regex.h 24.1 KB
Newer Older
1 2
/* Definitions for data structures and routines for the regular
   expression library.
3
   Copyright (C) 1985, 1989-2020 Free Software Foundation, Inc.
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
   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU General Public
   License as published by the Free Software Foundation; either
   version 3 of the License, or (at your option) any later version.

   The GNU C 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
   General Public License for more details.

   You should have received a copy of the GNU General Public
   License along with the GNU C Library; if not, see
   <https://www.gnu.org/licenses/>.  */

#ifndef _REGEX_H
#define _REGEX_H 1

#include <sys/types.h>

/* Allow the use in C++ code.  */
#ifdef __cplusplus
extern "C" {
#endif

/* Define __USE_GNU to declare GNU extensions that violate the
   POSIX name space rules.  */
#ifdef _GNU_SOURCE
# define __USE_GNU 1
#endif

#ifdef _REGEX_LARGE_OFFSETS

/* Use types and values that are wide enough to represent signed and
   unsigned byte offsets in memory.  This currently works only when
   the regex code is used outside of the GNU C library; it is not yet
   supported within glibc itself, and glibc users should not define
   _REGEX_LARGE_OFFSETS.  */

/* The type of object sizes.  */
typedef size_t __re_size_t;

/* The type of object sizes, in places where the traditional code
   uses unsigned long int.  */
typedef size_t __re_long_size_t;

#else

/* The traditional GNU regex implementation mishandles strings longer
   than INT_MAX.  */
typedef unsigned int __re_size_t;
typedef unsigned long int __re_long_size_t;

#endif

/* The following two types have to be signed and unsigned integer type
   wide enough to hold a value of a pointer.  For most ANSI compilers
   ptrdiff_t and size_t should be likely OK.  Still size of these two
   types is 2 for Microsoft C.  Ugh... */
typedef long int s_reg_t;
typedef unsigned long int active_reg_t;

/* The following bits are used to determine the regexp syntax we
   recognize.  The set/not-set meanings are chosen so that Emacs syntax
   remains the value 0.  The bits are given in alphabetical order, and
   the definitions shifted by one from the previous bit; thus, when we
   add or remove a bit, only one other definition need change.  */
typedef unsigned long int reg_syntax_t;

#ifdef __USE_GNU
/* If this bit is not set, then \ inside a bracket expression is literal.
   If set, then such a \ quotes the following character.  */
# define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)

/* If this bit is not set, then + and ? are operators, and \+ and \? are
     literals.
   If set, then \+ and \? are operators and + and ? are literals.  */
# define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)

/* If this bit is set, then character classes are supported.  They are:
     [:alpha:], [:upper:], [:lower:],  [:digit:], [:alnum:], [:xdigit:],
     [:space:], [:print:], [:punct:], [:graph:], and [:cntrl:].
   If not set, then character classes are not supported.  */
# define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1)

/* If this bit is set, then ^ and $ are always anchors (outside bracket
     expressions, of course).
   If this bit is not set, then it depends:
	^  is an anchor if it is at the beginning of a regular
	   expression or after an open-group or an alternation operator;
	$  is an anchor if it is at the end of a regular expression, or
	   before a close-group or an alternation operator.

   This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because
   POSIX draft 11.2 says that * etc. in leading positions is undefined.
   We already implemented a previous draft which made those constructs
   invalid, though, so we haven't changed the code back.  */
# define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1)

/* If this bit is set, then special characters are always special
     regardless of where they are in the pattern.
   If this bit is not set, then special characters are special only in
     some contexts; otherwise they are ordinary.  Specifically,
     * + ? and intervals are only special when not after the beginning,
     open-group, or alternation operator.  */
# define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1)

/* If this bit is set, then *, +, ?, and { cannot be first in an re or
     immediately after an alternation or begin-group operator.  */
# define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1)

/* If this bit is set, then . matches newline.
   If not set, then it doesn't.  */
# define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1)

/* If this bit is set, then . doesn't match NUL.
   If not set, then it does.  */
# define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1)

/* If this bit is set, nonmatching lists [^...] do not match newline.
   If not set, they do.  */
# define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1)

/* If this bit is set, either \{...\} or {...} defines an
     interval, depending on RE_NO_BK_BRACES.
   If not set, \{, \}, {, and } are literals.  */
# define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)

