]>
Commit | Line | Data |
---|---|---|
7c673cae FG |
1 | <html> |
2 | <head> | |
3 | <meta http-equiv="Content-Type" content="text/html; charset=US-ASCII"> | |
4 | <title>Partial Matches</title> | |
5 | <link rel="stylesheet" href="../../../../../doc/src/boostbook.css" type="text/css"> | |
6 | <meta name="generator" content="DocBook XSL Stylesheets V1.77.1"> | |
7 | <link rel="home" href="../index.html" title="Boost.Regex 5.1.2"> | |
8 | <link rel="up" href="../index.html" title="Boost.Regex 5.1.2"> | |
9 | <link rel="prev" href="captures.html" title="Understanding Marked Sub-Expressions and Captures"> | |
10 | <link rel="next" href="syntax.html" title="Regular Expression Syntax"> | |
11 | </head> | |
12 | <body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF"> | |
13 | <table cellpadding="2" width="100%"><tr> | |
14 | <td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../boost.png"></td> | |
15 | <td align="center"><a href="../../../../../index.html">Home</a></td> | |
16 | <td align="center"><a href="../../../../../libs/libraries.htm">Libraries</a></td> | |
17 | <td align="center"><a href="http://www.boost.org/users/people.html">People</a></td> | |
18 | <td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td> | |
19 | <td align="center"><a href="../../../../../more/index.htm">More</a></td> | |
20 | </tr></table> | |
21 | <hr> | |
22 | <div class="spirit-nav"> | |
23 | <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> | |
24 | </div> | |
25 | <div class="section"> | |
26 | <div class="titlepage"><div><div><h2 class="title" style="clear: both"> | |
27 | <a name="boost_regex.partial_matches"></a><a class="link" href="partial_matches.html" title="Partial Matches">Partial Matches</a> | |
28 | </h2></div></div></div> | |
29 | <p> | |
30 | 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> | |
31 | <code class="computeroutput"><span class="identifier">match_partial</span></code> can be passed | |
32 | 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_interfaces/regex_grep.html" title="regex_grep (Deprecated)"><code class="computeroutput"><span class="identifier">regex_grep</span></code></a>, and used with the iterator | |
33 | <a class="link" href="ref/regex_iterator.html" title="regex_iterator"><code class="computeroutput"><span class="identifier">regex_iterator</span></code></a>. | |
34 | When used it indicates that partial as well as full matches should be found. | |
35 | A partial match is one that matched one or more characters at the end of the | |
36 | text input, but did not match all of the regular expression (although it may | |
37 | have done so had more input been available). Partial matches are typically | |
38 | used when either validating data input (checking each character as it is entered | |
39 | on the keyboard), or when searching texts that are either too long to load | |
40 | into memory (or even into a memory mapped file), or are of indeterminate length | |
41 | (for example the source may be a socket or similar). Partial and full matches | |
42 | can be differentiated as shown in the following table (the variable M represents | |
43 | 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>, | |
44 | <a class="link" href="ref/regex_search.html" title="regex_search"><code class="computeroutput"><span class="identifier">regex_search</span></code></a> | |
45 | or <a class="link" href="ref/deprecated_interfaces/regex_grep.html" title="regex_grep (Deprecated)"><code class="computeroutput"><span class="identifier">regex_grep</span></code></a>): | |
46 | </p> | |
47 | <div class="informaltable"><table class="table"> | |
48 | <colgroup> | |
49 | <col> | |
50 | <col> | |
51 | <col> | |
52 | <col> | |
53 | <col> | |
54 | </colgroup> | |
55 | <thead><tr> | |
56 | <th> | |
57 | </th> | |
58 | <th> | |
59 | <p> | |
60 | Result | |
61 | </p> | |
62 | </th> | |
63 | <th> | |
64 | <p> | |
65 | M[0].matched | |
66 | </p> | |
67 | </th> | |
68 | <th> | |
69 | <p> | |
70 | M[0].first | |
71 | </p> | |
72 | </th> | |
73 | <th> | |
74 | <p> | |
75 | M[0].second | |
76 | </p> | |
77 | </th> | |
78 | </tr></thead> | |
79 | <tbody> | |
80 | <tr> | |
81 | <td> | |
82 | <p> | |
83 | No match | |
84 | </p> | |
85 | </td> | |
86 | <td> | |
87 | <p> | |
88 | False | |
89 | </p> | |
90 | </td> | |
91 | <td> | |
92 | <p> | |
93 | Undefined | |
94 | </p> | |
95 | </td> | |
96 | <td> | |
97 | <p> | |
98 | Undefined | |
99 | </p> | |
100 | </td> | |
101 | <td> | |
102 | <p> | |
103 | Undefined | |
104 | </p> | |
105 | </td> | |
106 | </tr> | |
107 | <tr> | |
108 | <td> | |
109 | <p> | |
110 | Partial match | |
111 | </p> | |
112 | </td> | |
113 | <td> | |
114 | <p> | |
115 | True | |
116 | </p> | |
117 | </td> | |
118 | <td> | |
119 | <p> | |
120 | False | |
121 | </p> | |
122 | </td> | |
123 | <td> | |
124 | <p> | |
125 | Start of partial match. | |
126 | </p> | |
127 | </td> | |
128 | <td> | |
129 | <p> | |
130 | End of partial match (end of text). | |
131 | </p> | |
132 | </td> | |
133 | </tr> | |
134 | <tr> | |
135 | <td> | |
136 | <p> | |
137 | Full match | |
138 | </p> | |
139 | </td> | |
140 | <td> | |
141 | <p> | |
142 | True | |
143 | </p> | |
144 | </td> | |
145 | <td> | |
146 | <p> | |
147 | True | |
148 | </p> | |
149 | </td> | |
150 | <td> | |
151 | <p> | |
152 | Start of full match. | |
153 | </p> | |
154 | </td> | |
155 | <td> | |
156 | <p> | |
157 | End of full match. | |
158 | </p> | |
159 | </td> | |
