devn00b
/
EQ2EMu


			
				
					
						
						
							123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316
							<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=US-ASCII">
<title>Partial Matches</title>
<link rel="stylesheet" href="../../../../../doc/src/boostbook.css" type="text/css">
<meta name="generator" content="DocBook XSL Stylesheets V1.79.1">
<link rel="home" href="../index.html" title="Boost.Regex 5.1.4">
<link rel="up" href="../index.html" title="Boost.Regex 5.1.4">
<link rel="prev" href="captures.html" title="Understanding Marked Sub-Expressions and Captures">
<link rel="next" href="syntax.html" title="Regular Expression Syntax">
</head>
<body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
<table cellpadding="2" width="100%"><tr>
<td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../boost.png"></td>
<td align="center"><a href="../../../../../index.html">Home</a></td>
<td align="center"><a href="../../../../../libs/libraries.htm">Libraries</a></td>
<td align="center"><a href="http://www.boost.org/users/people.html">People</a></td>
<td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td>
<td align="center"><a href="../../../../../more/index.htm">More</a></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="captures.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../index.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="syntax.html"><img src="../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
<div class="section">
<div class="titlepage"><div><div><h2 class="title" style="clear: both">
<a name="boost_regex.partial_matches"></a><a class="link" href="partial_matches.html" title="Partial Matches">Partial Matches</a>
</h2></div></div></div>
<p>
      The <a class="link" href="ref/match_flag_type.html" title="match_flag_type"><code class="computeroutput"><span class="identifier">match_flag_type</span></code></a>
      <code class="computeroutput"><span class="identifier">match_partial</span></code> can be passed
      to the following algorithms: <a class="link" href="ref/regex_match.html" title="regex_match"><code class="computeroutput"><span class="identifier">regex_match</span></code></a>, <a class="link" href="ref/regex_search.html" title="regex_search"><code class="computeroutput"><span class="identifier">regex_search</span></code></a>, and <a class="link" href="ref/deprecated/regex_grep.html" title="regex_grep (Deprecated)"><code class="computeroutput"><span class="identifier">regex_grep</span></code></a>, and used with the iterator
      <a class="link" href="ref/regex_iterator.html" title="regex_iterator"><code class="computeroutput"><span class="identifier">regex_iterator</span></code></a>.
      When used it indicates that partial as well as full matches should be found.
      A partial match is one that matched one or more characters at the end of the
      text input, but did not match all of the regular expression (although it may
      have done so had more input been available). Partial matches are typically
      used when either validating data input (checking each character as it is entered
      on the keyboard), or when searching texts that are either too long to load
      into memory (or even into a memory mapped file), or are of indeterminate length
      (for example the source may be a socket or similar). Partial and full matches
      can be differentiated as shown in the following table (the variable M represents
      an instance of <a class="link" href="ref/match_results.html" title="match_results"><code class="computeroutput"><span class="identifier">match_results</span></code></a> as filled in by <a class="link" href="ref/regex_match.html" title="regex_match"><code class="computeroutput"><span class="identifier">regex_match</span></code></a>,
      <a class="link" href="ref/regex_search.html" title="regex_search"><code class="computeroutput"><span class="identifier">regex_search</span></code></a>
      or <a class="link" href="ref/deprecated/regex_grep.html" title="regex_grep (Deprecated)"><code class="computeroutput"><span class="identifier">regex_grep</span></code></a>):
    </p>
<div class="informaltable"><table class="table">
<colgroup>
<col>
<col>
<col>
<col>
<col>
</colgroup>
<thead><tr>
<th>
            </th>
<th>
              <p>
                Result
              </p>
            </th>
<th>
              <p>
