384 lines
15 KiB
Groff
384 lines
15 KiB
Groff
'\"
|
|
'\" Copyright (c) 1994 The Regents of the University of California.
|
|
'\" Copyright (c) 1994-1996 Sun Microsystems, Inc.
|
|
'\" Copyright (c) 1998-1999 Scriptics Corporation
|
|
'\"
|
|
'\" See the file "license.terms" for information on usage and redistribution
|
|
'\" of this file, and for a DISCLAIMER OF ALL WARRANTIES.
|
|
'\"
|
|
.TH Tcl_RegExpMatch 3 8.1 Tcl "Tcl Library Procedures"
|
|
.so man.macros
|
|
.BS
|
|
.SH NAME
|
|
Tcl_RegExpMatch, Tcl_RegExpCompile, Tcl_RegExpExec, Tcl_RegExpRange, Tcl_GetRegExpFromObj, Tcl_RegExpMatchObj, Tcl_RegExpExecObj, Tcl_RegExpGetInfo \- Pattern matching with regular expressions
|
|
.SH SYNOPSIS
|
|
.nf
|
|
\fB#include <tcl.h>\fR
|
|
.sp
|
|
int
|
|
\fBTcl_RegExpMatchObj\fR(\fIinterp\fR, \fItextObj\fR, \fIpatObj\fR)
|
|
.sp
|
|
int
|
|
\fBTcl_RegExpMatch\fR(\fIinterp\fR, \fItext\fR, \fIpattern\fR)
|
|
.sp
|
|
Tcl_RegExp
|
|
\fBTcl_RegExpCompile\fR(\fIinterp\fR, \fIpattern\fR)
|
|
.sp
|
|
int
|
|
\fBTcl_RegExpExec\fR(\fIinterp\fR, \fIregexp\fR, \fItext\fR, \fIstart\fR)
|
|
.sp
|
|
void
|
|
\fBTcl_RegExpRange\fR(\fIregexp\fR, \fIindex\fR, \fIstartPtr\fR, \fIendPtr\fR)
|
|
.sp
|
|
Tcl_RegExp
|
|
\fBTcl_GetRegExpFromObj\fR(\fIinterp\fR, \fIpatObj\fR, \fIcflags\fR)
|
|
.sp
|
|
int
|
|
\fBTcl_RegExpExecObj\fR(\fIinterp\fR, \fIregexp\fR, \fItextObj\fR, \fIoffset\fR, \fInmatches\fR, \fIeflags\fR)
|
|
.sp
|
|
void
|
|
\fBTcl_RegExpGetInfo\fR(\fIregexp\fR, \fIinfoPtr\fR)
|
|
.fi
|
|
.SH ARGUMENTS
|
|
.AS Tcl_RegExpInfo *interp in/out
|
|
.AP Tcl_Interp *interp in
|
|
Tcl interpreter to use for error reporting. The interpreter may be
|
|
NULL if no error reporting is desired.
|
|
.AP Tcl_Obj *textObj in/out
|
|
Refers to the value from which to get the text to search. The
|
|
internal representation of the value may be converted to a form that
|
|
can be efficiently searched.
|
|
.AP Tcl_Obj *patObj in/out
|
|
Refers to the value from which to get a regular expression. The
|
|
compiled regular expression is cached in the value.
|
|
.AP "const char" *text in
|
|
Text to search for a match with a regular expression.
|
|
.AP "const char" *pattern in
|
|
String in the form of a regular expression pattern.
|
|
.AP Tcl_RegExp regexp in
|
|
Compiled regular expression. Must have been returned previously
|
|
by \fBTcl_GetRegExpFromObj\fR or \fBTcl_RegExpCompile\fR.
|
|
.AP "const char" *start in
|
|
If \fItext\fR is just a portion of some other string, this argument
|
|
identifies the beginning of the larger string.
|
|
If it is not the same as \fItext\fR, then no
|
|
.QW \fB^\fR
|
|
matches will be allowed.
|
|
.AP int index in
|
|
Specifies which range is desired: 0 means the range of the entire
|
|
match, 1 or greater means the range that matched a parenthesized
|
|
sub-expression.
