forked from boostorg/regex
144 lines
7.8 KiB
HTML
144 lines
7.8 KiB
HTML
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
|
|
<html>
|
|
<head>
|
|
<title>Boost.Regex: Algorithm regex_split (deprecated)</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">Algorithm regex_split (deprecated)</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>
|
|
<P>The algorithm regex_split has been deprecated in favour of the iterator <A href="regex_token_iterator.html">
|
|
regex_token_iterator</A> which has a more flexible and powerful interface,
|
|
as well as following the more usual standard library "pull" rather than "push"
|
|
semantics.</P>
|
|
<P>Code which uses regex_split will continue to compile, the following
|
|
documentation is taken from the previous boost.regex version:</P>
|
|
<H3><A name="regex_split"></A>Algorithm regex_split</H3>
|
|
<PRE>#include <<A href="../../../boost/regex.hpp">boost/regex.hpp</A>> </PRE>
|
|
<P>Algorithm regex_split performs a similar operation to the perl split operation,
|
|
and comes in three overloaded forms:
|
|
</P>
|
|
<PRE><B>template</B> <<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1, <B>class</B> Traits2, <B>class</B> Alloc2>
|
|
std::size_t regex_split(OutputIterator out,
|
|
std::basic_string<charT, Traits1, Alloc1>& s,
|
|
<B> const</B> basic_regex<charT, Traits2, Alloc2>& e,
|
|
<B> unsigned</B> flags,
|
|
std::size_t max_split);
|
|
|
|
<B>template</B> <<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1, <B>class</B> Traits2, <B>class</B> Alloc2>
|
|
std::size_t regex_split(OutputIterator out,
|
|
std::basic_string<charT, Traits1, Alloc1>& s,
|
|
<B> const</B> basic_regex<charT, Traits2, Alloc2>& e,
|
|
<B>unsigned</B> flags = match_default);
|
|
|
|
<B>template</B> <<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1>
|
|
std::size_t regex_split(OutputIterator out,
|
|
std::basic_string<charT, Traits1, Alloc1>& s);</PRE>
|
|
<P>Each version takes an output-iterator for output, and a string for input. If
|
|
the expression contains no marked sub-expressions, then the algorithm writes
|
|
one string onto the output-iterator for each section of input that does not
|
|
match the expression. If the expression does contain marked sub-expressions,
|
|
then each time a match is found, one string for each marked sub-expression will
|
|
be written to the output-iterator. No more than <I>max_split </I>strings will
|
|
be written to the output-iterator. Before returning, all the input processed
|
|
will be deleted from the string <I>s</I> (if <I>max_split </I>is not reached
|
|
then all of <I>s</I> will be deleted). Returns the number of strings written to
|
|
the output-iterator. If the parameter <I>max_split</I> is not specified then it
|
|
defaults to UINT_MAX. If no expression is specified, then it defaults to "\s+",
|
|
and splitting occurs on whitespace.
|
|
</P>
|
|
<P><A href="../example/snippets/regex_split_example_1.cpp">Example</A>: the following
|
|
function will split the input string into a series of tokens, and remove each
|
|
token from the string <I>s</I>:
|
|
</P>
|
|
<PRE><B>unsigned</B> tokenise(std::list<std::string>& l, std::string& s)
|
|
{
|
|
<B> return</B> boost::regex_split(std::back_inserter(l), s);
|
|
}</PRE>
|
|
<P><A href="../example/snippets/regex_split_example_2.cpp">Example</A>: the following
|
|
short program will extract all of the URL's from a html file, and print them
|
|
out to <I>cout</I>:
|
|
</P>
|
|
<PRE><FONT color=#008000>#include <list>
|
|
#include <fstream>
|
|
#include <iostream>
|
|
#include <boost/regex.hpp>
|
|
</FONT>
|
|
boost::regex e(<FONT color=#000080>"<\\s*A\\s+[^>]*href\\s*=\\s*\"([^\"]*)\""</FONT>,
|
|
boost::regbase::normal | boost::regbase::icase);
|
|
|
|
<B>void</B> load_file(std::string& s, std::istream& is)
|
|
{
|
|
s.erase();
|
|
<FONT color=#000080>//
|
|
// attempt to grow string buffer to match file size,
|
|
// this doesn't always work...
|
|
</FONT> s.reserve(is.rdbuf()-&gtin_avail());
|
|
<B>char</B> c;
|
|
<B>while</B>(is.get(c))
|
|
{
|
|
<FONT color=#000080>// use logarithmic growth stategy, in case
|
|
// in_avail (above) returned zero:
|
|
</FONT> <B>if</B>(s.capacity() == s.size())
|
|
s.reserve(s.capacity() * 3);
|
|
s.append(1, c);
|
|
}
|
|
}
|
|
|
|
|
|
<B>int</B> main(<B>int</B> argc, <B>char</B>** argv)
|
|
{
|
|
std::string s;
|
|
std::list<std::string> l;
|
|
|
|
<B>for</B>(<B>int</B> i = 1; i < argc; ++i)
|
|
{
|
|
std::cout << <FONT color=#000080>"Findings URL's in "</FONT> << argv[i] << <FONT color=#000080>":"</FONT> << std::endl;
|
|
s.erase();
|
|
std::ifstream is(argv[i]);
|
|
load_file(s, is);
|
|
boost::regex_split(std::back_inserter(l), s, e);
|
|
<B>while</B>(l.size())
|
|
{
|
|
s = *(l.begin());
|
|
l.pop_front();
|
|
std::cout << s << std::endl;
|
|
}
|
|
}
|
|
<B>return</B> 0;
|
|
}</PRE>
|
|
<P>
|
|
<HR>
|
|
<P></P>
|
|
<p>Revised
|
|
<!--webbot bot="Timestamp" S-Type="EDITED" S-Format="%d %B, %Y" startspan -->
|
|
11 April 2003
|
|
<!--webbot bot="Timestamp" endspan i-checksum="39359" -->
|
|
</p>
|
|
<P><I>© 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>
|