                M[0].matched
              </p>
            </th>
<th>
              <p>
                M[0].first
              </p>
            </th>
<th>
              <p>
                M[0].second
              </p>
            </th>
</tr></thead>
<tbody>
<tr>
<td>
              <p>
                No match
              </p>
            </td>
<td>
              <p>
                False
              </p>
            </td>
<td>
              <p>
                Undefined
              </p>
            </td>
<td>
              <p>
                Undefined
              </p>
            </td>
<td>
              <p>
                Undefined
              </p>
            </td>
</tr>
<tr>
<td>
              <p>
                Partial match
              </p>
            </td>
<td>
              <p>
                True
              </p>
            </td>
<td>
              <p>
                False
              </p>
            </td>
<td>
              <p>
                Start of partial match.
              </p>
            </td>
<td>
              <p>
                End of partial match (end of text).
              </p>
            </td>
</tr>
<tr>
<td>
              <p>
                Full match
              </p>
            </td>
<td>
              <p>
                True
              </p>
            </td>
<td>
              <p>
                True
              </p>
            </td>
<td>
              <p>
                Start of full match.
              </p>
            </td>
<td>
              <p>
                End of full match.
              </p>
            </td>
</tr>
</tbody>
</table></div>
<p>
      Be aware that using partial matches can sometimes result in somewhat imperfect
      behavior:
    </p>
<div class="itemizedlist"><ul class="itemizedlist" style="list-style-type: disc; ">
<li class="listitem">
          There are some expressions, such as ".*abc" that will always
          produce a partial match. This problem can be reduced by careful construction
          of the regular expressions used, or by setting flags like match_not_dot_newline
          so that expressions like .* can't match past line boundaries.
        </li>
<li class="listitem">
          Boost.Regex currently prefers leftmost matches to full matches, so for
          example matching "abc|b" against "ab" produces a partial
          match against the "ab" rather than a full match against "b".
          It's more efficient to work this way, but may not be the behavior you want
          in all situations.
        </li>
<li class="listitem">
          There are situations where full matches are found even though partial matches
          are also possible: for example if the partial string terminates with "abc"
          and the regular expression is "\w+", then a full match is found
          even though there may be more alphabetical characters to come. This particular
          case can be detected by checking if the match found terminates at the end
          of current input string. However, there are situations where that is not
          possible: for example an expression such as "abc.*123" may always
          have longer matches available since it could conceivably match the entire
          input string (no matter how long it may be).
        </li>
</ul></div>
<p>
      The following example tests to see whether the text could be a valid credit
      card number, as the user presses a key, the character entered would be added
      to the string being built up, and passed to <code class="computeroutput"><span class="identifier">is_possible_card_number</span></code>.
      If this returns true then the text could be a valid card number, so the user
      interface's OK button would be enabled. If it returns false, then this is not
      yet a valid card number, but could be with more input, so the user interface
      would disable the OK button. Finally, if the procedure throws an exception
      the input could never become a valid number, and the inputted character must
      be discarded, and a suitable error indication displayed to the user.
    </p>
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">string</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">iostream</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">regex</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span>

