Commit 81ed24dd04a9524e59c08248af3647dae5830d56

Authored by Romain Deveaud
1 parent 4b35d22277
Exists in master

modules revamp.

Showing 63 changed files with 2301 additions and 669 deletions Side-by-side Diff

doc/classes/Corpus.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: Corpus [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">Corpus</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../files/lib/rir/corpus_rb.html">
  57 +
  58 + lib/rir/corpus.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + Object
  74 +
  75 + </td>
  76 + </tr>
  77 +
  78 + </table>
  79 + </div>
  80 + <!-- banner header -->
  81 +
  82 + <div id="bodyContent">
  83 +
  84 + <div id="contextContent">
  85 +
  86 + </div>
  87 +
  88 +
  89 + <div id="method-list">
  90 + <h3 class="section-bar">Methods</h3>
  91 +
  92 + <div class="name-list">
  93 +
  94 + <a href="#M000002">files</a>&nbsp;&nbsp;
  95 +
  96 + <a href="#M000001">new</a>&nbsp;&nbsp;
  97 +
  98 + </div>
  99 + </div>
  100 +
  101 + </div>
  102 +
  103 + <!-- if includes -->
  104 +
  105 + <div id="section">
  106 +
  107 +
  108 +
  109 + <div id="attribute-list">
  110 + <h3 class="section-bar">Attributes</h3>
  111 +
  112 + <div class="name-list">
  113 + <table>
  114 +
  115 + <tr class="top-aligned-row context-row">
  116 + <td class="context-item-name">path</td>
  117 +
  118 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  119 +
  120 + <td class="context-item-desc"></td>
  121 + </tr>
  122 +
  123 + </table>
  124 + </div>
  125 + </div>
  126 +
  127 +
  128 + <!-- if method_list -->
  129 +
  130 + <div id="methods">
  131 +
  132 + <h3 class="section-bar">Public Class methods</h3>
  133 +
  134 +
  135 + <div id="method-M000001" class="method-detail">
  136 + <a name="M000001"></a>
  137 +
  138 + <div class="method-heading">
  139 +
  140 + <a href="Corpus.src/M000001.html" target="Code" class="method-signature"
  141 + onclick="popupCode('Corpus.src/M000001.html');return false;">
  142 +
  143 + <span class="method-name">new</span><span class="method-args">(path)</span>
  144 +
  145 + </a>
  146 +
  147 + </div>
  148 +
  149 + <div class="method-description">
  150 +
  151 + </div>
  152 + </div>
  153 +
  154 +
  155 + <h3 class="section-bar">Public Instance methods</h3>
  156 +
  157 +
  158 + <div id="method-M000002" class="method-detail">
  159 + <a name="M000002"></a>
  160 +
  161 + <div class="method-heading">
  162 +
  163 + <a href="Corpus.src/M000002.html" target="Code" class="method-signature"
  164 + onclick="popupCode('Corpus.src/M000002.html');return false;">
  165 +
  166 + <span class="method-name">files</span><span class="method-args">()</span>
  167 +
  168 + </a>
  169 +
  170 + </div>
  171 +
  172 + <div class="method-description">
  173 +
  174 + <p>
  175 +Recursively outputs all files in <tt>self.path</tt>. WARNING ! This
  176 +function may take a lot of time if many files are in subdirectories.
  177 +</p>
  178 +<pre>
  179 + c = Corpus.new &quot;my/path&quot;
  180 + c.files # =&gt; [&quot;README.txt&quot;, &quot;lib/code.rb&quot;]
  181 +</pre>
  182 +
  183 + </div>
  184 + </div>
  185 +
  186 +
  187 +
  188 + </div>
  189 +
  190 +
  191 +
  192 +
  193 + </div>
  194 +
  195 +<div id="validator-badges">
  196 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  197 +</div>
  198 +
  199 +</body>
  200 +</html>
doc/classes/Corpus.src/M000001.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>new (Corpus)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/corpus.rb, line 25</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">path</span>)
  12 + <span class="ruby-ivar">@path</span> = <span class="ruby-identifier">path</span>.<span class="ruby-identifier">chomp</span> <span class="ruby-value str">&quot;/&quot;</span>
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/Corpus.src/M000002.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>files (Corpus)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/corpus.rb, line 35</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">files</span>
  12 + <span class="ruby-constant">Dir</span>[<span class="ruby-node">&quot;#{@path}/**/*.*&quot;</span>]
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/Indri.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Module: Indri [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Module</strong></td>
  49 + <td class="class-name-in-header">Indri</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../files/lib/rir/query_rb.html">
  57 +
  58 + lib/rir/query.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + </table>
  70 + </div>
  71 + <!-- banner header -->
  72 +
  73 + <div id="bodyContent">
  74 +
  75 + <div id="contextContent">
  76 +
  77 + </div>
  78 +
  79 +
  80 + </div>
  81 +
  82 + <!-- if includes -->
  83 +
  84 + <div id="section">
  85 +
  86 + <div id="class-list">
  87 + <h3 class="section-bar">Classes and Modules</h3>
  88 +
  89 + Class <a href="Indri/IndriQuery.html" class="link">Indri::IndriQuery</a><br />
  90 +Class <a href="Indri/Parameters.html" class="link">Indri::Parameters</a><br />
  91 +
  92 + </div>
  93 +
  94 +
  95 +
  96 +
  97 + <!-- if method_list -->
  98 +
  99 +
  100 +
  101 +
  102 + </div>
  103 +
  104 +<div id="validator-badges">
  105 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  106 +</div>
  107 +
  108 +</body>
  109 +</html>
doc/classes/Indri/IndriQuery.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: Indri::IndriQuery [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">Indri::IndriQuery</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/query_rb.html">
  57 +
  58 + lib/rir/query.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + <a href="../Query.html">
  74 +
  75 + Query
  76 +
  77 + </a>
  78 +
  79 + </td>
  80 + </tr>
  81 +
  82 + </table>
  83 + </div>
  84 + <!-- banner header -->
  85 +
  86 + <div id="bodyContent">
  87 +
  88 + <div id="contextContent">
  89 +
  90 + </div>
  91 +
  92 +
  93 + <div id="method-list">
  94 + <h3 class="section-bar">Methods</h3>
  95 +
  96 + <div class="name-list">
  97 +
  98 + <a href="#M000020">new</a>&nbsp;&nbsp;
  99 +
  100 + <a href="#M000021">to_s</a>&nbsp;&nbsp;
  101 +
  102 + </div>
  103 + </div>
  104 +
  105 + </div>
  106 +
  107 + <!-- if includes -->
  108 +
  109 + <div id="section">
  110 +
  111 +
  112 +
  113 + <div id="attribute-list">
  114 + <h3 class="section-bar">Attributes</h3>
  115 +
  116 + <div class="name-list">
  117 + <table>
  118 +
  119 + <tr class="top-aligned-row context-row">
  120 + <td class="context-item-name">id</td>
  121 +
  122 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  123 +
  124 + <td class="context-item-desc"></td>
  125 + </tr>
  126 +
  127 + <tr class="top-aligned-row context-row">
  128 + <td class="context-item-name">params</td>
  129 +
  130 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  131 +
  132 + <td class="context-item-desc"></td>
  133 + </tr>
  134 +
  135 + <tr class="top-aligned-row context-row">
  136 + <td class="context-item-name">query</td>
  137 +
  138 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  139 +
  140 + <td class="context-item-desc"></td>
  141 + </tr>
  142 +
  143 + <tr class="top-aligned-row context-row">
  144 + <td class="context-item-name">rule</td>
  145 +
  146 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  147 +
  148 + <td class="context-item-desc"></td>
  149 + </tr>
  150 +
  151 + </table>
  152 + </div>
  153 + </div>
  154 +
  155 +
  156 + <!-- if method_list -->
  157 +
  158 + <div id="methods">
  159 +
  160 + <h3 class="section-bar">Public Class methods</h3>
  161 +
  162 +
  163 + <div id="method-M000020" class="method-detail">
  164 + <a name="M000020"></a>
  165 +
  166 + <div class="method-heading">
  167 +
  168 + <a href="IndriQuery.src/M000020.html" target="Code" class="method-signature"
  169 + onclick="popupCode('IndriQuery.src/M000020.html');return false;">
  170 +
  171 + <span class="method-name">new</span><span class="method-args">(id,query,params)</span>
  172 +
  173 + </a>
  174 +
  175 + </div>
  176 +
  177 + <div class="method-description">
  178 +
  179 + </div>
  180 + </div>
  181 +
  182 +
  183 + <h3 class="section-bar">Public Instance methods</h3>
  184 +
  185 +
  186 + <div id="method-M000021" class="method-detail">
  187 + <a name="M000021"></a>
  188 +
  189 + <div class="method-heading">
  190 +
  191 + <a href="IndriQuery.src/M000021.html" target="Code" class="method-signature"
  192 + onclick="popupCode('IndriQuery.src/M000021.html');return false;">
  193 +
  194 + <span class="method-name">to_s</span><span class="method-args">()</span>
  195 +
  196 + </a>
  197 +
  198 + </div>
  199 +
  200 + <div class="method-description">
  201 +
  202 + </div>
  203 + </div>
  204 +
  205 +
  206 +
  207 + </div>
  208 +
  209 +
  210 +
  211 +
  212 + </div>
  213 +
  214 +<div id="validator-badges">
  215 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  216 +</div>
  217 +
  218 +</body>
  219 +</html>
doc/classes/Indri/IndriQuery.src/M000020.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>new (Indri::IndriQuery)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 62</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">id</span>,<span class="ruby-identifier">query</span>,<span class="ruby-identifier">params</span>)
  12 + <span class="ruby-ivar">@params</span> = <span class="ruby-identifier">params</span>
  13 + <span class="ruby-comment cmt"># Here we set the default retrieval model as Language Modeling</span>
  14 + <span class="ruby-comment cmt"># with a Dirichlet smoothing at 2500.</span>
  15 + <span class="ruby-comment cmt"># TODO: maybe a Rule class...</span>
  16 + <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">rule</span> = <span class="ruby-value str">'method:dirichlet,mu:2500'</span> <span class="ruby-keyword kw">if</span> <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">rule</span>.<span class="ruby-identifier">nil?</span>
  17 +
  18 + <span class="ruby-ivar">@id</span> = <span class="ruby-identifier">id</span>
  19 + <span class="ruby-ivar">@query</span> = <span class="ruby-identifier">query</span>
  20 + <span class="ruby-keyword kw">end</span></pre>
  21 +</body>
  22 +</html>
doc/classes/Indri/IndriQuery.src/M000021.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>to_s (Indri::IndriQuery)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 73</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">to_s</span>
  12 + <span class="ruby-identifier">h</span> = <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">to_s</span>
  13 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">&quot;&lt;query&gt;\n&quot;</span>
  14 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;number&gt;#{@id}&lt;/number&gt;\n&quot;</span>
  15 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;text&gt;#{@query}&lt;/text&gt;\n&quot;</span>
  16 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">&quot;&lt;/query&gt;\n&quot;</span>
  17 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">&quot;&lt;/parameters&gt;&quot;</span>
  18 +
  19 + <span class="ruby-identifier">h</span>
  20 + <span class="ruby-keyword kw">end</span></pre>
  21 +</body>
  22 +</html>
doc/classes/Indri/Parameters.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: Indri::Parameters [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">Indri::Parameters</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/query_rb.html">
