diff options
author | Jason Molenda <jmolenda@apple.com> | 1998-06-10 18:28:48 +0000 |
---|---|---|
committer | Jason Molenda <jmolenda@apple.com> | 1998-06-10 18:28:48 +0000 |
commit | 9f85ab1afe4710d71f10ea5169046cf12fa55147 (patch) | |
tree | 320569c3237d247186264f427a200c277d4d2ad6 /gdb/gnu-regex.h | |
parent | f7065e881c8f8f85bd7d8ffd3cecfb63e0202c30 (diff) | |
download | gdb-9f85ab1afe4710d71f10ea5169046cf12fa55147.zip gdb-9f85ab1afe4710d71f10ea5169046cf12fa55147.tar.gz gdb-9f85ab1afe4710d71f10ea5169046cf12fa55147.tar.bz2 |
Wed Jun 10 11:27:39 1998 Jason Molenda (crash@bugshack.cygnus.com)
* gnu-regex.c, gnu-regex.h: Update to current FSF (glibc) versions.
Diffstat (limited to 'gdb/gnu-regex.h')
-rw-r--r-- | gdb/gnu-regex.h | 723 |
1 files changed, 557 insertions, 166 deletions
diff --git a/gdb/gnu-regex.h b/gdb/gnu-regex.h index 7b1a4af..cb26d54 100644 --- a/gdb/gnu-regex.h +++ b/gdb/gnu-regex.h @@ -1,181 +1,572 @@ -/* Definitions for data structures callers pass the regex library. - Copyright (C) 1985, 1989 Free Software Foundation, Inc. +/* Definitions for data structures and routines for the regular + expression library, version 0.12. + Copyright (C) 1985,89,90,91,92,93,95,96,97,98 Free Software Foundation, Inc. -This program 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 2 of the License, or -(at your option) any later version. + This file is part of the GNU C Library. Its master source is NOT part of + the C library, however. The master source lives in /gd/gnu/lib. -This program 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. + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Library General Public License as + published by the Free Software Foundation; either version 2 of the + License, or (at your option) any later version. -You should have received a copy of the GNU General Public License -along with this program; if not, write to the Free Software -Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ + 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 + Library General Public License for more details. -/* Define number of parens for which we record the beginnings and ends. - This affects how much space the `struct re_registers' type takes up. */ -#ifndef RE_NREGS -#define RE_NREGS 10 + You should have received a copy of the GNU Library General Public + License along with the GNU C Library; see the file COPYING.LIB. If not, + write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330, + Boston, MA 02111-1307, USA. */ + +#ifndef _REGEX_H +#define _REGEX_H 1 + +/* Allow the use in C++ code. */ +#ifdef __cplusplus +extern "C" { +#endif + +/* POSIX says that <sys/types.h> must be included (by the caller) before + <regex.h>. */ + +#if !defined _POSIX_C_SOURCE && !defined _POSIX_SOURCE && defined VMS +/* VMS doesn't have `size_t' in <sys/types.h>, even though POSIX says it + should be there. */ +# include <stddef.h> #endif -/* These bits are used in the obscure_syntax variable to choose among - alternative regexp syntaxes. */ - -/* 1 means plain parentheses serve as grouping, and backslash - parentheses are needed for literal searching. - 0 means backslash-parentheses are grouping, and plain parentheses - are for literal searching. */ -#define RE_NO_BK_PARENS 1 - -/* 1 means plain | serves as the "or"-operator, and \| is a literal. - 0 means \| serves as the "or"-operator, and | is a literal. */ -#define RE_NO_BK_VBAR 2 - -/* 0 means plain + or ? serves as an operator, and \+, \? are literals. - 1 means \+, \? are operators and plain +, ? are literals. */ -#define RE_BK_PLUS_QM 4 - -/* 1 means | binds tighter than ^ or $. - 0 means the contrary. */ -#define RE_TIGHT_VBAR 8 - -/* 1 means treat \n as an _OR operator - 0 means treat it as a normal character */ -#define RE_NEWLINE_OR 16 - -/* 0 means that a special characters (such as *, ^, and $) always have - their special meaning regardless of the surrounding context. - 1 means that special characters may act as normal characters in some - contexts. Specifically, this applies to: - ^ - only special at the beginning, or after ( or | - $ - only special at the end, or before ) or | - *, +, ? - only special when not after the beginning, (, or | */ -#define RE_CONTEXT_INDEP_OPS 32 - -/* Now define combinations of bits for the standard possibilities. */ -#define RE_SYNTAX_AWK (RE_NO_BK_PARENS | RE_NO_BK_VBAR | RE_CONTEXT_INDEP_OPS) -#define RE_SYNTAX_EGREP (RE_SYNTAX_AWK | RE_NEWLINE_OR) -#define RE_SYNTAX_GREP (RE_BK_PLUS_QM | RE_NEWLINE_OR) +/* 