Commit bc18b961bdd99fd9f3bb51dc8fd6e88757de3eb8

Authored by Romain Deveaud
1 parent 3e81fa06a9
Exists in master

more doc

Showing 25 changed files with 316 additions and 85 deletions Side-by-side Diff

doc/classes/RIR.html
... ... @@ -53,9 +53,9 @@
53 53 <td>
54 54  
55 55  
56   - <a href="../files/lib/rir/string_rb.html">
  56 + <a href="../files/lib/rir/corpus_rb.html">
57 57  
58   - lib/rir/string.rb
  58 + lib/rir/corpus.rb
59 59  
60 60 </a>
61 61  
62 62  
63 63  
... ... @@ -63,15 +63,25 @@
63 63 <br />
64 64  
65 65  
66   - <a href="../files/lib/rir/document_rb.html">
  66 + <a href="../files/lib/rir/query_rb.html">
67 67  
68   - lib/rir/document.rb
  68 + lib/rir/query.rb
69 69  
70 70 </a>
71 71  
72 72  
73 73 <br />
74 74  
  75 +
  76 + <a href="../files/lib/rir/string_rb.html">
  77 +
  78 + lib/rir/string.rb
  79 +
  80 + </a>
  81 +
  82 +
  83 + <br />
  84 +
75 85 </td>
76 86 </tr>
77 87  
78 88  
79 89  
80 90  
... ... @@ -86,11 +96,74 @@
86 96  
87 97 <div id="description">
88 98 <p>
89   -General module for many purposes related to Information Retrieval.
  99 +This file is a part of an Information Retrieval oriented Ruby library
90 100 </p>
  101 +<p>
  102 +Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
  103 +</p>
  104 +<p>
  105 +This program is free software: you can redistribute it and/or modify it
  106 +under the terms of the GNU General Public License as published by the Free
  107 +Software Foundation, either version 3 of the License, or (at your option)
  108 +any later version.
  109 +</p>
  110 +<p>
  111 +This program is distributed in the hope that it will be useful, but WITHOUT
  112 +ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  113 +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
  114 +more details.
  115 +</p>
  116 +<p>
  117 +You should have received a copy of the GNU General Public License along
  118 +with this program. If not, see <<a
  119 +href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
  120 +</p>
91 121 <hr size="1"></hr><p>
92   -General module for many purposes related to Information Retrieval.
  122 +This file is a part of an Information Retrieval oriented Ruby library
93 123 </p>
  124 +<p>
  125 +Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
  126 +</p>
  127 +<p>
  128 +This program is free software: you can redistribute it and/or modify it
  129 +under the terms of the GNU General Public License as published by the Free
  130 +Software Foundation, either version 3 of the License, or (at your option)
  131 +any later version.
  132 +</p>
  133 +<p>
  134 +This program is distributed in the hope that it will be useful, but WITHOUT
  135 +ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  136 +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
  137 +more details.
  138 +</p>
  139 +<p>
  140 +You should have received a copy of the GNU General Public License along
  141 +with this program. If not, see <<a
  142 +href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
  143 +</p>
  144 +<hr size="1"></hr><p>
  145 +This file is a part of an Information Retrieval oriented Ruby library
  146 +</p>
  147 +<p>
  148 +Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
  149 +</p>
  150 +<p>
  151 +This program is free software: you can redistribute it and/or modify it
  152 +under the terms of the GNU General Public License as published by the Free
  153 +Software Foundation, either version 3 of the License, or (at your option)
  154 +any later version.
  155 +</p>
  156 +<p>
  157 +This program is distributed in the hope that it will be useful, but WITHOUT
  158 +ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
  159 +FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
  160 +more details.