/* If this bit is set, +, ? and | aren't recognized as operators.
   If not set, they are.  */
# define RE_LIMITED_OPS (RE_INTERVALS << 1)

/* If this bit is set, newline is an alternation operator.
   If not set, newline is literal.  */
# define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1)

/* If this bit is set, then '{...}' defines an interval, and \{ and \}
     are literals.
  If not set, then '\{...\}' defines an interval.  */
# define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1)

/* If this bit is set, (...) defines a group, and \( and \) are literals.
   If not set, \(...\) defines a group, and ( and ) are literals.  */
# define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1)

/* If this bit is set, then \<digit> matches <digit>.
   If not set, then \<digit> is a back-reference.  */
# define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1)

/* If this bit is set, then | is an alternation operator, and \| is literal.
   If not set, then \| is an alternation operator, and | is literal.  */
# define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1)

/* If this bit is set, then an ending range point collating higher
     than the starting range point, as in [z-a], is invalid.
   If not set, then when ending range point collates higher than the
     starting range point, the range is ignored.  */
# define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1)

/* If this bit is set, then an unmatched ) is ordinary.
   If not set, then an unmatched ) is invalid.  */
# define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1)

/* If this bit is set, succeed as soon as we match the whole pattern,
   without further backtracking.  */
# define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)

/* If this bit is set, do not process the GNU regex operators.
   If not set, then the GNU regex operators are recognized. */
# define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)

/* If this bit is set, turn on internal regex debugging.
   If not set, and debugging was on, turn it off.
   This only works if regex.c is compiled -DDEBUG.
   We define this bit always, so that all that's needed to turn on
   debugging is to recompile regex.c; the calling code can always have
   this bit set, and it won't affect anything in the normal case. */
# define RE_DEBUG (RE_NO_GNU_OPS << 1)

/* If this bit is set, a syntactically invalid interval is treated as
   a string of ordinary characters.  For example, the ERE 'a{1' is
   treated as 'a\{1'.  */
# define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)

/* If this bit is set, then ignore case when matching.
   If not set, then case is significant.  */
# define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1)

/* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only
   for ^, because it is difficult to scan the regex backwards to find
   whether ^ should be special.  */
# define RE_CARET_ANCHORS_HERE (RE_ICASE << 1)

/* If this bit is set, then \{ cannot be first in a regex or
   immediately after an alternation, open-group or \} operator.  */
# define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1)

/* If this bit is set, then no_sub will be set to 1 during
   re_compile_pattern.  */
# define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1)
#endif

/* This global variable defines the particular regexp syntax to use (for
   some interfaces).  When a regexp is compiled, the syntax used is
   stored in the pattern buffer, so changing this does not affect
   already-compiled regexps.  */
extern reg_syntax_t re_syntax_options;

#ifdef __USE_GNU
/* Define combinations of the above bits for the standard possibilities.
   (The [[[ comments delimit what gets put into the Texinfo file, so
   don't delete them!)  */
/* [[[begin syntaxes]]] */
# define RE_SYNTAX_EMACS 0

# define RE_SYNTAX_AWK							\
  (RE_BACKSLASH_ESCAPE_IN_LISTS   | RE_DOT_NOT_NULL			\
   | RE_NO_BK_PARENS              | RE_NO_BK_REFS			\
   | RE_NO_BK_VBAR                | RE_NO_EMPTY_RANGES			\
   | RE_DOT_NEWLINE		  | RE_CONTEXT_INDEP_ANCHORS		\
   | RE_CHAR_CLASSES							\
   | RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS)

# define RE_SYNTAX_GNU_AWK						\
  ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS		\
    | RE_INVALID_INTERVAL_ORD)						\
   & ~(RE_DOT_NOT_NULL | RE_CONTEXT_INDEP_OPS				\
      | RE_CONTEXT_INVALID_OPS ))

# define RE_SYNTAX_POSIX_AWK						\
  (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS		\
   | RE_INTERVALS	    | RE_NO_GNU_OPS				\
   | RE_INVALID_INTERVAL_ORD)

# define RE_SYNTAX_GREP							\
  ((RE_SYNTAX_POSIX_BASIC | RE_NEWLINE_ALT)				\
   & ~(RE_CONTEXT_INVALID_DUP | RE_DOT_NOT_NULL))

