gnuregex.h

-

/*
 * $Id: GNUregex.h,v 1.6 1999/01/11 21:55:33 wessels Exp $
 */

/* Definitions for data structures and routines for the regular
 * expression library, version 0.12.
 * 
 * Copyright (C) 1985, 1989, 1990, 1991, 1992, 1993 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, 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., 59 Temple Place, Suite 330, Boston, MA 02111, USA.  */

#ifndef __REGEXP_LIBRARY_H__
#define __REGEXP_LIBRARY_H__

/* POSIX says that <sys/types.h> must be included (by the caller) before
 * <regex.h>.  */

#ifdef 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 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 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 (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)

/* 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

#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_UNMATCHED_RIGHT_PAREN_ORD)

#define RE_SYNTAX_POSIX_AWK 						\
  (RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS)

#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
#define RE_DUP_MAX ((1 << 15) - 1)


/* 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)