  161 +</p>
  162 +<p>
  163 +You should have received a copy of the GNU General Public License along
  164 +with this program. If not, see <<a
  165 +href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
  166 +</p>
94 167  
95 168 </div>
96 169  
... ... @@ -106,9 +179,9 @@
106 179 <div id="class-list">
107 180 <h3 class="section-bar">Classes and Modules</h3>
108 181  
109   - Class <a href="RIR/Document.html" class="link">RIR::Document</a><br />
110   -Class <a href="RIR/WebDocument.html" class="link">RIR::WebDocument</a><br />
111   -Class <a href="RIR/WikipediaPage.html" class="link">RIR::WikipediaPage</a><br />
  182 + Module <a href="RIR/Indri.html" class="link">RIR::Indri</a><br />
  183 +Class <a href="RIR/Corpus.html" class="link">RIR::Corpus</a><br />
  184 +Class <a href="RIR/Query.html" class="link">RIR::Query</a><br />
112 185  
113 186 </div>
114 187  
doc/classes/RIR/Document.html
... ... @@ -99,15 +99,15 @@
99 99  
100 100 <div class="name-list">
101 101  
102   - <a href="#M000012">count_words</a>&nbsp;&nbsp;
  102 + <a href="#M000021">count_words</a>&nbsp;&nbsp;
103 103  
104   - <a href="#M000013">entropy</a>&nbsp;&nbsp;
  104 + <a href="#M000022">entropy</a>&nbsp;&nbsp;
105 105  
106   - <a href="#M000010">format_words</a>&nbsp;&nbsp;
  106 + <a href="#M000019">format_words</a>&nbsp;&nbsp;
107 107  
108   - <a href="#M000014">new</a>&nbsp;&nbsp;
  108 + <a href="#M000023">new</a>&nbsp;&nbsp;
109 109  
110   - <a href="#M000011">ngrams</a>&nbsp;&nbsp;
  110 + <a href="#M000020">ngrams</a>&nbsp;&nbsp;
111 111  
112 112 </div>
113 113 </div>
114 114  
... ... @@ -154,13 +154,13 @@
154 154 <h3 class="section-bar">Public Class methods</h3>
155 155  
156 156  
157   - <div id="method-M000014" class="method-detail">
158   - <a name="M000014"></a>
  157 + <div id="method-M000023" class="method-detail">
  158 + <a name="M000023"></a>
159 159  
160 160 <div class="method-heading">
161 161  
162   - <a href="Document.src/M000014.html" target="Code" class="method-signature"
163   - onclick="popupCode('Document.src/M000014.html');return false;">
  162 + <a href="Document.src/M000023.html" target="Code" class="method-signature"
  163 + onclick="popupCode('Document.src/M000023.html');return false;">
164 164  
165 165 <span class="method-name">new</span><span class="method-args">(content)</span>
166 166  
167 167  
... ... @@ -177,13 +177,13 @@
177 177 <h3 class="section-bar">Public Instance methods</h3>
178 178  
179 179  
180   - <div id="method-M000012" class="method-detail">
181   - <a name="M000012"></a>
  180 + <div id="method-M000021" class="method-detail">
  181 + <a name="M000021"></a>
182 182  
183 183 <div class="method-heading">
184 184  
185   - <a href="Document.src/M000012.html" target="Code" class="method-signature"
186   - onclick="popupCode('Document.src/M000012.html');return false;">
  185 + <a href="Document.src/M000021.html" target="Code" class="method-signature"
  186 + onclick="popupCode('Document.src/M000021.html');return false;">
187 187  
188 188 <span class="method-name">count_words</span><span class="method-args">()</span>
189 189  
190 190  
... ... @@ -205,13 +205,13 @@
205 205 </div>
206 206  
207 207  
208   - <div id="method-M000013" class="method-detail">
209   - <a name="M000013"></a>
  208 + <div id="method-M000022" class="method-detail">
  209 + <a name="M000022"></a>
210 210  
211 211 <div class="method-heading">
212 212  
213   - <a href="Document.src/M000013.html" target="Code" class="method-signature"
214   - onclick="popupCode('Document.src/M000013.html');return false;">
  213 + <a href="Document.src/M000022.html" target="Code" class="method-signature"
  214 + onclick="popupCode('Document.src/M000022.html');return false;">
215 215  
216 216 <span class="method-name">entropy</span><span class="method-args">(s)</span>
217 217  
218 218  
... ... @@ -236,13 +236,13 @@
236 236 </div>
237 237  
238 238  
239   - <div id="method-M000011" class="method-detail">
240   - <a name="M000011"></a>
  239 + <div id="method-M000020" class="method-detail">
  240 + <a name="M000020"></a>
241 241  
242 242 <div class="method-heading">
243 243  
244   - <a href="Document.src/M000011.html" target="Code" class="method-signature"