# define RE_SYNTAX_EGREP						\
  ((RE_SYNTAX_POSIX_EXTENDED | RE_INVALID_INTERVAL_ORD | RE_NEWLINE_ALT) \
   & ~(RE_CONTEXT_INVALID_OPS | RE_DOT_NOT_NULL))

/* POSIX grep -E behavior is no longer incompatible with GNU.  */
# define RE_SYNTAX_POSIX_EGREP						\
  RE_SYNTAX_EGREP

/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff.  */
# define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC

# define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC

/* Syntax bits common to both basic and extended POSIX regex syntax.  */
# define _RE_SYNTAX_POSIX_COMMON					\
  (RE_CHAR_CLASSES | RE_DOT_NEWLINE      | RE_DOT_NOT_NULL		\
   | RE_INTERVALS  | RE_NO_EMPTY_RANGES)

# define RE_SYNTAX_POSIX_BASIC						\
  (_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM | RE_CONTEXT_INVALID_DUP)

/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes
   RE_LIMITED_OPS, i.e., \? \+ \| are not recognized.  Actually, this
   isn't minimal, since other operators, such as \`, aren't disabled.  */
# define RE_SYNTAX_POSIX_MINIMAL_BASIC					\
  (_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS)

# define RE_SYNTAX_POSIX_EXTENDED					\
  (_RE_SYNTAX_POSIX_COMMON  | RE_CONTEXT_INDEP_ANCHORS			\
   | RE_CONTEXT_INDEP_OPS   | RE_NO_BK_BRACES				\
   | RE_NO_BK_PARENS        | RE_NO_BK_VBAR				\
   | RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD)

/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is
   removed and RE_NO_BK_REFS is added.  */
# define RE_SYNTAX_POSIX_MINIMAL_EXTENDED				\
  (_RE_SYNTAX_POSIX_COMMON  | RE_CONTEXT_INDEP_ANCHORS			\
   | RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES				\
   | RE_NO_BK_PARENS        | RE_NO_BK_REFS				\
   | RE_NO_BK_VBAR	    | RE_UNMATCHED_RIGHT_PAREN_ORD)
/* [[[end syntaxes]]] */

/* Maximum number of duplicates an interval can allow.  POSIX-conforming
   systems might define this in <limits.h>, but we want our
   value, so remove any previous define.  */
# ifdef _REGEX_INCLUDE_LIMITS_H
#  include <limits.h>
# endif
# ifdef RE_DUP_MAX
#  undef RE_DUP_MAX
# endif

/* RE_DUP_MAX is 2**15 - 1 because an earlier implementation stored
   the counter as a 2-byte signed integer.  This is no longer true, so
   RE_DUP_MAX could be increased to (INT_MAX / 10 - 1), or to
   ((SIZE_MAX - 9) / 10) if _REGEX_LARGE_OFFSETS is defined.
   However, there would be a huge performance problem if someone
   actually used a pattern like a\{214748363\}, so RE_DUP_MAX retains
   its historical value.  */
# define RE_DUP_MAX (0x7fff)
#endif


/* POSIX 'cflags' bits (i.e., information for 'regcomp').  */

/* If this bit is set, then use extended regular expression syntax.
   If not set, then use basic regular expression syntax.  */
#define REG_EXTENDED 1

/* If this bit is set, then ignore case when matching.
   If not set, then case is significant.  */
#define REG_ICASE (1 << 1)

/* If this bit is set, then anchors do not match at newline
     characters in the string.
   If not set, then anchors do match at newlines.  */
#define REG_NEWLINE (1 << 2)

/* If this bit is set, then report only success or fail in regexec.
   If not set, then returns differ between not matching and errors.  */
#define REG_NOSUB (1 << 3)


/* POSIX 'eflags' bits (i.e., information for regexec).  */

/* If this bit is set, then the beginning-of-line operator doesn't match
     the beginning of the string (presumably because it's not the
     beginning of a line).
   If not set, then the beginning-of-line operator does match the
     beginning of the string.  */
#define REG_NOTBOL 1

/* Like REG_NOTBOL, except for the end-of-line.  */
#define REG_NOTEOL (1 << 1)

/* Use PMATCH[0] to delimit the start and end of the search in the
   buffer.  */
#define REG_STARTEND (1 << 2)


