GnuRegex.h

Go to the documentation of this file.

/*
 * Copyright (C) 1996-2022 The Squid Software Foundation and contributors
 *
 * Squid software is distributed under GPLv2+ license and includes
 * contributions from numerous individuals and organizations.
 * Please see the COPYING and CONTRIBUTORS files for details.
 */
 
#ifndef SQUID_REGEXP_LIBRARY_H
#define SQUID_REGEXP_LIBRARY_H
 
#if !USE_GNUREGEX /* try the system one by default */
 
/* POSIX says that <sys/types.h> must be included (by the caller) before
 * <regex.h>.  */
#if HAVE_SYS_TYPES_H
#include <sys/types.h>
#endif
#if HAVE_REGEX_H
#include <regex.h>
#endif
 
#else  /* USE_GNUREGEX */
 
#ifdef __cplusplus
extern "C" {
#endif
 
/* 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.  */
 
/* POSIX says that <sys/types.h> must be included (by the caller) before
 * <regex.h>.  */
 
/* 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)
 
/* 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)
 
/* If any error codes are removed, changed, or added, update the
 * `re_error_msg' table in regex.c.  */
typedef enum {
    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.  */
 
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.  */
    unsigned long allocated;
 
    /* Number of bytes actually used in `buffer'.  */
    unsigned long 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.  */
    char *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;
 
/* search.c (search_buffer) in Emacs needs this one opcode value.  It is
 * defined both in `regex.c' and here.  */
#define RE_EXACTN_VALUE 1

/* 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.  */
 
/* POSIX compatibility.  */
extern int regcomp(regex_t * preg, const char *pattern, int cflags);
extern int regexec(const regex_t * preg, const char *string, size_t nmatch, regmatch_t pmatch[], int eflags);
extern size_t regerror(int errcode, const regex_t * preg, char *errbuf, size_t errbuf_size);
extern void regfree(regex_t * preg);
 
#ifdef __cplusplus
}
#endif
 
#endif /* USE_GNUREGEX */
#endif /* SQUID_REGEXP_LIBRARY_H */
 
/*
 * Local variables:
 * make-backup-files: t
 * version-control: t
 * trim-versions-without-asking: nil
 * End:
 */