  57 +
  58 + lib/rir/query.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + Object
  74 +
  75 + </td>
  76 + </tr>
  77 +
  78 + </table>
  79 + </div>
  80 + <!-- banner header -->
  81 +
  82 + <div id="bodyContent">
  83 +
  84 + <div id="contextContent">
  85 +
  86 + </div>
  87 +
  88 +
  89 + <div id="method-list">
  90 + <h3 class="section-bar">Methods</h3>
  91 +
  92 + <div class="name-list">
  93 +
  94 + <a href="#M000018">new</a>&nbsp;&nbsp;
  95 +
  96 + <a href="#M000019">to_s</a>&nbsp;&nbsp;
  97 +
  98 + </div>
  99 + </div>
  100 +
  101 + </div>
  102 +
  103 + <!-- if includes -->
  104 +
  105 + <div id="section">
  106 +
  107 +
  108 +
  109 + <div id="attribute-list">
  110 + <h3 class="section-bar">Attributes</h3>
  111 +
  112 + <div class="name-list">
  113 + <table>
  114 +
  115 + <tr class="top-aligned-row context-row">
  116 + <td class="context-item-name">baseline</td>
  117 +
  118 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  119 +
  120 + <td class="context-item-desc"></td>
  121 + </tr>
  122 +
  123 + <tr class="top-aligned-row context-row">
  124 + <td class="context-item-name">count</td>
  125 +
  126 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  127 +
  128 + <td class="context-item-desc"></td>
  129 + </tr>
  130 +
  131 + <tr class="top-aligned-row context-row">
  132 + <td class="context-item-name">index_path</td>
  133 +
  134 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  135 +
  136 + <td class="context-item-desc"></td>
  137 + </tr>
  138 +
  139 + <tr class="top-aligned-row context-row">
  140 + <td class="context-item-name">memory</td>
  141 +
  142 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  143 +
  144 + <td class="context-item-desc"></td>
  145 + </tr>
  146 +
  147 + <tr class="top-aligned-row context-row">
  148 + <td class="context-item-name">offset</td>
  149 +
  150 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  151 +
  152 + <td class="context-item-desc"></td>
  153 + </tr>
  154 +
  155 + <tr class="top-aligned-row context-row">
  156 + <td class="context-item-name">print_docs</td>
  157 +
  158 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  159 +
  160 + <td class="context-item-desc"></td>
  161 + </tr>
  162 +
  163 + <tr class="top-aligned-row context-row">
  164 + <td class="context-item-name">print_query</td>
  165 +
  166 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  167 +
  168 + <td class="context-item-desc"></td>
  169 + </tr>
  170 +
  171 + <tr class="top-aligned-row context-row">
  172 + <td class="context-item-name">rule</td>
  173 +
  174 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  175 +
  176 + <td class="context-item-desc"></td>
  177 + </tr>
  178 +
  179 + <tr class="top-aligned-row context-row">
  180 + <td class="context-item-name">run_id</td>
  181 +
  182 + <td class="context-item-value">&nbsp;[RW]&nbsp;</td>
  183 +
  184 + <td class="context-item-desc"></td>
  185 + </tr>
  186 +
  187 + </table>
  188 + </div>
  189 + </div>
  190 +
  191 +
  192 + <!-- if method_list -->
  193 +
  194 + <div id="methods">
  195 +
  196 + <h3 class="section-bar">Public Class methods</h3>
  197 +
  198 +
  199 + <div id="method-M000018" class="method-detail">
  200 + <a name="M000018"></a>
  201 +
  202 + <div class="method-heading">
  203 +
  204 + <a href="Parameters.src/M000018.html" target="Code" class="method-signature"
  205 + onclick="popupCode('Parameters.src/M000018.html');return false;">
  206 +
  207 + <span class="method-name">new</span><span class="method-args">(corpus,mem=&quot;1g&quot;,count=&quot;1000&quot;,offset=&quot;1&quot;,run_id=&quot;default&quot;,print_query=false,print_docs=false)</span>
  208 +
  209 + </a>
  210 +
  211 + </div>
  212 +
  213 + <div class="method-description">
  214 +
  215 + </div>
  216 + </div>
  217 +
  218 +
  219 + <h3 class="section-bar">Public Instance methods</h3>
  220 +
  221 +
  222 + <div id="method-M000019" class="method-detail">
  223 + <a name="M000019"></a>
  224 +
  225 + <div class="method-heading">
  226 +
  227 + <a href="Parameters.src/M000019.html" target="Code" class="method-signature"
  228 + onclick="popupCode('Parameters.src/M000019.html');return false;">
  229 +
  230 + <span class="method-name">to_s</span><span class="method-args">()</span>
  231 +
  232 + </a>
  233 +
  234 + </div>
  235 +
  236 + <div class="method-description">
  237 +
  238 + </div>
  239 + </div>
  240 +
  241 +
  242 +
  243 + </div>
  244 +
  245 +
  246 +
  247 +
  248 + </div>
  249 +
  250 +<div id="validator-badges">
  251 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  252 +</div>
  253 +
  254 +</body>
  255 +</html>
doc/classes/Indri/Parameters.src/M000018.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>new (Indri::Parameters)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 30</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">corpus</span>,<span class="ruby-identifier">mem</span>=<span class="ruby-value str">&quot;1g&quot;</span>,<span class="ruby-identifier">count</span>=<span class="ruby-value str">&quot;1000&quot;</span>,<span class="ruby-identifier">offset</span>=<span class="ruby-value str">&quot;1&quot;</span>,<span class="ruby-identifier">run_id</span>=<span class="ruby-value str">&quot;default&quot;</span>,<span class="ruby-identifier">print_query</span>=<span class="ruby-keyword kw">false</span>,<span class="ruby-identifier">print_docs</span>=<span class="ruby-keyword kw">false</span>)
  12 + <span class="ruby-ivar">@index_path</span> = <span class="ruby-identifier">corpus</span>
  13 + <span class="ruby-ivar">@memory</span> = <span class="ruby-identifier">mem</span>
  14 + <span class="ruby-ivar">@count</span> = <span class="ruby-identifier">count</span>
  15 + <span class="ruby-ivar">@offset</span> = <span class="ruby-identifier">offset</span>
  16 + <span class="ruby-ivar">@run_id</span> = <span class="ruby-identifier">run_id</span>
  17 + <span class="ruby-ivar">@print_query</span> = <span class="ruby-identifier">print_query</span> <span class="ruby-value">? </span><span class="ruby-value str">&quot;true&quot;</span> <span class="ruby-operator">:</span> <span class="ruby-value str">&quot;false&quot;</span>
  18 + <span class="ruby-ivar">@print_docs</span> = <span class="ruby-identifier">print_docs</span> <span class="ruby-value">? </span><span class="ruby-value str">&quot;true&quot;</span> <span class="ruby-operator">:</span> <span class="ruby-value str">&quot;false&quot;</span>
  19 + <span class="ruby-keyword kw">end</span></pre>
  20 +</body>
  21 +</html>
doc/classes/Indri/Parameters.src/M000019.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>to_s (Indri::Parameters)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 40</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">to_s</span>
  12 + <span class="ruby-identifier">h</span> = <span class="ruby-value str">&quot;&lt;parameters&gt;\n&quot;</span>
  13 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;memory&gt;#{@memory}&lt;/memory&gt;\n&quot;</span>
  14 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;index&gt;#{@index_path}&lt;/index&gt;\n&quot;</span>
  15 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;count&gt;#{@count}&lt;/count&gt;\n&quot;</span>
  16 + <span class="ruby-keyword kw">unless</span> <span class="ruby-ivar">@baseline</span>.<span class="ruby-identifier">nil?</span>
  17 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;baseline&gt;#{@baseline}&lt;/baseline&gt;\n&quot;</span>
  18 + <span class="ruby-keyword kw">else</span>
  19 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;rule&gt;#{@rule}&lt;/rule&gt;\n&quot;</span>
  20 + <span class="ruby-keyword kw">end</span>
  21 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;queryOffset&gt;#{@offset}&lt;/queryOffset&gt;\n&quot;</span>
  22 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;runID&gt;#{@run_id}&lt;/runID&gt;\n&quot;</span>
  23 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;printQuery&gt;#{@print_query}&lt;/printQuery&gt;\n&quot;</span>
  24 + <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">&quot;&lt;printDocuments&gt;#{@print_docs}&lt;/printDocuments&gt;\n&quot;</span>
  25 +
  26 + <span class="ruby-identifier">h</span>
  27 + <span class="ruby-keyword kw">end</span></pre>
  28 +</body>
  29 +</html>
doc/classes/Query.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: Query [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">Query</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../files/lib/rir/query_rb.html">
  57 +
  58 + lib/rir/query.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + Object
  74 +
  75 + </td>
  76 + </tr>
  77 +
  78 + </table>
  79 + </div>
  80 + <!-- banner header -->
  81 +
  82 + <div id="bodyContent">
  83 +
  84 + <div id="contextContent">
  85 +
  86 + </div>
  87 +
  88 +
  89 + </div>
  90 +
  91 + <!-- if includes -->
  92 +
  93 + <div id="section">
  94 +
  95 +
  96 +
  97 +
  98 + <!-- if method_list -->
  99 +
  100 +
  101 +
  102 +
  103 + </div>
  104 +
  105 +<div id="validator-badges">
  106 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  107 +</div>
  108 +
  109 +</body>
  110 +</html>
doc/classes/RIR.html
... ... @@ -53,36 +53,6 @@
53 53 <td>
54 54  
55 55  
56   - <a href="../files/lib/rir/ttagger_rb.html">
57   -
58   - lib/rir/ttagger.rb
59   -
60   - </a>
61   -
62   -
63   - <br />
64   -
65   -
66   - <a href="../files/lib/rir/corpus_rb.html">
67   -
68   - lib/rir/corpus.rb
69   -
70   - </a>
71   -
72   -
73   - <br />
74   -
75   -
76   - <a href="../files/lib/rir/query_rb.html">
77   -
78   - lib/rir/query.rb
79   -
80   - </a>
81   -
82   -
83   - <br />
84   -
85   -
86 56 <a href="../files/lib/rir/string_rb.html">
87 57  
88 58 lib/rir/string.rb
... ... @@ -115,99 +85,7 @@
115 85 <div id="contextContent">
116 86  
117 87 <div id="description">
118   - <p>
119   -This file is a part of an Information Retrieval oriented Ruby library
120   -</p>
121   -<p>
122   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
123   -</p>
124   -<p>
125   -This program is free software: you can redistribute it and/or modify it
126   -under the terms of the GNU General Public License as published by the Free
127   -Software Foundation, either version 3 of the License, or (at your option)
128   -any later version.
129   -</p>
130   -<p>
131   -This program is distributed in the hope that it will be useful, but WITHOUT
132   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
133   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
134   -more details.
135   -</p>
136   -<p>
137   -You should have received a copy of the GNU General Public License along
138   -with this program. If not, see <<a
139   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
140   -</p>
141   -<hr size="1"></hr><p>
142   -This file is a part of an Information Retrieval oriented Ruby library
143   -</p>
144   -<p>
145   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
146   -</p>
147   -<p>
148   -This program is free software: you can redistribute it and/or modify it
149   -under the terms of the GNU General Public License as published by the Free
150   -Software Foundation, either version 3 of the License, or (at your option)
151   -any later version.