/* If any error codes are removed, changed, or added, update the
   '__re_error_msgid' table in regcomp.c.  */

typedef enum
{
  _REG_ENOSYS = -1,	/* This will never happen for this implementation.  */
  _REG_NOERROR = 0,	/* Success.  */
  _REG_NOMATCH,		/* Didn't find a match (for regexec).  */

  /* POSIX regcomp return error codes.  (In the order listed in the
     standard.)  */
  _REG_BADPAT,		/* Invalid pattern.  */
  _REG_ECOLLATE,	/* Invalid collating element.  */
  _REG_ECTYPE,		/* Invalid character class name.  */
  _REG_EESCAPE,		/* Trailing backslash.  */
  _REG_ESUBREG,		/* Invalid back reference.  */
  _REG_EBRACK,		/* Unmatched left bracket.  */
  _REG_EPAREN,		/* Parenthesis imbalance.  */
  _REG_EBRACE,		/* Unmatched \{.  */
  _REG_BADBR,		/* Invalid contents of \{\}.  */
  _REG_ERANGE,		/* Invalid range end.  */
  _REG_ESPACE,		/* Ran out of memory.  */
  _REG_BADRPT,		/* No preceding re for repetition op.  */

  /* Error codes we've added.  */
  _REG_EEND,		/* Premature end.  */
  _REG_ESIZE,		/* Too large (e.g., repeat count too large).  */
  _REG_ERPAREN		/* Unmatched ) or \); not returned from regcomp.  */
} reg_errcode_t;

#if defined _XOPEN_SOURCE || defined __USE_XOPEN2K
# define REG_ENOSYS	_REG_ENOSYS
#endif
#define REG_NOERROR	_REG_NOERROR
#define REG_NOMATCH	_REG_NOMATCH
#define REG_BADPAT	_REG_BADPAT
#define REG_ECOLLATE	_REG_ECOLLATE
#define REG_ECTYPE	_REG_ECTYPE
#define REG_EESCAPE	_REG_EESCAPE
#define REG_ESUBREG	_REG_ESUBREG
#define REG_EBRACK	_REG_EBRACK
#define REG_EPAREN	_REG_EPAREN
#define REG_EBRACE	_REG_EBRACE
#define REG_BADBR	_REG_BADBR
#define REG_ERANGE	_REG_ERANGE
#define REG_ESPACE	_REG_ESPACE
#define REG_BADRPT	_REG_BADRPT
#define REG_EEND	_REG_EEND
#define REG_ESIZE	_REG_ESIZE
#define REG_ERPAREN	_REG_ERPAREN

/* This data structure represents a compiled pattern.  Before calling
   the pattern compiler, the fields 'buffer', 'allocated', 'fastmap',
   and 'translate' can be set.  After the pattern has been compiled,
   the fields 're_nsub', 'not_bol' and 'not_eol' are available.  All
   other fields are private to the regex routines.  */

#ifndef RE_TRANSLATE_TYPE
# define __RE_TRANSLATE_TYPE unsigned char *
# ifdef __USE_GNU
#  define RE_TRANSLATE_TYPE __RE_TRANSLATE_TYPE
# endif
#endif

#ifdef __USE_GNU
# define __REPB_PREFIX(name) name
#else
# define __REPB_PREFIX(name) __##name
#endif

struct re_pattern_buffer
{
  /* Space that holds the compiled pattern.  The type
     'struct re_dfa_t' is private and is not declared here.  */
  struct re_dfa_t *__REPB_PREFIX(buffer);

  /* Number of bytes to which 'buffer' points.  */
  __re_long_size_t __REPB_PREFIX(allocated);

  /* Number of bytes actually used in 'buffer'.  */
  __re_long_size_t __REPB_PREFIX(used);

  /* Syntax setting with which the pattern was compiled.  */
  reg_syntax_t __REPB_PREFIX(syntax);

  /* Pointer to a fastmap, if any, otherwise zero.  re_search uses the
     fastmap, if there is one, to skip over impossible starting points
     for matches.  */
  char *__REPB_PREFIX(fastmap);

  /* Either a translate table to apply to all characters before
     comparing them, or zero for no translation.  The translation is
     applied to a pattern when it is compiled and to a string when it
     is matched.  */
  __RE_TRANSLATE_TYPE __REPB_PREFIX(translate);

