', '\\n' and '\\rn', and the single characters U+000B LINE TABULATION, U+000C FORM FEED (FF), U+0085 NEXT LINE (NEL), U+2028 LINE SEPARATOR and U+2029 PARAGRAPH SEPARATOR. @newin{2,34}
*
* @var RegexMatchFlags REGEX_MATCH_PARTIAL_SOFT
* An alias for REGEX_MATCH_PARTIAL. @newin{2,34}
*
* @var RegexMatchFlags REGEX_MATCH_PARTIAL_HARD
* Turns on the partial matching feature. In contrast to to REGEX_MATCH_PARTIAL_SOFT, this stops matching as soon as a partial match is found, without continuing to search for a possible complete match. See g_match_info_is_partial_match() for more information. @newin{2,34}
*
* @var RegexMatchFlags REGEX_MATCH_NOTEMPTY_ATSTART
* Like REGEX_MATCH_NOTEMPTY, but only applied to the start of the matched string. For anchored patterns this can only happen for pattern containing "\\K". @newin{2,34}
*
* @enum RegexMatchFlags
*
* Flags specifying match-time options.
*
* @newin{2,14}
* @ingroup glibmmEnums
* @par Bitwise operators:
* <tt>%RegexMatchFlags operator|(RegexMatchFlags, RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags operator&(RegexMatchFlags, RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags operator^(RegexMatchFlags, RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags operator~(RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags& operator|=(RegexMatchFlags&, RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags& operator&=(RegexMatchFlags&, RegexMatchFlags)</tt><br>
* <tt>%RegexMatchFlags& operator^=(RegexMatchFlags&, RegexMatchFlags)</tt><br>
*/
enum RegexMatchFlags
{
REGEX_MATCH_ANCHORED = 1 << 4,
REGEX_MATCH_NOTBOL = 1 << 7,
REGEX_MATCH_NOTEOL = 1 << 8,
REGEX_MATCH_NOTEMPTY = 1 << 10,
REGEX_MATCH_PARTIAL = 1 << 15,
REGEX_MATCH_NEWLINE_CR = 1 << 20,
REGEX_MATCH_NEWLINE_LF = 1 << 21,
REGEX_MATCH_NEWLINE_CRLF = 0x300000,
REGEX_MATCH_NEWLINE_ANY = 1 << 22,
REGEX_MATCH_NEWLINE_ANYCRLF = 0x500000,
REGEX_MATCH_BSR_ANYCRLF = 1 << 23,
REGEX_MATCH_BSR_ANY = 1 << 24,
REGEX_MATCH_PARTIAL_SOFT = 0x8000,
REGEX_MATCH_PARTIAL_HARD = 1 << 27,
REGEX_MATCH_NOTEMPTY_ATSTART = 1 << 28
};
/** @ingroup glibmmEnums */
inline RegexMatchFlags operator|(RegexMatchFlags lhs, RegexMatchFlags rhs)
{ return static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags operator&(RegexMatchFlags lhs, RegexMatchFlags rhs)
{ return static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags operator^(RegexMatchFlags lhs, RegexMatchFlags rhs)
{ return static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs)); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags operator~(RegexMatchFlags flags)
{ return static_cast<RegexMatchFlags>(~static_cast<unsigned>(flags)); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags& operator|=(RegexMatchFlags& lhs, RegexMatchFlags rhs)
{ return (lhs = static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) | static_cast<unsigned>(rhs))); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags& operator&=(RegexMatchFlags& lhs, RegexMatchFlags rhs)
{ return (lhs = static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) & static_cast<unsigned>(rhs))); }
/** @ingroup glibmmEnums */
inline RegexMatchFlags& operator^=(RegexMatchFlags& lhs, RegexMatchFlags rhs)
{ return (lhs = static_cast<RegexMatchFlags>(static_cast<unsigned>(lhs) ^ static_cast<unsigned>(rhs))); }
/** Exception class for Regex
*/
class RegexError : public Glib::Error
{
public:
enum Code
{
COMPILE = 0,
OPTIMIZE = 1,
REPLACE = 2,
MATCH = 3,
INTERNAL = 4,
STRAY_BACKSLASH = 101,
MISSING_CONTROL_CHAR = 102,
UNRECOGNIZED_ESCAPE = 103,
QUANTIFIERS_OUT_OF_ORDER = 104,
QUANTIFIER_TOO_BIG = 105,
UNTERMINATED_CHARACTER_CLASS = 106,
INVALID_ESCAPE_IN_CHARACTER_CLASS = 107,
RANGE_OUT_OF_ORDER = 108,
NOTHING_TO_REPEAT = 109,
UNRECOGNIZED_CHARACTER = 112,
POSIX_NAMED_CLASS_OUTSIDE_CLASS = 113,
UNMATCHED_PARENTHESIS = 114,
INEXISTENT_SUBPATTERN_REFERENCE = 115,
UNTERMINATED_COMMENT = 118,
EXPRESSION_TOO_LARGE = 120,
MEMORY_ERROR = 121,
VARIABLE_LENGTH_LOOKBEHIND = 125,
MALFORMED_CONDITION = 126,
TOO_MANY_CONDITIONAL_BRANCHES = 127,