|
|
.AP "const char" **startPtr out
|
|
The address of the first character in the range is stored here, or
|
|
NULL if there is no such range.
|
|
.AP "const char" **endPtr out
|
|
The address of the character just after the last one in the range
|
|
is stored here, or NULL if there is no such range.
|
|
.AP int cflags in
|
|
OR-ed combination of the compilation flags \fBTCL_REG_ADVANCED\fR,
|
|
\fBTCL_REG_EXTENDED\fR, \fBTCL_REG_BASIC\fR, \fBTCL_REG_EXPANDED\fR,
|
|
\fBTCL_REG_QUOTE\fR, \fBTCL_REG_NOCASE\fR, \fBTCL_REG_NEWLINE\fR,
|
|
\fBTCL_REG_NLSTOP\fR, \fBTCL_REG_NLANCH\fR, \fBTCL_REG_NOSUB\fR, and
|
|
\fBTCL_REG_CANMATCH\fR. See below for more information.
|
|
.AP int offset in
|
|
The character offset into the text where matching should begin.
|
|
The value of the offset has no impact on \fB^\fR matches. This
|
|
behavior is controlled by \fIeflags\fR.
|
|
.AP int nmatches in
|
|
The number of matching subexpressions that should be remembered for
|
|
later use. If this value is 0, then no subexpression match
|
|
information will be computed. If the value is \-1, then
|
|
all of the matching subexpressions will be remembered. Any other
|
|
value will be taken as the maximum number of subexpressions to
|
|
remember.
|
|
.AP int eflags in
|
|
OR-ed combination of the execution flags \fBTCL_REG_NOTBOL\fR and
|
|
\fBTCL_REG_NOTEOL\fR. See below for more information.
|
|
.AP Tcl_RegExpInfo *infoPtr out
|
|
The address of the location where information about a previous match
|
|
should be stored by \fBTcl_RegExpGetInfo\fR.
|
|
.BE
|
|
.SH DESCRIPTION
|
|
.PP
|
|
\fBTcl_RegExpMatch\fR determines whether its \fIpattern\fR argument
|
|
matches \fIregexp\fR, where \fIregexp\fR is interpreted
|
|
as a regular expression using the rules in the \fBre_syntax\fR
|
|
reference page.
|
|
If there is a match then \fBTcl_RegExpMatch\fR returns 1.
|
|
If there is no match then \fBTcl_RegExpMatch\fR returns 0.
|
|
If an error occurs in the matching process (e.g. \fIpattern\fR
|
|
is not a valid regular expression) then \fBTcl_RegExpMatch\fR
|
|
returns \-1 and leaves an error message in the interpreter result.
|
|
\fBTcl_RegExpMatchObj\fR is similar to \fBTcl_RegExpMatch\fR except it
|
|
operates on the Tcl values \fItextObj\fR and \fIpatObj\fR instead of
|
|
UTF strings.
|
|
\fBTcl_RegExpMatchObj\fR is generally more efficient than
|
|
\fBTcl_RegExpMatch\fR, so it is the preferred interface.
|
|
.PP
|
|
\fBTcl_RegExpCompile\fR, \fBTcl_RegExpExec\fR, and \fBTcl_RegExpRange\fR
|
|
provide lower-level access to the regular expression pattern matcher.
|
|
\fBTcl_RegExpCompile\fR compiles a regular expression string into
|
|
the internal form used for efficient pattern matching.
|
|
The return value is a token for this compiled form, which can be
|
|
used in subsequent calls to \fBTcl_RegExpExec\fR or \fBTcl_RegExpRange\fR.
|
|
If an error occurs while compiling the regular expression then
|
|
\fBTcl_RegExpCompile\fR returns NULL and leaves an error message
|
|
in the interpreter result.
|
|
Note: the return value from \fBTcl_RegExpCompile\fR is only valid
|
|
up to the next call to \fBTcl_RegExpCompile\fR; it is not safe to
|
|
retain these values for long periods of time.
|
|
.PP
|
|
\fBTcl_RegExpExec\fR executes the regular expression pattern matcher.
