| <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"> |
| <html xmlns="http://www.w3.org/1999/xhtml"> |
| <head> |
| <meta http-equiv="Content-Type" content="text/xhtml;charset=UTF-8"/> |
| <meta http-equiv="X-UA-Compatible" content="IE=9"/> |
| <title>Boost.Locale: wboundary.cpp</title> |
| |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| <link href="navtree.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="resize.js"></script> |
| <script type="text/javascript" src="navtree.js"></script> |
| <script type="text/javascript"> |
| $(document).ready(initResizable); |
| </script> |
| |
| |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div! --> |
| |
| |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr style="height: 56px;"> |
| |
| <td id="projectlogo"><img alt="Logo" src="boost-small.png"/></td> |
| |
| |
| <td style="padding-left: 0.5em;"> |
| <div id="projectname">Boost.Locale |
| |
| </div> |
| |
| </td> |
| |
| |
| |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| |
| <!-- Generated by Doxygen 1.7.6.1 --> |
| <div id="navrow1" class="tabs"> |
| <ul class="tablist"> |
| <li><a href="index.html"><span>Main Page</span></a></li> |
| <li><a href="modules.html"><span>Modules</span></a></li> |
| <li><a href="namespaces.html"><span>Namespaces</span></a></li> |
| <li><a href="annotated.html"><span>Classes</span></a></li> |
| <li><a href="files.html"><span>Files</span></a></li> |
| <li><a href="examples.html"><span>Examples</span></a></li> |
| </ul> |
| </div> |
| </div> |
| <div id="side-nav" class="ui-resizable side-nav-resizable"> |
| <div id="nav-tree"> |
| <div id="nav-tree-contents"> |
| </div> |
| </div> |
| <div id="splitbar" style="-moz-user-select:none;" |
| class="ui-resizable-handle"> |
| </div> |
| </div> |
| <script type="text/javascript"> |
| initNavTree('wboundary_8cpp-example.html',''); |
| </script> |
| <div id="doc-content"> |
| <div class="header"> |
| <div class="headertitle"> |
| <div class="title">wboundary.cpp</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| <p>Example of using segment_index over wide strings</p> |
| <div class="fragment"><pre class="fragment"><span class="comment">//</span> |
| <span class="comment">// Copyright (c) 2009-2011 Artyom Beilis (Tonkikh)</span> |
| <span class="comment">//</span> |
| <span class="comment">// Distributed under the Boost Software License, Version 1.0. (See</span> |
| <span class="comment">// accompanying file LICENSE_1_0.txt or copy at</span> |
| <span class="comment">// http://www.boost.org/LICENSE_1_0.txt)</span> |
| <span class="comment">//</span> |
| |
| <span class="comment">//</span> |
| <span class="comment">// ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !</span> |
| <span class="comment">//</span> |
| <span class="comment">// BIG FAT WARNING FOR Microsoft Visual Studio Users</span> |
| <span class="comment">//</span> |
| <span class="comment">// YOU NEED TO CONVERT THIS SOURCE FILE ENCODING TO UTF-8 WITH BOM ENCODING.</span> |
| <span class="comment">//</span> |
| <span class="comment">// Unfortunately MSVC understands that the source code is encoded as</span> |
| <span class="comment">// UTF-8 only if you add useless BOM in the beginning.</span> |
| <span class="comment">//</span> |
| <span class="comment">// So, before you compile "wide" examples with MSVC, please convert them to text</span> |
| <span class="comment">// files with BOM. There are two very simple ways to do it:</span> |
| <span class="comment">//</span> |
| <span class="comment">// 1. Open file with Notepad and save it from there. It would convert </span> |
| <span class="comment">// it to file with BOM.</span> |
| <span class="comment">// 2. In Visual Studio go File->Advances Save Options... and select</span> |
| <span class="comment">// Unicode (UTF-8 with signature) Codepage 65001</span> |
| <span class="comment">//</span> |
| <span class="comment">// Note: once converted to UTF-8 with BOM, this source code would not</span> |
| <span class="comment">// compile with other compilers, because no-one uses BOM with UTF-8 today</span> |
| <span class="comment">// because it is absolutely meaningless in context of UTF-8.</span> |
| <span class="comment">//</span> |
| <span class="comment">// ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !</span> |
| <span class="comment">//</span> |
| <span class="preprocessor">#include <boost/locale.hpp></span> |
| <span class="preprocessor">#include <iostream></span> |
| <span class="preprocessor">#include <cassert></span> |
| <span class="preprocessor">#include <ctime></span> |
| |
| <span class="keywordtype">int</span> main() |
| { |
| <span class="keyword">using namespace </span>boost::locale; |
| <span class="keyword">using namespace </span>std; |
| |
| <span class="comment">// Create system default locale</span> |
| <a name="_a0"></a><a class="code" href="classboost_1_1locale_1_1generator.html" title="the major class used for locale generation">generator</a> gen; |
