Planet
navi homePPSaboutscreenshotsdownloaddevelopmentforum

source: downloads/boost_1_34_1/libs/regex/doc/regex_split.html @ 35

Last change on this file since 35 was 29, checked in by landauf, 16 years ago

updated boost from 1_33_1 to 1_34_1
File size: 8.0 KB
Line 
1<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
2<html>
3   <head>
4      <title>Boost.Regex: Algorithm regex_split (deprecated)</title>
5      <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
6      <link rel="stylesheet" type="text/css" href="../../../boost.css">
7   </head>
8   <body>
9      <P>
10         <TABLE id="Table1" cellSpacing="1" cellPadding="1" width="100%" border="0">
11            <TR>
12               <td valign="top" width="300">
13                  <h3><a href="../../../index.htm"><img height="86" width="277" alt="C++ Boost" src="../../../boost.png" border="0"></a></h3>
14               </td>
15               <TD width="353">
16                  <H1 align="center">Boost.Regex</H1>
17                  <H2 align="center">Algorithm regex_split (deprecated)</H2>
18               </TD>
19               <td width="50">
20                  <h3><a href="index.html"><img height="45" width="43" alt="Boost.Regex Index" src="uarrow.gif" border="0"></a></h3>
21               </td>
22            </TR>
23         </TABLE>
24      </P>
25      <HR>
26      <p></p>
27      <P>The algorithm regex_split has been deprecated in favor of the iterator <A href="regex_token_iterator.html">
28            regex_token_iterator</A> which has a more flexible and powerful interface,
29         as well as following the more usual standard library "pull" rather than "push"
30         semantics.</P>
31      <P>Code which uses regex_split will continue to compile, the following
32         documentation is taken from the previous boost.regex version:</P>
33      <H3><A name="regex_split"></A>Algorithm regex_split</H3>
34      <PRE>#include &lt;<A href="../../../boost/regex.hpp">boost/regex.hpp</A>&gt; </PRE>
35      <P>Algorithm regex_split performs a similar operation to the perl split operation,
36         and comes in three overloaded forms:
37      </P>
38      <PRE><B>template</B> &lt;<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1, <B>class</B> Traits2&gt;
39std::size_t regex_split(OutputIterator out,&nbsp;
40&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; std::basic_string&lt;charT, Traits1, Alloc1&gt;&amp; s,&nbsp;
41&nbsp;<B>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;const</B> basic_regex&lt;charT, Traits2&gt;&amp; e,
42&nbsp;<STRONG>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</STRONG>boost::match_flag_type flags,
43&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; std::size_t max_split);
44
45<B>template</B> &lt;<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1, <B>class</B> Traits2&gt;
46std::size_t regex_split(OutputIterator out,&nbsp;
47&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; std::basic_string&lt;charT, Traits1, Alloc1&gt;&amp; s,&nbsp;
48&nbsp;<B>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;const</B> basic_regex&lt;charT, Traits2&gt;&amp; e,
49&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; boost::match_flag_type flags = match_default);
50
51<B>template</B> &lt;<B>class</B> OutputIterator, <B>class</B> charT, <B>class</B> Traits1, <B>class</B> Alloc1&gt;
52std::size_t regex_split(OutputIterator out,
53                        std::basic_string&lt;charT, Traits1, Alloc1&gt;&amp; s);</PRE>
54      <P><STRONG>Effects: </STRONG>Each version of the algorithm takes an
55         output-iterator for output, and a string for input. If the expression contains
56         no marked sub-expressions, then the algorithm writes one string onto the
57         output-iterator for each section of input that does not match the expression.
58         If the expression does contain marked sub-expressions, then each time a match
59         is found, one string for each marked sub-expression will be written to the
60         output-iterator. No more than <I>max_split </I>strings will be written to the