160 | </tr> | |
161 | </tbody> | |
162 | </table></div> | |
163 | <p> | |
164 | Be aware that using partial matches can sometimes result in somewhat imperfect | |
165 | behavior: | |
166 | </p> | |
167 | <div class="itemizedlist"><ul class="itemizedlist" style="list-style-type: disc; "> | |
168 | <li class="listitem"> | |
169 | There are some expressions, such as ".*abc" that will always | |
170 | produce a partial match. This problem can be reduced by careful construction | |
171 | of the regular expressions used, or by setting flags like match_not_dot_newline | |
172 | so that expressions like .* can't match past line boundaries. | |
173 | </li> | |
174 | <li class="listitem"> | |
175 | Boost.Regex currently prefers leftmost matches to full matches, so for | |
176 | example matching "abc|b" against "ab" produces a partial | |
177 | match against the "ab" rather than a full match against "b". | |
178 | It's more efficient to work this way, but may not be the behavior you want | |
179 | in all situations. | |
180 | </li> | |
181 | <li class="listitem"> | |
182 | There are situations where full matches are found even though partial matches | |
183 | are also possible: for example if the partial string terminates with "abc" | |
184 | and the regular expression is "\w+", then a full match is found | |
185 | even though there may be more alphabetical characters to come. This particular | |
186 | case can be detected by checking if the match found terminates at the end | |
187 | of current input string. However, there are situations where that is not | |
188 | possible: for example an expression such as "abc.*123" may always | |
189 | have longer matches available since it could conceivably match the entire | |
190 | input string (no matter how long it may be). | |
191 | </li> | |
192 | </ul></div> | |
193 | <p> | |
194 | The following example tests to see whether the text could be a valid credit | |
195 | card number, as the user presses a key, the character entered would be added | |
196 | to the string being built up, and passed to <code class="computeroutput"><span class="identifier">is_possible_card_number</span></code>. | |
197 | If this returns true then the text could be a valid card number, so the user | |
198 | interface's OK button would be enabled. If it returns false, then this is not | |
199 | yet a valid card number, but could be with more input, so the user interface | |
200 | would disable the OK button. Finally, if the procedure throws an exception | |
201 | the input could never become a valid number, and the inputted character must | |
202 | be discarded, and a suitable error indication displayed to the user. | |
203 | </p> | |
204 | <pre class="programlisting"><span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">string</span><span class="special">></span> | |
205 | <span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">iostream</span><span class="special">></span> | |
206 | <span class="preprocessor">#include</span> <span class="special"><</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">></span> | |
207 | ||
208 | <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> | |
209 | ||
210 | <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">&</span> <span class="identifier">input</span><span class="special">)</span> | |
211 | <span class="special">{</span> | |
212 | <span class="comment">//</span> | |
213 | <span class="comment">// return false for partial match, true for full match, or throw for</span> | |
214 | <span class="comment">// impossible match based on what we have so far...</span> | |
215 | <span class="identifier">boost</span><span class="special">::</span><span class="identifier">match_results</span><span class="special"><</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">></span> <span class="identifier">what</span><span class="special">;</span> | |
216 | <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> | |
217 | <span class="special">{</span> | |
218 | <span class="comment">// the input so far could not possibly be valid so reject it:</span> | |
219 | <span class="keyword">throw</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">runtime_error</span><span class="special">(</span> | |
220 | <span class="string">"Invalid data entered - this could not possibly be a valid card number"</span><span class="special">);</span> | |
221 | <span class="special">}</span> | |
222 | <span class="comment">// OK so far so good, but have we finished?</span> | |
223 | <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> | |
224 | <span class="special">{</span> | |
225 | <span class="comment">// excellent, we have a result:</span> | |
226 | <span class="keyword">return</span> <span class="keyword">true</span><span class="special">;</span> | |
227 | <span class="special">}</span> | |
228 | <span class="comment">// what we have so far is only a partial match...</span> | |
229 | <span class="keyword">return</span> <span class="keyword">false</span><span class="special">;</span> | |
230 | <span class="special">}</span> | |
231 | </pre> | |
232 | <p> | |
233 | In the following example, text input is taken from a stream containing an unknown | |
234 | amount of text; this example simply counts the number of html tags encountered | |
235 | in the stream. The text is loaded into a buffer and searched a part at a time, | |
236 | if a partial match was encountered, then the partial match gets searched a | |