152   -</p>
153   -<p>
154   -This program is distributed in the hope that it will be useful, but WITHOUT
155   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
156   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
157   -more details.
158   -</p>
159   -<p>
160   -You should have received a copy of the GNU General Public License along
161   -with this program. If not, see <<a
162   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
163   -</p>
164   -<hr size="1"></hr><p>
165   -This file is a part of an Information Retrieval oriented Ruby library
166   -</p>
167   -<p>
168   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
169   -</p>
170   -<p>
171   -This program is free software: you can redistribute it and/or modify it
172   -under the terms of the GNU General Public License as published by the Free
173   -Software Foundation, either version 3 of the License, or (at your option)
174   -any later version.
175   -</p>
176   -<p>
177   -This program is distributed in the hope that it will be useful, but WITHOUT
178   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
179   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
180   -more details.
181   -</p>
182   -<p>
183   -You should have received a copy of the GNU General Public License along
184   -with this program. If not, see <<a
185   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
186   -</p>
187   -<hr size="1"></hr><p>
188   -This file is a part of an Information Retrieval oriented Ruby library
189   -</p>
190   -<p>
191   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
192   -</p>
193   -<p>
194   -This program is free software: you can redistribute it and/or modify it
195   -under the terms of the GNU General Public License as published by the Free
196   -Software Foundation, either version 3 of the License, or (at your option)
197   -any later version.
198   -</p>
199   -<p>
200   -This program is distributed in the hope that it will be useful, but WITHOUT
201   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
202   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
203   -more details.
204   -</p>
205   -<p>
206   -You should have received a copy of the GNU General Public License along
207   -with this program. If not, see <<a
208   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
209   -</p>
210   -<hr size="1"></hr><p>
  88 + <hr size="1"></hr><p>
211 89 General module for many purposes related to Information Retrieval.
212 90 </p>
213 91  
... ... @@ -225,11 +103,7 @@
225 103 <div id="class-list">
226 104 <h3 class="section-bar">Classes and Modules</h3>
227 105  
228   - Module <a href="RIR/Indri.html" class="link">RIR::Indri</a><br />
229   -Module <a href="RIR/TreeTagger.html" class="link">RIR::TreeTagger</a><br />
230   -Class <a href="RIR/Corpus.html" class="link">RIR::Corpus</a><br />
231   -Class <a href="RIR/Document.html" class="link">RIR::Document</a><br />
232   -Class <a href="RIR/Query.html" class="link">RIR::Query</a><br />
  106 + Class <a href="RIR/Document.html" class="link">RIR::Document</a><br />
233 107 Class <a href="RIR/WebDocument.html" class="link">RIR::WebDocument</a><br />
234 108 Class <a href="RIR/WikipediaPage.html" class="link">RIR::WikipediaPage</a><br />
235 109  
doc/classes/RIR/Document.src/M000022.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 31</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 34</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">format_words</span>
12 12 <span class="ruby-identifier">wo</span> = []
13 13  
doc/classes/RIR/Document.src/M000023.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 46</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 49</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">ngrams</span>(<span class="ruby-identifier">n</span>)
12 12 <span class="ruby-identifier">window</span> = []
13 13 <span class="ruby-identifier">ngrams_array</span> = []
doc/classes/RIR/Document.src/M000024.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 64</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 67</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">count_words</span>
12 12 <span class="ruby-identifier">counts</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">h</span>,<span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">h</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-value">0</span> }
13 13 <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> }
doc/classes/RIR/Document.src/M000025.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 78</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 81</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">entropy</span>(<span class="ruby-identifier">s</span>)
12 12 <span class="ruby-identifier">en</span> = <span class="ruby-value">0</span><span class="ruby-value">.0</span>
13 13 <span class="ruby-identifier">counts</span> = <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>
doc/classes/RIR/Document.src/M000026.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 94</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 97</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">tf</span>(<span class="ruby-identifier">s</span>)
12 12 <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>[<span class="ruby-identifier">s</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">size</span>.<span class="ruby-identifier">to_f</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
doc/classes/RIR/Document.src/M000027.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 99</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 102</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">content</span>)
12 12 <span class="ruby-ivar">@doc_content</span> = <span class="ruby-identifier">content</span>
13 13 <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">format_words</span>
doc/classes/RIR/WebDocument.src/M000028.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 112</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 115</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>)
12 12 <span class="ruby-identifier">require</span> <span class="ruby-value str">'net/http'</span>
13 13 <span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>(<span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span>(<span class="ruby-identifier">url</span>))
doc/classes/RIR/WebDocument.src/M000029.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 119</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 122</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">url</span>)
12 12 <span class="ruby-ivar">@url</span> = <span class="ruby-identifier">url</span>
13 13 <span class="ruby-keyword kw">super</span> <span class="ruby-constant">WebDocument</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>).<span class="ruby-identifier">strip_javascripts</span>.<span class="ruby-identifier">strip_stylesheets</span>.<span class="ruby-identifier">strip_xml_tags</span>
doc/classes/RIR/WikipediaPage.src/M000030.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 132</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 135</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_wikipedia_titles</span>(<span class="ruby-identifier">name</span>)
12 12 <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">&quot;Bad encoding&quot;</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span>
13 13  
doc/classes/RIR/WikipediaPage.src/M000031.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 140</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 143</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_url</span>(<span class="ruby-identifier">name</span>)
12 12 <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">&quot;Bad encoding&quot;</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span>
13 13  
doc/classes/RIR/WikipediaPage.src/M000032.html
... ... @@ -7,7 +7,7 @@
7 7 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 148</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 151</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_homepage</span>(<span class="ruby-identifier">name</span>)
12 12 <span class="ruby-identifier">title</span> = <span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">search_wikipedia_titles</span> <span class="ruby-identifier">name</span>
13 13  
doc/classes/Regexp.html
... ... @@ -83,33 +83,6 @@
83 83  
84 84 <div id="contextContent">
85 85  
86   - <div id="description">
87   - <p>
88   -This file is a part of an Information Retrieval oriented Ruby library
89   -</p>
90   -<p>
91   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
92   -</p>
93   -<p>
94   -This program is free software: you can redistribute it and/or modify it
95   -under the terms of the GNU General Public License as published by the Free
96   -Software Foundation, either version 3 of the License, or (at your option)
97   -any later version.
98   -</p>
99   -<p>
100   -This program is distributed in the hope that it will be useful, but WITHOUT
101   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
102   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
103   -more details.
104   -</p>
105   -<p>
106   -You should have received a copy of the GNU General Public License along
107   -with this program. If not, see <<a
108   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
109   -</p>
110   -
111   - </div>
112   -
113 86 </div>
114 87  
115 88  
... ... @@ -118,7 +91,7 @@
118 91  
119 92 <div class="name-list">
120 93  
121   - <a href="#M000001">negated</a>&nbsp;&nbsp;
  94 + <a href="#M000003">negated</a>&nbsp;&nbsp;
122 95  
123 96 </div>
124 97 </div>
125 98  
... ... @@ -139,13 +112,13 @@
139 112 <h3 class="section-bar">Public Instance methods</h3>
140 113  
141 114  
142   - <div id="method-M000001" class="method-detail">
143   - <a name="M000001"></a>
  115 + <div id="method-M000003" class="method-detail">
  116 + <a name="M000003"></a>
144 117  
145 118 <div class="method-heading">
146 119  
147   - <a href="Regexp.src/M000001.html" target="Code" class="method-signature"
148   - onclick="popupCode('Regexp.src/M000001.html');return false;">
  120 + <a href="Regexp.src/M000003.html" target="Code" class="method-signature"
  121 + onclick="popupCode('Regexp.src/M000003.html');return false;">
149 122  
150 123 <span class="method-name">negated</span><span class="method-args">()</span>
151 124  
doc/classes/Regexp.src/M000003.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>negated (Regexp)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/regexp.rb, line 24</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">negated</span>
  12 + <span class="ruby-node">/^((?!#{self}).)*$/</span>
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/String.html
... ... @@ -99,27 +99,27 @@
99 99  
100 100 <div class="name-list">
101 101  
102   - <a href="#M000012">extract_xmltags_values</a>&nbsp;&nbsp;
  102 + <a href="#M000014">extract_xmltags_values</a>&nbsp;&nbsp;
103 103  
104   - <a href="#M000002">is_stopword?</a>&nbsp;&nbsp;
  104 + <a href="#M000004">is_stopword?</a>&nbsp;&nbsp;
105 105  
106   - <a href="#M000003">remove_special_characters</a>&nbsp;&nbsp;
  106 + <a href="#M000005">remove_special_characters</a>&nbsp;&nbsp;
107 107  
108   - <a href="#M000007">strip_javascripts</a>&nbsp;&nbsp;
  108 + <a href="#M000009">strip_javascripts</a>&nbsp;&nbsp;
109 109  
110   - <a href="#M000006">strip_javascripts!</a>&nbsp;&nbsp;
  110 + <a href="#M000008">strip_javascripts!</a>&nbsp;&nbsp;
111 111  
112   - <a href="#M000011">strip_punctuation</a>&nbsp;&nbsp;
  112 + <a href="#M000013">strip_punctuation</a>&nbsp;&nbsp;
113 113  
114   - <a href="#M000010">strip_punctuation!</a>&nbsp;&nbsp;
  114 + <a href="#M000012">strip_punctuation!</a>&nbsp;&nbsp;
115 115  
116   - <a href="#M000009">strip_stylesheets</a>&nbsp;&nbsp;
  116 + <a href="#M000011">strip_stylesheets</a>&nbsp;&nbsp;
117 117  
118   - <a href="#M000008">strip_stylesheets!</a>&nbsp;&nbsp;
  118 + <a href="#M000010">strip_stylesheets!</a>&nbsp;&nbsp;
119 119  
120   - <a href="#M000005">strip_xml_tags</a>&nbsp;&nbsp;
  120 + <a href="#M000007">strip_xml_tags</a>&nbsp;&nbsp;
121 121  
122   - <a href="#M000004">strip_xml_tags!</a>&nbsp;&nbsp;
  122 + <a href="#M000006">strip_xml_tags!</a>&nbsp;&nbsp;
123 123  
124 124 </div>
125 125 </div>
126 126  
... ... @@ -150,13 +150,13 @@
150 150 <h3 class="section-bar">Public Instance methods</h3>
151 151  
152 152  
153   - <div id="method-M000012" class="method-detail">
154   - <a name="M000012"></a>
  153 + <div id="method-M000014" class="method-detail">
  154 + <a name="M000014"></a>
155 155  
156 156 <div class="method-heading">
157 157  
158   - <a href="String.src/M000012.html" target="Code" class="method-signature"
159   - onclick="popupCode('String.src/M000012.html');return false;">
  158 + <a href="String.src/M000014.html" target="Code" class="method-signature"
  159 + onclick="popupCode('String.src/M000014.html');return false;">
160 160  
161 161 <span class="method-name">extract_xmltags_values</span><span class="method-args">(tag_name)</span>
162 162  
163 163  
... ... @@ -178,13 +178,13 @@
178 178 </div>
179 179  
180 180  
181   - <div id="method-M000002" class="method-detail">
182   - <a name="M000002"></a>
  181 + <div id="method-M000004" class="method-detail">
  182 + <a name="M000004"></a>
183 183  
184 184 <div class="method-heading">
185 185  
186   - <a href="String.src/M000002.html" target="Code" class="method-signature"
187   - onclick="popupCode('String.src/M000002.html');return false;">
  186 + <a href="String.src/M000004.html" target="Code" class="method-signature"
  187 + onclick="popupCode('String.src/M000004.html');return false;">
188 188  
189 189 <span class="method-name">is_stopword?</span><span class="method-args">()</span>
190 190  
191 191  
... ... @@ -203,13 +203,13 @@
203 203 </div>
204 204  
205 205  
206   - <div id="method-M000003" class="method-detail">
207   - <a name="M000003"></a>
  206 + <div id="method-M000005" class="method-detail">
  207 + <a name="M000005"></a>
208 208  
209 209 <div class="method-heading">
210 210  
211   - <a href="String.src/M000003.html" target="Code" class="method-signature"
212   - onclick="popupCode('String.src/M000003.html');return false;">
  211 + <a href="String.src/M000005.html" target="Code" class="method-signature"
  212 + onclick="popupCode('String.src/M000005.html');return false;">
213 213  
214 214 <span class="method-name">remove_special_characters</span><span class="method-args">()</span>
215 215  
216 216  
... ... @@ -227,13 +227,13 @@
227 227 </div>
228 228  
229 229  
230   - <div id="method-M000007" class="method-detail">
231   - <a name="M000007"></a>
  230 + <div id="method-M000009" class="method-detail">
  231 + <a name="M000009"></a>
232 232  
233 233 <div class="method-heading">
234 234  
235   - <a href="String.src/M000007.html" target="Code" class="method-signature"
236   - onclick="popupCode('String.src/M000007.html');return false;">
