path: root/man3/regex.3

'\" t
.\" Copyright (C), 1995, Graeme W. Wilford. (Wilf.)
.\"
.\" SPDX-License-Identifier: Linux-man-pages-copyleft
.\"
.\" Wed Jun 14 16:10:28 BST 1995 Wilf. (G.Wilford@ee.surrey.ac.uk)
.\" Tiny change in formatting - aeb, 950812
.\" Modified 8 May 1998 by Joseph S. Myers (jsm28@cam.ac.uk)
.\"
.\" show the synopsis section nicely
.TH regex 3 (date) "Linux man-pages (unreleased)"
.SH NAME
regcomp, regexec, regerror, regfree \- POSIX regex functions
.SH LIBRARY
Standard C library
.RI ( libc ", " \-lc )
.SH SYNOPSIS
.nf
.B #include <regex.h>
.PP
.BI "int regcomp(regex_t *restrict " preg ", const char *restrict " regex ,
.BI "            int " cflags );
.BI "int regexec(const regex_t *restrict " preg \
", const char *restrict " string ,
.BI "            size_t " nmatch ", regmatch_t " pmatch "[_Nullable restrict ." nmatch ],
.BI "            int " eflags );
.PP
.BI "size_t regerror(int " errcode ", const regex_t *_Nullable restrict " preg ,
.BI "            char " errbuf "[_Nullable restrict ." errbuf_size ],
.BI "            size_t " errbuf_size );
.BI "void regfree(regex_t *" preg );
.PP
.B typedef struct {
.BR "    size_t    re_nsub;" "  /* Number of parenthesized subexpressions */"
.B } regex_t;
.PP
.B typedef struct {
.BR "    regoff_t  rm_so;" "    /* Byte offset from start of string"
                           to start of substring */
.BR "    regoff_t  rm_eo;" "    /* Byte offset from start of string to"
                           the first character after the end of
                           substring */
.B } regmatch_t;
.PP
.BR typedef " /* ... */  " regoff_t;
.fi
.SH DESCRIPTION
.SS Compilation
.BR regcomp ()
is used to compile a regular expression into a form that is suitable
for subsequent
.BR regexec ()
searches.
.PP
On success, the pattern buffer at
.I *preg
is initialized.
.I regex
is a null-terminated string.
The locale must be the same when running
.BR regexec ().
.PP
.I cflags
is the
bitwise OR
of zero or more of the following:
.TP
.B REG_EXTENDED
Use
POSIX
Extended Regular Expression syntax when interpreting
.IR regex .
If not set,
POSIX
Basic Regular Expression syntax is used.
.TP
.B REG_ICASE
Do not differentiate case.
Subsequent
.BR regexec ()
searches using this pattern buffer will be case insensitive.
.TP
.B REG_NOSUB
Do not report position of matches.
The
.I nmatch
and
.I pmatch
.BR regexec ()
arguments will be ignored for this purpose (but
.I pmatch
may still be used for
.BR REG_STARTEND ).
.TP
.B REG_NEWLINE
Match-any-character operators don't match a newline.
.IP
A nonmatching list
.RB ( [\[ha]...] )
not containing a newline does not match a newline.
.IP
Match-beginning-of-line operator
.RB ( \[ha] )
matches the empty string immediately after a newline, regardless of
whether
.IR eflags ,
the execution flags of
.BR regexec (),
contains
.BR REG_NOTBOL .
.IP
Match-end-of-line operator
.RB ( $ )
matches the empty string immediately before a newline, regardless of
whether
.I eflags
contains
.BR REG_NOTEOL .
.SS Matching
.BR regexec ()
is used to match a null-terminated string
against the compiled pattern buffer in
.IR *preg ,
which must have been initialised with
.BR regexec ().
.I eflags
is the
bitwise OR
of zero or more of the following flags:
.TP
.B REG_NOTBOL
The match-beginning-of-line operator always fails to match (but see the
compilation flag
.B REG_NEWLINE
above).
This flag may be used when different portions of a string are passed to
.BR regexec ()
and the beginning of the string should not be interpreted as the
beginning of the line.
.TP
.B REG_NOTEOL
The match-end-of-line operator always fails to match (but see the
compilation flag
.B REG_NEWLINE
above).
.TP
.B REG_STARTEND
Match
.RI [ "string + pmatch[0].rm_so" , " string + pmatch[0].rm_eo" )
instead of
.RI [ string , " string + strlen(string)" ).
This allows matching embedded NUL bytes
and avoids a
.BR strlen (3)
on known-length strings.
If any matches are returned
.RB ( REG_NOSUB
wasn't passed to
.BR regcomp (),
the match succeeded, and
.I nmatch
> 0), they overwrite
.I pmatch
as usual, and the match offsets remain relative to
.I string
(not
.IR "string + pmatch[0].rm_so" ).
This flag is a BSD extension, not present in POSIX.
.SS Match offsets
Unless
.B REG_NOSUB
was set for the compilation of the pattern buffer, it is possible to
obtain match addressing information.
.I pmatch
must be dimensioned to have at least
.I nmatch
elements.
These are filled in by
.BR regexec ()
with substring match addresses.
The offsets of the subexpression starting at the
.IR i th
open parenthesis are stored in
.IR pmatch[i] .
The entire regular expression's match addresses are stored in
.IR pmatch[0] .
(Note that to return the offsets of
.I N
subexpression matches,
.I nmatch
must be at least
.IR N+1 .)
Any unused structure elements will contain the value \-1.
.PP
The
.I regmatch_t
structure which is the type of
.I pmatch
is defined in
.IR <regex.h> .
.PP
.in +4n
.EX
typedef struct {
    regoff_t rm_so;
    regoff_t rm_eo;
} regmatch_t;
.EE
.in
.PP
Each
.I rm_so
element that is not \-1 indicates the start offset of the next largest
substring match within the string.
The relative
.I rm_eo
element indicates the end offset of the match,
which is the offset of the first character after the matching text.
.PP
.I regoff_t
It is a signed integer type
capable of storing the largest value that can be stored in either an
.I ptrdiff_t
type or a
.I ssize_t
type.
.SS Error reporting
.BR regerror ()
is used to turn the error codes that can be returned by both
.BR regcomp ()
and
.BR regexec ()
into error message strings.
.PP
.BR regerror ()
is passed the error code,
.IR errcode ,
the pattern buffer,
.IR preg ,
a pointer to a character string buffer,
.IR errbuf ,
and the size of the string buffer,
.IR errbuf_size .
It returns the size of the
.I errbuf
required to contain the null-terminated error message string.
If both
.I errbuf
and
.I errbuf_size
are nonzero,
.I errbuf
is filled in with the first
.I "errbuf_size \- 1"
characters of the error message and a terminating null byte (\[aq]\e0\[aq]).
.SS Freeing
.BR regfree ()
deinitializes the pattern buffer at
.IR *preg ,
freeing any associated memory;
.I *preg
must have been initialized via
.BR regcomp ().
.SH RETURN VALUE
.BR regcomp ()
returns zero for a successful compilation or an error code for failure.
.PP
.BR regexec ()
returns zero for a successful match or
.B REG_NOMATCH
for failure.
.SH ERRORS
The following errors can be returned by
.BR regcomp ():
.TP
.B REG_BADBR
Invalid use of back reference operator.
.TP
.B REG_BADPAT
Invalid use of pattern operators such as group or list.
.TP
.B REG_BADRPT
Invalid use of repetition operators such as using \[aq]*\[aq]
as the first character.
.TP
.B REG_EBRACE
Un-matched brace interval operators.
.TP
.B REG_EBRACK
Un-matched bracket list operators.
.TP
.B REG_ECOLLATE
Invalid collating element.
.TP
.B REG_ECTYPE
Unknown character class name.
.TP
.B REG_EEND
Nonspecific error.
This is not defined by POSIX.
.TP
.B REG_EESCAPE
Trailing backslash.
.TP
.B REG_EPAREN
Un-matched parenthesis group operators.
.TP
.B REG_ERANGE
Invalid use of the range operator; for example, the ending point of the range
occurs prior to the starting point.
.TP
.B REG_ESIZE
Compiled regular expression requires a pattern buffer larger than 64\ kB.
This is not defined by POSIX.
.TP
.B REG_ESPACE
The regex routines ran out of memory.
.TP
.B REG_ESUBREG
Invalid back reference to a subexpression.
.SH ATTRIBUTES
For an explanation of the terms used in this section, see
.BR attributes (7).
.ad l
.nh
.TS
allbox;
lbx lb lb
l l l.
Interface	Attribute	Value
T{
.BR regcomp (),
.BR regexec ()
T}	Thread safety	MT-Safe locale
T{
.BR regerror ()
T}	Thread safety	MT-Safe env
T{
.BR regfree ()
T}	Thread safety	MT-Safe
.TE
.hy
.ad
.sp 1
.SH STANDARDS
POSIX.1-2008.
.SH HISTORY
POSIX.1-2001.
.PP
Prior to POSIX.1-2008,
the type was
capable of storing the largest value that can be stored in either an
.I off_t
type or a
.I ssize_t
type.
.SH EXAMPLES
.EX
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <regex.h>

