Commit 35f45ab54d40489d2fe5d4fc5d39c40290635dea

Authored by Romain Deveaud
1 parent 7043da90bf
Exists in master

changing the main module name, generating RDoc

Showing 22 changed files with 935 additions and 935 deletions Inline Diff

doc/classes/RIR.html
File was created 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: RIR [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">RIR</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/string_rb.html">
57
58 lib/rir/string.rb
59
60 </a>
61
62
63 <br />
64
65
66 <a href="../files/lib/rir/document_rb.html">
67
68 lib/rir/document.rb
69
70 </a>
71
72
73 <br />
74
75 </td>
76 </tr>
77
78
79 </table>
80 </div>
81 <!-- banner header -->
82
83 <div id="bodyContent">
84
85 <div id="contextContent">
86
87 <div id="description">
88 <p>
89 General module for many purposes related to Information Retrieval.
90 </p>
91 <hr size="1"></hr><p>
92 General module for many purposes related to Information Retrieval.
93 </p>
94
95 </div>
96
97 </div>
98
99
100 </div>
101
102 <!-- if includes -->
103
104 <div id="section">
105
106 <div id="class-list">
107 <h3 class="section-bar">Classes and Modules</h3>
108
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 />
112
113 </div>
114
115 <div id="constants-list">
116 <h3 class="section-bar">Constants</h3>
117
118 <div class="name-list">
119 <table summary="Constants">
120
121 <tr class="top-aligned-row context-row">
122 <td class="context-item-name">Stoplist</td>
123 <td>=</td>
124 <td class="context-item-value">[ &quot;a&quot;, &quot;anything&quot;, &quot;anyway&quot;, &quot;anywhere&quot;, &quot;apart&quot;, &quot;are&quot;, &quot;around&quot;, &quot;as&quot;, &quot;at&quot;, &quot;av&quot;, &quot;be&quot;, &quot;became&quot;, &quot;because&quot;, &quot;become&quot;, &quot;becomes&quot;, &quot;becoming&quot;, &quot;been&quot;, &quot;before&quot;, &quot;beforehand&quot;, &quot;behind&quot;, &quot;being&quot;, &quot;below&quot;, &quot;beside&quot;, &quot;besides&quot;, &quot;between&quot;, &quot;beyond&quot;, &quot;both&quot;, &quot;but&quot;, &quot;by&quot;, &quot;can&quot;, &quot;cannot&quot;, &quot;canst&quot;, &quot;certain&quot;, &quot;cf&quot;, &quot;choose&quot;, &quot;contrariwise&quot;, &quot;cos&quot;, &quot;could&quot;, &quot;cu&quot;, &quot;day&quot;, &quot;do&quot;, &quot;does&quot;, &quot;doesn't&quot;, &quot;doing&quot;, &quot;dost&quot;, &quot;doth&quot;, &quot;double&quot;, &quot;down&quot;, &quot;dual&quot;, &quot;during&quot;, &quot;each&quot;, &quot;either&quot;, &quot;else&quot;, &quot;elsewhere&quot;, &quot;enough&quot;, &quot;et&quot;, &quot;etc&quot;, &quot;even&quot;, &quot;ever&quot;, &quot;every&quot;, &quot;everybody&quot;, &quot;everyone&quot;, &quot;everything&quot;, &quot;everywhere&quot;, &quot;except&quot;, &quot;excepted&quot;, &quot;excepting&quot;, &quot;exception&quot;, &quot;exclude&quot;, &quot;excluding&quot;, &quot;exclusive&quot;, &quot;far&quot;, &quot;farther&quot;, &quot;farthest&quot;, &quot;few&quot;, &quot;ff&quot;, &quot;first&quot;, &quot;for&quot;, &quot;formerly&quot;, &quot;forth&quot;, &quot;forward&quot;, &quot;from&quot;, &quot;front&quot;, &quot;further&quot;, &quot;furthermore&quot;, &quot;furthest&quot;, &quot;get&quot;, &quot;go&quot;, &quot;had&quot;, &quot;halves&quot;, &quot;hardly&quot;, &quot;has&quot;, &quot;hast&quot;, &quot;hath&quot;, &quot;have&quot;, &quot;he&quot;, &quot;hence&quot;, &quot;henceforth&quot;, &quot;her&quot;, &quot;here&quot;, &quot;hereabouts&quot;, &quot;hereafter&quot;, &quot;hereby&quot;, &quot;herein&quot;, &quot;hereto&quot;, &quot;hereupon&quot;, &quot;hers&quot;, &quot;herself&quot;, &quot;him&quot;, &quot;himself&quot;, &quot;hindmost&quot;, &quot;his&quot;, &quot;hither&quot;, &quot;hitherto&quot;, &quot;how&quot;, &quot;however&quot;, &quot;howsoever&quot;, &quot;i&quot;, &quot;ie&quot;, &quot;if&quot;, &quot;in&quot;, &quot;inasmuch&quot;, &quot;inc&quot;, &quot;include&quot;, &quot;included&quot;, &quot;including&quot;, &quot;indeed&quot;, &quot;indoors&quot;, &quot;inside&quot;, &quot;insomuch&quot;, &quot;instead&quot;, &quot;into&quot;, &quot;inward&quot;, &quot;inwards&quot;, &quot;is&quot;, &quot;it&quot;, &quot;its&quot;, &quot;itself&quot;, &quot;just&quot;, &quot;kind&quot;, &quot;kg&quot;, &quot;km&quot;, &quot;last&quot;, &quot;latter&quot;, &quot;latterly&quot;, &quot;less&quot;, &quot;lest&quot;, &quot;let&quot;, &quot;like&quot;, &quot;little&quot;, &quot;ltd&quot;, &quot;many&quot;, &quot;may&quot;, &quot;maybe&quot;, &quot;me&quot;, &quot;meantime&quot;, &quot;meanwhile&quot;, &quot;might&quot;, &quot;moreover&quot;, &quot;most&quot;, &quot;mostly&quot;, &quot;more&quot;, &quot;mr&quot;, &quot;mrs&quot;, &quot;ms&quot;, &quot;much&quot;, &quot;must&quot;, &quot;my&quot;, &quot;myself&quot;, &quot;namely&quot;, &quot;need&quot;, &quot;neither&quot;, &quot;never&quot;, &quot;nevertheless&quot;, &quot;next&quot;, &quot;no&quot;, &quot;nobody&quot;, &quot;none&quot;, &quot;nonetheless&quot;, &quot;noone&quot;, &quot;nope&quot;, &quot;nor&quot;, &quot;not&quot;, &quot;nothing&quot;, &quot;notwithstanding&quot;, &quot;now&quot;, &quot;nowadays&quot;, &quot;nowhere&quot;, &quot;of&quot;, &quot;off&quot;, &quot;often&quot;, &quot;ok&quot;, &quot;on&quot;, &quot;once&quot;, &quot;one&quot;, &quot;only&quot;, &quot;onto&quot;, &quot;or&quot;, &quot;other&quot;, &quot;others&quot;, &quot;otherwise&quot;, &quot;ought&quot;, &quot;our&quot;, &quot;ours&quot;, &quot;ourselves&quot;, &quot;out&quot;, &quot;outside&quot;, &quot;over&quot;, &quot;own&quot;, &quot;per&quot;, &quot;perhaps&quot;, &quot;plenty&quot;, &quot;provide&quot;, &quot;quite&quot;, &quot;rather&quot;, &quot;really&quot;, &quot;round&quot;, &quot;said&quot;, &quot;sake&quot;, &quot;same&quot;, &quot;sang&quot;, &quot;save&quot;, &quot;saw&quot;, &quot;see&quot;, &quot;seeing&quot;, &quot;seem&quot;, &quot;seemed&quot;, &quot;seeming&quot;, &quot;seems&quot;, &quot;seen&quot;, &quot;seldom&quot;, &quot;selves&quot;, &quot;sent&quot;, &quot;several&quot;, &quot;shalt&quot;, &quot;she&quot;, &quot;should&quot;, &quot;shown&quot;, &quot;sideways&quot;, &quot;since&quot;, &quot;slept&quot;, &quot;slew&quot;, &quot;slung&quot;, &quot;slunk&quot;, &quot;smote&quot;, &quot;so&quot;, &quot;some&quot;, &quot;somebody&quot;, &quot;somehow&quot;, &quot;someone&quot;, &quot;something&quot;, &quot;sometime&quot;, &quot;sometimes&quot;, &quot;somewhat&quot;, &quot;somewhere&quot;, &quot;spake&quot;, &quot;spat&quot;, &quot;spoke&quot;, &quot;spoken&quot;, &quot;sprang&quot;, &quot;sprung&quot;, &quot;stave&quot;, &quot;staves&quot;, &quot;still&quot;, &quot;such&quot;, &quot;supposing&quot