mirror of
https://github.com/boostorg/regex.git
synced 2025-07-05 08:36:31 +02:00
289 lines
13 KiB
HTML
289 lines
13 KiB
HTML
|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
|
|||
|
|
<html>
|
|||
|
|
<head>
|
|||
|
|
<title>Boost.Regex: POSIX API Compatibility Functions</title>
|
|||
|
|
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
|
|||
|
|
<link rel="stylesheet" type="text/css" href="../../../boost.css">
|
|||
|
|
</head>
|
|||
|
|
<body>
|
|||
|
|
<P>
|
|||
|
|
<TABLE id="Table1" cellSpacing="1" cellPadding="1" width="100%" border="0">
|
|||
|
|
<TR>
|
|||
|
|
<td valign="top" width="300">
|
|||
|
|
<h3><a href="../../../index.htm"><img height="86" width="277" alt="C++ Boost" src="../../../c++boost.gif" border="0"></a></h3>
|
|||
|
|
</td>
|
|||
|
|
<TD width="353">
|
|||
|
|
<H1 align="center">Boost.Regex</H1>
|
|||
|
|
<H2 align="center">POSIX API Compatibility Functions</H2>
|
|||
|
|
</TD>
|
|||
|
|
<td width="50">
|
|||
|
|
<h3><a href="index.html"><img height="45" width="43" alt="Boost.Regex Index" src="uarrow.gif" border="0"></a></h3>
|
|||
|
|
</td>
|
|||
|
|
</TR>
|
|||
|
|
</TABLE>
|
|||
|
|
</P>
|
|||
|
|
<HR>
|
|||
|
|
<p></p>
|
|||
|
|
<PRE>#include <boost/cregex.hpp>
|
|||
|
|
<I>or</I>:
|
|||
|
|
#include <boost/regex.h></PRE>
|
|||
|
|
<P>The following functions are available for users who need a POSIX compatible C
|
|||
|
|
library, they are available in both Unicode and narrow character versions, the
|
|||
|
|
standard POSIX API names are macros that expand to one version or the other
|
|||
|
|
depending upon whether UNICODE is defined or not.
|
|||
|
|
</P>
|
|||
|
|
<P><B>Important</B>: Note that all the symbols defined here are enclosed inside
|
|||
|
|
namespace <I>boost</I> when used in C++ programs, unless you use #include
|
|||
|
|
<boost/regex.h> instead - in which case the symbols are still defined in
|
|||
|
|
namespace boost, but are made available in the global namespace as well.</P>
|
|||
|
|
<P>The functions are defined as:
|
|||
|
|
</P>
|
|||
|
|
<PRE>extern "C" {
|
|||
|
|
<B>int</B> regcompA(regex_tA*, <B>const</B> <B>char</B>*, <B>int</B>);
|
|||
|
|
<B>unsigned</B> <B>int</B> regerrorA(<B>int</B>, <B>const</B> regex_tA*, <B>char</B>*, <B>unsigned</B> <B>int</B>);
|
|||
|
|
<B>int</B> regexecA(<B>const</B> regex_tA*, <B>const</B> <B>char</B>*, <B>unsigned</B> <B>int</B>, regmatch_t*, <B>int</B>);
|
|||
|
|
<B>void</B> regfreeA(regex_tA*);
|
|||
|
|
|
|||
|
|
<B>int</B> regcompW(regex_tW*, <B>const</B> <B>wchar_t</B>*, <B>int</B>);
|
|||
|
|
<B>unsigned</B> <B>int</B> regerrorW(<B>int</B>, <B>const</B> regex_tW*, <B>wchar_t</B>*, <B>unsigned</B> <B>int</B>);
|
|||
|
|
<B>int</B> regexecW(<B>const</B> regex_tW*, <B>const</B> <B>wchar_t</B>*, <B>unsigned</B> <B>int</B>, regmatch_t*, <B>int</B>);
|
|||
|
|
<B>void</B> regfreeW(regex_tW*);
|
|||
|
|
|
|||
|
|
#ifdef UNICODE
|
|||
|
|
#define regcomp regcompW
|
|||
|
|
#define regerror regerrorW
|
|||
|
|
#define regexec regexecW
|
|||
|
|
#define regfree regfreeW
|
|||
|
|
#define regex_t regex_tW
|
|||
|
|
#else
|
|||
|
|
#define regcomp regcompA
|
|||
|
|
#define regerror regerrorA
|
|||
|
|
#define regexec regexecA
|
|||
|
|
#define regfree regfreeA
|
|||
|
|
#define regex_t regex_tA
|
|||
|
|
#endif
|
|||
|
|
}</PRE>
|
|||
|
|
<P>All the functions operate on structure <B>regex_t</B>, which exposes two public
|
|||
|
|
members:
|
|||
|
|
</P>
|
|||
|
|
<P><B>unsigned int re_nsub</B> this is filled in by <B>regcomp</B> and indicates
|
|||
|
|
the number of sub-expressions contained in the regular expression.