  /* Number of subexpressions found by the compiler.  */
  size_t re_nsub;

  /* Zero if this pattern cannot match the empty string, one else.
     Well, in truth it's used only in 're_search_2', to see whether or
     not we should use the fastmap, so we don't set this absolutely
     perfectly; see 're_compile_fastmap' (the "duplicate" case).  */
  unsigned __REPB_PREFIX(can_be_null) : 1;

  /* If REGS_UNALLOCATED, allocate space in the 'regs' structure
     for 'max (RE_NREGS, re_nsub + 1)' groups.
     If REGS_REALLOCATE, reallocate space if necessary.
     If REGS_FIXED, use what's there.  */
#ifdef __USE_GNU
# define REGS_UNALLOCATED 0
# define REGS_REALLOCATE 1
# define REGS_FIXED 2
#endif
  unsigned __REPB_PREFIX(regs_allocated) : 2;

  /* Set to zero when 're_compile_pattern' compiles a pattern; set to
     one by 're_compile_fastmap' if it updates the fastmap.  */
  unsigned __REPB_PREFIX(fastmap_accurate) : 1;

  /* If set, 're_match_2' does not return information about
     subexpressions.  */
  unsigned __REPB_PREFIX(no_sub) : 1;

  /* If set, a beginning-of-line anchor doesn't match at the beginning
     of the string.  */
  unsigned __REPB_PREFIX(not_bol) : 1;

  /* Similarly for an end-of-line anchor.  */
  unsigned __REPB_PREFIX(not_eol) : 1;

  /* If true, an anchor at a newline matches.  */
  unsigned __REPB_PREFIX(newline_anchor) : 1;
};

typedef struct re_pattern_buffer regex_t;

/* Type for byte offsets within the string.  POSIX mandates this.  */
#ifdef _REGEX_LARGE_OFFSETS
/* POSIX 1003.1-2008 requires that regoff_t be at least as wide as
   ptrdiff_t and ssize_t.  We don't know of any hosts where ptrdiff_t
   is wider than ssize_t, so ssize_t is safe.  ptrdiff_t is not
   visible here, so use ssize_t.  */
typedef ssize_t regoff_t;
#else
/* The traditional GNU regex implementation mishandles strings longer
   than INT_MAX.  */
typedef int regoff_t;
#endif


#ifdef __USE_GNU
/* This is the structure we store register match data in.  See
   regex.texinfo for a full description of what registers match.  */
struct re_registers
{
  __re_size_t num_regs;
  regoff_t *start;
  regoff_t *end;
};


/* If 'regs_allocated' is REGS_UNALLOCATED in the pattern buffer,
   're_match_2' returns information about at least this many registers
   the first time a 'regs' structure is passed.  */
# ifndef RE_NREGS
#  define RE_NREGS 30
# endif
#endif


/* POSIX specification for registers.  Aside from the different names than
   're_registers', POSIX uses an array of structures, instead of a
   structure of arrays.  */
typedef struct
{
  regoff_t rm_so;  /* Byte offset from string's start to substring's start.  */
  regoff_t rm_eo;  /* Byte offset from string's start to substring's end.  */
} regmatch_t;

/* Declarations for routines.  */

#ifdef __USE_GNU
/* Sets the current default syntax to SYNTAX, and return the old syntax.
   You can also simply assign to the 're_syntax_options' variable.  */
extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax);

/* Compile the regular expression PATTERN, with length LENGTH
   and syntax given by the global 're_syntax_options', into the buffer
   BUFFER.  Return NULL if successful, and an error string if not.