|
|
It returns 1 if \fItext\fR contains a range of characters that
|
|
match \fIregexp\fR, 0 if no match is found, and
|
|
\-1 if an error occurs.
|
|
In the case of an error, \fBTcl_RegExpExec\fR leaves an error
|
|
message in the interpreter result.
|
|
When searching a string for multiple matches of a pattern,
|
|
it is important to distinguish between the start of the original
|
|
string and the start of the current search.
|
|
For example, when searching for the second occurrence of a
|
|
match, the \fItext\fR argument might point to the character
|
|
just after the first match; however, it is important for the
|
|
pattern matcher to know that this is not the start of the entire string,
|
|
so that it does not allow
|
|
.QW \fB^\fR
|
|
atoms in the pattern to match.
|
|
The \fIstart\fR argument provides this information by pointing
|
|
to the start of the overall string containing \fItext\fR.
|
|
\fIStart\fR will be less than or equal to \fItext\fR; if it
|
|
is less than \fItext\fR then no \fB^\fR matches will be allowed.
|
|
.PP
|
|
\fBTcl_RegExpRange\fR may be invoked after \fBTcl_RegExpExec\fR
|
|
returns; it provides detailed information about what ranges of
|
|
the string matched what parts of the pattern.
|
|
\fBTcl_RegExpRange\fR returns a pair of pointers in \fI*startPtr\fR
|
|
and \fI*endPtr\fR that identify a range of characters in
|
|
the source string for the most recent call to \fBTcl_RegExpExec\fR.
|
|
\fIIndex\fR indicates which of several ranges is desired:
|
|
if \fIindex\fR is 0, information is returned about the overall range
|
|
of characters that matched the entire pattern; otherwise,
|
|
information is returned about the range of characters that matched the
|
|
\fIindex\fR'th parenthesized subexpression within the pattern.
|
|
If there is no range corresponding to \fIindex\fR then NULL
|
|
is stored in \fI*startPtr\fR and \fI*endPtr\fR.
|
|
.PP
|
|
\fBTcl_GetRegExpFromObj\fR, \fBTcl_RegExpExecObj\fR, and
|
|
\fBTcl_RegExpGetInfo\fR are value interfaces that provide the most
|
|
direct control of Henry Spencer's regular expression library. For
|
|
users that need to modify compilation and execution options directly,
|
|
it is recommended that you use these interfaces instead of calling the
|
|
internal regexp functions. These interfaces handle the details of UTF
|
|
to Unicode translations as well as providing improved performance
|
|
through caching in the pattern and string values.
|
|
.PP
|
|
\fBTcl_GetRegExpFromObj\fR attempts to return a compiled regular
|
|
expression from the \fIpatObj\fR. If the value does not already
|
|
contain a compiled regular expression it will attempt to create one
|
|
from the string in the value and assign it to the internal
|
|
representation of the \fIpatObj\fR. The return value of this function
|
|
is of type \fBTcl_RegExp\fR. The return value is a token for this
|
|
compiled form, which can be used in subsequent calls to
|
|
\fBTcl_RegExpExecObj\fR or \fBTcl_RegExpGetInfo\fR. If an error
|
|
occurs while compiling the regular expression then
|
|
\fBTcl_GetRegExpFromObj\fR returns NULL and leaves an error message in
|
|
the interpreter result. The regular expression token can be used as
|
|
long as the internal representation of \fIpatObj\fR refers to the
|
|
compiled form. The \fIcflags\fR argument is a bit-wise OR of
|
|
zero or more of the following flags that control the compilation of
|
|
\fIpatObj\fR:
|
|
.RS 2
|
|
.TP
|
|
\fBTCL_REG_ADVANCED\fR
|
|
Compile advanced regular expressions
|
|
.PQ ARE s .
|
|
This mode corresponds to
|
|
the normal regular expression syntax accepted by the Tcl \fBregexp\fR and
|
|
\fBregsub\fR commands.
|
|
.TP
|
|
\fBTCL_REG_EXTENDED\fR
|
|
Compile extended regular expressions
|
|
.PQ ERE s .
|
|
This mode corresponds
|
|
to the regular expression syntax recognized by Tcl 8.0 and earlier
|
|
versions.