<span class="identifier">boost</span><span class="special">::</span><span class="identifier">regex</span> <span class="identifier">e</span><span class="special">(</span><span class="string">"(\\d{3,4})[- ]?(\\d{4})[- ]?(\\d{4})[- ]?(\\d{4})"</span><span class="special">);</span>

<span class="keyword">bool</span> <span class="identifier">is_possible_card_number</span><span class="special">(</span><span class="keyword">const</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">string</span><span class="special">&amp;</span> <span class="identifier">input</span><span class="special">)</span>
<span class="special">{</span>
   <span class="comment">//</span>
   <span class="comment">// return false for partial match, true for full match, or throw for</span>
   <span class="comment">// impossible match based on what we have so far...</span>
   <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_results</span><span class="special">&lt;</span><span class="identifier">std</span><span class="special">::</span><span class="identifier">string</span><span class="special">::</span><span class="identifier">const_iterator</span><span class="special">&gt;</span> <span class="identifier">what</span><span class="special">;</span>
   <span class="keyword">if</span><span class="special">(</span><span class="number">0</span> <span class="special">==</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">regex_match</span><span class="special">(</span><span class="identifier">input</span><span class="special">,</span> <span class="identifier">what</span><span class="special">,</span> <span class="identifier">e</span><span class="special">,</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_default</span> <span class="special">|</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_partial</span><span class="special">))</span>
   <span class="special">{</span>
      <span class="comment">// the input so far could not possibly be valid so reject it:</span>
      <span class="keyword">throw</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">runtime_error</span><span class="special">(</span>
         <span class="string">"Invalid data entered - this could not possibly be a valid card number"</span><span class="special">);</span>
   <span class="special">}</span>
   <span class="comment">// OK so far so good, but have we finished?</span>
   <span class="keyword">if</span><span class="special">(</span><span class="identifier">what</span><span class="special">[</span><span class="number">0</span><span class="special">].</span><span class="identifier">matched</span><span class="special">)</span>
   <span class="special">{</span>
      <span class="comment">// excellent, we have a result:</span>
      <span class="keyword">return</span> <span class="keyword">true</span><span class="special">;</span>
   <span class="special">}</span>
   <span class="comment">// what we have so far is only a partial match...</span>
   <span class="keyword">return</span> <span class="keyword">false</span><span class="special">;</span>
<span class="special">}</span>
</pre>
<p>
      In the following example, text input is taken from a stream containing an unknown
      amount of text; this example simply counts the number of html tags encountered
      in the stream. The text is loaded into a buffer and searched a part at a time,
      if a partial match was encountered, then the partial match gets searched a
      second time as the start of the next batch of text:
    </p>
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">iostream</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">fstream</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">sstream</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">string</span><span class="special">&gt;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">regex</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span>

<span class="comment">// match some kind of html tag:</span>
<span class="identifier">boost</span><span class="special">::</span><span class="identifier">regex</span> <span class="identifier">e</span><span class="special">(</span><span class="string">"&lt;[^&gt;]*&gt;"</span><span class="special">);</span>
<span class="comment">// count how many:</span>
<span class="keyword">unsigned</span> <span class="keyword">int</span> <span class="identifier">tags</span> <span class="special">=</span> <span class="number">0</span><span class="special">;</span>

<span class="keyword">void</span> <span class="identifier">search</span><span class="special">(</span><span class="identifier">std</span><span class="special">::</span><span class="identifier">istream</span><span class="special">&amp;</span> <span class="identifier">is</span><span class="special">)</span>
<span class="special">{</span>
   <span class="comment">// buffer we'll be searching in:</span>
   <span class="keyword">char</span> <span class="identifier">buf</span><span class="special">[</span><span class="number">4096</span><span class="special">];</span>
   <span class="comment">// saved position of end of partial match:</span>
   <span class="keyword">const</span> <span class="keyword">char</span><span class="special">*</span> <span class="identifier">next_pos</span> <span class="special">=</span> <span class="identifier">buf</span> <span class="special">+</span> <span class="keyword">sizeof</span><span class="special">(</span><span class="identifier">buf</span><span class="special">);</span>
   <span class="comment">// flag to indicate whether there is more input to come:</span>
   <span class="keyword">bool</span> <span class="identifier">have_more</span> <span class="special">=</span> <span class="keyword">true</span><span class="special">;</span>