  235 + <a href="String.src/M000009.html" target="Code" class="method-signature"
  236 + onclick="popupCode('String.src/M000009.html');return false;">
237 237  
238 238 <span class="method-name">strip_javascripts</span><span class="method-args">()</span>
239 239  
240 240  
... ... @@ -260,13 +260,13 @@
260 260 </div>
261 261  
262 262  
263   - <div id="method-M000006" class="method-detail">
264   - <a name="M000006"></a>
  263 + <div id="method-M000008" class="method-detail">
  264 + <a name="M000008"></a>
265 265  
266 266 <div class="method-heading">
267 267  
268   - <a href="String.src/M000006.html" target="Code" class="method-signature"
269   - onclick="popupCode('String.src/M000006.html');return false;">
  268 + <a href="String.src/M000008.html" target="Code" class="method-signature"
  269 + onclick="popupCode('String.src/M000008.html');return false;">
270 270  
271 271 <span class="method-name">strip_javascripts!</span><span class="method-args">()</span>
272 272  
273 273  
... ... @@ -294,13 +294,13 @@
294 294 </div>
295 295  
296 296  
297   - <div id="method-M000011" class="method-detail">
298   - <a name="M000011"></a>
  297 + <div id="method-M000013" class="method-detail">
  298 + <a name="M000013"></a>
299 299  
300 300 <div class="method-heading">
301 301  
302   - <a href="String.src/M000011.html" target="Code" class="method-signature"
303   - onclick="popupCode('String.src/M000011.html');return false;">
  302 + <a href="String.src/M000013.html" target="Code" class="method-signature"
  303 + onclick="popupCode('String.src/M000013.html');return false;">
304 304  
305 305 <span class="method-name">strip_punctuation</span><span class="method-args">()</span>
306 306  
307 307  
... ... @@ -322,13 +322,13 @@
322 322 </div>
323 323  
324 324  
325   - <div id="method-M000010" class="method-detail">
326   - <a name="M000010"></a>
  325 + <div id="method-M000012" class="method-detail">
  326 + <a name="M000012"></a>
327 327  
328 328 <div class="method-heading">
329 329  
330   - <a href="String.src/M000010.html" target="Code" class="method-signature"
331   - onclick="popupCode('String.src/M000010.html');return false;">
  330 + <a href="String.src/M000012.html" target="Code" class="method-signature"
  331 + onclick="popupCode('String.src/M000012.html');return false;">
332 332  
333 333 <span class="method-name">strip_punctuation!</span><span class="method-args">()</span>
334 334  
335 335  
... ... @@ -351,13 +351,13 @@
351 351 </div>
352 352  
353 353  
354   - <div id="method-M000009" class="method-detail">
355   - <a name="M000009"></a>
  354 + <div id="method-M000011" class="method-detail">
  355 + <a name="M000011"></a>
356 356  
357 357 <div class="method-heading">
358 358  
359   - <a href="String.src/M000009.html" target="Code" class="method-signature"
360   - onclick="popupCode('String.src/M000009.html');return false;">
  359 + <a href="String.src/M000011.html" target="Code" class="method-signature"
  360 + onclick="popupCode('String.src/M000011.html');return false;">
361 361  
362 362 <span class="method-name">strip_stylesheets</span><span class="method-args">()</span>
363 363  
364 364  
... ... @@ -371,13 +371,13 @@
371 371 </div>
372 372  
373 373  
374   - <div id="method-M000008" class="method-detail">
375   - <a name="M000008"></a>
  374 + <div id="method-M000010" class="method-detail">
  375 + <a name="M000010"></a>
376 376  
377 377 <div class="method-heading">
378 378  
379   - <a href="String.src/M000008.html" target="Code" class="method-signature"
380   - onclick="popupCode('String.src/M000008.html');return false;">
  379 + <a href="String.src/M000010.html" target="Code" class="method-signature"
  380 + onclick="popupCode('String.src/M000010.html');return false;">
381 381  
382 382 <span class="method-name">strip_stylesheets!</span><span class="method-args">()</span>
383 383  
384 384  
... ... @@ -391,13 +391,13 @@
391 391 </div>
392 392  
393 393  
394   - <div id="method-M000005" class="method-detail">
395   - <a name="M000005"></a>
  394 + <div id="method-M000007" class="method-detail">
  395 + <a name="M000007"></a>
396 396  
397 397 <div class="method-heading">
398 398  
399   - <a href="String.src/M000005.html" target="Code" class="method-signature"
400   - onclick="popupCode('String.src/M000005.html');return false;">
  399 + <a href="String.src/M000007.html" target="Code" class="method-signature"
  400 + onclick="popupCode('String.src/M000007.html');return false;">
401 401  
402 402 <span class="method-name">strip_xml_tags</span><span class="method-args">()</span>
403 403  
404 404  
... ... @@ -420,13 +420,13 @@
420 420 </div>
421 421  
422 422  
423   - <div id="method-M000004" class="method-detail">
424   - <a name="M000004"></a>
  423 + <div id="method-M000006" class="method-detail">
  424 + <a name="M000006"></a>
425 425  
426 426 <div class="method-heading">
427 427  
428   - <a href="String.src/M000004.html" target="Code" class="method-signature"
429   - onclick="popupCode('String.src/M000004.html');return false;">
  428 + <a href="String.src/M000006.html" target="Code" class="method-signature"
  429 + onclick="popupCode('String.src/M000006.html');return false;">
430 430  
431 431 <span class="method-name">strip_xml_tags!</span><span class="method-args">()</span>
432 432  
doc/classes/String.src/M000004.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_xml_tags! (String)</title>
  5 + <title>is_stopword? (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 91</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span>
12   - <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/?[^&gt;]*&gt;/</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 78</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">is_stopword?</span>
  12 + <span class="ruby-constant">Stoplist</span>.<span class="ruby-identifier">include?</span>(<span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">downcase</span>)
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000005.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_xml_tags (String)</title>
  5 + <title>remove_special_characters (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 100</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span>
12   - <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_xml_tags!</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 84</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">remove_special_characters</span>
  12 + <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">w</span>.<span class="ruby-identifier">gsub</span>(<span class="ruby-regexp re">/\W/</span>,<span class="ruby-value str">' '</span>).<span class="ruby-identifier">split</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">w</span>.<span class="ruby-identifier">gsub</span>(<span class="ruby-regexp re">/\W/</span>,<span class="ruby-value str">' '</span>).<span class="ruby-identifier">strip</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/\A.\z/</span>, <span class="ruby-value str">''</span>)}.<span class="ruby-identifier">join</span>(<span class="ruby-value str">' '</span>).<span class="ruby-identifier">strip</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/\A.\z/</span>, <span class="ruby-value str">''</span>)}.<span class="ruby-identifier">join</span>(<span class="ruby-value str">' '</span>)
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000006.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_javascripts! (String)</title>
  5 + <title>strip_xml_tags! (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 114</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span>
12   - <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">script</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/javascript&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/script&gt;/</span><span class="ruby-identifier">m</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 93</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span>
  12 + <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/?[^&gt;]*&gt;/</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000007.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_javascripts (String)</title>
  5 + <title>strip_xml_tags (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 127</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</span>
12   - <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_javascripts!</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 102</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span>
  12 + <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_xml_tags!</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000008.html
... ... @@ -2,15 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_stylesheets! (String)</title>
  5 + <title>strip_javascripts! (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 131</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span>
12   - <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</span>
13   - <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">style</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/css&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/style&gt;/</span><span class="ruby-identifier">m</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 116</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span>
  12 + <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">script</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/javascript&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/script&gt;/</span><span class="ruby-identifier">m</span>
14 13 <span class="ruby-keyword kw">end</span></pre>
15 14 </body>
16 15 </html>
doc/classes/String.src/M000009.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_stylesheets (String)</title>
  5 + <title>strip_javascripts (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 136</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</span>
12   - <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_stylesheets!</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 129</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</span>
  12 + <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_javascripts!</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000010.html
... ... @@ -2,14 +2,15 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_punctuation! (String)</title>
  5 + <title>strip_stylesheets! (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 145</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation!</span>
12   - <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span>[<span class="ruby-operator">^</span><span class="ruby-identifier">a</span><span class="ruby-operator">-</span><span class="ruby-identifier">zA</span><span class="ruby-operator">-</span><span class="ruby-constant">Z0</span><span class="ruby-operator">-</span><span class="ruby-value">9</span>\<span class="ruby-operator">-</span>\<span class="ruby-identifier">s</span>]<span class="ruby-operator">/</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 133</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span>
  12 + <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</span>
  13 + <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">style</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/css&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/style&gt;/</span><span class="ruby-identifier">m</span>
13 14 <span class="ruby-keyword kw">end</span></pre>
14 15 </body>
15 16 </html>
doc/classes/String.src/M000011.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>strip_punctuation (String)</title>
  5 + <title>strip_stylesheets (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 153</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation</span>
12   - <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_punctuation!</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 138</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</span>
  12 + <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_stylesheets!</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000012.html
... ... @@ -2,14 +2,14 @@
2 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
3 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 4 <head>
5   - <title>extract_xmltags_values (String)</title>
  5 + <title>strip_punctuation! (String)</title>
6 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 8 </head>
9 9 <body class="standalone-code">
10   - <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 161</span>
11   - <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">extract_xmltags_values</span>(<span class="ruby-identifier">tag_name</span>)
12   - <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">scan</span>(<span class="ruby-node">/&lt;#{tag_name}.*?&gt;(.+?)&lt;\/#{tag_name}&gt;/</span>).<span class="ruby-identifier">flatten</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 147</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation!</span>
  12 + <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span>[<span class="ruby-operator">^</span><span class="ruby-identifier">a</span><span class="ruby-operator">-</span><span class="ruby-identifier">zA</span><span class="ruby-operator">-</span><span class="ruby-constant">Z0</span><span class="ruby-operator">-</span><span class="ruby-value">9</span>\<span class="ruby-operator">-</span>\<span class="ruby-identifier">s</span>]<span class="ruby-operator">/</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
14 14 </body>
15 15 </html>
doc/classes/String.src/M000013.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>strip_punctuation (String)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 155</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation</span>
  12 + <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_punctuation!</span>
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/String.src/M000014.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>extract_xmltags_values (String)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 163</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">extract_xmltags_values</span>(<span class="ruby-identifier">tag_name</span>)
  12 + <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">scan</span>(<span class="ruby-node">/&lt;#{tag_name}.*?&gt;(.+?)&lt;\/#{tag_name}&gt;/</span>).<span class="ruby-identifier">flatten</span>
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/TreeTagger.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Module: TreeTagger [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Module</strong></td>
  49 + <td class="class-name-in-header">TreeTagger</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + </table>
  70 + </div>
  71 + <!-- banner header -->
  72 +
  73 + <div id="bodyContent">
  74 +
  75 + <div id="contextContent">
  76 +
  77 + <div id="description">
  78 + <p>
  79 +TreeTagger-related stuff module.