| locale loc=gen(<span class="stringliteral">""</span>); |
| locale::global(loc); |
| wcout.imbue(loc); |
| |
| <span class="comment">// This is needed to prevent C library to</span> |
| <span class="comment">// convert strings to narrow </span> |
| <span class="comment">// instead of C++ on some platforms</span> |
| std::ios_base::sync_with_stdio(<span class="keyword">false</span>); |
| |
| |
| wstring text=L<span class="stringliteral">"Hello World! あにま! Linux2.6 and Windows7 is word and number. שָלוֹם עוֹלָם!"</span>; |
| |
| wcout<<text<<endl; |
| |
| <a name="_a1"></a><a class="code" href="classboost_1_1locale_1_1boundary_1_1segment__index.html" title="This class holds an index of segments in the text range and allows to iterate over them...">boundary::wssegment_index</a> index(<a name="a2"></a><a class="code" href="group__boundary.html#gga15de9963ce9bb6037c8525901dfbf641a99aad8b8a5e25baa9f695abe5e574bb6" title="Analyse the text for word boundaries.">boundary::word</a>,text.begin(),text.end()); |
| <a class="code" href="group__boundary.html#gaf7a775e77dbbca3495e11d646df96fd2">boundary::wssegment_index::iterator</a> p,e; |
| |
| <span class="keywordflow">for</span>(p=index.begin(),e=index.end();p!=e;++p) { |
| wcout<<L<span class="stringliteral">"Part ["</span><<*p<<L<span class="stringliteral">"] has "</span>; |
| <span class="keywordflow">if</span>(p->rule() & <a name="a3"></a><a class="code" href="group__boundary.html#gaac78a3a6b9e671e253a2591cb56a479b" title="Word that appear to be a number.">boundary::word_number</a>) |
| wcout<<L<span class="stringliteral">"number(s) "</span>; |
| <span class="keywordflow">if</span>(p->rule() & <a name="a4"></a><a class="code" href="group__boundary.html#ga8b7e6ce2fcb185845fa85a1a4c42b3c4" title="Word that contains letters, excluding kana and ideographic characters.">boundary::word_letter</a>) |
| wcout<<L<span class="stringliteral">"letter(s) "</span>; |
| <span class="keywordflow">if</span>(p->rule() & <a name="a5"></a><a class="code" href="group__boundary.html#ga52d8c63e1f3f8c898c645352206a78ef" title="Word that contains kana characters.">boundary::word_kana</a>) |
| wcout<<L<span class="stringliteral">"kana character(s) "</span>; |
| <span class="keywordflow">if</span>(p->rule() & <a name="a6"></a><a class="code" href="group__boundary.html#ga705ab96f9e62810c8ed977c90d404ef8" title="Word that contains ideographic characters.">boundary::word_ideo</a>) |
| wcout<<L<span class="stringliteral">"ideographic character(s) "</span>; |
| <span class="keywordflow">if</span>(p->rule() & <a name="a7"></a><a class="code" href="group__boundary.html#ga90cf4f01b95658f659685377226677e7" title="Not a word, like white space or punctuation mark.">boundary::word_none</a>) |
| wcout<<L<span class="stringliteral">"no word characters"</span>; |
| wcout<<endl; |
| } |
| |
| index.<a name="a8"></a><a class="code" href="group__boundary.html#gafa2a756b10d3522743204b45b794bb3e">map</a>(<a name="a9"></a><a class="code" href="group__boundary.html#gga15de9963ce9bb6037c8525901dfbf641ae80c964112541d88af9b875dafb6605d" title="Analyse the text for character boundaries.">boundary::character</a>,text.begin(),text.end()); |
| |
| <span class="keywordflow">for</span>(p=index.begin(),e=index.end();p!=e;++p) { |
| wcout<<L<span class="stringliteral">"|"</span> <<*p ; |
| } |
| wcout<<L<span class="stringliteral">"|\n\n"</span>; |
| |
| index.map(<a name="a10"></a><a class="code" href="group__boundary.html#gga15de9963ce9bb6037c8525901dfbf641a72895419fdd7219b3695cf0abd602ea4" title="Analyse the text for positions suitable for line breaks.">boundary::line</a>,text.begin(),text.end()); |
| |
| <span class="keywordflow">for</span>(p=index.begin(),e=index.end();p!=e;++p) { |
| wcout<<L<span class="stringliteral">"|"</span> <<*p ; |
| } |
| wcout<<L<span class="stringliteral">"|\n\n"</span>; |
| |
| index.map(<a name="a11"></a><a class="code" href="group__boundary.html#gga15de9963ce9bb6037c8525901dfbf641a88aa1509eace7589f5df87d4694871e9" title="Analyse the text for Find sentence boundaries.">boundary::sentence</a>,text.begin(),text.end()); |
| |
| <span class="keywordflow">for</span>(p=index.begin(),e=index.end();p!=e;++p) { |
| wcout<<L<span class="stringliteral">"|"</span> <<*p ; |
| } |
| wcout<<<span class="stringliteral">"|\n\n"</span>; |
| |
| } |
| |
| |
| <span class="comment">// vim: tabstop=4 expandtab shiftwidth=4 softtabstop=4</span> |
| |
| <span class="comment">// boostinspect:noascii</span> |
| |
| </pre></div> </div><!-- contents --> |
| </div><!-- contents --> |
| </div> |
| <div id="nav-path" class="navpath"> |
| <ul> |
| |
| <li class="footer"> |
| © Copyright 2009-2012 Artyom Beilis, Distributed under the <a href="http://www.boost.org/LICENSE_1_0.txt">Boost Software License</a>, Version 1.0. |
| </li> |
| </ul> |
| </div> |
| |
| |
| </body> |
| </html> |