ASSERTION_EXPECTED = 128,
UNKNOWN_POSIX_CLASS_NAME = 130,
POSIX_COLLATING_ELEMENTS_NOT_SUPPORTED = 131,
HEX_CODE_TOO_LARGE = 134,
INVALID_CONDITION = 135,
SINGLE_BYTE_MATCH_IN_LOOKBEHIND = 136,
INFINITE_LOOP = 140,
MISSING_SUBPATTERN_NAME_TERMINATOR = 142,
DUPLICATE_SUBPATTERN_NAME = 143,
MALFORMED_PROPERTY = 146,
UNKNOWN_PROPERTY = 147,
SUBPATTERN_NAME_TOO_LONG = 148,
TOO_MANY_SUBPATTERNS = 149,
INVALID_OCTAL_VALUE = 151,
TOO_MANY_BRANCHES_IN_DEFINE = 154,
DEFINE_REPETION = 155,
INCONSISTENT_NEWLINE_OPTIONS = 156,
MISSING_BACK_REFERENCE = 157,
INVALID_RELATIVE_REFERENCE = 158,
BACKTRACKING_CONTROL_VERB_ARGUMENT_FORBIDDEN = 159,
UNKNOWN_BACKTRACKING_CONTROL_VERB = 160,
NUMBER_TOO_BIG = 161,
MISSING_SUBPATTERN_NAME = 162,
MISSING_DIGIT = 163,
INVALID_DATA_CHARACTER = 164,
EXTRA_SUBPATTERN_NAME = 165,
BACKTRACKING_CONTROL_VERB_ARGUMENT_REQUIRED = 166,
INVALID_CONTROL_CHAR = 168,
MISSING_NAME = 169,
NOT_SUPPORTED_IN_CLASS = 171,
TOO_MANY_FORWARD_REFERENCES = 172,
NAME_TOO_LONG = 175,
CHARACTER_VALUE_TOO_LARGE = 176
};
RegexError(Code error_code, const Glib::ustring& error_message);
explicit RegexError(GError* gobject);
Code code() const;
#ifndef DOXYGEN_SHOULD_SKIP_THIS
private:
static void throw_func(GError* gobject);
friend void wrap_init(); // uses throw_func()
#endif //DOXYGEN_SHOULD_SKIP_THIS
};
class MatchInfo;
/** Perl-compatible regular expressions - matches strings against regular expressions.
*
* The Glib::Regex functions implement regular expression pattern matching using
* syntax and semantics similar to Perl regular expression.
*
* Some functions accept a start_position argument, setting it differs from just
* passing over a shortened string and setting REGEX_MATCH_NOTBOL in the case
* of a pattern that begins with any kind of lookbehind assertion. For example,
* consider the pattern "\Biss\B" which finds occurrences of "iss" in the middle
* of words. ("\B" matches only if the current position in the subject is not a
* word boundary.) When applied to the string "Mississipi" from the fourth byte,
* namely "issipi", it does not match, because "\B" is always false at the
* start of the subject, which is deemed to be a word boundary. However, if
* the entire string is passed , but with start_position set to 4, it finds the
* second occurrence of "iss" because it is able to look behind the starting point
* to discover that it is preceded by a letter.
*
* Note that, unless you set the REGEX_RAW flag, all the strings passed to these
* functions must be encoded in UTF-8. The lengths and the positions inside the
* strings are in bytes and not in characters, so, for instance,
* "\xc3\xa0" (i.e. "à") is two bytes long but it is treated as a single
* character. If you set REGEX_RAW the strings can be non-valid UTF-8 strings
* and a byte is treated as a character, so "\xc3\xa0" is two bytes and
* two characters long.
*
* When matching a pattern, "\n" matches only against a "\n" character in the
* string, and "\r" matches only a "\r" character. To match any newline sequence
* use "\R". This particular group matches either the two-character sequence
* CR + LF ("\r\n"), or one of the single characters LF (linefeed, U+000A, "\n"),
* VT (vertical tab, U+000B, "\v"), FF (formfeed, U+000C, "\f"), CR (carriage
* return, U+000D, "\r"), NEL (next line, U+0085), LS (line separator, U+2028),
* or PS (paragraph separator, U+2029).
*
* The behaviour of the dot, circumflex, and dollar metacharacters are affected
* by newline characters, the default is to recognize any newline character (the
* same characters recognized by "\R"). This can be changed with REGEX_NEWLINE_CR,
* REGEX_NEWLINE_LF and REGEX_NEWLINE_CRLF compile options, and with
* REGEX_MATCH_NEWLINE_ANY, REGEX_MATCH_NEWLINE_CR, REGEX_MATCH_NEWLINE_LF
* and REGEX_MATCH_NEWLINE_CRLF match options. These settings are also
* relevant when compiling a pattern if REGEX_EXTENDED is set, and an unescaped
* "#" outside a character class is encountered. This indicates a comment that
* lasts until after the next newline.