;, &quot;than&quot;, &quot;that&quot;, &quot;the&quot;, &quot;thee&quot;, &quot;their&quot;, &quot;them&quot;, &quot;themselves&quot;, &quot;then&quot;, &quot;thence&quot;, &quot;thenceforth&quot;, &quot;there&quot;, &quot;thereabout&quot;, &quot;thereabouts&quot;, &quot;thereafter&quot;, &quot;thereby&quot;, &quot;therefore&quot;, &quot;therein&quot;, &quot;thereof&quot;, &quot;thereon&quot;, &quot;thereto&quot;, &quot;thereupon&quot;, &quot;these&quot;, &quot;they&quot;, &quot;this&quot;, &quot;those&quot;, &quot;thou&quot;, &quot;though&quot;, &quot;thrice&quot;, &quot;through&quot;, &quot;throughout&quot;, &quot;thru&quot;, &quot;thus&quot;, &quot;thy&quot;, &quot;thyself&quot;, &quot;till&quot;, &quot;to&quot;, &quot;together&quot;, &quot;too&quot;, &quot;toward&quot;, &quot;towards&quot;, &quot;ugh&quot;, &quot;unable&quot;, &quot;under&quot;, &quot;underneath&quot;, &quot;unless&quot;, &quot;unlike&quot;, &quot;until&quot;, &quot;up&quot;, &quot;upon&quot;, &quot;upward&quot;, &quot;upwards&quot;, &quot;us&quot;, &quot;use&quot;, &quot;used&quot;, &quot;using&quot;, &quot;very&quot;, &quot;via&quot;, &quot;vs&quot;, &quot;want&quot;, &quot;was&quot;, &quot;we&quot;, &quot;week&quot;, &quot;well&quot;, &quot;were&quot;, &quot;what&quot;, &quot;whatever&quot;, &quot;whatsoever&quot;, &quot;when&quot;, &quot;whence&quot;, &quot;whenever&quot;, &quot;whensoever&quot;, &quot;where&quot;, &quot;whereabouts&quot;, &quot;whereafter&quot;, &quot;whereas&quot;, &quot;whereat&quot;, &quot;whereby&quot;, &quot;wherefore&quot;, &quot;wherefrom&quot;, &quot;wherein&quot;, &quot;whereinto&quot;, &quot;whereof&quot;, &quot;whereon&quot;, &quot;wheresoever&quot;, &quot;whereto&quot;, &quot;whereunto&quot;, &quot;whereupon&quot;, &quot;wherever&quot;, &quot;wherewith&quot;, &quot;whether&quot;, &quot;whew&quot;, &quot;which&quot;, &quot;whichever&quot;, &quot;whichsoever&quot;, &quot;while&quot;, &quot;whilst&quot;, &quot;whither&quot;, &quot;who&quot;, &quot;whoa&quot;, &quot;whoever&quot;, &quot;whole&quot;, &quot;whom&quot;, &quot;whomever&quot;, &quot;whomsoever&quot;, &quot;whose&quot;, &quot;whosoever&quot;, &quot;why&quot;, &quot;will&quot;, &quot;wilt&quot;, &quot;with&quot;, &quot;within&quot;, &quot;without&quot;, &quot;worse&quot;, &quot;worst&quot;, &quot;would&quot;, &quot;wow&quot;, &quot;ye&quot;, &quot;yet&quot;, &quot;year&quot;, &quot;yippee&quot;, &quot;you&quot;, &quot;your&quot;, &quot;yours&quot;, &quot;yourself&quot;, &quot;yourselves&quot; ]</td>
125
126 <td>&nbsp;</td>
127 <td class="context-item-desc">
128 These are the default stopwords provided by Lemur.
129
130 </td>
131
132 </tr>
133
134 </table>
135 </div>
136 </div>
137
138
139
140
141 <!-- if method_list -->
142
143
144
145
146 </div>
147
148 <div id="validator-badges">
149 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
150 </div>
151
152 </body>
153 </html>
154
doc/classes/RIR/Document.html
File was created 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: RIR::Document [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">RIR::Document</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/document_rb.html">
57
58 lib/rir/document.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 A <a href="Document.html">Document</a> is a bag of words and is constructed
89 from a string.