245   - onclick="popupCode('Document.src/M000011.html');return false;">
  244 + <a href="Document.src/M000020.html" target="Code" class="method-signature"
  245 + onclick="popupCode('Document.src/M000020.html');return false;">
246 246  
247 247 <span class="method-name">ngrams</span><span class="method-args">(n)</span>
248 248  
249 249  
... ... @@ -267,13 +267,13 @@
267 267 <h3 class="section-bar">Protected Instance methods</h3>
268 268  
269 269  
270   - <div id="method-M000010" class="method-detail">
271   - <a name="M000010"></a>
  270 + <div id="method-M000019" class="method-detail">
  271 + <a name="M000019"></a>
272 272  
273 273 <div class="method-heading">
274 274  
275   - <a href="Document.src/M000010.html" target="Code" class="method-signature"
276   - onclick="popupCode('Document.src/M000010.html');return false;">
  275 + <a href="Document.src/M000019.html" target="Code" class="method-signature"
  276 + onclick="popupCode('Document.src/M000019.html');return false;">
277 277  
278 278 <span class="method-name">format_words</span><span class="method-args">()</span>
279 279  
doc/classes/RIR/WebDocument.html
... ... @@ -103,9 +103,9 @@
103 103  
104 104 <div class="name-list">
105 105  
106   - <a href="#M000015">get_content</a>&nbsp;&nbsp;
  106 + <a href="#M000024">get_content</a>&nbsp;&nbsp;
107 107  
108   - <a href="#M000016">new</a>&nbsp;&nbsp;
  108 + <a href="#M000025">new</a>&nbsp;&nbsp;
109 109  
110 110 </div>
111 111 </div>
112 112  
... ... @@ -144,13 +144,13 @@
144 144 <h3 class="section-bar">Public Class methods</h3>
145 145  
146 146  
147   - <div id="method-M000015" class="method-detail">
148   - <a name="M000015"></a>
  147 + <div id="method-M000024" class="method-detail">
  148 + <a name="M000024"></a>
149 149  
150 150 <div class="method-heading">
151 151  
152   - <a href="WebDocument.src/M000015.html" target="Code" class="method-signature"
153   - onclick="popupCode('WebDocument.src/M000015.html');return false;">
  152 + <a href="WebDocument.src/M000024.html" target="Code" class="method-signature"
  153 + onclick="popupCode('WebDocument.src/M000024.html');return false;">
154 154  
155 155 <span class="method-name">get_content</span><span class="method-args">(url)</span>
156 156  
157 157  
... ... @@ -168,13 +168,13 @@
168 168 </div>
169 169  
170 170  
171   - <div id="method-M000016" class="method-detail">
172   - <a name="M000016"></a>
  171 + <div id="method-M000025" class="method-detail">
  172 + <a name="M000025"></a>
173 173  
174 174 <div class="method-heading">
175 175  
176   - <a href="WebDocument.src/M000016.html" target="Code" class="method-signature"
177   - onclick="popupCode('WebDocument.src/M000016.html');return false;">
  176 + <a href="WebDocument.src/M000025.html" target="Code" class="method-signature"
  177 + onclick="popupCode('WebDocument.src/M000025.html');return false;">
178 178  
179 179 <span class="method-name">new</span><span class="method-args">(url)</span>
180 180  
doc/classes/RIR/WikipediaPage.html
... ... @@ -98,6 +98,20 @@
98 98 </div>
99 99  
100 100  
  101 + <div id="method-list">
  102 + <h3 class="section-bar">Methods</h3>
  103 +
  104 + <div class="name-list">
  105 +
  106 + <a href="#M000027">get_url</a>&nbsp;&nbsp;
  107 +
  108 + <a href="#M000028">search_homepage</a>&nbsp;&nbsp;
  109 +
  110 + <a href="#M000026">search_wikipedia_titles</a>&nbsp;&nbsp;
  111 +
  112 + </div>
  113 + </div>
  114 +
101 115 </div>
102 116  
103 117 <!-- if includes -->
... ... @@ -108,6 +122,74 @@
108 122  
109 123  
110 124 <!-- if method_list -->
  125 +
  126 + <div id="methods">
  127 +
  128 + <h3 class="section-bar">Public Class methods</h3>
  129 +
  130 +
  131 + <div id="method-M000027" class="method-detail">
  132 + <a name="M000027"></a>
  133 +
  134 + <div class="method-heading">
  135 +
  136 + <a href="WikipediaPage.src/M000027.html" target="Code" class="method-signature"
  137 + onclick="popupCode('WikipediaPage.src/M000027.html');return false;">
  138 +
  139 + <span class="method-name">get_url</span><span class="method-args">(name)</span>
  140 +
  141 + </a>
  142 +
  143 + </div>
  144 +
  145 + <div class="method-description">