*
* Creating and manipulating the same Glib::Regex class from different threads is
* not a problem as Glib::Regex does not modify its internal state between creation and
* destruction, on the other hand Glib::MatchInfo is not threadsafe.
*
* The regular expressions low level functionalities are obtained through the
* excellent PCRE library written by Philip Hazel.
*
* @newin{2,14}
*/
class Regex
{
public:
#ifndef DOXYGEN_SHOULD_SKIP_THIS
typedef Regex CppObjectType;
typedef GRegex BaseObjectType;
#endif /* DOXYGEN_SHOULD_SKIP_THIS */
/** Increment the reference count for this object.
* You should never need to do this manually - use the object via a RefPtr instead.
*/
void reference() const;
/** Decrement the reference count for this object.
* You should never need to do this manually - use the object via a RefPtr instead.
*/
void unreference() const;
///Provides access to the underlying C instance.
GRegex* gobj();
///Provides access to the underlying C instance.
const GRegex* gobj() const;
///Provides access to the underlying C instance. The caller is responsible for unrefing it. Use when directly setting fields in structs.
GRegex* gobj_copy() const;
protected:
// Do not derive this. Glib::Regex can neither be constructed nor deleted.
Regex();
void operator delete(void*, std::size_t);
private:
// noncopyable
Regex(const Regex&);
Regex& operator=(const Regex&);
public:
static Glib::RefPtr<Glib::Regex> create(const Glib::ustring& pattern, RegexCompileFlags compile_options = static_cast<RegexCompileFlags>(0), RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/** Gets the pattern string associated with @a regex, i.e.\ a copy of
* the string passed to g_regex_new().
*
* @newin{2,14}
*
* @return The pattern of @a regex.
*/
Glib::ustring get_pattern() const;
/** Returns the number of the highest back reference
* in the pattern, or 0 if the pattern does not contain
* back references.
*
* @newin{2,14}
*
* @return The number of the highest back reference.
*/
int get_max_backref() const;
/** Returns the number of capturing subpatterns in the pattern.
*
* @newin{2,14}
*
* @return The number of capturing subpatterns.
*/
int get_capture_count() const;
/** Checks whether the pattern contains explicit CR or LF references.
*
* @newin{2,34}
*
* @return <tt>true</tt> if the pattern contains explicit CR or LF references.
*/
bool get_has_cr_or_lf() const;
/** Gets the number of characters in the longest lookbehind assertion in the
* pattern. This information is useful when doing multi-segment matching using
* the partial matching facilities.
*
* @newin{2,38}
*
* @return The number of characters in the longest lookbehind assertion.
*/
int get_max_lookbehind() const;
/** Retrieves the number of the subexpression named @a name.
*
* @newin{2,14}
*
* @param name Name of the subexpression.
* @return The number of the subexpression or -1 if @a name
* does not exists.
*/
int get_string_number(const Glib::ustring& name) const;
/** Returns the compile options that @a regex was created with.
*
* @newin{2,26}
*
* @return Flags from RegexCompileFlags.
*/
RegexCompileFlags get_compile_flags() const;
/** Returns the match options that @a regex was created with.
*
* @newin{2,26}
*
* @return Flags from RegexMatchFlags.
*/
RegexMatchFlags get_match_flags() const;
static Glib::ustring escape_string(const Glib::ustring& string);
/** Scans for a match in @a string for @a pattern.
*
* This function is equivalent to g_regex_match() but it does not
* require to compile the pattern with g_regex_new(), avoiding some
* lines of code when you need just to do a match without extracting
* substrings, capture counts, and so on.
*
* If this function is to be called on the same @a pattern more than
* once, it's more efficient to compile the pattern once with
* g_regex_new() and then use g_regex_match().
*
* @newin{2,14}
*
* @param pattern The regular expression.
* @param string The string to scan for matches.
* @param compile_options Compile options for the regular expression, or 0.
* @param match_options Match options, or 0.
* @return <tt>true</tt> if the string matched, <tt>false</tt> otherwise.
*/
static bool match_simple(const Glib::ustring& pattern, const Glib::ustring& string, RegexCompileFlags compile_options = static_cast<RegexCompileFlags>(0), RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/** Scans for a match in string for the pattern in @a regex.
* The @a match_options are combined with the match options specified
* when the @a regex structure was created, letting you have more
* flexibility in reusing Regex structures.
*
* A MatchInfo structure, used to get information on the match,
* is stored in @a match_info if not <tt>0</tt>. Note that if @a match_info
* is not <tt>0</tt> then it is created even if the function returns <tt>false</tt>,
* i.e. you must free it regardless if regular expression actually matched.
*
* To retrieve all the non-overlapping matches of the pattern in
* string you can use g_match_info_next().
*
*
* [C example ellipted]
*
* @a string is not copied and is used in MatchInfo internally. If
* you use any MatchInfo method (except g_match_info_free()) after
* freeing or modifying @a string then the behaviour is undefined.
*
* @newin{2,14}
*
* @param string The string to scan for matches.
* @param match_options Match options.
* @param match_info Pointer to location where to store
* the MatchInfo, or <tt>0</tt> if you do not need it.
* @return <tt>true</tt> is the string matched, <tt>false</tt> otherwise.
*/
bool match(
const Glib::ustring& string,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/// A match() method not requiring a Glib::MatchInfo.
bool match(const Glib::ustring& string, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/// A match() method with a start position and a Glib::MatchInfo.
bool match(
const Glib::ustring& string,
int start_position,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/** Scans for a match in string for the pattern in @a regex.
* The @a match_options are combined with the match options specified
* when the @a regex structure was created, letting you have more
* flexibility in reusing Regex structures.
*
* Setting @a start_position differs from just passing over a shortened
* string and setting REGEX_MATCH_NOTBOL in the case of a pattern
* that begins with any kind of lookbehind assertion, such as "\\b".
*
* A MatchInfo structure, used to get information on the match, is
* stored in @a match_info if not <tt>0</tt>. Note that if @a match_info is
* not <tt>0</tt> then it is created even if the function returns <tt>false</tt>,
* i.e. you must free it regardless if regular expression actually
* matched.
*
* @a string is not copied and is used in MatchInfo internally. If
* you use any MatchInfo method (except g_match_info_free()) after
* freeing or modifying @a string then the behaviour is undefined.
*
* To retrieve all the non-overlapping matches of the pattern in
* string you can use g_match_info_next().
*
*
* [C example ellipted]
*
* @newin{2,14}
*
* @param string The string to scan for matches.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param match_options Match options.
* @param match_info Pointer to location where to store
* the MatchInfo, or <tt>0</tt> if you do not need it.
* @return <tt>true</tt> is the string matched, <tt>false</tt> otherwise.
*/
bool match(
const Glib::ustring& string,
gssize string_len,
int start_position,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/// A match() method with a start position not requiring a Glib::MatchInfo.
bool match(const Glib::ustring& string, int start_position, RegexMatchFlags match_options);
/** A match() method with a string length and start position not requiring a
* Glib::MatchInfo.
*/
bool match(const Glib::ustring& string, gssize string_len, int start_position, RegexMatchFlags match_options);
/** Using the standard algorithm for regular expression matching only
* the longest match in the string is retrieved. This function uses
* a different algorithm so it can retrieve all the possible matches.
* For more documentation see g_regex_match_all_full().
*
* A MatchInfo structure, used to get information on the match, is
* stored in @a match_info if not <tt>0</tt>. Note that if @a match_info is
* not <tt>0</tt> then it is created even if the function returns <tt>false</tt>,
* i.e. you must free it regardless if regular expression actually
* matched.
*
* @a string is not copied and is used in MatchInfo internally. If
* you use any MatchInfo method (except g_match_info_free()) after
* freeing or modifying @a string then the behaviour is undefined.
*
* @newin{2,14}
*
* @param string The string to scan for matches.
* @param match_options Match options.
* @param match_info Pointer to location where to store
* the MatchInfo, or <tt>0</tt> if you do not need it.
* @return <tt>true</tt> is the string matched, <tt>false</tt> otherwise.
*/
bool match_all(
const Glib::ustring& string,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/// A match_all() method not requiring a Glib::MatchInfo.
bool match_all(const Glib::ustring& string, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/// A match_all() method with a start positon and a Glib::MatchInfo.
bool match_all(
const Glib::ustring& string,
int start_position,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/** Using the standard algorithm for regular expression matching only
* the longest match in the string is retrieved, it is not possible
* to obtain all the available matches. For instance matching
* "<a> <b> <c>" against the pattern "<.*>"
* you get "<a> <b> <c>".
*
* This function uses a different algorithm (called DFA, i.e. deterministic
* finite automaton), so it can retrieve all the possible matches, all
* starting at the same point in the string. For instance matching
* "<a> <b> <c>" against the pattern "<.*>;"
* you would obtain three matches: "<a> <b> <c>",
* "<a> <b>" and "<a>".
*
* The number of matched strings is retrieved using
* g_match_info_get_match_count(). To obtain the matched strings and
* their position you can use, respectively, g_match_info_fetch() and
* g_match_info_fetch_pos(). Note that the strings are returned in
* reverse order of length; that is, the longest matching string is
* given first.
*
* Note that the DFA algorithm is slower than the standard one and it
* is not able to capture substrings, so backreferences do not work.
*
* Setting @a start_position differs from just passing over a shortened
* string and setting REGEX_MATCH_NOTBOL in the case of a pattern
* that begins with any kind of lookbehind assertion, such as "\\b".
*
* A MatchInfo structure, used to get information on the match, is
* stored in @a match_info if not <tt>0</tt>. Note that if @a match_info is
* not <tt>0</tt> then it is created even if the function returns <tt>false</tt>,
* i.e. you must free it regardless if regular expression actually
* matched.
*
* @a string is not copied and is used in MatchInfo internally. If
* you use any MatchInfo method (except g_match_info_free()) after
* freeing or modifying @a string then the behaviour is undefined.