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="#M000012">count_words</a>&nbsp;&nbsp;
103
104 <a href="#M000013">entropy</a>&nbsp;&nbsp;
105
106 <a href="#M000010">format_words</a>&nbsp;&nbsp;
107
108 <a href="#M000014">new</a>&nbsp;&nbsp;
109
110 <a href="#M000011">ngrams</a>&nbsp;&nbsp;
111
112 </div>
113 </div>
114
115 </div>
116
117 <!-- if includes -->
118
119 <div id="section">
120
121
122
123 <div id="attribute-list">
124 <h3 class="section-bar">Attributes</h3>
125
126 <div class="name-list">
127 <table>
128
129 <tr class="top-aligned-row context-row">
130 <td class="context-item-name">doc_content</td>
131
132 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
133
134 <td class="context-item-desc"></td>
135 </tr>
136
137 <tr class="top-aligned-row context-row">
138 <td class="context-item-name">words</td>
139
140 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
141
142 <td class="context-item-desc"></td>
143 </tr>
144
145 </table>
146 </div>
147 </div>
148
149
150 <!-- if method_list -->
151
152 <div id="methods">
153
154 <h3 class="section-bar">Public Class methods</h3>
155
156
157 <div id="method-M000014" class="method-detail">
158 <a name="M000014"></a>
159
160 <div class="method-heading">
161
162 <a href="Document.src/M000014.html" target="Code" class="method-signature"
163 onclick="popupCode('Document.src/M000014.html');return false;">
164
165 <span class="method-name">new</span><span class="method-args">(content)</span>
166
167 </a>
168
169 </div>
170
171 <div class="method-description">
172
173 </div>
174 </div>
175
176
177 <h3 class="section-bar">Public Instance methods</h3>
178
179
180 <div id="method-M000012" class="method-detail">
181 <a name="M000012"></a>
182
183 <div class="method-heading">
184
185 <a href="Document.src/M000012.html" target="Code" class="method-signature"
186 onclick="popupCode('Document.src/M000012.html');return false;">
187
188 <span class="method-name">count_words</span><span class="method-args">()</span>
189
190 </a>
191
192 </div>
193
194 <div class="method-description">
195
196 <p>
197 Returns a Hash containing the words and their associated counts in the
198 current <a href="Document.html">Document</a>.
199 </p>
200 <pre>
201 count_words #=&gt; { &quot;guitar&quot;=&gt;1, &quot;bass&quot;=&gt;3, &quot;album&quot;=&gt;20, ... }
202 </pre>
203
204 </div>
205 </div>
206
207
208 <div id="method-M000013" class="method-detail">
209 <a name="M000013"></a>
210
211 <div class="method-heading">
212
213 <a href="Document.src/M000013.html" target="Code" class="method-signature"
214 onclick="popupCode('Document.src/M000013.html');return false;">
215
216 <span class="method-name">entropy</span><span class="method-args">(s)</span>
217
218 </a>
219
220 </div>
221
222 <div class="method-description">
223
224 <p>
225 Computes the entropy of a given string <tt>s</tt> inside the document.
226 </p>
227 <p>
228 If the string parameter is composed of many words (i.e. tokens separated by
229 whitespace(s)), it is considered as an ngram.
230 </p>
231 <pre>
232 entropy(&quot;guitar&quot;) #=&gt; 0.00389919463243839
233 </pre>
234
235 </div>
236 </div>
237
238
239 <div id="method-M000011" class="method-detail">
240 <a name="M000011"></a>
241
242 <div class="method-heading">
243
244 <a href="Document.src/M000011.html" target="Code" class="method-signature"
245 onclick="popupCode('Document.src/M000011.html');return false;">
246
247 <span class="method-name">ngrams</span><span class="method-args">(n)</span>
248
249 </a>
250
251 </div>
252
253 <div class="method-description">
254
255 <p>
256 Returns an Array containing the <tt>n</tt>-grams (words) from the current
257 <a href="Document.html">Document</a>.
258 </p>
259 <pre>
260 ngrams(2) #=&gt; [&quot;the free&quot;, &quot;free encyclopedia&quot;, &quot;encyclopedia var&quot;, &quot;var skin&quot;, ...]