  146 +
  147 + </div>
  148 + </div>
  149 +
  150 +
  151 + <div id="method-M000028" class="method-detail">
  152 + <a name="M000028"></a>
  153 +
  154 + <div class="method-heading">
  155 +
  156 + <a href="WikipediaPage.src/M000028.html" target="Code" class="method-signature"
  157 + onclick="popupCode('WikipediaPage.src/M000028.html');return false;">
  158 +
  159 + <span class="method-name">search_homepage</span><span class="method-args">(name)</span>
  160 +
  161 + </a>
  162 +
  163 + </div>
  164 +
  165 + <div class="method-description">
  166 +
  167 + </div>
  168 + </div>
  169 +
  170 +
  171 + <div id="method-M000026" class="method-detail">
  172 + <a name="M000026"></a>
  173 +
  174 + <div class="method-heading">
  175 +
  176 + <a href="WikipediaPage.src/M000026.html" target="Code" class="method-signature"
  177 + onclick="popupCode('WikipediaPage.src/M000026.html');return false;">
  178 +
  179 + <span class="method-name">search_wikipedia_titles</span><span class="method-args">(name)</span>
  180 +
  181 + </a>
  182 +
  183 + </div>
  184 +
  185 + <div class="method-description">
  186 +
  187 + </div>
  188 + </div>
  189 +
  190 +
  191 +
  192 + </div>
111 193  
112 194  
113 195  
doc/classes/String.html
... ... @@ -99,7 +99,7 @@
99 99  
100 100 <div class="name-list">
101 101  
102   - <a href="#M000009">extract_xmltags_values</a>&nbsp;&nbsp;
  102 + <a href="#M000011">extract_xmltags_values</a>&nbsp;&nbsp;
103 103  
104 104 <a href="#M000001">is_stopword?</a>&nbsp;&nbsp;
105 105  
... ... @@ -109,6 +109,10 @@
109 109  
110 110 <a href="#M000005">strip_javascripts!</a>&nbsp;&nbsp;
111 111  
  112 + <a href="#M000010">strip_punctuation</a>&nbsp;&nbsp;
  113 +
  114 + <a href="#M000009">strip_punctuation!</a>&nbsp;&nbsp;
  115 +
112 116 <a href="#M000008">strip_stylesheets</a>&nbsp;&nbsp;
113 117  
114 118 <a href="#M000007">strip_stylesheets!</a>&nbsp;&nbsp;
115 119  
... ... @@ -146,13 +150,13 @@
146 150 <h3 class="section-bar">Public Instance methods</h3>
147 151  
148 152  
149   - <div id="method-M000009" class="method-detail">
150   - <a name="M000009"></a>
  153 + <div id="method-M000011" class="method-detail">
  154 + <a name="M000011"></a>
151 155  
152 156 <div class="method-heading">
153 157  
154   - <a href="String.src/M000009.html" target="Code" class="method-signature"
155   - onclick="popupCode('String.src/M000009.html');return false;">
  158 + <a href="String.src/M000011.html" target="Code" class="method-signature"
  159 + onclick="popupCode('String.src/M000011.html');return false;">
156 160  
157 161 <span class="method-name">extract_xmltags_values</span><span class="method-args">(tag_name)</span>
158 162  
... ... @@ -284,6 +288,63 @@
284 288 test&quot;
285 289 s.strip_javascripts!
286 290 s #=&gt; &quot;test&quot;
  291 +</pre>
  292 +
  293 + </div>
  294 + </div>
  295 +
  296 +
  297 + <div id="method-M000010" class="method-detail">
  298 + <a name="M000010"></a>
  299 +
  300 + <div class="method-heading">
  301 +
  302 + <a href="String.src/M000010.html" target="Code" class="method-signature"
  303 + onclick="popupCode('String.src/M000010.html');return false;">
  304 +
  305 + <span class="method-name">strip_punctuation</span><span class="method-args">()</span>
  306 +
  307 + </a>
  308 +
  309 + </div>
  310 +
  311 + <div class="method-description">
  312 +
  313 + <p>
  314 +Removes punctuation from <tt>self</tt>.
  315 +</p>
  316 +<pre>
  317 + s = &quot;hello, world. how are you?!&quot;
  318 + s.strip_punctuation # =&gt; &quot;hello world how are you&quot;
  319 +</pre>
  320 +
  321 + </div>
  322 + </div>
  323 +
  324 +
  325 + <div id="method-M000009" class="method-detail">
  326 + <a name="M000009"></a>
  327 +
  328 + <div class="method-heading">
  329 +
  330 + <a href="String.src/M000009.html" target="Code" class="method-signature"
  331 + onclick="popupCode('String.src/M000009.html');return false;">
  332 +
  333 + <span class="method-name">strip_punctuation!</span><span class="method-args">()</span>
  334 +
  335 + </a>
  336 +
  337 + </div>
  338 +
  339 + <div class="method-description">
  340 +
  341 + <p>
  342 +Removes punctuation from <tt>self</tt>.