237 | second time as the start of the next batch of text: | |
238 | </p> | |
239 | <pre class="programlisting"><span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">iostream</span><span class="special">></span> | |
240 | <span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">fstream</span><span class="special">></span> | |
241 | <span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">sstream</span><span class="special">></span> | |
242 | <span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">string</span><span class="special">></span> | |
243 | <span class="preprocessor">#include</span> <span class="special"><</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">></span> | |
244 | ||
245 | <span class="comment">// match some kind of html tag:</span> | |
246 | <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">"<[^>]*>"</span><span class="special">);</span> | |
247 | <span class="comment">// count how many:</span> | |
248 | <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> | |
249 | ||
250 | <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">&</span> <span class="identifier">is</span><span class="special">)</span> | |
251 | <span class="special">{</span> | |
252 | <span class="comment">// buffer we'll be searching in:</span> | |
253 | <span class="keyword">char</span> <span class="identifier">buf</span><span class="special">[</span><span class="number">4096</span><span class="special">];</span> | |
254 | <span class="comment">// saved position of end of partial match:</span> | |
255 | <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> | |
256 | <span class="comment">// flag to indicate whether there is more input to come:</span> | |
257 | <span class="keyword">bool</span> <span class="identifier">have_more</span> <span class="special">=</span> <span class="keyword">true</span><span class="special">;</span> | |
258 | ||
259 | <span class="keyword">while</span><span class="special">(</span><span class="identifier">have_more</span><span class="special">)</span> | |
260 | <span class="special">{</span> | |
261 | <span class="comment">// how much do we copy forward from last try:</span> | |
262 | <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> | |
263 | <span class="comment">// and how much is left to fill:</span> | |
264 | <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> | |
265 | <span class="comment">// copy forward whatever we have left:</span> | |
266 | <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> | |
267 | <span class="comment">// fill the rest from the stream:</span> | |
268 | <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> | |
269 | <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> | |
270 | <span class="comment">// check to see if we've run out of text:</span> | |
271 | <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> | |
272 | <span class="comment">// reset next_pos:</span> | |
273 | <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> | |
274 | <span class="comment">// and then iterate:</span> | |
275 | <span class="identifier">boost</span><span class="special">::</span><span class="identifier">cregex_iterator</span> <span class="identifier">a</span><span class="special">(</span> | |
276 | <span class="identifier">buf</span><span class="special">,</span> | |
277 | <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> | |
278 | <span class="identifier">e</span><span class="special">,</span> | |
279 | <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> | |
280 | <span class="identifier">boost</span><span class="special">::</span><span class="identifier">cregex_iterator</span> <span class="identifier">b</span><span class="special">;</span> | |
281 | ||
282 | <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> | |
283 | <span class="special">{</span> | |
284 | <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> | |
285 | <span class="special">{</span> | |
286 | <span class="comment">// Partial match, save position and break:</span> | |
287 | <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> | |
288 | <span class="keyword">break</span><span class="special">;</span> | |
289 | <span class="special">}</span> | |
290 | <span class="keyword">else</span> | |
291 | <span class="special">{</span> | |
292 | <span class="comment">// full match:</span> | |
293 | <span class="special">++</span><span class="identifier">tags</span><span class="special">;</span> | |
294 | <span class="special">}</span> | |
295 | ||
296 | <span class="comment">// move to next match:</span> | |
297 | <span class="special">++</span><span class="identifier">a</span><span class="special">;</span> | |
298 | <span class="special">}</span> | |
299 | <span class="special">}</span> | |
300 | <span class="special">}</span> | |
301 | </pre> | |
302 | </div> | |
303 | <table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr> | |
304 | <td align="left"></td> | |
305 | <td align="right"><div class="copyright-footer">Copyright © 1998-2013 John Maddock<p> | |
306 | Distributed under the Boost Software License, Version 1.0. (See accompanying | |
307 | 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>) | |
308 | </p> | |
309 | </div></td> | |
310 | </tr></table> | |
311 | <hr> | |
312 | <div class="spirit-nav"> | |
313 | <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> | |
314 | </div> | |
315 | </body> | |
316 | </html> |