|
|
.TP
|
|
\fBTCL_REG_BASIC\fR
|
|
Compile basic regular expressions
|
|
.PQ BRE s .
|
|
This mode corresponds
|
|
to the regular expression syntax recognized by common Unix utilities
|
|
like \fBsed\fR and \fBgrep\fR. This is the default if no flags are
|
|
specified.
|
|
.TP
|
|
\fBTCL_REG_EXPANDED\fR
|
|
Compile the regular expression (basic, extended, or advanced) using an
|
|
expanded syntax that allows comments and whitespace. This mode causes
|
|
non-backslashed non-bracket-expression white
|
|
space and #-to-end-of-line comments to be ignored.
|
|
.TP
|
|
\fBTCL_REG_QUOTE\fR
|
|
Compile a literal string, with all characters treated as ordinary characters.
|
|
.TP
|
|
\fBTCL_REG_NOCASE\fR
|
|
Compile for matching that ignores upper/lower case distinctions.
|
|
.TP
|
|
\fBTCL_REG_NEWLINE\fR
|
|
Compile for newline-sensitive matching. By default, newline is a
|
|
completely ordinary character with no special meaning in either
|
|
regular expressions or strings. With this flag,
|
|
.QW [^
|
|
bracket expressions and
|
|
.QW .
|
|
never match newline,
|
|
.QW ^
|
|
matches an empty string
|
|
after any newline in addition to its normal function, and
|
|
.QW $
|
|
matches
|
|
an empty string before any newline in addition to its normal function.
|
|
\fBREG_NEWLINE\fR is the bit-wise OR of \fBREG_NLSTOP\fR and
|
|
\fBREG_NLANCH\fR.
|
|
.TP
|
|
\fBTCL_REG_NLSTOP\fR
|
|
Compile for partial newline-sensitive matching,
|
|
with the behavior of
|
|
.QW [^
|
|
bracket expressions and
|
|
.QW .
|
|
affected, but not the behavior of
|
|
.QW ^
|
|
and
|
|
.QW $ .
|
|
In this mode,
|
|
.QW [^
|
|
bracket expressions and
|
|
.QW .
|
|
never match newline.
|
|
.TP
|
|
\fBTCL_REG_NLANCH\fR
|
|
Compile for inverse partial newline-sensitive matching,
|
|
with the behavior of
|
|
.QW ^
|
|
and
|
|
.QW $
|
|
(the
|
|
.QW anchors )
|
|
affected, but not the behavior of
|
|
.QW [^
|
|
bracket expressions and
|
|
.QW . .
|
|
In this mode
|
|
.QW ^
|
|
matches an empty string
|
|
after any newline in addition to its normal function, and
|
|
.QW $
|
|
matches
|
|
an empty string before any newline in addition to its normal function.
|
|
.TP
|
|
\fBTCL_REG_NOSUB\fR
|
|
Compile for matching that reports only success or failure,
|
|
not what was matched. This reduces compile overhead and may improve
|
|
performance. Subsequent calls to \fBTcl_RegExpGetInfo\fR or
|
|
\fBTcl_RegExpRange\fR will not report any match information.
|
|
.TP
|
|
\fBTCL_REG_CANMATCH\fR
|
|
Compile for matching that reports the potential to complete a partial
|
|
match given more text (see below).
|
|
.RE
|
|
.PP
|
|
Only one of
|
|
\fBTCL_REG_EXTENDED\fR,
|
|
\fBTCL_REG_ADVANCED\fR,
|
|
\fBTCL_REG_BASIC\fR, and
|
|
\fBTCL_REG_QUOTE\fR may be specified.
|
|
.PP
|
|
\fBTcl_RegExpExecObj\fR executes the regular expression pattern
|
|
matcher. It returns 1 if \fIobjPtr\fR contains a range of characters
|
|
that match \fIregexp\fR, 0 if no match is found, and \-1 if an error
|
|
occurs. In the case of an error, \fBTcl_RegExpExecObj\fR leaves an
|
|
error message in the interpreter result. The \fInmatches\fR value
|
|
indicates to the matcher how many subexpressions are of interest. If
|
|
\fInmatches\fR is 0, then no subexpression match information is
|
|
recorded, which may allow the matcher to make various optimizations.