   <span class="keyword">while</span><span class="special">(</span><span class="identifier">have_more</span><span class="special">)</span>
   <span class="special">{</span>
      <span class="comment">// how much do we copy forward from last try:</span>
      <span class="keyword">unsigned</span> <span class="identifier">leftover</span> <span class="special">=</span> <span class="special">(</span><span class="identifier">buf</span> <span class="special">+</span> <span class="keyword">sizeof</span><span class="special">(</span><span class="identifier">buf</span><span class="special">))</span> <span class="special">-</span> <span class="identifier">next_pos</span><span class="special">;</span>
      <span class="comment">// and how much is left to fill:</span>
      <span class="keyword">unsigned</span> <span class="identifier">size</span> <span class="special">=</span> <span class="identifier">next_pos</span> <span class="special">-</span> <span class="identifier">buf</span><span class="special">;</span>
      <span class="comment">// copy forward whatever we have left:</span>
      <span class="identifier">std</span><span class="special">::</span><span class="identifier">memmove</span><span class="special">(</span><span class="identifier">buf</span><span class="special">,</span> <span class="identifier">next_pos</span><span class="special">,</span> <span class="identifier">leftover</span><span class="special">);</span>
      <span class="comment">// fill the rest from the stream:</span>
      <span class="identifier">is</span><span class="special">.</span><span class="identifier">read</span><span class="special">(</span><span class="identifier">buf</span> <span class="special">+</span> <span class="identifier">leftover</span><span class="special">,</span> <span class="identifier">size</span><span class="special">);</span>
      <span class="keyword">unsigned</span> <span class="identifier">read</span> <span class="special">=</span> <span class="identifier">is</span><span class="special">.</span><span class="identifier">gcount</span><span class="special">();</span>
      <span class="comment">// check to see if we've run out of text:</span>
      <span class="identifier">have_more</span> <span class="special">=</span> <span class="identifier">read</span> <span class="special">==</span> <span class="identifier">size</span><span class="special">;</span>
      <span class="comment">// reset next_pos:</span>
      <span class="identifier">next_pos</span> <span class="special">=</span> <span class="identifier">buf</span> <span class="special">+</span> <span class="keyword">sizeof</span><span class="special">(</span><span class="identifier">buf</span><span class="special">);</span>
      <span class="comment">// and then iterate:</span>
      <span class="identifier">boost</span><span class="special">::</span><span class="identifier">cregex_iterator</span> <span class="identifier">a</span><span class="special">(</span>
         <span class="identifier">buf</span><span class="special">,</span>
         <span class="identifier">buf</span> <span class="special">+</span> <span class="identifier">read</span> <span class="special">+</span> <span class="identifier">leftover</span><span class="special">,</span>
         <span class="identifier">e</span><span class="special">,</span>
         <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_default</span> <span class="special">|</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_partial</span><span class="special">);</span>
      <span class="identifier">boost</span><span class="special">::</span><span class="identifier">cregex_iterator</span> <span class="identifier">b</span><span class="special">;</span>

      <span class="keyword">while</span><span class="special">(</span><span class="identifier">a</span> <span class="special">!=</span> <span class="identifier">b</span><span class="special">)</span>
      <span class="special">{</span>
         <span class="keyword">if</span><span class="special">((*</span><span class="identifier">a</span><span class="special">)[</span><span class="number">0</span><span class="special">].</span><span class="identifier">matched</span> <span class="special">==</span> <span class="keyword">false</span><span class="special">)</span>
         <span class="special">{</span>
            <span class="comment">// Partial match, save position and break:</span>
            <span class="identifier">next_pos</span> <span class="special">=</span> <span class="special">(*</span><span class="identifier">a</span><span class="special">)[</span><span class="number">0</span><span class="special">].</span><span class="identifier">first</span><span class="special">;</span>
            <span class="keyword">break</span><span class="special">;</span>
         <span class="special">}</span>
         <span class="keyword">else</span>
         <span class="special">{</span>
            <span class="comment">// full match:</span>
            <span class="special">++</span><span class="identifier">tags</span><span class="special">;</span>
         <span class="special">}</span>

         <span class="comment">// move to next match:</span>
         <span class="special">++</span><span class="identifier">a</span><span class="special">;</span>
      <span class="special">}</span>
   <span class="special">}</span>
<span class="special">}</span>
</pre>
</div>
<table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr>
<td align="left"></td>
<td align="right"><div class="copyright-footer">Copyright &#169; 1998-2013 John Maddock<p>
        Distributed under the Boost Software License, Version 1.0. (See accompanying
        file LICENSE_1_0.txt or copy at <a href="http://www.boost.org/LICENSE_1_0.txt" target="_top">http://www.boost.org/LICENSE_1_0.txt</a>)
      </p>
</div></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="captures.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../index.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="syntax.html"><img src="../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
</body>
</html>