#define ARRAY_SIZE(arr) (sizeof((arr)) / sizeof((arr)[0]))

static const char *const str =
        "1) John Driverhacker;\en2) John Doe;\en3) John Foo;\en";
static const char *const re = "John.*o";

int main(void)
{
    static const char *s = str;
    regex_t     regex;
    regmatch_t  pmatch[1];
    regoff_t    off, len;

    if (regcomp(&regex, re, REG_NEWLINE))
        exit(EXIT_FAILURE);

    printf("String = \e"%s\e"\en", str);
    printf("Matches:\en");

    for (unsigned int i = 0; ; i++) {
        if (regexec(&regex, s, ARRAY_SIZE(pmatch), pmatch, 0))
            break;

        off = pmatch[0].rm_so + (s \- str);
        len = pmatch[0].rm_eo \- pmatch[0].rm_so;
        printf("#%zu:\en", i);
        printf("offset = %jd; length = %jd\en", (intmax_t) off,
                (intmax_t) len);
        printf("substring = \e"%.*s\e"\en", len, s + pmatch[0].rm_so);

        s += pmatch[0].rm_eo;
    }

    exit(EXIT_SUCCESS);
}
.EE
.SH SEE ALSO
.BR grep (1),
.BR regex (7)
.PP
The glibc manual section,
.I "Regular Expressions"