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; + +/* 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) + +/* 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; + +/* 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 -/* This data structure is used to represent a compiled pattern. */ +#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_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS) + +#define RE_SYNTAX_GNU_AWK \ + ((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DEBUG) \ + & ~(RE_DOT_NOT_NULL | RE_INTERVALS | RE_CONTEXT_INDEP_OPS)) + +#define RE_SYNTAX_POSIX_AWK \ + (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \ + | RE_INTERVALS | RE_NO_GNU_OPS) + +#define RE_SYNTAX_GREP \ + (RE_BK_PLUS_QM | RE_CHAR_CLASSES \ + | RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \ + | RE_NEWLINE_ALT) + +#define RE_SYNTAX_EGREP \ + (RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \ + | RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \ + | RE_NEWLINE_ALT | RE_NO_BK_PARENS \ + | RE_NO_BK_VBAR) + +#define RE_SYNTAX_POSIX_EGREP \ + (RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES) + +/* 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) + +/* 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_UNMATCHED_RIGHT_PAREN_ORD) + +/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INVALID_OPS + replaces RE_CONTEXT_INDEP_OPS 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. Some systems + (erroneously) define this in other header files, but we want our + value, so remove any previous define. */ +#ifdef RE_DUP_MAX +# undef RE_DUP_MAX +#endif +/* If sizeof(int) == 2, then ((1 << 15) - 1) overflows. */ +#define RE_DUP_MAX (0x7fff) + + +/* 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 (REG_EXTENDED << 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 (REG_ICASE << 1) + +/* 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 (REG_NEWLINE << 1) + + +/* 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) + + +/* If any error codes are removed, changed, or added, update the + `re_error_msg' table in regex.c. */ +typedef enum +{ +#if (_XOPEN_SOURCE - 0) == 500 + REG_NOSYS = -1, /* This will never happen for this implementation. */ +#endif + + 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, /* Not implemented. */ + 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, /* Compiled pattern bigger than 2^16 bytes. */ + REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */ +} reg_errcode_t; + +/* This data structure represents a compiled pattern. Before calling + the pattern compiler, the fields `buffer', `allocated', `fastmap', + `translate', and `no_sub' can be set. After the pattern has been + compiled, the `re_nsub' field is available. All other fields are + private to the regex routines. */ + +#ifndef RE_TRANSLATE_TYPE +# define RE_TRANSLATE_TYPE char * +#endif struct re_pattern_buffer - { - char *buffer; /* Space holding the compiled pattern commands. */ - int allocated; /* Size of space that buffer points to */ - int used; /* Length of portion of buffer actually occupied */ - char *fastmap; /* Pointer to fastmap, if any, or zero if none. */ - /* re_search uses the fastmap, if there is one, - to skip quickly over totally implausible characters */ - char *translate; /* Translate table to apply to all characters before comparing. - Or zero for no translation. - The translation is applied to a pattern when it is compiled - and to data when it is matched. */ - char fastmap_accurate; - /* Set to zero when a new pattern is stored, - set to one when the fastmap is updated from it. */ - char can_be_null; /* Set to one by compiling fastmap - if this pattern might match the null string. - It does not necessarily match the null string - in that case, but if this is zero, it cannot. - 2 as value means can match null string - but at end of range or before a character - listed in the fastmap. */ - }; - -/* Structure to store "register" contents data in. - - Pass the address of such a structure as an argument to re_match, etc., - if you want this information back. - - start[i] and end[i] record the string matched by \( ... \) grouping i, - for i from 1 to RE_NREGS - 1. - start[0] and end[0] record the entire string matched. */ +{ +/* [[[begin pattern_buffer]]] */ + /* Space that holds the compiled pattern. It is declared as + `unsigned char *' because its elements are + sometimes used as array indexes. */ + unsigned char *buffer; + + /* Number of