unicode-data-wordbreak.js.html revision 7d9dd27c758ee750e3ea3b2cf2932691378d5cdd
<head>
</head>
<body id="yahoo-com">
<div id="doc3" class="yui-t2">
<div id="hd">
<h3>unicode <span class="subtitle">3.3.0</span></h3>
> unicode-data-wordbreak.js (source view)
<form onsubmit="return false">
<div id="propertysearch">
Search: <input autocomplete="off" id="searchinput" />
<div id="searchresults">
</div>
</div>
</form>
</div>
<div id="bd">
<div id="yui-main">
<div class="yui-b">
<form action="#" name="yui-classopts-form" method="get" id="yui-classopts-form">
<fieldset>
<legend>Filters</legend>
<span class="classopts"><input type="checkbox" name="show_private" id="show_private" /> <label for="show_private">Show Private</label></span>
<span class="classopts"><input type="checkbox" name="show_protected" id="show_protected" /> <label for="show_protected">Show Protected</label></span>
<span class="classopts"><input type="checkbox" name="show_deprecated" id="show_deprecated" /> <label for="show_deprecated">Show Deprecated</label></span>
</fieldset>
</form>
<div id="srcout">
<style>
#doc3 .classopts { display:none; }
</style>
<div class="highlight"><pre><span class="cm">/**</span>
<span class="cm"> * <p></span>
<span class="cm"> * Unicode data used by the word breaking algorithm.</span>
<span class="cm"> * </p></span>
<span class="cm"> *</span>
<span class="cm"> * <p></span>
<span class="cm"> * Whenever possible, word breaking should be done on the server, where it's</span>
<span class="cm"> * possible to use tools that are both more complete and more performant. It</span>
<span class="cm"> * should only be done on the client as an absolute last resort.</span>
<span class="cm"> * </p></span>
<span class="cm"> *</span>
<span class="cm"> * @module unicode</span>
<span class="cm"> * @submodule unicode-data-wordbreak</span>
<span class="cm"> * @static</span>
<span class="cm"> */</span>
<span class="nx">Y</span><span class="p">.</span><span class="nx">namespace</span><span class="p">(</span><span class="s1">'Unicode.Data'</span><span class="p">).</span><span class="nx">WordBreak</span> <span class="o">=</span> <span class="p">{</span>
<span class="c1">// The UnicodeSet utility is helpful for enumerating the specific code</span>
<span class="c1">// points covered by each of these regular expressions:</span>
<span class="c1">//</span>
<span class="c1">// The code sets from which these regexes were derived can be generated</span>
<span class="c1">// by the UnicodeSet utility using the links here:</span>
<span class="nx">aletter</span> <span class="o">:</span> <span class="s1">'[A-Za-zÀ-ÖØ-öø-ƿǀ-ʯʰ-ˁˆ-ˑˠ-ˤˬˮҊ-ԣᴀ-ᶿḀ-ἕⅠ-ↈⱠ-Ɐⱱ-ⱽ]'</span><span class="p">,</span>
<span class="nx">midnumlet</span> <span class="o">:</span> <span class="s2">"['\\.‘’․﹒'.]"</span><span class="p">,</span>