|
|||
|
|
</P>
|
|||
|
|
<P><B>const TCHAR* re_endp</B> points to the end of the expression to compile when
|
|||
|
|
the flag REG_PEND is set.
|
|||
|
|
</P>
|
|||
|
|
<P><I>Footnote: regex_t is actually a #define - it is either regex_tA or regex_tW
|
|||
|
|
depending upon whether UNICODE is defined or not, TCHAR is either char or
|
|||
|
|
wchar_t again depending upon the macro UNICODE.</I>
|
|||
|
|
</P>
|
|||
|
|
<H3>regcomp</H3>
|
|||
|
|
<P><B>regcomp</B> takes a pointer to a <B>regex_t</B>, a pointer to the expression
|
|||
|
|
to compile and a flags parameter which can be a combination of:
|
|||
|
|
<BR>
|
|||
|
|
|
|||
|
|
</P>
|
|||
|
|
<P>
|
|||
|
|
<TABLE id="Table2" cellSpacing="0" cellPadding="7" width="100%" border="0">
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_EXTENDED</TD>
|
|||
|
|
<TD vAlign="top" width="45%">Compiles modern regular expressions. Equivalent to
|
|||
|
|
regbase::char_classes | regbase::intervals | regbase::bk_refs.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_BASIC</TD>
|
|||
|
|
<TD vAlign="top" width="45%">Compiles basic (obsolete) regular expression syntax.
|
|||
|
|
Equivalent to regbase::char_classes | regbase::intervals | regbase::limited_ops
|
|||
|
|
| regbase::bk_braces | regbase::bk_parens | regbase::bk_refs.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_NOSPEC</TD>
|
|||
|
|
<TD vAlign="top" width="45%">All characters are ordinary, the expression is a
|
|||
|
|
literal string.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_ICASE</TD>
|
|||
|
|
<TD vAlign="top" width="45%">Compiles for matching that ignores character case.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_NOSUB</TD>
|
|||
|
|
<TD vAlign="top" width="45%">Has no effect in this library.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_NEWLINE</TD>
|
|||
|
|
<TD vAlign="top" width="45%">When this flag is set a dot does not match the
|
|||
|
|
newline character.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_PEND</TD>
|
|||
|
|
<TD vAlign="top" width="45%">When this flag is set the re_endp parameter of the
|
|||
|
|
regex_t structure must point to the end of the regular expression to compile.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_NOCOLLATE</TD>
|
|||
|
|
<TD vAlign="top" width="45%">When this flag is set then locale dependent collation
|
|||
|
|
for character ranges is turned off.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_ESCAPE_IN_LISTS<BR>
|
|||
|
|
, , ,
|
|||
|
|
</TD>
|
|||
|
|
<TD vAlign="top" width="45%">When this flag is set, then escape sequences are
|
|||
|
|
permitted in bracket expressions (character sets).</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_NEWLINE_ALT </TD>
|
|||
|
|
<TD vAlign="top" width="45%">When this flag is set then the newline character is
|
|||
|
|
equivalent to the alternation operator |.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_PERL </TD>
|
|||
|
|
<TD vAlign="top" width="45%">Compiles Perl like regular expressions.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_AWK</TD>
|
|||
|
|
<TD vAlign="top" width="45%">A shortcut for awk-like behavior: REG_EXTENDED |
|
|||
|
|
REG_ESCAPE_IN_LISTS</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_GREP</TD>
|
|||
|
|
<TD vAlign="top" width="45%">A shortcut for grep like behavior: REG_BASIC |
|
|||
|
|
REG_NEWLINE_ALT</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="45%">REG_EGREP</TD>
|
|||
|
|
<TD vAlign="top" width="45%"> A shortcut for egrep like behavior:
|
|||
|
|
REG_EXTENDED | REG_NEWLINE_ALT</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
</TABLE>
|
|||
|
|
</P>
|
|||
|
|
<H3>regerror</H3>
|
|||
|
|
<P>regerror takes the following parameters, it maps an error code to a human
|
|||
|
|
readable string:
|
|||
|
|
<BR>
|
|||
|
|
</P>
|
|||
|
|
<P>
|
|||
|
|
<TABLE id="Table3" cellSpacing="0" cellPadding="7" width="100%" border="0">
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">int code</TD>
|
|||
|
|
<TD vAlign="top" width="50%">The error code.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">const regex_t* e</TD>
|
|||
|
|
<TD vAlign="top" width="50%">The regular expression (can be null).</TD>
|
|||
|
|
<TD> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">char* buf</TD>
|
|||
|
|
<TD vAlign="top" width="50%">The buffer to fill in with the error message.</TD>
|
|||
|
|
<TD> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">unsigned int buf_size</TD>
|
|||
|
|
<TD vAlign="top" width="50%">The length of buf.</TD>
|
|||
|
|
<TD> </TD>
|
|||
|
|
</TR>
|
|||
|
|
</TABLE>
|
|||
|
|
</P>
|
|||
|
|
<P>If the error code is OR'ed with REG_ITOA then the message that results is the
|
|||
|
|
printable name of the code rather than a message, for example "REG_BADPAT". If
|
|||
|
|
the code is REG_ATIO then <B>e</B> must not be null and <B>e->re_pend</B> must
|
|||
|
|
point to the printable name of an error code, the return value is then the
|
|||
|
|
value of the error code. For any other value of <B>code</B>, the return value
|
|||
|
|
is the number of characters in the error message, if the return value is
|
|||
|
|
greater than or equal to <B>buf_size</B> then <B>regerror</B> will have to be
|
|||
|
|
called again with a larger buffer.</P>
|
|||
|
|
<H3>regexec</H3>
|
|||
|
|
<P><B>regexec</B> finds the first occurrence of expression <B>e</B> within string <B>buf</B>.