261 </pre>
262
263 </div>
264 </div>
265
266
267 <h3 class="section-bar">Protected Instance methods</h3>
268
269
270 <div id="method-M000010" class="method-detail">
271 <a name="M000010"></a>
272
273 <div class="method-heading">
274
275 <a href="Document.src/M000010.html" target="Code" class="method-signature"
276 onclick="popupCode('Document.src/M000010.html');return false;">
277
278 <span class="method-name">format_words</span><span class="method-args">()</span>
279
280 </a>
281
282 </div>
283
284 <div class="method-description">
285
286 <p>
287 Any non-word characters are removed from the words (see <a
288 href="http://perldoc.perl.org/perlre.html">perldoc.perl.org/perlre.html</a>
289 and the W special escape).
290 </p>
291 <p>
292 Protected function, only meant to by called at the initialization.
293 </p>
294
295 </div>
296 </div>
297
298
299
300 </div>
301
302
303
304
305 </div>
306
307 <div id="validator-badges">
308 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
309 </div>
310
311 </body>
312 </html>
313
doc/classes/RIR/Document.src/M000010.html
File was created 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>format_words (RIR::Document)</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/document.rb, line 31</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">format_words</span>
12 <span class="ruby-identifier">wo</span> = []
13
14 <span class="ruby-ivar">@doc_content</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
15 <span class="ruby-identifier">w</span>.<span class="ruby-identifier">split</span>(<span class="ruby-regexp re">/\W/</span>).<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">sw</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">wo</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">sw</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">sw</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/[a-zA-Z]/</span>
17 <span class="ruby-keyword kw">end</span>
18 <span class="ruby-keyword kw">end</span>
19
20 <span class="ruby-identifier">wo</span>
21 <span class="ruby-keyword kw">end</span></pre>
22 </body>
23 </html>
24
doc/classes/RIR/Document.src/M000011.html
File was created 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>ngrams (RIR::Document)</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/document.rb, line 46</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">ngrams</span>(<span class="ruby-identifier">n</span>)
12 <span class="ruby-identifier">window</span> = []
13 <span class="ruby-identifier">ngrams_array</span> = []
14
15 <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">window</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">w</span>)
17 <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">size</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">n</span>
18 <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">push</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">&quot; &quot;</span>)
19 <span class="ruby-identifier">window</span>.<span class="ruby-identifier">delete_at</span>(<span class="ruby-value">0</span>)
20 <span class="ruby-keyword kw">end</span>
21 <span class="ruby-keyword kw">end</span>
22
23 <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">uniq</span>
24 <span class="ruby-keyword kw">end</span></pre>
25 </body>
26 </html>
27
doc/classes/RIR/Document.src/M000012.html
File was created 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>count_words (RIR::Document)</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/document.rb, line 64</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">count_words</span>
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 <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-identifier">downcase</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> }
14
15 <span class="ruby-identifier">counts</span>
16 <span class="ruby-keyword kw">end</span></pre>
17 </body>
18 </html>
19
doc/classes/RIR/Document.src/M000013.html
File was created 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>entropy (RIR::Document)</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/document.rb, line 77</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">entropy</span>(<span class="ruby-identifier">s</span>)
12 <span class="ruby-identifier">en</span> = <span class="ruby-value">0</span><span class="ruby-value">.0</span>
13 <span class="ruby-identifier">counts</span> = <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>
14
15 <span class="ruby-identifier">s</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">p_wi</span> = <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">count</span>.<span class="ruby-identifier">to_f</span>
17 <span class="ruby-identifier">en</span> <span class="ruby-operator">+=</span> <span class="ruby-identifier">p_wi</span><span class="ruby-operator">*</span><span class="ruby-constant">Math</span>.<span class="ruby-identifier">log2</span>(<span class="ruby-identifier">p_wi</span>)
18 <span class="ruby-keyword kw">end</span>
19
20 <span class="ruby-identifier">en</span> <span class="ruby-operator">*=</span> <span class="ruby-value">-1</span>
21 <span class="ruby-identifier">en</span>
22 <span class="ruby-keyword kw">end</span></pre>
23 </body>
24 </html>
25
doc/classes/RIR/Document.src/M000014.html
File was created 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 (RIR::Document)</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/document.rb, line 92</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">content</span>)
12 <span class="ruby-ivar">@doc_content</span> = <span class="ruby-identifier">content</span>
13 <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">format_words</span>
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17
doc/classes/RIR/WebDocument.html
File was created 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: RIR::WebDocument [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">RIR::WebDocument</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/document_rb.html">
57
58 lib/rir/document.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="Document.html">
74
75 RIR::Document
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 id="description">
91 <p>
92 A <a href="WebDocument.html">WebDocument</a> is a <a
93 href="Document.html">Document</a> with a <tt>url</tt>.
