Mercurial > emacs
view src/regex.h @ 108511:f8e62c2bf3e9
Reformat some comments in src/s/*.h.
author | Glenn Morris <rgm@gnu.org> |
---|---|
date | Tue, 11 May 2010 23:53:03 -0700 |
parents | 1d1d5d9bd884 |
children | 376148b31b5e |
line wrap: on
line source
/* Definitions for data structures and routines for the regular expression library, version 0.12. Copyright (C) 1985, 1989, 1990, 1991, 1992, 1993, 1995, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 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 3, or (at your option) any later version. 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. 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, 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 /* The following bits are used to determine the regexp syntax we recognize. The set/not-set meanings where historically chosen so that Emacs syntax had 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, then *?, +? and ?? match non greedily. */ #define RE_FRUGAL (RE_NO_GNU_OPS << 1) /* If this bit is set, then (?:...) is treated as a shy group. */ #define RE_SHY_GROUPS (RE_FRUGAL << 1) /* If this bit is set, ^ and $ only match at beg/end of buffer. */ #define RE_NO_NEWLINE_ANCHOR (RE_SHY_GROUPS << 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_NEWLINE_ANCHOR << 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; #ifdef emacs /* In Emacs, this is the string or buffer in which we are matching. It is used for looking up syntax properties. */ extern Lisp_Object re_match_object; #endif /* 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 \ (RE_CHAR_CLASSES | RE_INTERVALS | RE_SHY_GROUPS | RE_FRUGAL) #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_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. 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 { #ifdef _XOPEN_SOURCE REG_ENOSYS = -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_ERANGEX /* Range striding over charsets. */ } 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 { /* [[[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. */ size_t allocated; /* Number of bytes actually used in `buffer'. */ size_t 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'. */ 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, the compilation of the pattern had to look up the syntax table, so the compiled pattern is only valid for the current syntax table. */ unsigned used_syntax : 1; #ifdef emacs /* If true, multi-byte form in the regexp pattern should be recognized as a multibyte character. */ unsigned multibyte : 1; /* If true, multi-byte form in the target of match should be recognized as a multibyte character. */ unsigned target_multibyte : 1; /* Charset of unibyte characters at compiling time. */ int charset_unibyte; #endif /* [[[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 { 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; /* 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 defined __STDC__ || defined PROTOTYPES # define _RE_ARGS(args) args #else /* not __STDC__ || PROTOTYPES */ # define _RE_ARGS(args) () #endif /* not __STDC__ || PROTOTYPES */ /* 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)); /* 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)); /* 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)); /* 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)); /* 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)); /* 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)); /* 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)); /* 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)); #if defined _REGEX_RE_COMP || defined _LIBC # ifndef _CRAY /* 4.2 bsd compatibility. */ extern char *re_comp _RE_ARGS ((const char *)); extern int re_exec _RE_ARGS ((const char *)); # endif #endif /* GCC 2.95 and later have "__restrict"; C99 compilers have "restrict", and "configure" may have defined "restrict". */ #ifndef __restrict # if ! (2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)) # if defined restrict || 199901L <= __STDC_VERSION__ # define __restrict restrict # else # define __restrict # endif # endif #endif /* For now conditionally define __restrict_arr to expand to nothing. Ideally we would have a test for the compiler which allows defining it to restrict. */ #ifndef __restrict_arr # define __restrict_arr #endif /* POSIX compatibility. */ extern int regcomp _RE_ARGS ((regex_t *__restrict __preg, const char *__restrict __pattern, int __cflags)); extern int regexec _RE_ARGS ((const regex_t *__restrict __preg, const char *__restrict __string, size_t __nmatch, regmatch_t __pmatch[__restrict_arr], int __eflags)); 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)); #ifdef __cplusplus } #endif /* C++ */ /* For platform which support the ISO C amendement 1 functionality we support user defined character classes. */ #if WIDE_CHAR_SUPPORT /* Solaris 2.5 has a bug: <wchar.h> must be included before <wctype.h>. */ # include <wchar.h> # include <wctype.h> #endif #if WIDE_CHAR_SUPPORT /* The GNU C library provides support for user-defined character classes and the functions from ISO C amendement 1. */ # ifdef CHARCLASS_NAME_MAX # define CHAR_CLASS_MAX_LENGTH CHARCLASS_NAME_MAX # else /* This shouldn't happen but some implementation might still have this problem. Use a reasonable default value. */ # define CHAR_CLASS_MAX_LENGTH 256 # endif typedef wctype_t re_wctype_t; typedef wchar_t re_wchar_t; # define re_wctype wctype # define re_iswctype iswctype # define re_wctype_to_bit(cc) 0 #else # define CHAR_CLASS_MAX_LENGTH 9 /* Namely, `multibyte'. */ # define btowc(c) c /* Character classes. */ typedef enum { RECC_ERROR = 0, RECC_ALNUM, RECC_ALPHA, RECC_WORD, RECC_GRAPH, RECC_PRINT, RECC_LOWER, RECC_UPPER, RECC_PUNCT, RECC_CNTRL, RECC_DIGIT, RECC_XDIGIT, RECC_BLANK, RECC_SPACE, RECC_MULTIBYTE, RECC_NONASCII, RECC_ASCII, RECC_UNIBYTE } re_wctype_t; extern char re_iswctype (int ch, re_wctype_t cc); extern re_wctype_t re_wctype (const unsigned char* str); typedef int re_wchar_t; extern void re_set_whitespace_regexp (const char *regexp); #endif /* not WIDE_CHAR_SUPPORT */ #endif /* regex.h */ /* arch-tag: bda6e3ec-3c02-4237-a55a-01ad2e120083 (do not change this comment) */