*
* @newin{2,14}
*
* @param string The string to scan for matches.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param match_options Match options.
* @param match_info Pointer to location where to store
* the MatchInfo, or <tt>0</tt> if you do not need it.
* @return <tt>true</tt> is the string matched, <tt>false</tt> otherwise.
*/
/// @throw Glib::Error.
bool match_all(
const Glib::ustring& string,
gssize string_len,
int start_position,
Glib::MatchInfo& match_info,
RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0)
);
/** A match_all() method with a start position not requiring a
* Glib::MatchInfo.
*/
bool match_all(const Glib::ustring& string, int start_position, RegexMatchFlags match_options);
/** A match_all() method with a start position and a string length not
* requiring a Glib::MatchInfo.
*/
bool match_all(const Glib::ustring& string, gssize string_len, int start_position, RegexMatchFlags match_options);
/** Breaks the string on the pattern, and returns an array of
* the tokens. If the pattern contains capturing parentheses,
* then the text for each of the substrings will also be returned.
* If the pattern does not match anywhere in the string, then the
* whole string is returned as the first token.
*
* This function is equivalent to g_regex_split() but it does
* not require to compile the pattern with g_regex_new(), avoiding
* some lines of code when you need just to do a split without
* extracting substrings, capture counts, and so on.
*
* If this function is to be called on the same @a pattern more than
* once, it's more efficient to compile the pattern once with
* g_regex_new() and then use g_regex_split().
*
* As a special case, the result of splitting the empty string ""
* is an empty vector, not a vector containing a single string.
* The reason for this special case is that being able to represent
* a empty vector is typically more useful than consistent handling
* of empty elements. If you do need to represent empty elements,
* you'll need to check for the empty string before calling this
* function.
*
* A pattern that can match empty strings splits @a string into
* separate characters wherever it matches the empty string between
* characters. For example splitting "ab c" using as a separator
* "\\s*", you will get "a", "b" and "c".
*
* @newin{2,14}
*
* @param pattern The regular expression.
* @param string The string to scan for matches.
* @param compile_options Compile options for the regular expression, or 0.
* @param match_options Match options, or 0.
* @return A <tt>0</tt>-terminated array of strings. Free
* it using g_strfreev().
*/
static Glib::StringArrayHandle split_simple(const Glib::ustring& pattern, const Glib::ustring& string, RegexCompileFlags compile_options = static_cast<RegexCompileFlags>(0), RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/** Breaks the string on the pattern, and returns an array of the tokens.
* If the pattern contains capturing parentheses, then the text for each
* of the substrings will also be returned. If the pattern does not match
* anywhere in the string, then the whole string is returned as the first
* token.
*
* As a special case, the result of splitting the empty string "" is an
* empty vector, not a vector containing a single string. The reason for
* this special case is that being able to represent a empty vector is
* typically more useful than consistent handling of empty elements. If
* you do need to represent empty elements, you'll need to check for the
* empty string before calling this function.
*
* A pattern that can match empty strings splits @a string into separate
* characters wherever it matches the empty string between characters.
* For example splitting "ab c" using as a separator "\\s*", you will get
* "a", "b" and "c".
*
* @newin{2,14}
*
* @param string The string to split with the pattern.
* @param match_options Match time option flags.
* @return A <tt>0</tt>-terminated gchar ** array. Free
* it using g_strfreev().
*/
Glib::StringArrayHandle split(const Glib::ustring& string, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
/** Breaks the string on the pattern, and returns an array of the tokens.
* If the pattern contains capturing parentheses, then the text for each
* of the substrings will also be returned. If the pattern does not match
* anywhere in the string, then the whole string is returned as the first
* token.
*
* As a special case, the result of splitting the empty string "" is an
* empty vector, not a vector containing a single string. The reason for
* this special case is that being able to represent a empty vector is
* typically more useful than consistent handling of empty elements. If
* you do need to represent empty elements, you'll need to check for the
* empty string before calling this function.
*
* A pattern that can match empty strings splits @a string into separate
* characters wherever it matches the empty string between characters.
* For example splitting "ab c" using as a separator "\\s*", you will get
* "a", "b" and "c".
*
* Setting @a start_position differs from just passing over a shortened
* string and setting REGEX_MATCH_NOTBOL in the case of a pattern
* that begins with any kind of lookbehind assertion, such as "\\b".
*
* @newin{2,14}
*
* @param string The string to split with the pattern.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param match_options Match time option flags.
* @param max_tokens The maximum number of tokens to split @a string into.
* If this is less than 1, the string is split completely.
* @return A <tt>0</tt>-terminated gchar ** array. Free
* it using g_strfreev().
*/
Glib::StringArrayHandle split(const gchar* string, gssize string_len, int start_position, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0), int max_tokens = 0) const;
Glib::StringArrayHandle split(const Glib::ustring& string, int start_position, RegexMatchFlags match_options, int max_tokens) const;
/** Replaces all occurrences of the pattern in @a regex with the
* replacement text. Backreferences of the form '\\number' or
* '\\g<number>' in the replacement text are interpolated by the
* number-th captured subexpression of the match, '\\g<name>' refers
* to the captured subexpression with the given name. '\\0' refers
* to the complete match, but '\\0' followed by a number is the octal
* representation of a character. To include a literal '\\' in the
* replacement, write '\\\\'.