<span class="nx">midletter</span> <span class="o">:</span> <span class="s1">'[:··״‧︓﹕:]'</span><span class="p">,</span>
<span class="nx">midnum</span> <span class="o">:</span> <span class="s1">'[,;;։،؍٬߸⁄︐︔﹐﹔,;]'</span><span class="p">,</span>
<span class="nx">numeric</span> <span class="o">:</span> <span class="s1">'[0-9٠-٩٫۰-۹߀-߉०-९০-৯੦-੯૦-૯୦-୯௦-௯౦-౯೦-೯൦-൯๐-๙໐-໙༠-༩၀-၉႐-႙០-៩᠐-᠙᥆-᥏᧐-᧙᪀-᪉᪐-᪙᭐-᭙᮰-᮹᱀-᱉᱐-᱙꘠-꘩꣐-꣙꤀-꤉꧐-꧙꩐-꩙꯰-꯹]'</span><span class="p">,</span>
<span class="nx">cr</span> <span class="o">:</span> <span class="s1">'\\r'</span><span class="p">,</span>
<span class="nx">lf</span> <span class="o">:</span> <span class="s1">'\\n'</span><span class="p">,</span>
<span class="nx">newline</span> <span class="o">:</span> <span class="s1">'[\u000B\u000C\u0085\u2028\u2029]'</span><span class="p">,</span>
<span class="nx">extend</span> <span class="o">:</span> <span class="s1">'[\u0300-\u036F\u0483-\u0489\u0591-\u05BD\u05BF\u05C1\u05C2\u05C4\u05C5\u05C7\u0610-\u061A\u064B-\u065F\u0670\u06D6-\u06DC\u06DF-\u06E4\u06E7\u06E8\u06EA-\u06ED\u0711\u0730-\u074A\u07A6-\u07B0\u07EB-\u07F3\u0816-\u0819\u081B-\u0823\u0825-\u0827\u0829-\u082D\u0859-\u085B\u0900-\u0903\u093A-\u093C\u093E-\u094F\u0951-\u0957\u0962\u0963\u0981-\u0983\u09BC\u09BE-\u09C4\u09C7\u09C8\u09CB-\u09CD\u09D7\u09E2\u09E3\u0A01-\u0A03\u0A3C\u0A3E-\u0A42\u0A47\u0A48\u0A4B-\u0A4D\u0A51\u0A70\u0A71\u0A75\u0A81-\u0A83\u0ABC\u0ABE-\u0AC5\u0AC7-\u0AC9\u0ACB-\u0ACD\u0AE2\u0AE3\u0B01-\u0B03\u0B3C\u0B3E-\u0B44\u0B47\u0B48\u0B4B-\u0B4D\u0B56\u0B57\u0B62\u0B63\u0B82\u0BBE-\u0BC2\u0BC6-\u0BC8\u0BCA-\u0BCD\u0BD7\u0C01-\u0C03\u0C3E-\u0C44\u0C46-\u0C48\u0C4A-\u0C4D\u0C55\u0C56\u0C62\u0C63\u0C82\u0C83\u0CBC\u0CBE-\u0CC4\u0CC6-\u0CC8\u0CCA-\u0CCD\u0CD5\u0CD6\u0CE2\u0CE3\u0D02\u0D03\u0D3E-\u0D44\u0D46-\u0D48\u0D4A-\u0D4D\u0D57\u0D62\u0D63\u0D82\u0D83\u0DCA\u0DCF-\u0DD4\u0DD6\u0DD8-\u0DDF\u0DF2\u0DF3\u0E31\u0E34-\u0E3A\u0E47-\u0E4E\u0EB1\u0EB4-\u0EB9\u0EBB\u0EBC\u0EC8-\u0ECD\u0F18\u0F19\u0F35\u0F37\u0F39\u0F3E\u0F3F\u0F71-\u0F84\u0F86\u0F87\u0F8D-\u0F97\u0F99-\u0FBC\u0FC6\u102B-\u103E\u1056-\u1059\u105E-\u1060\u1062-\u1064\u1067-\u106D\u1071-\u1074\u1082-\u108D\u108F\u109A-\u109D\u135D-\u135F\u1712-\u1714\u1732-\u1734\u1752\u1753\u1772\u1773\u17B6-\u17D3\u17DD\u180B-\u180D\u18A9\u1920-\u192B\u1930-\u193B\u19B0-\u19C0\u19C8\u19C9\u1A17-\u1A1B\u1A55-\u1A5E\u1A60-\u1A7C\u1A7F\u1B00-\u1B04\u1B34-\u1B44\u1B6B-\u1B73\u1B80-\u1B82\u1BA1-\u1BAA\u1BE6-\u1BF3\u1C24-\u1C37\u1CD0-\u1CD2\u1CD4-\u1CE8\u1CED\u1CF2\u1DC0-\u1DE6\u1DFC-\u1DFF\u200C\u200D\u20D0-\u20F0\u2CEF-\u2CF1\u2D7F\u2DE0-\u2DFF\u302A-\u302F\u3099\u309A\uA66F-\uA672\uA67C\uA67D\uA6F0\uA6F1\uA802\uA806\uA80B\uA823-\uA827\uA880\uA881\uA8B4-\uA8C4\uA8E0-\uA8F1\uA926-\uA92D\uA947-\uA953\uA980-\uA983\uA9B3-\uA9C0\uAA29-\uAA36\uAA43\uAA4C\uAA4D\uAA7B\uAAB0\uAAB2-\uAAB4\uAAB7\uAAB8\uAABE\uAABF\uAAC1\uABE3-\uABEA\uABEC\uABED\uFB1E\uFE00-\uFE0F\uFE20-\uFE26\uFF9E\uFF9F]'</span><span class="p">,</span>