   To free the allocated storage, you must call 'regfree' on BUFFER.
   Note that the translate table must either have been initialized by
   'regcomp', with a malloc'ed value, or set to NULL before calling
   'regfree'.  */
extern const char *re_compile_pattern (const char *__pattern, size_t __length,
				       struct re_pattern_buffer *__buffer);


/* Compile a fastmap for the compiled pattern in BUFFER; used to
   accelerate searches.  Return 0 if successful and -2 if was an
   internal error.  */
extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);


/* Search in the string STRING (with length LENGTH) for the pattern
   compiled into BUFFER.  Start searching at position START, for RANGE
   characters.  Return the starting position of the match, -1 for no
   match, or -2 for an internal error.  Also return register
   information in REGS (if REGS and BUFFER->no_sub are nonzero).  */
extern regoff_t re_search (struct re_pattern_buffer *__buffer,
			   const char *__String, regoff_t __length,
			   regoff_t __start, regoff_t __range,
			   struct re_registers *__regs);


/* Like 're_search', but search in the concatenation of STRING1 and
   STRING2.  Also, stop searching at index START + STOP.  */
extern regoff_t re_search_2 (struct re_pattern_buffer *__buffer,
			     const char *__string1, regoff_t __length1,
			     const char *__string2, regoff_t __length2,
			     regoff_t __start, regoff_t __range,
			     struct re_registers *__regs,
			     regoff_t __stop);


/* Like 're_search', but return how many characters in STRING the regexp
   in BUFFER matched, starting at position START.  */
extern regoff_t re_match (struct re_pattern_buffer *__buffer,
			  const char *__String, regoff_t __length,
			  regoff_t __start, struct re_registers *__regs);


/* Relates to 're_match' as 're_search_2' relates to 're_search'.  */
extern regoff_t re_match_2 (struct re_pattern_buffer *__buffer,
			    const char *__string1, regoff_t __length1,
			    const char *__string2, regoff_t __length2,
			    regoff_t __start, struct re_registers *__regs,
			    regoff_t __stop);


/* Set REGS to hold NUM_REGS registers, storing them in STARTS and
   ENDS.  Subsequent matches using BUFFER and REGS will use this memory
   for recording register information.  STARTS and ENDS must be
   allocated with malloc, and must each be at least 'NUM_REGS * sizeof
   (regoff_t)' bytes long.

   If NUM_REGS == 0, then subsequent matches should allocate their own
   register data.

   Unless this function is called, the first search or match using
   BUFFER will allocate its own register data, without
   freeing the old data.  */
extern void re_set_registers (struct re_pattern_buffer *__buffer,
			      struct re_registers *__regs,
			      __re_size_t __num_regs,
			      regoff_t *__starts, regoff_t *__ends);
#endif	/* Use GNU */

#if defined _REGEX_RE_COMP || (defined _LIBC && defined __USE_MISC)
# ifndef _CRAY
/* 4.2 bsd compatibility.  */
extern char *re_comp (const char *);
extern int re_exec (const char *);
# endif
#endif

/* For plain 'restrict', use glibc's __restrict if defined.
   Otherwise, GCC 2.95 and later have "__restrict"; C99 compilers have
   "restrict", and "configure" may have defined "restrict".
   Other compilers use __restrict, __restrict__, and _Restrict, and
   'configure' might #define 'restrict' to those words, so pick a
   different name.  */
#ifndef _Restrict_
# if defined __restrict || 2 < __GNUC__ + (95 <= __GNUC_MINOR__)
#  define _Restrict_ __restrict
# elif 199901L <= __STDC_VERSION__ || defined restrict
#  define _Restrict_ restrict
# else
#  define _Restrict_
# endif
#endif
/* For [restrict], use glibc's __restrict_arr if available.
   Otherwise, GCC 3.1 (not in C++ mode) and C99 support [restrict].  */
#ifndef _Restrict_arr_
# ifdef __restrict_arr
#  define _Restrict_arr_ __restrict_arr
# elif ((199901L <= __STDC_VERSION__ || 3 < __GNUC__ + (1 <= __GNUC_MINOR__)) \
        && !defined __GNUG__)
#  define _Restrict_arr_ _Restrict_
# else
#  define _Restrict_arr_
# endif
#endif

/* POSIX compatibility.  */
extern int regcomp (regex_t *_Restrict_ __preg,
		    const char *_Restrict_ __pattern,
		    int __cflags);

extern int regexec (const regex_t *_Restrict_ __preg,
		    const char *_Restrict_ __String, size_t __nmatch,
		    regmatch_t __pmatch[_Restrict_arr_],
		    int __eflags);

extern size_t regerror (int __errcode, const regex_t *_Restrict_ __preg,
			char *_Restrict_ __errbuf, size_t __errbuf_size);

extern void regfree (regex_t *__preg);


#ifdef __cplusplus
}
#endif	/* C++ */

#endif /* regex.h */