| <!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"/> |
| <meta name="generator" content="Doxygen 1.8.3"/> |
| <title>Lucene.Net: Lucene.Net.Analysis.WordlistLoader Class Reference</title> |
| <link href="tabs.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="jquery.js"></script> |
| <script type="text/javascript" src="dynsections.js"></script> |
| <link href="search/search.css" rel="stylesheet" type="text/css"/> |
| <script type="text/javascript" src="search/search.js"></script> |
| <script type="text/javascript"> |
| $(document).ready(function() { searchBox.OnSelectItem(0); }); |
| </script> |
| <link href="doxygen.css" rel="stylesheet" type="text/css" /> |
| </head> |
| <body> |
| <div id="top"><!-- do not remove this div, it is closed by doxygen! --> |
| <div id="titlearea"> |
| <table cellspacing="0" cellpadding="0"> |
| <tbody> |
| <tr style="height: 56px;"> |
| <td id="projectlogo"><img alt="Logo" src="lucene-net-icon-128x128.png"/></td> |
| <td style="padding-left: 0.5em;"> |
| <div id="projectname">Lucene.Net |
|  <span id="projectnumber">3.0.3</span> |
| </div> |
| <div id="projectbrief">Lucene.Net is a .NET port of the Java Lucene Indexing Library</div> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| </div> |
| <!-- end header part --> |
| <!-- Generated by Doxygen 1.8.3 --> |
| <script type="text/javascript"> |
| var searchBox = new SearchBox("searchBox", "search",false,'Search'); |
| </script> |
| <div id="navrow1" class="tabs"> |
| <ul class="tablist"> |
| <li><a href="Index.html"><span>Main Page</span></a></li> |
| <li><a href="namespaces.html"><span>Packages</span></a></li> |
| <li class="current"><a href="annotated.html"><span>Classes</span></a></li> |
| <li><a href="files.html"><span>Files</span></a></li> |
| <li> |
| <div id="MSearchBox" class="MSearchBoxInactive"> |
| <span class="left"> |
| <img id="MSearchSelect" src="search/mag_sel.png" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| alt=""/> |
| <input type="text" id="MSearchField" value="Search" accesskey="S" |
| onfocus="searchBox.OnSearchFieldFocus(true)" |
| onblur="searchBox.OnSearchFieldFocus(false)" |
| onkeyup="searchBox.OnSearchFieldChange(event)"/> |
| </span><span class="right"> |
| <a id="MSearchClose" href="javascript:searchBox.CloseResultsWindow()"><img id="MSearchCloseImg" border="0" src="search/close.png" alt=""/></a> |
| </span> |
| </div> |
| </li> |
| </ul> |
| </div> |
| <div id="navrow2" class="tabs2"> |
| <ul class="tablist"> |
| <li><a href="annotated.html"><span>Class List</span></a></li> |
| <li><a href="classes.html"><span>Class Index</span></a></li> |
| <li><a href="hierarchy.html"><span>Class Hierarchy</span></a></li> |
| <li><a href="functions.html"><span>Class Members</span></a></li> |
| </ul> |
| </div> |
| <!-- window showing the filter options --> |
| <div id="MSearchSelectWindow" |
| onmouseover="return searchBox.OnSearchSelectShow()" |
| onmouseout="return searchBox.OnSearchSelectHide()" |
| onkeydown="return searchBox.OnSearchSelectKey(event)"> |
| <a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(0)"><span class="SelectionMark"> </span>All</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(1)"><span class="SelectionMark"> </span>Classes</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(2)"><span class="SelectionMark"> </span>Namespaces</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(3)"><span class="SelectionMark"> </span>Files</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(4)"><span class="SelectionMark"> </span>Functions</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(5)"><span class="SelectionMark"> </span>Variables</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(6)"><span class="SelectionMark"> </span>Typedefs</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(7)"><span class="SelectionMark"> </span>Enumerations</a><a class="SelectItem" href="javascript:void(0)" onclick="searchBox.OnSelectItem(8)"><span class="SelectionMark"> </span>Properties</a></div> |
| |
| <!-- iframe showing the search results (closed by default) --> |
| <div id="MSearchResultsWindow"> |
| <iframe src="javascript:void(0)" frameborder="0" |
| name="MSearchResults" id="MSearchResults"> |
| </iframe> |
| </div> |
| |
| <div id="nav-path" class="navpath"> |
| <ul> |
| <li class="navelem"><a class="el" href="namespace_lucene.html">Lucene</a></li><li class="navelem"><a class="el" href="namespace_lucene_1_1_net.html">Net</a></li><li class="navelem"><a class="el" href="namespace_lucene_1_1_net_1_1_analysis.html">Analysis</a></li><li class="navelem"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html">WordlistLoader</a></li> </ul> |
| </div> |
| </div><!-- top --> |
| <div class="header"> |
| <div class="summary"> |
| <a href="#pub-static-methods">Static Public Member Functions</a> | |
| <a href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader-members.html">List of all members</a> </div> |
| <div class="headertitle"> |
| <div class="title">Lucene.Net.Analysis.WordlistLoader Class Reference</div> </div> |
| </div><!--header--> |
| <div class="contents"> |
| |
| <p>Loader for text files that represent a list of stopwords. |
| <a href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#details">More...</a></p> |
| <table class="memberdecls"> |