<span class="nx">format</span> <span class="o">:</span> <span class="s1">'[\u00AD\u0600-\u0603\u06DD\u070F\u17B4\u17B5\u200E\u200F\u202A-\u202E\u2060-\u2064\u206A-\u206F\uFEFF\uFFF9-\uFFFB]'</span><span class="p">,</span>
<span class="nx">katakana</span> <span class="o">:</span> <span class="s1">'[\u3031-\u3035\u309B\u309C\u30A0-\u30FA\u30FC-\u30FF\u31F0-\u31FF\u32D0-\u32FE\u3300-\u3357\uFF66-\uFF9D]'</span><span class="p">,</span>
<span class="nx">extendnumlet</span><span class="o">:</span> <span class="s1">'[_\u203F\u2040\u2054\uFE33\uFE34\uFE4D-\uFE4F\uFF3F]'</span><span class="p">,</span>
<span class="nx">punctuation</span> <span class="o">:</span> <span class="s1">'[!-#%-*,-/\\:;?@\\[-\\]_\\{\\}¡«·»¿;·՚-՟։\u058A\u05BE\u05C0\u05C3\u05C6\u05F3\u05F4\u0609\u060A\u060C\u060D\u061B\u061E\u061F\u066A-\u066D\u06D4\u0700-\u070D\u07F7-\u07F9\u0830-\u083E\u085E\u0964\u0965\u0970\u0DF4\u0E4F\u0E5A\u0E5B\u0F04-\u0F12\u0F3A-\u0F3D\u0F85\u0FD0-\u0FD4\u0FD9\u0FDA\u104A-\u104F\u10FB\u1361-\u1368\u1400\u166D\u166E\u169B\u169C\u16EB-\u16ED\u1735\u1736\u17D4-\u17D6\u17D8-\u17DA\u1800-\u180A\u1944\u1945\u1A1E\u1A1F\u1AA0-\u1AA6\u1AA8-\u1AAD\u1B5A-\u1B60\u1BFC-\u1BFF\u1C3B-\u1C3F\u1C7E\u1C7F\u1CD3\u2010-\u2027\u2030-\u2043\u2045-\u2051\u2053-\u205E\u207D\u207E\u208D\u208E\u2329\u232A\u2768-\u2775\u27C5\u27C6\u27E6-\u27EF\u2983-\u2998\u29D8-\u29DB\u29FC\u29FD\u2CF9-\u2CFC\u2CFE\u2CFF\u2D70\u2E00-\u2E2E\u2E30\u2E31\u3001-\u3003\u3008-\u3011\u3014-\u301F\u3030\u303D\u30A0\u30FB\uA4FE\uA4FF\uA60D-\uA60F\uA673\uA67E\uA6F2-\uA6F7\uA874-\uA877\uA8CE\uA8CF\uA8F8-\uA8FA\uA92E\uA92F\uA95F\uA9C1-\uA9CD\uA9DE\uA9DF\uAA5C-\uAA5F\uAADE\uAADF\uABEB\uFD3E\uFD3F\uFE10-\uFE19\uFE30-\uFE52\uFE54-\uFE61\uFE63\uFE68\uFE6A\uFE6B\uFF01-\uFF03\uFF05-\uFF0A\uFF0C-\uFF0F\uFF1A\uFF1B\uFF1F\uFF20\uFF3B-\uFF3D\uFF3F\uFF5B\uFF5D\uFF5F-\uFF65]'</span>
<span class="p">};</span>
</pre></div>
</div>
</div>
</div>
<div class="yui-b">
<div class="nav">
<div id="moduleList" class="module">
<h4>Modules</h4>
<ul class="content">
<li class=""><a href="module_classnamemanager.html" title="classnamemanager">classnamemanager</a></li>
<li class=""><a href="module_event-valuechange.html" title="event-valuechange">event-valuechange</a></li>
<li class=""><a href="module_history-deprecated.html" title="history-deprecated">history-deprecated</a></li>
<li class=""><a href="module_node-focusmanager.html" title="node-focusmanager">node-focusmanager</a></li>
<li class=""><a href="module_scrollview-paginator.html" title="scrollview-paginator">scrollview-paginator</a></li>