  80 +</p>
  81 +<p>
  82 +See <a
  83 +href="http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html">www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html</a>
  84 +</p>
  85 +
  86 + </div>
  87 +
  88 + </div>
  89 +
  90 +
  91 + </div>
  92 +
  93 + <!-- if includes -->
  94 +
  95 + <div id="section">
  96 +
  97 + <div id="class-list">
  98 + <h3 class="section-bar">Classes and Modules</h3>
  99 +
  100 + Class <a href="TreeTagger/Chunk.html" class="link">TreeTagger::Chunk</a><br />
  101 +Class <a href="TreeTagger/TaggerChunker.html" class="link">TreeTagger::TaggerChunker</a><br />
  102 +Class <a href="TreeTagger/TaggerChunkerEnglish.html" class="link">TreeTagger::TaggerChunkerEnglish</a><br />
  103 +Class <a href="TreeTagger/TaggerChunkerFrench.html" class="link">TreeTagger::TaggerChunkerFrench</a><br />
  104 +Class <a href="TreeTagger/TaggerChunkerGerman.html" class="link">TreeTagger::TaggerChunkerGerman</a><br />
  105 +
  106 + </div>
  107 +
  108 +
  109 +
  110 +
  111 + <!-- if method_list -->
  112 +
  113 +
  114 +
  115 +
  116 + </div>
  117 +
  118 +<div id="validator-badges">
  119 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  120 +</div>
  121 +
  122 +</body>
  123 +</html>
doc/classes/TreeTagger/Chunk.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: TreeTagger::Chunk [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">TreeTagger::Chunk</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + Object
  74 +
  75 + </td>
  76 + </tr>
  77 +
  78 + </table>
  79 + </div>
  80 + <!-- banner header -->
  81 +
  82 + <div id="bodyContent">
  83 +
  84 + <div id="contextContent">
  85 +
  86 + <div id="description">
  87 + <p>
  88 +Represents a <a href="Chunk.html">Chunk</a> extracted when parsing a <a
  89 +href="TaggerChunker.html">TaggerChunker</a> file.
  90 +</p>
  91 +
  92 + </div>
  93 +
  94 + </div>
  95 +
  96 +
  97 + <div id="method-list">
  98 + <h3 class="section-bar">Methods</h3>
  99 +
  100 + <div class="name-list">
  101 +
  102 + <a href="#M000017">new</a>&nbsp;&nbsp;
  103 +
  104 + </div>
  105 + </div>
  106 +
  107 + </div>
  108 +
  109 + <!-- if includes -->
  110 +
  111 + <div id="section">
  112 +
  113 +
  114 +
  115 + <div id="attribute-list">
  116 + <h3 class="section-bar">Attributes</h3>
  117 +
  118 + <div class="name-list">
  119 + <table>
  120 +
  121 + <tr class="top-aligned-row context-row">
  122 + <td class="context-item-name">tag</td>
  123 +
  124 + <td class="context-item-value">&nbsp;[R]&nbsp;</td>
  125 +
  126 + <td class="context-item-desc"></td>
  127 + </tr>
  128 +
  129 + <tr class="top-aligned-row context-row">
  130 + <td class="context-item-name">words</td>
  131 +
  132 + <td class="context-item-value">&nbsp;[R]&nbsp;</td>
  133 +
  134 + <td class="context-item-desc"></td>
  135 + </tr>
  136 +
  137 + </table>
  138 + </div>
  139 + </div>
  140 +
  141 +
  142 + <!-- if method_list -->
  143 +
  144 + <div id="methods">
  145 +
  146 + <h3 class="section-bar">Public Class methods</h3>
  147 +
  148 +
  149 + <div id="method-M000017" class="method-detail">
  150 + <a name="M000017"></a>
  151 +
  152 + <div class="method-heading">
  153 +
  154 + <a href="Chunk.src/M000017.html" target="Code" class="method-signature"
  155 + onclick="popupCode('Chunk.src/M000017.html');return false;">
  156 +
  157 + <span class="method-name">new</span><span class="method-args">(str,tag)</span>
  158 +
  159 + </a>
  160 +
  161 + </div>
  162 +
  163 + <div class="method-description">
  164 +
  165 + <p>
  166 +Creates a <a href="Chunk.html">Chunk</a>.
  167 +</p>
  168 +<ul>
  169 +<li><tt>str</tt> are whitespace-separated terms.
  170 +
  171 +</li>
  172 +<li><tt>tag</tt> see : <a
  173 +href="ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt">ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt</a>
  174 +
  175 +</li>
  176 +</ul>
  177 +
  178 + </div>
  179 + </div>
  180 +
  181 +
  182 +
  183 + </div>
  184 +
  185 +
  186 +
  187 +
  188 + </div>
  189 +
  190 +<div id="validator-badges">
  191 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  192 +</div>
  193 +
  194 +</body>
  195 +</html>
doc/classes/TreeTagger/Chunk.src/M000017.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>new (TreeTagger::Chunk)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 89</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span> <span class="ruby-identifier">str</span>,<span class="ruby-identifier">tag</span>
  12 + <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">str</span>.<span class="ruby-identifier">split</span>
  13 + <span class="ruby-ivar">@tag</span> = <span class="ruby-identifier">tag</span>[<span class="ruby-value">1</span><span class="ruby-operator">..</span><span class="ruby-value">-2</span>]
  14 + <span class="ruby-keyword kw">end</span></pre>
  15 +</body>
  16 +</html>
doc/classes/TreeTagger/TaggerChunker.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: TreeTagger::TaggerChunker [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">TreeTagger::TaggerChunker</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + Object
  74 +
  75 + </td>
  76 + </tr>
  77 +
  78 + </table>
  79 + </div>
  80 + <!-- banner header -->
  81 +
  82 + <div id="bodyContent">
  83 +
  84 + <div id="contextContent">
  85 +
  86 + <div id="description">
  87 + <p>
  88 +This class handles generic parsing of tagger-chunker outputs.
  89 +</p>
  90 +
  91 + </div>
  92 +
  93 + </div>
  94 +
  95 +
  96 + <div id="method-list">
  97 + <h3 class="section-bar">Methods</h3>
  98 +
  99 + <div class="name-list">
  100 +
  101 + <a href="#M000016">new</a>&nbsp;&nbsp;
  102 +
  103 + <a href="#M000015">parse</a>&nbsp;&nbsp;
  104 +
  105 + </div>
  106 + </div>
  107 +
  108 + </div>
  109 +
  110 + <!-- if includes -->
  111 +
  112 + <div id="section">
  113 +
  114 +
  115 +
  116 + <div id="attribute-list">
  117 + <h3 class="section-bar">Attributes</h3>
  118 +
  119 + <div class="name-list">
  120 + <table>
  121 +
  122 + <tr class="top-aligned-row context-row">
  123 + <td class="context-item-name">chunks</td>
  124 +
  125 + <td class="context-item-value">&nbsp;[R]&nbsp;</td>
  126 +
  127 + <td class="context-item-desc"></td>
  128 + </tr>
  129 +
  130 + <tr class="top-aligned-row context-row">
  131 + <td class="context-item-name">file</td>
  132 +
  133 + <td class="context-item-value">&nbsp;[R]&nbsp;</td>
  134 +
  135 + <td class="context-item-desc"></td>
  136 + </tr>
  137 +
  138 + </table>
  139 + </div>
  140 + </div>
  141 +
  142 +
  143 + <!-- if method_list -->
  144 +
  145 + <div id="methods">
  146 +
  147 + <h3 class="section-bar">Public Class methods</h3>
  148 +
  149 +
  150 + <div id="method-M000016" class="method-detail">
  151 + <a name="M000016"></a>
  152 +
  153 + <div class="method-heading">
  154 +
  155 + <a href="TaggerChunker.src/M000016.html" target="Code" class="method-signature"
  156 + onclick="popupCode('TaggerChunker.src/M000016.html');return false;">
  157 +
  158 + <span class="method-name">new</span><span class="method-args">(chunk_file)</span>
  159 +
  160 + </a>
  161 +
  162 + </div>
  163 +
  164 + <div class="method-description">
  165 +
  166 + <p>
  167 +Initializes parsing. <tt>chunk_file</tt> is the output of
  168 +<tt>tagger-chunker-</tt> and must be a valid path to the file.
  169 +</p>
  170 +<pre>
  171 + TaggerChunker.new(&quot;ttout/2010020&quot;) #=&gt; #&lt;RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#&lt;RIR::TreeTagger::Chunk:0x8ec5a10 @words=[&quot;robert&quot;, &quot;schumann&quot;], @tag=&quot;NC&quot;&gt;, ...] ...&gt;
  172 +</pre>
  173 +
  174 + </div>
  175 + </div>
  176 +
  177 +
  178 + <div id="method-M000015" class="method-detail">
  179 + <a name="M000015"></a>
  180 +
  181 + <div class="method-heading">
  182 +
  183 + <a href="TaggerChunker.src/M000015.html" target="Code" class="method-signature"
  184 + onclick="popupCode('TaggerChunker.src/M000015.html');return false;">
  185 +
  186 + <span class="method-name">parse</span><span class="method-args">(chunk_lines)</span>
  187 +
  188 + </a>
  189 +
  190 + </div>
  191 +
  192 + <div class="method-description">
  193 +
  194 + <p>
  195 +Parses a tagger-chunker output and returns an Array of <a
  196 +href="Chunk.html">Chunk</a>.