bytes to which `buffer' points. */ + unsigned long int allocated; + + /* Number of bytes actually used in `buffer'. */ + unsigned long int used; + + /* Syntax setting with which the pattern was compiled. */ + reg_syntax_t 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 *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 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 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. */ +#define REGS_UNALLOCATED 0 +#define REGS_REALLOCATE 1 +#define REGS_FIXED 2 + unsigned regs_allocated : 2; + + /* Set to zero when `regex_compile' compiles a pattern; set to one + by `re_compile_fastmap' if it updates the fastmap. */ + unsigned fastmap_accurate : 1; + + /* If set, `re_match_2' does not return information about + subexpressions. */ + unsigned no_sub : 1; + /* If set, a beginning-of-line anchor doesn't match at the + beginning of the string. */ + unsigned not_bol : 1; + + /* Similarly for an end-of-line anchor. */ + unsigned not_eol : 1; + + /* If true, an anchor at a newline matches. */ + unsigned newline_anchor : 1; + +/* [[[end pattern_buffer]]] */ +}; + +typedef struct re_pattern_buffer regex_t; + +/* Type for byte offsets within the string. POSIX mandates this. */ +typedef int regoff_t; + + +/* This is the structure we store register match data in. See + regex.texinfo for a full description of what registers match. */ struct re_registers - { - int start[RE_NREGS]; - int end[RE_NREGS]; - }; - -/* These are the command codes that appear in compiled regular expressions, one per byte. - Some command codes are followed by argument bytes. - A command code can specify any interpretation whatever for its arguments. - Zero-bytes may appear in the compiled regular expression. */ - -enum regexpcode - { - unused, - exactn, /* followed by one byte giving n, and then by n literal bytes */ - begline, /* fails unless at beginning of line */ - endline, /* fails unless at end of line */ - jump, /* followed by two bytes giving relative address to jump to */ - on_failure_jump, /* followed by two bytes giving relative address of place - to resume at in case of failure. */ - finalize_jump, /* Throw away latest failure point and then jump to address. */ - maybe_finalize_jump, /* Like jump but finalize if safe to do so. - This is used to jump back to the beginning - of a repeat. If the command that follows - this jump is clearly incompatible with the - one at the beginning of the repeat, such that - we can be sure that there is no use backtracking - out of repetitions already completed, - then we finalize. */ - dummy_failure_jump, /* jump, and push a dummy failure point. - This failure point will be thrown away - if an attempt is made to use it for a failure. - A + construct makes this before the first repeat. */ - anychar, /* matches any one character */ - charset, /* matches any one char belonging to specified set. - First following byte is # bitmap bytes. - Then come bytes for a bit-map saying which chars are in. - Bits in each byte are ordered low-bit-first. - A character is in the set if its bit is 1. - A character too large to have a bit in the map - is automatically not in the set */ - charset_not, /* similar but match any character that is NOT one of those specified */ - start_memory, /* starts remembering the text that is matched - and stores it in a memory register. - followed by one byte containing the register number. - Register numbers must be in the range 0 through NREGS. */ - stop_memory, /* stops remembering the text that is matched - and stores it in a memory register. - followed by one byte containing the register number. - Register numbers must be in the range 0 through NREGS. */ - duplicate, /* match a duplicate of something remembered. - Followed by one byte containing the index of the memory register. */ - before_dot, /* Succeeds if before dot */ - at_dot, /* Succeeds if at dot */ - after_dot, /* Succeeds if after dot */ - begbuf, /* Succeeds if at beginning of buffer */ - endbuf, /* Succeeds if at end of buffer */ - wordchar, /* Matches any word-constituent character */ - notwordchar, /* Matches any char that is not a word-constituent */ - wordbeg, /* Succeeds if at word beginning */ - wordend, /* Succeeds if at word end */ - wordbound, /* Succeeds if at a word boundary */ - notwordbound, /* Succeeds if not at a word boundary */ - syntaxspec, /* Matches any character whose syntax is specified. - followed by a byte which contains a syntax code, Sword or such like */ - notsyntaxspec /* Matches any character whose syntax differs from the specified. */ - }; +{ + unsigned 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 + + +/* 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; -extern char *re_compile_pattern (); -/* Is this really advertised? */ -extern void re_compile_fastmap (); -extern int re_search (), re_search_2 (); -extern int re_match (), re_match_2 (); - -/* 4.2 bsd compatibility (yuck) */ -extern char *re_comp (); -extern int re_exec (); - -#ifdef SYNTAX_TABLE -extern char *re_syntax_table; +/* Declarations for routines. */ + +/* To avoid duplicating every routine declaration -- once with a + prototype (if we are ANSI), and once without (if we aren't) -- we + use the following macro to declare argument types. This + unfortunately clutters up the declarations a bit, but I think it's + worth it. */ + +#if __STDC__ + +# define _RE_ARGS(args) args + +#else /* not __STDC__ */ + +# define _RE_ARGS(args) () + +#endif /* not __STDC__ */ + +/* 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 _RE_ARGS ((reg_syntax_t syntax)); +extern reg_syntax_t re_set_syntax _RE_ARGS ((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. */ +extern const char *__re_compile_pattern + _RE_ARGS ((const char *pattern, size_t length, + struct re_pattern_buffer *buffer)); +extern const char *re_compile_pattern + _RE_ARGS ((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 _RE_ARGS ((struct re_pattern_buffer *buffer)); +extern int re_compile_fastmap _RE_ARGS ((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 int __re_search + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, int range, struct re_registers *regs)); +extern int re_search + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, int 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 int __re_search_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, int range, struct re_registers *regs, int stop)); +extern int re_search_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, int range, struct re_registers *regs, int stop)); + + +/* Like `re_search', but return how many characters in STRING the regexp + in BUFFER matched, starting at position START. */ +extern int __re_match + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, struct re_registers *regs)); +extern int re_match + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string, + int length, int start, struct re_registers *regs)); + + +/* Relates to `re_match' as `re_search_2' relates to `re_search'. */ +extern int __re_match_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, struct re_registers *regs, int stop)); +extern int re_match_2 + _RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1, + int length1, const char *string2, int length2, + int start, struct re_registers *regs, int 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 + PATTERN_BUFFER will allocate its own register data, without + freeing the old data. */ +extern void __re_set_registers + _RE_ARGS ((struct re_pattern_buffer *buffer, struct re_registers *regs, + unsigned num_regs, regoff_t *starts, regoff_t *ends)); +extern void re_set_registers + _RE_ARGS ((struct re_pattern_buffer *buffer, struct re_registers *regs, + unsigned num_regs, regoff_t *starts, regoff_t *ends)); + +#ifdef _REGEX_RE_COMP +# ifndef _CRAY +/* 4.2 bsd compatibility. */ +extern char *re_comp _RE_ARGS ((const char *)); +extern int re_exec _RE_ARGS ((const char *)); +# endif #endif -extern int re_set_syntax (); +/* POSIX compatibility. */ +extern int __regcomp _RE_ARGS ((regex_t *__preg, const char *__pattern, + int __cflags)); +extern int regcomp _RE_ARGS ((regex_t *__preg, const char *__pattern, + int __cflags)); + +extern int __regexec _RE_ARGS ((const regex_t *__preg, + const char *__string, size_t __nmatch, + regmatch_t __pmatch[], int __eflags)); +extern int regexec _RE_ARGS ((const regex_t *__preg, + const char *__string, size_t __nmatch, + regmatch_t __pmatch[], int __eflags)); + +extern size_t __regerror _RE_ARGS ((int __errcode, const regex_t *__preg, + char *__errbuf, size_t __errbuf_size)); +extern size_t regerror _RE_ARGS ((int __errcode, const regex_t *__preg, + char *__errbuf, size_t __errbuf_size)); + +extern void __regfree _RE_ARGS ((regex_t *__preg)); +extern void regfree _RE_ARGS ((regex_t *__preg)); + + +#ifdef __cplusplus +} +#endif /* C++ */ + +#endif /* regex.h */ + +/* +Local variables: +make-backup-files: t +version-control: t +trim-versions-without-asking: nil +End: +*/ |