61         output-iterator. Before returning, all the input processed will be deleted from
62         the string <I>s</I> (if <I>max_split </I>is not reached then all of <I>s</I> will
63         be deleted). Returns the number of strings written to the output-iterator. If
64         the parameter <I>max_split</I> is not specified then it defaults to UINT_MAX.
65         If no expression is specified, then it defaults to "\s+", and splitting occurs
66         on whitespace.
67      </P>
68      <P><STRONG>Throws:</STRONG> <CODE>std::runtime_error</CODE> if the complexity of
69         matching the expression against an N character string begins to exceed O(N<SUP>2</SUP>),
70         or if the program runs out of stack space while matching the expression (if
71         Boost.regex is <A href="configuration.html">configured</A> in recursive mode),
72         or if the matcher exhausts it's permitted memory allocation (if Boost.regex is <A href="configuration.html">
73            configured</A> in non-recursive mode).</P>
74      <P><A href="../example/snippets/regex_split_example_1.cpp">Example</A>: the
75         following function will split the input string into a series of tokens, and
76         remove each token from the string <I>s</I>:
77      </P>
78      <PRE><B>unsigned</B> tokenise(std::list&lt;std::string&gt;&amp; l, std::string&amp; s)
79{
80<B>&nbsp;&nbsp; return</B> boost::regex_split(std::back_inserter(l), s);
81}</PRE>
82      <P><A href="../example/snippets/regex_split_example_2.cpp">Example</A>: the
83         following short program will extract all of the URL's from a html file, and
84         print them out to <I>cout</I>:
85      </P>
86      <PRE><FONT color=#008000>#include &lt;list&gt;
87#include &lt;fstream&gt;
88#include &lt;iostream&gt;
89#include &lt;boost/regex.hpp&gt;
90</FONT>
91boost::regex e(<FONT color=#000080>"&lt;\\s*A\\s+[^&gt;]*href\\s*=\\s*\"([^\"]*)\""</FONT>,
92               boost::regbase::normal | boost::regbase::icase);
93
94<B>void</B> load_file(std::string&amp; s, std::istream&amp; is)
95{
96   s.erase();
97   <FONT color=#000080>//
98   // attempt to grow string buffer to match file size,
99   // this doesn't always work...
100</FONT>   s.reserve(is.rdbuf()-&amp;gtin_avail());
101   <B>char</B> c;
102   <B>while</B>(is.get(c))
103   {
104      <FONT color=#000080>// use logarithmic growth stategy, in case
105      // in_avail (above) returned zero:
106</FONT>      <B>if</B>(s.capacity() == s.size())
107         s.reserve(s.capacity() * 3);
108      s.append(1, c);
109   }
110}
111
112
113<B>int</B> main(<B>int</B> argc, <B>char</B>** argv)
114{
115   std::string s;
116   std::list&lt;std::string&gt; l;
117
118   <B>for</B>(<B>int</B> i = 1; i &lt; argc; ++i)
119   {
120      std::cout &lt;&lt; <FONT color=#000080>"Findings URL's in "</FONT> &lt;&lt; argv[i] &lt;&lt; <FONT color=#000080>":"</FONT> &lt;&lt; std::endl;
121      s.erase();
122      std::ifstream is(argv[i]);
123      load_file(s, is);
124      boost::regex_split(std::back_inserter(l), s, e);
125      <B>while</B>(l.size())
126      {
127         s = *(l.begin());
128         l.pop_front();
129         std::cout &lt;&lt; s &lt;&lt; std::endl;
130      }
131   }
132   <B>return</B> 0;
133}</PRE>
134      <HR>
135      <p>Revised&nbsp; 
136         <!--webbot bot="Timestamp" S-Type="EDITED" S-Format="%d %B, %Y" startspan --> 
137         26 June&nbsp;2004
138         <!--webbot bot="Timestamp" endspan i-checksum="39359" --></p>
139      <p><i>© Copyright John Maddock&nbsp;1998-
140            <!--webbot bot="Timestamp" S-Type="EDITED" S-Format="%Y" startspan -->  2004<!--webbot bot="Timestamp" endspan i-checksum="39359" --></i></p>
141      <P><I>Use, modification and distribution are subject to the Boost Software License,
142            Version 1.0. (See accompanying file <A href="../../../LICENSE_1_0.txt">LICENSE_1_0.txt</A>
143            or copy at <A href="http://www.boost.org/LICENSE_1_0.txt">http://www.boost.org/LICENSE_1_0.txt</A>)</I></P>
144   </body>
145</html>
Note: See TracBrowser for help on using the repository browser.