  343 +</p>
  344 +<pre>
  345 + s = &quot;hello, world. how are you?!&quot;
  346 + s.strip_punctuation!
  347 + s # =&gt; &quot;hello world how are you&quot;
287 348 </pre>
288 349  
289 350 </div>
doc/classes/String.src/M000001.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/string.rb, line 77</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 76</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">is_stopword?</span>
12 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>
doc/classes/String.src/M000002.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/string.rb, line 83</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 82</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">remove_special_characters</span>
12 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>
doc/classes/String.src/M000003.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/string.rb, line 92</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 91</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span>
12 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>
doc/classes/String.src/M000004.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/string.rb, line 101</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 100</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span>
12 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>
doc/classes/String.src/M000005.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/string.rb, line 115</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 114</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span>
12 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>
13 13 <span class="ruby-keyword kw">end</span></pre>
doc/classes/String.src/M000006.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/string.rb, line 128</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 127</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</span>
12 12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_javascripts!</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
doc/classes/String.src/M000007.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/string.rb, line 132</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 131</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span>
12 12 <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</span>
13 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>
doc/classes/String.src/M000008.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/string.rb, line 137</span>
  10 + <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 136</span>
11 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</span>
12 12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_stylesheets!</span>
13 13 <span class="ruby-keyword kw">end</span></pre>
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>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 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">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>
  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>
1   -Fri, 05 Nov 2010 15:06:41 +0100
  1 +Tue, 23 Nov 2010 18:20:46 +0100
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>2010-11-05 15:06:24 +0100</td>
  56 + <td>2010-11-23 18:14:13 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -96,6 +96,12 @@
96 96 <div class="name-list">
97 97  
98 98 net/http&nbsp;&nbsp;
  99 +
  100 + rexml/document&nbsp;&nbsp;
  101 +
  102 + net/http&nbsp;&nbsp;
  103 +
  104 + kconv&nbsp;&nbsp;
99 105  
100 106 </div>
101 107 </div>
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>2010-11-05 15:06:35 +0100</td>
  56 + <td>2010-11-23 18:20:41 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
doc/files/lib/rir_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>2010-11-05 14:39:35 +0100</td>
  56 + <td>2010-11-19 11:27:16 +0100</td>
57 57 </tr>
58 58 </table>
59 59 </div>
... ... @@ -71,6 +71,12 @@
71 71 rir/document&nbsp;&nbsp;
72 72  
73 73 rir/string&nbsp;&nbsp;
  74 +
  75 + rir/query&nbsp;&nbsp;
  76 +
  77 + rir/corpus&nbsp;&nbsp;
  78 +
  79 + rir/regexp&nbsp;&nbsp;
74 80  
75 81 </div>
76 82 </div>
doc/fr_class_index.html
... ... @@ -19,11 +19,15 @@
19 19  
20 20 <a href="classes/RIR.html">RIR</a><br />
21 21  
22   - <a href="classes/RIR/Document.html">RIR::Document</a><br />
  22 + <a href="classes/RIR/Corpus.html">RIR::Corpus</a><br />
23 23  
24   - <a href="classes/RIR/WebDocument.html">RIR::WebDocument</a><br />
  24 + <a href="classes/RIR/Indri.html">RIR::Indri</a><br />