|
|||
|
|
If <B>len</B> is non-zero then *<B>m</B> is filled in with what matched the
|
|||
|
|
regular expression, <B>m[0]</B> contains what matched the whole string, <B>m[1] </B>
|
|||
|
|
the first sub-expression etc, see <B>regmatch_t</B> in the header file
|
|||
|
|
declaration for more details. The <B>eflags</B> parameter can be a combination
|
|||
|
|
of:
|
|||
|
|
<BR>
|
|||
|
|
|
|||
|
|
</P>
|
|||
|
|
<P>
|
|||
|
|
<TABLE id="Table4" cellSpacing="0" cellPadding="7" width="100%" border="0">
|
|||
|
|
<TR>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">REG_NOTBOL</TD>
|
|||
|
|
<TD vAlign="top" width="50%">Parameter <B>buf </B>does not represent the start of
|
|||
|
|
a line.</TD>
|
|||
|
|
<TD width="5%"> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">REG_NOTEOL</TD>
|
|||
|
|
<TD vAlign="top" width="50%">Parameter <B>buf</B> does not terminate at the end of
|
|||
|
|
a line.</TD>
|
|||
|
|
<TD> </TD>
|
|||
|
|
</TR>
|
|||
|
|
<TR>
|
|||
|
|
<TD> </TD>
|
|||
|
|
<TD vAlign="top" width="50%">REG_STARTEND</TD>
|
|||
|
|
<TD vAlign="top" width="50%">The string searched starts at buf + pmatch[0].rm_so
|
|||
|
|
and ends at buf + pmatch[0].rm_eo.</TD>
|
|||
|
|
<TD> </TD>
|
|||
|
|
</TR>
|
|||
|
|
</TABLE>
|
|||
|
|
</P>
|
|||
|
|
<H3>regfree</H3>
|
|||
|
|
<P>Finally <B>regfree</B> frees all the memory that was allocated by regcomp.
|
|||
|
|
</P>
|
|||
|
|
<P><I>Footnote: this is an abridged reference to the POSIX API functions, it is
|
|||
|
|
provided for compatibility with other libraries, rather than an API to be used
|
|||
|
|
in new code (unless you need access from a language other than C++). This
|
|||
|
|
version of these functions should also happily coexist with other versions, as
|
|||
|
|
the names used are macros that expand to the actual function names.</I>
|
|||
|
|
<P>
|
|||
|
|
<HR>
|
|||
|
|
<P></P>
|
|||
|
|
<p>Revised
|
|||
|
|
<!--webbot bot="Timestamp" S-Type="EDITED" S-Format="%d %B, %Y" startspan -->
|
|||
|
|
17 May 2003
|
|||
|
|
<!--webbot bot="Timestamp" endspan i-checksum="39359" -->
|
|||
|
|
</p>
|
|||
|
|
<P><I><EFBFBD> Copyright <a href="mailto:jm@regex.fsnet.co.uk">John Maddock</a> 1998-<!--webbot bot="Timestamp" S-Type="EDITED" S-Format="%Y" startspan --> 2003<!--webbot bot="Timestamp" endspan i-checksum="39359" --></I></P>
|
|||
|
|
<P align="left"><I>Permission to use, copy, modify, distribute and sell this software
|
|||
|
|
and its documentation for any purpose is hereby granted without fee, provided
|
|||
|
|
that the above copyright notice appear in all copies and that both that
|
|||
|
|
copyright notice and this permission notice appear in supporting documentation.
|
|||
|
|
Dr John Maddock makes no representations about the suitability of this software
|
|||
|
|
for any purpose. It is provided "as is" without express or implied warranty.</I></P>
|
|||
|
|
</body>
|
|||
|
|
</html>
|
|||
|
|
|