  197 +</p>
  198 +
  199 + </div>
  200 + </div>
  201 +
  202 +
  203 +
  204 + </div>
  205 +
  206 +
  207 +
  208 +
  209 + </div>
  210 +
  211 +<div id="validator-badges">
  212 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  213 +</div>
  214 +
  215 +</body>
  216 +</html>
doc/classes/TreeTagger/TaggerChunker.src/M000015.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>parse (TreeTagger::TaggerChunker)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 34</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">parse</span> <span class="ruby-identifier">chunk_lines</span>
  12 + <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">false</span>
  13 + <span class="ruby-identifier">tag</span> = <span class="ruby-keyword kw">nil</span>
  14 +
  15 + <span class="ruby-identifier">chunks</span> = []
  16 + <span class="ruby-identifier">words</span> = []
  17 +
  18 + <span class="ruby-identifier">chunk_lines</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">l</span><span class="ruby-operator">|</span>
  19 + <span class="ruby-identifier">l</span>.<span class="ruby-identifier">chomp!</span>
  20 + <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/^&lt;\w+&gt;$/</span>
  21 + <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">true</span>
  22 + <span class="ruby-identifier">tag</span> = <span class="ruby-identifier">l</span>
  23 + <span class="ruby-keyword kw">elsif</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/^&lt;\/\w+&gt;$/</span>
  24 + <span class="ruby-keyword kw">if</span> <span class="ruby-operator">!</span><span class="ruby-identifier">words</span>.<span class="ruby-identifier">empty?</span> <span class="ruby-operator">&amp;&amp;</span> <span class="ruby-identifier">open</span> <span class="ruby-operator">&amp;&amp;</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">tag</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/&lt;/</span>, <span class="ruby-value str">'&lt;/'</span>)
  25 + <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">false</span>
  26 + <span class="ruby-identifier">chunks</span>.<span class="ruby-identifier">push</span> <span class="ruby-constant">Chunk</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">words</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">&quot; &quot;</span>), <span class="ruby-identifier">tag</span>)
  27 + <span class="ruby-identifier">words</span>.<span class="ruby-identifier">clear</span>
  28 + <span class="ruby-keyword kw">else</span>
  29 + <span class="ruby-keyword kw">next</span>
  30 + <span class="ruby-keyword kw">end</span>
  31 + <span class="ruby-keyword kw">else</span>
  32 + <span class="ruby-identifier">words</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">l</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">first</span>)
  33 + <span class="ruby-keyword kw">end</span>
  34 + <span class="ruby-keyword kw">end</span>
  35 +
  36 + <span class="ruby-identifier">chunks</span>
  37 + <span class="ruby-keyword kw">end</span></pre>
  38 +</body>
  39 +</html>
doc/classes/TreeTagger/TaggerChunker.src/M000016.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>new (TreeTagger::TaggerChunker)</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
  8 +</head>
  9 +<body class="standalone-code">
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 66</span>
  11 + <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span> <span class="ruby-identifier">chunk_file</span>
  12 + <span class="ruby-ivar">@chunks</span> = <span class="ruby-constant">TaggerChunker</span>.<span class="ruby-identifier">parse</span> <span class="ruby-constant">File</span>.<span class="ruby-identifier">open</span>(<span class="ruby-identifier">chunk_file</span>).<span class="ruby-identifier">readlines</span>
  13 + <span class="ruby-keyword kw">end</span></pre>
  14 +</body>
  15 +</html>
doc/classes/TreeTagger/TaggerChunkerEnglish.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: TreeTagger::TaggerChunkerEnglish [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">TreeTagger::TaggerChunkerEnglish</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + <a href="TaggerChunker.html">
  74 +
  75 + TreeTagger::TaggerChunker
  76 +
  77 + </a>
  78 +
  79 + </td>
  80 + </tr>
  81 +
  82 + </table>
  83 + </div>
  84 + <!-- banner header -->
  85 +
  86 + <div id="bodyContent">
  87 +
  88 + <div id="contextContent">
  89 +
  90 + </div>
  91 +
  92 +
  93 + </div>
  94 +
  95 + <!-- if includes -->
  96 +
  97 + <div id="section">
  98 +
  99 +
  100 +
  101 +
  102 + <!-- if method_list -->
  103 +
  104 +
  105 +
  106 +
  107 + </div>
  108 +
  109 +<div id="validator-badges">
  110 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  111 +</div>
  112 +
  113 +</body>
  114 +</html>
doc/classes/TreeTagger/TaggerChunkerFrench.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: TreeTagger::TaggerChunkerFrench [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">TreeTagger::TaggerChunkerFrench</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + <a href="TaggerChunker.html">
  74 +
  75 + TreeTagger::TaggerChunker
  76 +
  77 + </a>
  78 +
  79 + </td>
  80 + </tr>
  81 +
  82 + </table>
  83 + </div>
  84 + <!-- banner header -->
  85 +
  86 + <div id="bodyContent">
  87 +
  88 + <div id="contextContent">
  89 +
  90 + </div>
  91 +
  92 +
  93 + </div>
  94 +
  95 + <!-- if includes -->
  96 +
  97 + <div id="section">
  98 +
  99 +
  100 +
  101 +
  102 + <!-- if method_list -->
  103 +
  104 +
  105 +
  106 +
  107 + </div>
  108 +
  109 +<div id="validator-badges">
  110 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  111 +</div>
  112 +
  113 +</body>
  114 +</html>
doc/classes/TreeTagger/TaggerChunkerGerman.html
  1 +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
  2 +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
  3 +<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
  4 +<head>
  5 + <title>Class: TreeTagger::TaggerChunkerGerman [RDoc Documentation]</title>
  6 + <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
  7 + <meta http-equiv="Content-Script-Type" content="text/javascript" />
  8 + <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
  9 + <script type="text/javascript">
  10 + // <![CDATA[
  11 +
  12 + function popupCode( url ) {
  13 + window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  14 + }
  15 +
  16 + function toggleCode( id ) {
  17 + if ( document.getElementById )
  18 + elem = document.getElementById( id );
  19 + else if ( document.all )
  20 + elem = eval( "document.all." + id );
  21 + else
  22 + return false;
  23 +
  24 + elemStyle = elem.style;
  25 +
  26 + if ( elemStyle.display != "block" ) {
  27 + elemStyle.display = "block"
  28 + } else {
  29 + elemStyle.display = "none"
  30 + }
  31 +
  32 + return true;
  33 + }
  34 +
  35 + // Make codeblocks hidden by default
  36 + document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
  37 +
  38 + // ]]>
  39 + </script>
  40 +
  41 +</head>
  42 +<body>
  43 +
  44 +
  45 + <div id="classHeader">
  46 + <table class="header-table">
  47 + <tr class="top-aligned-row">
  48 + <td><strong>Class</strong></td>
  49 + <td class="class-name-in-header">TreeTagger::TaggerChunkerGerman</td>
  50 + </tr>
  51 + <tr class="top-aligned-row">
  52 + <td><strong>In:</strong></td>
  53 + <td>
  54 +
  55 +
  56 + <a href="../../files/lib/rir/ttagger_rb.html">
  57 +
  58 + lib/rir/ttagger.rb
  59 +
  60 + </a>
  61 +
  62 +
  63 + <br />
  64 +
  65 + </td>
  66 + </tr>
  67 +
  68 +
  69 + <tr class="top-aligned-row">
  70 + <td><strong>Parent:</strong></td>
  71 + <td>
  72 +
  73 + <a href="TaggerChunker.html">
  74 +
  75 + TreeTagger::TaggerChunker
  76 +
  77 + </a>
  78 +
  79 + </td>
  80 + </tr>
  81 +
  82 + </table>
  83 + </div>
  84 + <!-- banner header -->
  85 +
  86 + <div id="bodyContent">
  87 +
  88 + <div id="contextContent">
  89 +
  90 + </div>
  91 +
  92 +
  93 + </div>
  94 +
  95 + <!-- if includes -->
  96 +
  97 + <div id="section">
  98 +
  99 +
  100 +
  101 +
  102 + <!-- if method_list -->
  103 +
  104 +
  105 +
  106 +
  107 + </div>
  108 +
  109 +<div id="validator-badges">
  110 + <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
  111 +</div>
  112 +
  113 +</body>
  114 +</html>
1   -Thu, 25 Nov 2010 17:10:04 +0100
  1 +Thu, 25 Nov 2010 17:21:51 +0100
doc/files/lib/rir/corpus_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-23 18:20:24 +0100</td>
  56 + <td>2010-11-25 17:20:52 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -62,33 +62,6 @@
62 62 <div id="bodyContent">
63 63  
64 64 <div id="contextContent">
65   -
66   - <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89   -</p>
90   -
91   - </div>
92 65  
93 66 </div>
94 67  
doc/files/lib/rir/document_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-25 16:04:20 +0100</td>
  56 + <td>2010-11-25 17:20:25 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -62,33 +62,6 @@
62 62 <div id="bodyContent">
63 63  
64 64 <div id="contextContent">
65   -
66   - <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89   -</p>
90   -
91   - </div>
92 65  
93 66 <div id="requires-list">
94 67 <h3 class="section-bar">Required files</h3>
doc/files/lib/rir/query_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-25 13:25:18 +0100</td>
  56 + <td>2010-11-25 17:21:14 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -62,33 +62,6 @@
62 62 <div id="bodyContent">
63 63  
64 64 <div id="contextContent">
65   -
66   - <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89   -</p>
90   -
91   - </div>
92 65  
93 66 </div>
94 67  
doc/files/lib/rir/regexp_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-19 11:27:06 +0100</td>
  56 + <td>2010-11-25 17:19:39 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -62,33 +62,6 @@
62 62 <div id="bodyContent">
63 63  
64 64 <div id="contextContent">
65   -
66   - <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89   -</p>
90   -
91   - </div>
92 65  
93 66 </div>
94 67  
doc/files/lib/rir/string_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-23 18:20:41 +0100</td>
  56 + <td>2010-11-25 17:20:14 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -64,28 +64,8 @@
64 64 <div id="contextContent">
65 65  
66 66 <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
  67 + <hr size="1"></hr><p>
  68 +General module for many purposes related to Information Retrieval.
89 69 </p>
90 70  
91 71 </div>
doc/files/lib/rir/ttagger_rb.html
... ... @@ -53,7 +53,7 @@
53 53 </tr>
54 54 <tr class="top-aligned-row">
55 55 <td><strong>Last Update:</strong></td>
56   - <td>2010-11-25 17:01:46 +0100</td>
  56 + <td>2010-11-25 17:21:44 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -62,105 +62,6 @@
62 62 <div id="bodyContent">
63 63  
64 64 <div id="contextContent">
65   -
66   - <div id="description">
67   - <p>
68   -This file is a part of an Information Retrieval oriented Ruby library
69   -</p>
70   -<p>
71   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72   -</p>
73   -<p>
74   -This program is free software: you can redistribute it and/or modify it
75   -under the terms of the GNU General Public License as published by the Free
76   -Software Foundation, either version 3 of the License, or (at your option)
77   -any later version.
78   -</p>
79   -<p>
80   -This program is distributed in the hope that it will be useful, but WITHOUT
81   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83   -more details.
84   -</p>
85   -<p>
86   -You should have received a copy of the GNU General Public License along
87   -with this program. If not, see <<a
88   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89   -</p>
90   -<hr size="1"></hr><p>
91   -This file is a part of an Information Retrieval oriented Ruby library
92   -</p>
93   -<p>
94   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
95   -</p>
96   -<p>
97   -This program is free software: you can redistribute it and/or modify it
98   -under the terms of the GNU General Public License as published by the Free
99   -Software Foundation, either version 3 of the License, or (at your option)
100   -any later version.