*
* There are also escapes that changes the case of the following text:
*
* - \\l: Convert to lower case the next character
* - \\u: Convert to upper case the next character
* - \\L: Convert to lower case till \\E
* - \\U: Convert to upper case till \\E
* - \\E: End case modification
*
* If you do not need to use backreferences use g_regex_replace_literal().
*
* The @a replacement string must be UTF-8 encoded even if REGEX_RAW was
* passed to g_regex_new(). If you want to use not UTF-8 encoded stings
* you can use g_regex_replace_literal().
*
* Setting @a start_position differs from just passing over a shortened
* string and setting REGEX_MATCH_NOTBOL in the case of a pattern that
* begins with any kind of lookbehind assertion, such as "\\b".
*
* @newin{2,14}
*
* @param string The string to perform matches against.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param replacement Text to replace each match with.
* @param match_options Options for the match.
* @return A newly allocated string containing the replacements.
*/
Glib::ustring replace(const gchar* string, gssize string_len, int start_position, const Glib::ustring& replacement, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
Glib::ustring replace(const Glib::ustring& string, int start_position, const Glib::ustring& replacement, RegexMatchFlags match_options);
/** Replaces all occurrences of the pattern in @a regex with the
* replacement text. @a replacement is replaced literally, to
* include backreferences use g_regex_replace().
*
* Setting @a start_position differs from just passing over a
* shortened string and setting REGEX_MATCH_NOTBOL in the
* case of a pattern that begins with any kind of lookbehind
* assertion, such as "\\b".
*
* @newin{2,14}
*
* @param string The string to perform matches against.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param replacement Text to replace each match with.
* @param match_options Options for the match.
* @return A newly allocated string containing the replacements.
*/
Glib::ustring replace_literal(const gchar * string, gssize string_len, int start_position, const Glib::ustring& replacement, RegexMatchFlags match_options = static_cast<RegexMatchFlags>(0));
Glib::ustring replace_literal(const Glib::ustring& string, int start_position, const Glib::ustring& replacement, RegexMatchFlags match_options);
/** Replaces occurrences of the pattern in regex with the output of
* @a eval for that occurrence.
*
* Setting @a start_position differs from just passing over a shortened
* string and setting REGEX_MATCH_NOTBOL in the case of a pattern
* that begins with any kind of lookbehind assertion, such as "\\b".
*
* The following example uses g_regex_replace_eval() to replace multiple
* strings at once:
*
* [C example ellipted]
*
* @newin{2,14}
*
* @param string String to perform matches against.
* @param string_len The length of @a string, or -1 if @a string is nul-terminated.
* @param start_position Starting index of the string to match.
* @param match_options Options for the match.
* @param eval A function to call for each match.
* @param user_data User data to pass to the function.
* @return A newly allocated string containing the replacements.
*/
Glib::ustring replace_eval(const Glib::ustring& string, gssize string_len, int start_position, RegexMatchFlags match_options, GRegexEvalCallback eval, gpointer user_data);
/** Checks whether @a replacement is a valid replacement string
* (see g_regex_replace()), i.e.\ that all escape sequences in
* it are valid.
*
* If @a has_references is not <tt>0</tt> then @a replacement is checked
* for pattern references. For instance, replacement text 'foo\\n'
* does not contain references and may be evaluated without information
* about actual match, but '\\0\\1' (whole match followed by first
* subpattern) requires valid MatchInfo object.
*
* @newin{2,14}
*
* @param replacement The replacement string.
* @param has_references Location to store information about
* references in @a replacement or <tt>0</tt>.
* @return Whether @a replacement is a valid replacement string.
*/
static bool check_replacement(const Glib::ustring& replacement, gboolean* has_references);
};
//TODO: Add C++ iterator like functionality for this class.
/** MatchInfo - MatchInfo is used to retrieve information about the regular
* expression match which created it.
* @newin{2,28}
*/
class MatchInfo
{
public:
#ifndef DOXYGEN_SHOULD_SKIP_THIS
typedef MatchInfo CppObjectType;
typedef GMatchInfo BaseObjectType;
#endif /* DOXYGEN_SHOULD_SKIP_THIS */
private:
public:
/// Default constructor.
MatchInfo();
/** C object constructor.
* @param castitem The C object.
* @param take_ownership Whether to destroy the C object with the wrapper or
* not.
*/
explicit MatchInfo(GMatchInfo* castitem, bool take_ownership = true);
/// Destructor.
virtual ~MatchInfo();
/// Provides access to the underlying C object.