94 </p>
95
96 </div>
97
98 </div>
99
100
101 <div id="method-list">
102 <h3 class="section-bar">Methods</h3>
103
104 <div class="name-list">
105
106 <a href="#M000015">get_content</a>&nbsp;&nbsp;
107
108 <a href="#M000016">new</a>&nbsp;&nbsp;
109
110 </div>
111 </div>
112
113 </div>
114
115 <!-- if includes -->
116
117 <div id="section">
118
119
120
121 <div id="attribute-list">
122 <h3 class="section-bar">Attributes</h3>
123
124 <div class="name-list">
125 <table>
126
127 <tr class="top-aligned-row context-row">
128 <td class="context-item-name">url</td>
129
130 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
131
132 <td class="context-item-desc"></td>
133 </tr>
134
135 </table>
136 </div>
137 </div>
138
139
140 <!-- if method_list -->
141
142 <div id="methods">
143
144 <h3 class="section-bar">Public Class methods</h3>
145
146
147 <div id="method-M000015" class="method-detail">
148 <a name="M000015"></a>
149
150 <div class="method-heading">
151
152 <a href="WebDocument.src/M000015.html" target="Code" class="method-signature"
153 onclick="popupCode('WebDocument.src/M000015.html');return false;">
154
155 <span class="method-name">get_content</span><span class="method-args">(url)</span>
156
157 </a>
158
159 </div>
160
161 <div class="method-description">
162
163 <p>
164 Returns the HTML text from the page of a given <tt>url</tt>.
165 </p>
166
167 </div>
168 </div>
169
170
171 <div id="method-M000016" class="method-detail">
172 <a name="M000016"></a>
173
174 <div class="method-heading">
175
176 <a href="WebDocument.src/M000016.html" target="Code" class="method-signature"
177 onclick="popupCode('WebDocument.src/M000016.html');return false;">
178
179 <span class="method-name">new</span><span class="method-args">(url)</span>
180
181 </a>
182
183 </div>
184
185 <div class="method-description">
186
187 <p>
188 <a href="WebDocument.html">WebDocument</a> constructor, the content of the
189 <a href="Document.html">Document</a> is the HTML page without the tags.
190 </p>
191
192 </div>
193 </div>
194
195
196
197 </div>
198
199
200
201
202 </div>
203
204 <div id="validator-badges">
205 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
206 </div>
207
208 </body>
209 </html>
210
doc/classes/RIR/WebDocument.src/M000015.html
File was created 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>get_content (RIR::WebDocument)</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/document.rb, line 105</span>
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 <span class="ruby-identifier">require</span> <span class="ruby-value str">'net/http'</span>
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>))
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17
doc/classes/RIR/WebDocument.src/M000016.html
File was created 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 (RIR::WebDocument)</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/document.rb, line 112</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">url</span>)
12 <span class="ruby-ivar">@url</span> = <span class="ruby-identifier">url</span>
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>
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17
doc/classes/RIR/WikipediaPage.html
File was created 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: RIR::WikipediaPage [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">RIR::WikipediaPage</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/document_rb.html">
57
58 lib/rir/document.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="WebDocument.html">
74
75 RIR::WebDocument
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 id="description">
91 <p>
92 A <a href="WikipediaPage.html">WikipediaPage</a> is a <a
93 href="WebDocument.html">WebDocument</a>.