| <tr class="heading"><td colspan="2"><h2 class="groupheader"><a name="pub-static-methods"></a> |
| Static Public Member Functions</h2></td></tr> |
| <tr class="memitem:a8c03d44044716caeb31ea634057f164f"><td class="memItemLeft" align="right" valign="top">static ISet< string > </td><td class="memItemRight" valign="bottom"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#a8c03d44044716caeb31ea634057f164f">GetWordSet</a> (System.IO.FileInfo wordfile)</td></tr> |
| <tr class="memdesc:a8c03d44044716caeb31ea634057f164f"><td class="mdescLeft"> </td><td class="mdescRight">Loads a text file and adds every line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the file should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). <a href="#a8c03d44044716caeb31ea634057f164f"></a><br/></td></tr> |
| <tr class="separator:a8c03d44044716caeb31ea634057f164f"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a9cb9e743592d83000add7e62caeb1675"><td class="memItemLeft" align="right" valign="top">static ISet< string > </td><td class="memItemRight" valign="bottom"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#a9cb9e743592d83000add7e62caeb1675">GetWordSet</a> (System.IO.FileInfo wordfile, System.String comment)</td></tr> |
| <tr class="memdesc:a9cb9e743592d83000add7e62caeb1675"><td class="mdescLeft"> </td><td class="mdescRight">Loads a text file and adds every non-comment line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the file should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). <a href="#a9cb9e743592d83000add7e62caeb1675"></a><br/></td></tr> |
| <tr class="separator:a9cb9e743592d83000add7e62caeb1675"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a379750a77b612c2b25532db7e781e4c8"><td class="memItemLeft" align="right" valign="top">static ISet< string > </td><td class="memItemRight" valign="bottom"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#a379750a77b612c2b25532db7e781e4c8">GetWordSet</a> (System.IO.TextReader reader)</td></tr> |
| <tr class="memdesc:a379750a77b612c2b25532db7e781e4c8"><td class="mdescLeft"> </td><td class="mdescRight">Reads lines from a Reader and adds every line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the Reader should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). <a href="#a379750a77b612c2b25532db7e781e4c8"></a><br/></td></tr> |
| <tr class="separator:a379750a77b612c2b25532db7e781e4c8"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a27658a0a61bd1059f0e5d69632168b9b"><td class="memItemLeft" align="right" valign="top">static ISet< string > </td><td class="memItemRight" valign="bottom"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#a27658a0a61bd1059f0e5d69632168b9b">GetWordSet</a> (System.IO.TextReader reader, System.String comment)</td></tr> |
| <tr class="memdesc:a27658a0a61bd1059f0e5d69632168b9b"><td class="mdescLeft"> </td><td class="mdescRight">Reads lines from a Reader and adds every non-comment line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the Reader should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). <a href="#a27658a0a61bd1059f0e5d69632168b9b"></a><br/></td></tr> |
| <tr class="separator:a27658a0a61bd1059f0e5d69632168b9b"><td class="memSeparator" colspan="2"> </td></tr> |
| <tr class="memitem:a554fc1a6206c235be69f5c9e4c358372"><td class="memItemLeft" align="right" valign="top">static Dictionary< string, string > </td><td class="memItemRight" valign="bottom"><a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_wordlist_loader.html#a554fc1a6206c235be69f5c9e4c358372">GetStemDict</a> (System.IO.FileInfo wordstemfile)</td></tr> |
| <tr class="memdesc:a554fc1a6206c235be69f5c9e4c358372"><td class="mdescLeft"> </td><td class="mdescRight">Reads a stem dictionary. Each line contains: <code>word<b></b>stem</code> (i.e. two tab seperated words) <a href="#a554fc1a6206c235be69f5c9e4c358372"></a><br/></td></tr> |
| <tr class="separator:a554fc1a6206c235be69f5c9e4c358372"><td class="memSeparator" colspan="2"> </td></tr> |
| </table> |
| <a name="details" id="details"></a><h2 class="groupheader">Detailed Description</h2> |
| <div class="textblock"><p>Loader for text files that represent a list of stopwords.</p> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00024">24</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| </div><h2 class="groupheader">Member Function Documentation</h2> |
| <a class="anchor" id="a554fc1a6206c235be69f5c9e4c358372"></a> |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static Dictionary<string, string> Lucene.Net.Analysis.WordlistLoader.GetStemDict </td> |
| <td>(</td> |
| <td class="paramtype">System.IO.FileInfo </td> |
| <td class="paramname"><em>wordstemfile</em></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Reads a stem dictionary. Each line contains: <code>word<b></b>stem</code> (i.e. two tab seperated words) </p> |
| <dl class="section return"><dt>Returns</dt><dd>stem dictionary that overrules the stemming algorithm </dd></dl> |
| <p><throws> IOException </throws> </p> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00117">117</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| |
| </div> |
| </div> |
| <a class="anchor" id="a8c03d44044716caeb31ea634057f164f"></a> |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static ISet<string> Lucene.Net.Analysis.WordlistLoader.GetWordSet </td> |
| <td>(</td> |
| <td class="paramtype">System.IO.FileInfo </td> |