GMatchInfo* gobj()
{ return reinterpret_cast<GMatchInfo*>(gobject_); }
/// Provides access to the underlying C object.
const GMatchInfo* gobj() const
{ return reinterpret_cast<GMatchInfo*>(gobject_); }
private:
// noncopyable
MatchInfo(const MatchInfo& other);
MatchInfo& operator=(const MatchInfo& other);
friend class Regex;
public:
/** Returns Regex object used in @a match_info. It belongs to Glib
* and must not be freed. Use g_regex_ref() if you need to keep it
* after you free @a match_info object.
*
* @newin{2,14}
*
* @return Regex object used in @a match_info.
*/
Glib::RefPtr<Regex> get_regex();
/** Returns Regex object used in @a match_info. It belongs to Glib
* and must not be freed. Use g_regex_ref() if you need to keep it
* after you free @a match_info object.
*
* @newin{2,14}
*
* @return Regex object used in @a match_info.
*/
Glib::RefPtr<const Regex> get_regex() const;
/** Returns the string searched with @a match_info. This is the
* string passed to g_regex_match() or g_regex_replace() so
* you may not free it before calling this function.
*
* @newin{2,14}
*
* @return The string searched with @a match_info.
*/
Glib::ustring get_string() const;
/** Returns whether the previous match operation succeeded.
*
* @newin{2,14}
*
* @return <tt>true</tt> if the previous match operation succeeded,
* <tt>false</tt> otherwise.
*/
bool matches() const;
/** Scans for the next match using the same parameters of the previous
* call to g_regex_match_full() or g_regex_match() that returned
* @a match_info.
*
* The match is done on the string passed to the match function, so you
* cannot free it before calling this function.
*
* @newin{2,14}
*
* @return <tt>true</tt> is the string matched, <tt>false</tt> otherwise.
*/
bool next();
/** Retrieves the number of matched substrings (including substring 0,
* that is the whole matched text), so 1 is returned if the pattern
* has no substrings in it and 0 is returned if the match failed.
*
* If the last match was obtained using the DFA algorithm, that is
* using g_regex_match_all() or g_regex_match_all_full(), the retrieved
* count is not that of the number of capturing parentheses but that of
* the number of matched substrings.
*
* @newin{2,14}
*
* @return Number of matched substrings, or -1 if an error occurred.
*/
int get_match_count() const;
/** Usually if the string passed to g_regex_match*() matches as far as
* it goes, but is too short to match the entire pattern, <tt>false</tt> is
* returned. There are circumstances where it might be helpful to
* distinguish this case from other cases in which there is no match.
*
* Consider, for example, an application where a human is required to
* type in data for a field with specific formatting requirements. An
* example might be a date in the form ddmmmyy, defined by the pattern
* "^\\d?\\d(jan|feb|mar|apr|may|jun|jul|aug|sep|oct|nov|dec)\\d\\d$".
* If the application sees the user’s keystrokes one by one, and can
* check that what has been typed so far is potentially valid, it is
* able to raise an error as soon as a mistake is made.
*
* GRegex supports the concept of partial matching by means of the
* REGEX_MATCH_PARTIAL_SOFT and REGEX_MATCH_PARTIAL_HARD flags.
* When they are used, the return code for
* g_regex_match() or g_regex_match_full() is, as usual, <tt>true</tt>
* for a complete match, <tt>false</tt> otherwise. But, when these functions
* return <tt>false</tt>, you can check if the match was partial calling
* g_match_info_is_partial_match().
*
* The difference between REGEX_MATCH_PARTIAL_SOFT and
* REGEX_MATCH_PARTIAL_HARD is that when a partial match is encountered
* with REGEX_MATCH_PARTIAL_SOFT, matching continues to search for a
* possible complete match, while with REGEX_MATCH_PARTIAL_HARD matching
* stops at the partial match.
* When both REGEX_MATCH_PARTIAL_SOFT and REGEX_MATCH_PARTIAL_HARD
* are set, the latter takes precedence.
*
* There were formerly some restrictions on the pattern for partial matching.
* The restrictions no longer apply.
*
* See pcrepartial(3) for more information on partial matching.
*
* @newin{2,14}
*
* @return <tt>true</tt> if the match was partial, <tt>false</tt> otherwise.
*/
bool is_partial_match() const;
/** Returns a new string containing the text in @a string_to_expand with
* references and escape sequences expanded. References refer to the last
* match done with @a string against @a regex and have the same syntax used by
* g_regex_replace().
*
* The @a string_to_expand must be UTF-8 encoded even if REGEX_RAW was
* passed to g_regex_new().
*
* The backreferences are extracted from the string passed to the match
* function, so you cannot call this function after freeing the string.
*
* @a match_info may be <tt>0</tt> in which case @a string_to_expand must not
* contain references. For instance "foo\\n" does not refer to an actual
* pattern and '\\n' merely will be replaced with \\n character,
* while to expand "\\0" (whole match) one needs the result of a match.
* Use g_regex_check_replacement() to find out whether @a string_to_expand
* contains references.
*
* @newin{2,14}
*
* @param string_to_expand The string to expand.
* @return The expanded string, or <tt>0</tt> if an error occurred.