101   -</p>
102   -<p>
103   -This program is distributed in the hope that it will be useful, but WITHOUT
104   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
105   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
106   -more details.
107   -</p>
108   -<p>
109   -You should have received a copy of the GNU General Public License along
110   -with this program. If not, see <<a
111   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
112   -</p>
113   -<hr size="1"></hr><p>
114   -This file is a part of an Information Retrieval oriented Ruby library
115   -</p>
116   -<p>
117   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
118   -</p>
119   -<p>
120   -This program is free software: you can redistribute it and/or modify it
121   -under the terms of the GNU General Public License as published by the Free
122   -Software Foundation, either version 3 of the License, or (at your option)
123   -any later version.
124   -</p>
125   -<p>
126   -This program is distributed in the hope that it will be useful, but WITHOUT
127   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
128   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
129   -more details.
130   -</p>
131   -<p>
132   -You should have received a copy of the GNU General Public License along
133   -with this program. If not, see <<a
134   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
135   -</p>
136   -<hr size="1"></hr><p>
137   -This file is a part of an Information Retrieval oriented Ruby library
138   -</p>
139   -<p>
140   -Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
141   -</p>
142   -<p>
143   -This program is free software: you can redistribute it and/or modify it
144   -under the terms of the GNU General Public License as published by the Free
145   -Software Foundation, either version 3 of the License, or (at your option)
146   -any later version.
147   -</p>
148   -<p>
149   -This program is distributed in the hope that it will be useful, but WITHOUT
150   -ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
151   -FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
152   -more details.
153   -</p>
154   -<p>
155   -You should have received a copy of the GNU General Public License along
156   -with this program. If not, see <<a
157   -href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
158   -</p>
159   -<hr size="1"></hr><p>
160   -General module for many purposes related to Information Retrieval.
161   -</p>
162   -
163   - </div>
164 65  
165 66 </div>
166 67  
doc/fr_class_index.html
... ... @@ -17,39 +17,39 @@
17 17 <h1 class="section-bar">Classes</h1>
18 18 <div id="index-entries">
19 19  
20   - <a href="classes/RIR.html">RIR</a><br />
  20 + <a href="classes/Corpus.html">Corpus</a><br />
21 21  
22   - <a href="classes/RIR/Corpus.html">RIR::Corpus</a><br />
  22 + <a href="classes/Indri.html">Indri</a><br />
23 23  
24   - <a href="classes/RIR/Document.html">RIR::Document</a><br />
  24 + <a href="classes/Indri/IndriQuery.html">Indri::IndriQuery</a><br />
25 25  
26   - <a href="classes/RIR/Indri.html">RIR::Indri</a><br />
  26 + <a href="classes/Indri/Parameters.html">Indri::Parameters</a><br />
27 27  
28   - <a href="classes/RIR/Indri/IndriQuery.html">RIR::Indri::IndriQuery</a><br />
  28 + <a href="classes/Query.html">Query</a><br />
29 29  
30   - <a href="classes/RIR/Indri/Parameters.html">RIR::Indri::Parameters</a><br />
  30 + <a href="classes/RIR.html">RIR</a><br />
31 31  
32   - <a href="classes/RIR/Query.html">RIR::Query</a><br />
  32 + <a href="classes/RIR/Document.html">RIR::Document</a><br />
33 33  
34   - <a href="classes/RIR/TreeTagger.html">RIR::TreeTagger</a><br />
  34 + <a href="classes/RIR/WebDocument.html">RIR::WebDocument</a><br />
35 35  
36   - <a href="classes/RIR/TreeTagger/Chunk.html">RIR::TreeTagger::Chunk</a><br />
  36 + <a href="classes/RIR/WikipediaPage.html">RIR::WikipediaPage</a><br />
37 37  
38   - <a href="classes/RIR/TreeTagger/TaggerChunker.html">RIR::TreeTagger::TaggerChunker</a><br />
  38 + <a href="classes/Regexp.html">Regexp</a><br />
39 39  
40   - <a href="classes/RIR/TreeTagger/TaggerChunkerEnglish.html">RIR::TreeTagger::TaggerChunkerEnglish</a><br />
  40 + <a href="classes/String.html">String</a><br />
41 41  
42   - <a href="classes/RIR/TreeTagger/TaggerChunkerFrench.html">RIR::TreeTagger::TaggerChunkerFrench</a><br />
  42 + <a href="classes/TreeTagger.html">TreeTagger</a><br />
43 43  
44   - <a href="classes/RIR/TreeTagger/TaggerChunkerGerman.html">RIR::TreeTagger::TaggerChunkerGerman</a><br />
  44 + <a href="classes/TreeTagger/Chunk.html">TreeTagger::Chunk</a><br />
45 45  
46   - <a href="classes/RIR/WebDocument.html">RIR::WebDocument</a><br />
  46 + <a href="classes/TreeTagger/TaggerChunker.html">TreeTagger::TaggerChunker</a><br />
47 47  
48   - <a href="classes/RIR/WikipediaPage.html">RIR::WikipediaPage</a><br />
  48 + <a href="classes/TreeTagger/TaggerChunkerEnglish.html">TreeTagger::TaggerChunkerEnglish</a><br />
49 49  
50   - <a href="classes/Regexp.html">Regexp</a><br />
  50 + <a href="classes/TreeTagger/TaggerChunkerFrench.html">TreeTagger::TaggerChunkerFrench</a><br />
51 51  
52   - <a href="classes/String.html">String</a><br />
  52 + <a href="classes/TreeTagger/TaggerChunkerGerman.html">TreeTagger::TaggerChunkerGerman</a><br />
53 53  
54 54 </div>
55 55 </div>
doc/fr_file_index.html
... ... @@ -17,8 +17,6 @@
17 17 <h1 class="section-bar">Files</h1>
18 18 <div id="index-entries">
19 19  
20   - <a href="files/lib/rir_rb.html">lib/rir.rb</a><br />
21   -
22 20 <a href="files/lib/rir/corpus_rb.html">lib/rir/corpus.rb</a><br />
23 21  
24 22 <a href="files/lib/rir/document_rb.html">lib/rir/document.rb</a><br />
doc/fr_method_index.html
... ... @@ -21,9 +21,9 @@
21 21  
22 22 <a href="classes/RIR/Document.html#M000025">entropy (RIR::Document)</a><br />
23 23  
24   - <a href="classes/String.html#M000012">extract_xmltags_values (String)</a><br />
  24 + <a href="classes/String.html#M000014">extract_xmltags_values (String)</a><br />
25 25  
26   - <a href="classes/RIR/Corpus.html#M000021">files (RIR::Corpus)</a><br />
  26 + <a href="classes/Corpus.html#M000002">files (Corpus)</a><br />
27 27  
28 28 <a href="classes/RIR/Document.html#M000022">format_words (RIR::Document)</a><br />
29 29  
30 30  
31 31  
32 32  
33 33  
34 34  
35 35  
36 36  
37 37  
38 38  
39 39  
40 40  
41 41  
42 42  
43 43  
44 44  
45 45  
46 46  
47 47  
... ... @@ -31,55 +31,55 @@
31 31  
32 32 <a href="classes/RIR/WikipediaPage.html#M000031">get_url (RIR::WikipediaPage)</a><br />
33 33  
34   - <a href="classes/String.html#M000002">is_stopword? (String)</a><br />
  34 + <a href="classes/String.html#M000004">is_stopword? (String)</a><br />
35 35  
36   - <a href="classes/Regexp.html#M000001">negated (Regexp)</a><br />
  36 + <a href="classes/Regexp.html#M000003">negated (Regexp)</a><br />
37 37  
38 38 <a href="classes/RIR/Document.html#M000027">new (RIR::Document)</a><br />
39 39  
40 40 <a href="classes/RIR/WebDocument.html#M000029">new (RIR::WebDocument)</a><br />
41 41  
42   - <a href="classes/RIR/Indri/IndriQuery.html#M000018">new (RIR::Indri::IndriQuery)</a><br />
  42 + <a href="classes/Indri/IndriQuery.html#M000020">new (Indri::IndriQuery)</a><br />
43 43  
44   - <a href="classes/RIR/Corpus.html#M000020">new (RIR::Corpus)</a><br />
  44 + <a href="classes/Indri/Parameters.html#M000018">new (Indri::Parameters)</a><br />
45 45  
46   - <a href="classes/RIR/TreeTagger/TaggerChunker.html#M000014">new (RIR::TreeTagger::TaggerChunker)</a><br />
  46 + <a href="classes/Corpus.html#M000001">new (Corpus)</a><br />
47 47  
48   - <a href="classes/RIR/Indri/Parameters.html#M000016">new (RIR::Indri::Parameters)</a><br />
  48 + <a href="classes/TreeTagger/TaggerChunker.html#M000016">new (TreeTagger::TaggerChunker)</a><br />
49 49  
50   - <a href="classes/RIR/TreeTagger/Chunk.html#M000015">new (RIR::TreeTagger::Chunk)</a><br />
  50 + <a href="classes/TreeTagger/Chunk.html#M000017">new (TreeTagger::Chunk)</a><br />
51 51  
52 52 <a href="classes/RIR/Document.html#M000023">ngrams (RIR::Document)</a><br />
53 53  
54   - <a href="classes/RIR/TreeTagger/TaggerChunker.html#M000013">parse (RIR::TreeTagger::TaggerChunker)</a><br />
  54 + <a href="classes/TreeTagger/TaggerChunker.html#M000015">parse (TreeTagger::TaggerChunker)</a><br />
55 55  
56   - <a href="classes/String.html#M000003">remove_special_characters (String)</a><br />
  56 + <a href="classes/String.html#M000005">remove_special_characters (String)</a><br />
57 57  
58 58 <a href="classes/RIR/WikipediaPage.html#M000032">search_homepage (RIR::WikipediaPage)</a><br />
59 59  
60 60 <a href="classes/RIR/WikipediaPage.html#M000030">search_wikipedia_titles (RIR::WikipediaPage)</a><br />
61 61  
62   - <a href="classes/String.html#M000007">strip_javascripts (String)</a><br />
  62 + <a href="classes/String.html#M000009">strip_javascripts (String)</a><br />
63 63  
64   - <a href="classes/String.html#M000006">strip_javascripts! (String)</a><br />
  64 + <a href="classes/String.html#M000008">strip_javascripts! (String)</a><br />
65 65  
66   - <a href="classes/String.html#M000011">strip_punctuation (String)</a><br />
  66 + <a href="classes/String.html#M000013">strip_punctuation (String)</a><br />
67 67  
68   - <a href="classes/String.html#M000010">strip_punctuation! (String)</a><br />
  68 + <a href="classes/String.html#M000012">strip_punctuation! (String)</a><br />
69 69  
70   - <a href="classes/String.html#M000009">strip_stylesheets (String)</a><br />
  70 + <a href="classes/String.html#M000011">strip_stylesheets (String)</a><br />
71 71  
72   - <a href="classes/String.html#M000008">strip_stylesheets! (String)</a><br />
  72 + <a href="classes/String.html#M000010">strip_stylesheets! (String)</a><br />
73 73  
74   - <a href="classes/String.html#M000005">strip_xml_tags (String)</a><br />
  74 + <a href="classes/String.html#M000007">strip_xml_tags (String)</a><br />
75 75  
76   - <a href="classes/String.html#M000004">strip_xml_tags! (String)</a><br />
  76 + <a href="classes/String.html#M000006">strip_xml_tags! (String)</a><br />
77 77  
78 78 <a href="classes/RIR/Document.html#M000026">tf (RIR::Document)</a><br />
79 79  
80   - <a href="classes/RIR/Indri/IndriQuery.html#M000019">to_s (RIR::Indri::IndriQuery)</a><br />
  80 + <a href="classes/Indri/Parameters.html#M000019">to_s (Indri::Parameters)</a><br />
81 81  
82   - <a href="classes/RIR/Indri/Parameters.html#M000017">to_s (RIR::Indri::Parameters)</a><br />
  82 + <a href="classes/Indri/IndriQuery.html#M000021">to_s (Indri::IndriQuery)</a><br />
83 83  
84 84 </div>
85 85 </div>
... ... @@ -16,7 +16,7 @@
16 16 <frame src="fr_class_index.html" name="Classes" />
17 17 <frame src="fr_method_index.html" name="Methods" />
18 18 </frameset>
19   - <frame src="files/lib/rir_rb.html" name="docwin" />
  19 + <frame src="files/lib/rir/ttagger_rb.html" name="docwin" />
20 20 </frameset>
21 21 </html>
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 7  
7 8  
8 9  
... ... @@ -16,26 +17,23 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
19 21  
20   -module RIR
  22 +class Corpus
  23 + attr_accessor :path
21 24  
22   - class Corpus
23   - attr_accessor :path
24   -
25   - def initialize(path)
26   - @path = path.chomp "/"
27   - end
28   -
29   - # Recursively outputs all files in +self.path+.