| <td class="paramname"><em>wordfile</em></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Loads a text file and adds every line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the file should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). </p> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramname">wordfile</td><td>File containing the wordlist</td></tr> |
| </table> |
| </dd> |
| </dl> |
| <dl class="section return"><dt>Returns</dt><dd>A HashSet with the file's words</dd></dl> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00034">34</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| |
| </div> |
| </div> |
| <a class="anchor" id="a9cb9e743592d83000add7e62caeb1675"></a> |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static ISet<string> Lucene.Net.Analysis.WordlistLoader.GetWordSet </td> |
| <td>(</td> |
| <td class="paramtype">System.IO.FileInfo </td> |
| <td class="paramname"><em>wordfile</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">System.String </td> |
| <td class="paramname"><em>comment</em> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Loads a text file and adds every non-comment line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the file should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). </p> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramname">wordfile</td><td>File containing the wordlist</td></tr> |
| <tr><td class="paramname">comment</td><td>The comment string to ignore</td></tr> |
| </table> |
| </dd> |
| </dl> |
| <dl class="section return"><dt>Returns</dt><dd>A HashSet with the file's words</dd></dl> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00050">50</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| |
| </div> |
| </div> |
| <a class="anchor" id="a379750a77b612c2b25532db7e781e4c8"></a> |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static ISet<string> Lucene.Net.Analysis.WordlistLoader.GetWordSet </td> |
| <td>(</td> |
| <td class="paramtype">System.IO.TextReader </td> |
| <td class="paramname"><em>reader</em></td><td>)</td> |
| <td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Reads lines from a Reader and adds every line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the Reader should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). </p> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramname">reader</td><td>Reader containing the wordlist</td></tr> |
| </table> |
| </dd> |
| </dl> |
| <dl class="section return"><dt>Returns</dt><dd>A HashSet with the reader's words</dd></dl> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00066">66</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| |
| </div> |
| </div> |
| <a class="anchor" id="a27658a0a61bd1059f0e5d69632168b9b"></a> |
| <div class="memitem"> |
| <div class="memproto"> |
| <table class="mlabels"> |
| <tr> |
| <td class="mlabels-left"> |
| <table class="memname"> |
| <tr> |
| <td class="memname">static ISet<string> Lucene.Net.Analysis.WordlistLoader.GetWordSet </td> |
| <td>(</td> |
| <td class="paramtype">System.IO.TextReader </td> |
| <td class="paramname"><em>reader</em>, </td> |
| </tr> |
| <tr> |
| <td class="paramkey"></td> |
| <td></td> |
| <td class="paramtype">System.String </td> |
| <td class="paramname"><em>comment</em> </td> |
| </tr> |
| <tr> |
| <td></td> |
| <td>)</td> |
| <td></td><td></td> |
| </tr> |
| </table> |
| </td> |
| <td class="mlabels-right"> |
| <span class="mlabels"><span class="mlabel">static</span></span> </td> |
| </tr> |
| </table> |
| </div><div class="memdoc"> |
| |
| <p>Reads lines from a Reader and adds every non-comment line as an entry to a HashSet (omitting leading and trailing whitespace). Every line of the Reader should contain only one word. The words need to be in lowercase if you make use of an <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_analyzer.html" title="An Analyzer builds TokenStreams, which analyze text. It thus represents a policy for extracting index...">Analyzer</a> which uses <a class="el" href="class_lucene_1_1_net_1_1_analysis_1_1_lower_case_filter.html" title="Normalizes token text to lower case.">LowerCaseFilter</a> (like StandardAnalyzer). </p> |
| <dl class="params"><dt>Parameters</dt><dd> |
| <table class="params"> |
| <tr><td class="paramname">reader</td><td>Reader containing the wordlist </td></tr> |
| <tr><td class="paramname">comment</td><td>The string representing a comment. </td></tr> |
| </table> |
| </dd> |
| </dl> |
| <dl class="section return"><dt>Returns</dt><dd>A HashSet with the reader's words </dd></dl> |
| |
| <p>Definition at line <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html#l00091">91</a> of file <a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a>.</p> |
| |
| </div> |
| </div> |
| <hr/>The documentation for this class was generated from the following file:<ul> |
| <li>core/Analysis/<a class="el" href="core_2_analysis_2_wordlist_loader_8cs_source.html">WordlistLoader.cs</a></li> |
| </ul> |
| </div><!-- contents --> |
| <!-- start footer part --> |
| <hr class="footer"/><address class="footer"><small> |
| Generated on Thu Jan 3 2013 02:12:48 for Lucene.Net by  <a href="http://www.doxygen.org/index.html"> |
| <img class="footer" src="doxygen.png" alt="doxygen"/> |
| </a> 1.8.3 |
| </small></address> |
| </body> |
| </html> |