|
|
If the value is \-1, then all of the subexpressions in the pattern are
|
|
remembered. If the value is a positive integer, then only that number
|
|
of subexpressions will be remembered. Matching begins at the
|
|
specified Unicode character index given by \fIoffset\fR. Unlike
|
|
\fBTcl_RegExpExec\fR, the behavior of anchors is not affected by the
|
|
offset value. Instead the behavior of the anchors is explicitly
|
|
controlled by the \fIeflags\fR argument, which is a bit-wise OR of
|
|
zero or more of the following flags:
|
|
.RS 2
|
|
.TP
|
|
\fBTCL_REG_NOTBOL\fR
|
|
The starting character will not be treated as the beginning of a
|
|
line or the beginning of the string, so
|
|
.QW ^
|
|
will not match there.
|
|
Note that this flag has no effect on how
|
|
.QW \fB\eA\fR
|
|
matches.
|
|
.TP
|
|
\fBTCL_REG_NOTEOL\fR
|
|
The last character in the string will not be treated as the end of a
|
|
line or the end of the string, so
|
|
.QW $
|
|
will not match there.
|
|
Note that this flag has no effect on how
|
|
.QW \fB\eZ\fR
|
|
matches.
|
|
.RE
|
|
.PP
|
|
\fBTcl_RegExpGetInfo\fR retrieves information about the last match
|
|
performed with a given regular expression \fIregexp\fR. The
|
|
\fIinfoPtr\fR argument contains a pointer to a structure that is
|
|
defined as follows:
|
|
.PP
|
|
.CS
|
|
typedef struct Tcl_RegExpInfo {
|
|
int \fInsubs\fR;
|
|
Tcl_RegExpIndices *\fImatches\fR;
|
|
long \fIextendStart\fR;
|
|
} \fBTcl_RegExpInfo\fR;
|
|
.CE
|
|
.PP
|
|
The \fInsubs\fR field contains a count of the number of parenthesized
|
|
subexpressions within the regular expression. If the \fBTCL_REG_NOSUB\fR
|
|
was used, then this value will be zero. The \fImatches\fR field
|
|
points to an array of \fInsubs\fR+1 values that indicate the bounds of each
|
|
subexpression matched. The first element in the array refers to the
|
|
range matched by the entire regular expression, and subsequent elements
|
|
refer to the parenthesized subexpressions in the order that they
|
|
appear in the pattern. Each element is a structure that is defined as
|
|
follows:
|
|
.PP
|
|
.CS
|
|
typedef struct Tcl_RegExpIndices {
|
|
long \fIstart\fR;
|
|
long \fIend\fR;
|
|
} \fBTcl_RegExpIndices\fR;
|
|
.CE
|
|
.PP
|
|
The \fIstart\fR and \fIend\fR values are Unicode character indices
|
|
relative to the offset location within \fIobjPtr\fR where matching began.
|
|
The \fIstart\fR index identifies the first character of the matched
|
|
subexpression. The \fIend\fR index identifies the first character
|
|
after the matched subexpression. If the subexpression matched the
|
|
empty string, then \fIstart\fR and \fIend\fR will be equal. If the
|
|
subexpression did not participate in the match, then \fIstart\fR and
|
|
\fIend\fR will be set to \-1.
|
|
.PP
|
|
The \fIextendStart\fR field in \fBTcl_RegExpInfo\fR is only set if the
|
|
\fBTCL_REG_CANMATCH\fR flag was used. It indicates the first
|
|
character in the string where a match could occur. If a match was
|
|
found, this will be the same as the beginning of the current match.
|
|
If no match was found, then it indicates the earliest point at which a
|
|
match might occur if additional text is appended to the string. If it
|
|
is no match is possible even with further text, this field will be set
|
|
to \-1.
|
|
.SH "SEE ALSO"
|
|
re_syntax(n)
|
|
.SH KEYWORDS
|
|
match, pattern, regular expression, string, subexpression, Tcl_RegExpIndices, Tcl_RegExpInfo
|