25 25  
26   - <a href="classes/RIR/WikipediaPage.html">RIR::WikipediaPage</a><br />
  26 + <a href="classes/RIR/Indri/IndriQuery.html">RIR::Indri::IndriQuery</a><br />
  27 +
  28 + <a href="classes/RIR/Indri/Parameters.html">RIR::Indri::Parameters</a><br />
  29 +
  30 + <a href="classes/RIR/Query.html">RIR::Query</a><br />
27 31  
28 32 <a href="classes/String.html">String</a><br />
29 33  
doc/fr_file_index.html
... ... @@ -17,11 +17,11 @@
17 17 <h1 class="section-bar">Files</h1>
18 18 <div id="index-entries">
19 19  
20   - <a href="files/lib/rir/document_rb.html">lib/rir/document.rb</a><br />
  20 + <a href="files/lib/rir/corpus_rb.html">lib/rir/corpus.rb</a><br />
21 21  
22   - <a href="files/lib/rir/string_rb.html">lib/rir/string.rb</a><br />
  22 + <a href="files/lib/rir/query_rb.html">lib/rir/query.rb</a><br />
23 23  
24   - <a href="files/main_rb.html">main.rb</a><br />
  24 + <a href="files/lib/rir/string_rb.html">lib/rir/string.rb</a><br />
25 25  
26 26 </div>
27 27 </div>
doc/fr_method_index.html
... ... @@ -17,23 +17,17 @@
17 17 <h1 class="section-bar">Methods</h1>
18 18 <div id="index-entries">
19 19  
20   - <a href="classes/RIR/Document.html#M000012">count_words (RIR::Document)</a><br />
  20 + <a href="classes/String.html#M000011">extract_xmltags_values (String)</a><br />
21 21  
22   - <a href="classes/RIR/Document.html#M000013">entropy (RIR::Document)</a><br />
  22 + <a href="classes/RIR/Corpus.html#M000017">files (RIR::Corpus)</a><br />
23 23  
24   - <a href="classes/String.html#M000009">extract_xmltags_values (String)</a><br />
25   -
26   - <a href="classes/RIR/Document.html#M000010">format_words (RIR::Document)</a><br />
27   -
28   - <a href="classes/RIR/WebDocument.html#M000015">get_content (RIR::WebDocument)</a><br />
29   -
30 24 <a href="classes/String.html#M000001">is_stopword? (String)</a><br />
31 25  
32   - <a href="classes/RIR/WebDocument.html#M000016">new (RIR::WebDocument)</a><br />
  26 + <a href="classes/RIR/Corpus.html#M000016">new (RIR::Corpus)</a><br />
33 27  
34   - <a href="classes/RIR/Document.html#M000014">new (RIR::Document)</a><br />
  28 + <a href="classes/RIR/Indri/Parameters.html#M000012">new (RIR::Indri::Parameters)</a><br />
35 29  
36   - <a href="classes/RIR/Document.html#M000011">ngrams (RIR::Document)</a><br />
  30 + <a href="classes/RIR/Indri/IndriQuery.html#M000014">new (RIR::Indri::IndriQuery)</a><br />
37 31  
38 32 <a href="classes/String.html#M000002">remove_special_characters (String)</a><br />
39 33  
... ... @@ -41,6 +35,10 @@
41 35  
42 36 <a href="classes/String.html#M000005">strip_javascripts! (String)</a><br />
43 37  
  38 + <a href="classes/String.html#M000010">strip_punctuation (String)</a><br />
  39 +
  40 + <a href="classes/String.html#M000009">strip_punctuation! (String)</a><br />
  41 +
44 42 <a href="classes/String.html#M000008">strip_stylesheets (String)</a><br />
45 43  
46 44 <a href="classes/String.html#M000007">strip_stylesheets! (String)</a><br />
... ... @@ -48,6 +46,10 @@
48 46 <a href="classes/String.html#M000004">strip_xml_tags (String)</a><br />
49 47  
50 48 <a href="classes/String.html#M000003">strip_xml_tags! (String)</a><br />
  49 +
  50 + <a href="classes/RIR/Indri/Parameters.html#M000013">to_s (RIR::Indri::Parameters)</a><br />
  51 +
  52 + <a href="classes/RIR/Indri/IndriQuery.html#M000015">to_s (RIR::Indri::IndriQuery)</a><br />
51 53  
52 54 </div>
53 55 </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/string_rb.html" name="docwin" />
  19 + <frame src="files/lib/rir/corpus_rb.html" name="docwin" />
20 20 </frameset>
21 21 </html>
... ... @@ -17,7 +17,6 @@
17 17 # You should have received a copy of the GNU General Public License
18 18 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 19  
20   -# General module for many purposes related to Information Retrieval.
21 20 module RIR
22 21  
23 22 class Corpus
... ... @@ -17,7 +17,6 @@
17 17 # You should have received a copy of the GNU General Public License
18 18 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 19  
20   -# General module for many purposes related to Information Retrieval.
21 20 module RIR
22 21  
23 22 class Query
... ... @@ -17,7 +17,6 @@
17 17 # You should have received a copy of the GNU General Public License
18 18 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 19  
20   -# General module for many purposes related to Information Retrieval.
21 20 module RIR
22 21  
23 22 # These are the default stopwords provided by Lemur.