30   - # WARNING ! This function may take a lot of time if many
31   - # files are in subdirectories.
32   - #
33   - # c = Corpus.new "my/path"
34   - # c.files # => ["README.txt", "lib/code.rb"]
35   - def files
36   - Dir["#{@path}/**/*.*"]
37   - end
  25 + def initialize(path)
  26 + @path = path.chomp "/"
38 27 end
39 28  
  29 + # Recursively outputs all files in +self.path+.
  30 + # WARNING ! This function may take a lot of time if many
  31 + # files are in subdirectories.
  32 + #
  33 + # c = Corpus.new "my/path"
  34 + # c.files # => ["README.txt", "lib/code.rb"]
  35 + def files
  36 + Dir["#{@path}/**/*.*"]
  37 + end
40 38 end
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
... ... @@ -16,6 +17,8 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
  21 +
19 22  
20 23 # General module for many purposes related to Information Retrieval.
21 24 module RIR
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 7  
7 8  
8 9  
9 10  
10 11  
11 12  
12 13  
13 14  
14 15  
15 16  
16 17  
17 18  
18 19  
19 20  
... ... @@ -16,72 +17,70 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
19 21  
20   -module RIR
  22 +class Query
  23 +end
21 24  
22   - class Query
23   - end
  25 +module Indri
24 26  
25   - module Indri
  27 + class Parameters
  28 + attr_accessor :index_path, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline
26 29  
27   - class Parameters
28   - attr_accessor :index_path, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline
  30 + def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false)
  31 + @index_path = corpus
  32 + @memory = mem
  33 + @count = count
  34 + @offset = offset
  35 + @run_id = run_id
  36 + @print_query = print_query ? "true" : "false"
  37 + @print_docs = print_docs ? "true" : "false"
  38 + end
29 39  
30   - def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false)
31   - @index_path = corpus
32   - @memory = mem
33   - @count = count
34   - @offset = offset
35   - @run_id = run_id
36   - @print_query = print_query ? "true" : "false"
37   - @print_docs = print_docs ? "true" : "false"
  40 + def to_s
  41 + h = "<parameters>\n"
  42 + h += "<memory>#{@memory}</memory>\n"
  43 + h += "<index>#{@index_path}</index>\n"
  44 + h += "<count>#{@count}</count>\n"
  45 + unless @baseline.nil?
  46 + h += "<baseline>#{@baseline}</baseline>\n"
  47 + else
  48 + h += "<rule>#{@rule}</rule>\n"
38 49 end
  50 + h += "<queryOffset>#{@offset}</queryOffset>\n"
  51 + h += "<runID>#{@run_id}</runID>\n"
  52 + h += "<printQuery>#{@print_query}</printQuery>\n"
  53 + h += "<printDocuments>#{@print_docs}</printDocuments>\n"
39 54  
40   - def to_s
41   - h = "<parameters>\n"
42   - h += "<memory>#{@memory}</memory>\n"
43   - h += "<index>#{@index_path}</index>\n"
44   - h += "<count>#{@count}</count>\n"
45   - unless @baseline.nil?
46   - h += "<baseline>#{@baseline}</baseline>\n"
47   - else
48   - h += "<rule>#{@rule}</rule>\n"
49   - end
50   - h += "<queryOffset>#{@offset}</queryOffset>\n"
51   - h += "<runID>#{@run_id}</runID>\n"
52   - h += "<printQuery>#{@print_query}</printQuery>\n"
53   - h += "<printDocuments>#{@print_docs}</printDocuments>\n"
54   -
55   - h
56   - end
  55 + h
57 56 end
58   -
59   - class IndriQuery < Query
60   - attr_accessor :id, :query, :params, :rule
  57 + end
  58 +
  59 + class IndriQuery < Query
  60 + attr_accessor :id, :query, :params, :rule
61 61  
62   - def initialize(id,query,params)
63   - @params = params
64   - # Here we set the default retrieval model as Language Modeling
65   - # with a Dirichlet smoothing at 2500.
66   - # TODO: maybe a Rule class...
67   - @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil?
  62 + def initialize(id,query,params)
  63 + @params = params
  64 + # Here we set the default retrieval model as Language Modeling
  65 + # with a Dirichlet smoothing at 2500.
  66 + # TODO: maybe a Rule class...
  67 + @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil?
68 68  
69   - @id = id
70   - @query = query
71   - end
  69 + @id = id
  70 + @query = query
  71 + end
72 72  
73   - def to_s
74   - h = @params.to_s
75   - h += "<query>\n"
76   - h += "<number>#{@id}</number>\n"
77   - h += "<text>#{@query}</text>\n"
78   - h += "</query>\n"
79   - h += "</parameters>"
  73 + def to_s
  74 + h = @params.to_s
  75 + h += "<query>\n"
  76 + h += "<number>#{@id}</number>\n"
  77 + h += "<text>#{@query}</text>\n"
  78 + h += "</query>\n"
  79 + h += "</parameters>"
80 80  
81   - h
82   - end
  81 + h
83 82 end
84   -
85 83 end
  84 +
86 85 end
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
... ... @@ -16,6 +17,7 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
19 21  
20 22 class Regexp
21 23  
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
... ... @@ -16,6 +17,7 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
19 21  
20 22 module RIR
21 23  
1 1 #!/usr/bin/env ruby
2 2  
  3 +#--
3 4 # This file is a part of an Information Retrieval oriented Ruby library
4 5 #
5 6 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 7  
7 8  
8 9  
9 10  
10 11  
11 12  
12 13  
13 14  
14 15  
15 16  
16 17  
17 18  
18 19  
19 20  
20 21  
21 22  
... ... @@ -16,79 +17,80 @@
16 17 #
17 18 # You should have received a copy of the GNU General Public License
18 19 # along with this program. If not, see <http://www.gnu.org/licenses/>.
  20 +#++
19 21  
20   -module RIR
21 22  
22   - # TreeTagger-related stuff module.
23   - #
24   - # See http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html
25   - module TreeTagger
26   -
27   - # This class handles generic parsing of tagger-chunker outputs.
28   - class TaggerChunker
29   - attr_reader :chunks, :file
  23 +# TreeTagger-related stuff module.
  24 +#
  25 +# See http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html
  26 +module TreeTagger
  27 +
  28 + # This class handles generic parsing of tagger-chunker outputs.
  29 + class TaggerChunker
  30 + attr_reader :chunks, :file
30 31  
31 32  
32   - # Parses a tagger-chunker output and returns an Array of Chunk.
33   - def self.parse chunk_lines
34   - open = false
35   - tag = nil
  33 + # Parses a tagger-chunker output and returns an Array of Chunk.
  34 + def self.parse chunk_lines
  35 + open = false
  36 + tag = nil
36 37  
37   - chunks = []
38   - words = []
  38 + chunks = []
  39 + words = []
39 40  
40   - chunk_lines.each do |l|
41   - l.chomp!
42   - if l =~ /^<\w+>$/
43   - open = true
44   - tag = l
45   - elsif l =~ /^<\/\w+>$/
46   - if !words.empty? && open && l == tag.sub(/</, '</')
47   - open = false
48   - chunks.push Chunk.new(words.join(" "), tag)
49   - words.clear
50   - else
51   - next
52   - end
  41 + chunk_lines.each do |l|
  42 + l.chomp!
  43 + if l =~ /^<\w+>$/
  44 + open = true
  45 + tag = l
  46 + elsif l =~ /^<\/\w+>$/
  47 + if !words.empty? && open && l == tag.sub(/</, '</')
  48 + open = false
  49 + chunks.push Chunk.new(words.join(" "), tag)
  50 + words.clear
53 51 else
54   - words.push(l.split.first)
  52 + next
55 53 end
  54 + else
  55 + words.push(l.split.first)
56 56 end
57   -
58   - chunks
59 57 end
60 58  
61   - # Initializes parsing. +chunk_file+ is the output of +tagger-chunker-+ and must
62   - # be a valid path to the file.
63   - #
64   - # TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...>
65   - def initialize chunk_file
66   - @chunks = TaggerChunker.parse File.open(chunk_file).readlines
67   - end
68   -
  59 + chunks
69 60 end
70 61  
71   - class TaggerChunkerEnglish < TaggerChunker
  62 + # Initializes parsing. +chunk_file+ is the output of +tagger-chunker-+ and must
  63 + # be a valid path to the file.
  64 + #
  65 + # TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...>
  66 + def initialize chunk_file
  67 + @chunks = TaggerChunker.parse File.open(chunk_file).readlines
72 68 end
73 69  
74   - class TaggerChunkerFrench < TaggerChunker
75   - end
  70 + end
76 71  
77   - class TaggerChunkerGerman < TaggerChunker
78   - end
  72 + class TaggerChunkerEnglish < TaggerChunker
  73 + end
79 74  
80   - # Represents a Chunk extracted when parsing a TaggerChunker file.
81   - class Chunk
82   - attr_reader :words, :tag
  75 + class TaggerChunkerFrench < TaggerChunker
  76 + end
83 77  
84   - # +str+ are whitespace-separated terms.
85   - # +tag+ see : ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt
86   - def initialize str,tag
87   - @words = str.split
88   - @tag = tag[1..-2]
89   - end
90   - end
  78 + class TaggerChunkerGerman < TaggerChunker
  79 + end
91 80  
  81 + # Represents a Chunk extracted when parsing a TaggerChunker file.
  82 + class Chunk
  83 + attr_reader :words, :tag
  84 +
  85 + # Creates a Chunk.
  86 + #
  87 + # * +str+ are whitespace-separated terms.
  88 + # * +tag+ see : ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt
  89 + def initialize str,tag
  90 + @words = str.split
  91 + @tag = tag[1..-2]
  92 + end
92 93 end
  94 +
93 95 end