<li class=""><a href="module_scrollview-scrollbars.html" title="scrollview-scrollbars">scrollview-scrollbars</a></li>
<li class=""><a href="module_widget-position-align.html" title="widget-position-align">widget-position-align</a></li>
<li class=""><a href="module_widget-position-constrain.html" title="widget-position-constrain">widget-position-constrain</a></li>
</ul>
</div>
<div id="classList" class="module">
<h4>Classes</h4>
<ul class="content">
<li class=""><a href="Unicode.AccentFold.html" title="Unicode.AccentFold">Unicode.AccentFold</a></li>
<li class=""><a href="Unicode.Data.AccentFold.html" title="Unicode.Data.AccentFold">Unicode.Data.AccentFold</a></li>
<li class=""><a href="Unicode.Data.WordBreak.html" title="Unicode.Data.WordBreak">Unicode.Data.WordBreak</a></li>
</ul>
</div>
<div id="fileList" class="module">
<h4>Files</h4>
<ul class="content">
<li class=""><a href="unicode-accentfold.js.html" title="unicode-accentfold.js">unicode-accentfold.js</a></li>
<li class=""><a href="unicode-data-accentfold.js.html" title="unicode-data-accentfold.js">unicode-data-accentfold.js</a></li>
<li class="selected"><a href="unicode-data-wordbreak.js.html" title="unicode-data-wordbreak.js">unicode-data-wordbreak.js</a></li>
<li class=""><a href="unicode-wordbreak.js.html" title="unicode-wordbreak.js">unicode-wordbreak.js</a></li>
</ul>
</div>
</div>
</div>
</div>
<div id="ft">
<hr />
Copyright © 2010 Yahoo! Inc. All rights reserved.
</div>
</div>
<script type="text/javascript">
var ALL_YUI_PROPS = [{"access": "", "host": "Unicode.AccentFold", "name": "canFold", "url": "Unicode.AccentFold.html#method_canFold", "type": "method"}, {"access": "protected", "host": "Unicode.WordBreak", "name": "_classify", "url": "Unicode.WordBreak.html#method__classify", "type": "method"}, {"access": "", "host": "Unicode.AccentFold", "name": "compare", "url": "Unicode.AccentFold.html#method_compare", "type": "method"}, {"access": "", "host": "Unicode.AccentFold", "name": "filter", "url": "Unicode.AccentFold.html#method_filter", "type": "method"}, {"access": "", "host": "Unicode.AccentFold", "name": "fold", "url": "Unicode.AccentFold.html#method_fold", "type": "method"}, {"access": "", "host": "Unicode.WordBreak", "name": "getUniqueWords", "url": "Unicode.WordBreak.html#method_getUniqueWords", "type": "method"}, {"access": "", "host": "Unicode.WordBreak", "name": "getWords", "url": "Unicode.WordBreak.html#method_getWords", "type": "method"}, {"access": "protected", "host": "Unicode.WordBreak", "name": "_isWordBoundary", "url": "Unicode.WordBreak.html#method__isWordBoundary", "type": "method"}, {"access": "", "host": "Unicode.WordBreak", "name": "isWordBoundary", "url": "Unicode.WordBreak.html#method_isWordBoundary", "type": "method"}];
</script>
</body>
</html>