*/
Glib::ustring expand_references(const Glib::ustring& string_to_expand);
/** Retrieves the text matching the @a match_num'th capturing
* parentheses. 0 is the full text of the match, 1 is the first paren
* set, 2 the second, and so on.
*
* If @a match_num is a valid sub pattern but it didn't match anything
* (e.g. sub pattern 1, matching "b" against "(a)?b") then an empty
* string is returned.
*
* If the match was obtained using the DFA algorithm, that is using
* g_regex_match_all() or g_regex_match_all_full(), the retrieved
* string is not that of a set of parentheses but that of a matched
* substring. Substrings are matched in reverse order of length, so
* 0 is the longest match.
*
* The string is fetched from the string passed to the match function,
* so you cannot call this function after freeing the string.
*
* @newin{2,14}
*
* @param match_num Number of the sub expression.
* @return The matched substring, or <tt>0</tt> if an error
* occurred. You have to free the string yourself.
*/
Glib::ustring fetch(int match_num);
/** Retrieves the position in bytes of the @a match_num'th capturing
* parentheses. 0 is the full text of the match, 1 is the first
* paren set, 2 the second, and so on.
*
* If @a match_num is a valid sub pattern but it didn't match anything
* (e.g. sub pattern 1, matching "b" against "(a)?b") then @a start_pos
* and @a end_pos are set to -1 and <tt>true</tt> is returned.
*
* If the match was obtained using the DFA algorithm, that is using
* g_regex_match_all() or g_regex_match_all_full(), the retrieved
* position is not that of a set of parentheses but that of a matched
* substring. Substrings are matched in reverse order of length, so
* 0 is the longest match.
*
* @newin{2,14}
*
* @param match_num Number of the sub expression.
* @param start_pos Pointer to location where to store
* the start position, or <tt>0</tt>.
* @param end_pos Pointer to location where to store
* the end position, or <tt>0</tt>.
* @return <tt>true</tt> if the position was fetched, <tt>false</tt> otherwise. If
* the position cannot be fetched, @a start_pos and @a end_pos are left
* unchanged.
*/
bool fetch_pos(int match_num, int& start_pos, int& end_pos);
/** Retrieves the text matching the capturing parentheses named @a name.
*
* If @a name is a valid sub pattern name but it didn't match anything
* (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
* then an empty string is returned.
*
* The string is fetched from the string passed to the match function,
* so you cannot call this function after freeing the string.
*
* @newin{2,14}
*
* @param name Name of the subexpression.
* @return The matched substring, or <tt>0</tt> if an error
* occurred. You have to free the string yourself.
*/
Glib::ustring fetch_named(const Glib::ustring& name);
/** Retrieves the position in bytes of the capturing parentheses named @a name.
*
* If @a name is a valid sub pattern name but it didn't match anything
* (e.g. sub pattern "X", matching "b" against "(?P<X>a)?b")
* then @a start_pos and @a end_pos are set to -1 and <tt>true</tt> is returned.
*
* @newin{2,14}
*
* @param name Name of the subexpression.
* @param start_pos Pointer to location where to store
* the start position, or <tt>0</tt>.
* @param end_pos Pointer to location where to store
* the end position, or <tt>0</tt>.
* @return <tt>true</tt> if the position was fetched, <tt>false</tt> otherwise.
* If the position cannot be fetched, @a start_pos and @a end_pos
* are left unchanged.
*/
bool fetch_named_pos(const Glib::ustring& name, int& start_pos, int& end_pos);
/** Bundles up pointers to each of the matching substrings from a match
* and stores them in an array of gchar pointers. The first element in
* the returned array is the match number 0, i.e. the entire matched
* text.
*
* If a sub pattern didn't match anything (e.g. sub pattern 1, matching
* "b" against "(a)?b") then an empty string is inserted.
*
* If the last match was obtained using the DFA algorithm, that is using
* g_regex_match_all() or g_regex_match_all_full(), the retrieved
* strings are not that matched by sets of parentheses but that of the
* matched substring. Substrings are matched in reverse order of length,
* so the first one is the longest match.
*
* The strings are fetched from the string passed to the match function,
* so you cannot call this function after freeing the string.
*
* @newin{2,14}
*
* @return A <tt>0</tt>-terminated array of gchar *
* pointers. It must be freed using g_strfreev(). If the previous
* match failed <tt>0</tt> is returned.
*/
Glib::StringArrayHandle fetch_all();
protected:
GMatchInfo* gobject_; // The C object.
bool take_ownership; // Bool signaling ownership.
protected:
// So that Glib::Regex::match() can set the C object.
void set_gobject(GMatchInfo* castitem, bool take_ownership = true);
};
} // namespace Glib
namespace Glib
{
/** A Glib::wrap() method for this object.
*
* @param object The C instance.
* @param take_copy False if the result should take ownership of the C instance. True if it should take a new copy or ref.
* @result A C++ instance that wraps this C instance.
*
* @relates Glib::Regex
*/
Glib::RefPtr<Glib::Regex> wrap(GRegex* object, bool take_copy = false);
} // namespace Glib
#endif /* _GLIBMM_REGEX_H */
|