94 </p>
95
96 </div>
97
98 </div>
99
100
101 </div>
102
103 <!-- if includes -->
104
105 <div id="section">
106
107
108
109
110 <!-- if method_list -->
111
112
113
114
115 </div>
116
117 <div id="validator-badges">
118 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
119 </div>
120
121 </body>
122 </html>
123
doc/classes/Rir.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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: Rir [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">Rir</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/string_rb.html">
57
58 lib/rir/string.rb
59
60 </a>
61
62
63 <br />
64
65
66 <a href="../files/lib/rir/document_rb.html">
67
68 lib/rir/document.rb
69
70 </a>
71
72
73 <br />
74
75 </td>
76 </tr>
77
78
79 </table>
80 </div>
81 <!-- banner header -->
82
83 <div id="bodyContent">
84
85 <div id="contextContent">
86
87 <div id="description">
88 <p>
89 General module for many purposes related to Information Retrieval.
90 </p>
91 <hr size="1"></hr><p>
92 General module for many purposes related to Information Retrieval.
93 </p>
94
95 </div>
96
97 </div>
98
99
100 </div>
101
102 <!-- if includes -->
103
104 <div id="section">
105
106 <div id="class-list">
107 <h3 class="section-bar">Classes and Modules</h3>
108
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 />
112
113 </div>
114
115 <div id="constants-list">
116 <h3 class="section-bar">Constants</h3>
117
118 <div class="name-list">
119 <table summary="Constants">
120
121 <tr class="top-aligned-row context-row">
122 <td class="context-item-name">Stoplist</td>
123 <td>=</td>
124 <td class="context-item-value">[ &quot;a&quot;, &quot;anything&quot;, &quot;anyway&quot;, &quot;anywhere&quot;, &quot;apart&quot;, &quot;are&quot;, &quot;around&quot;, &quot;as&quot;, &quot;at&quot;, &quot;av&quot;, &quot;be&quot;, &quot;became&quot;, &quot;because&quot;, &quot;become&quot;, &quot;becomes&quot;, &quot;becoming&quot;, &quot;been&quot;, &quot;before&quot;, &quot;beforehand&quot;, &quot;behind&quot;, &quot;being&quot;, &quot;below&quot;, &quot;beside&quot;, &quot;besides&quot;, &quot;between&quot;, &quot;beyond&quot;, &quot;both&quot;, &quot;but&quot;, &quot;by&quot;, &quot;can&quot;, &quot;cannot&quot;, &quot;canst&quot;, &quot;certain&quot;, &quot;cf&quot;, &quot;choose&quot;, &quot;contrariwise&quot;, &quot;cos&quot;, &quot;could&quot;, &quot;cu&quot;, &quot;day&quot;, &quot;do&quot;, &quot;does&quot;, &quot;doesn't&quot;, &quot;doing&quot;, &quot;dost&quot;, &quot;doth&quot;, &quot;double&quot;, &quot;down&quot;, &quot;dual&quot;, &quot;during&quot;, &quot;each&quot;, &quot;either&quot;, &quot;else&quot;, &quot;elsewhere&quot;, &quot;enough&quot;, &quot;et&quot;, &quot;etc&quot;, &quot;even&quot;, &quot;ever&quot;, &quot;every&quot;, &quot;everybody&quot;, &quot;everyone&quot;, &quot;everything&quot;, &quot;everywhere&quot;, &quot;except&quot;, &quot;excepted&quot;, &quot;excepting&quot;, &quot;exception&quot;, &quot;exclude&quot;, &quot;excluding&quot;, &quot;exclusive&quot;, &quot;far&quot;, &quot;farther&quot;, &quot;farthest&quot;, &quot;few&quot;, &quot;ff&quot;, &quot;first&quot;, &quot;for&quot;, &quot;formerly&quot;, &quot;forth&quot;, &quot;forward&quot;, &quot;from&quot;, &quot;front&quot;, &quot;further&quot;, &quot;furthermore&quot;, &quot;furthest&quot;, &quot;get&quot;, &quot;go&quot;, &quot;had&quot;, &quot;halves&quot;, &quot;hardly&quot;, &quot;has&quot;, &quot;hast&quot;, &quot;hath&quot;, &quot;have&quot;, &quot;he&quot;, &quot;hence&quot;, &quot;henceforth&quot;, &quot;her&quot;, &quot;here&quot;, &quot;hereabouts&quot;, &quot;hereafter&quot;, &quot;hereby&quot;, &quot;herein&quot;, &quot;hereto&quot;, &quot;hereupon&quot;, &quot;hers&quot;, &quot;herself&quot;, &quot;him&quot;, &quot;himself&quot;, &quot;hindmost&quot;, &quot;his&quot;, &quot;hither&quot;, &quot;hitherto&quot;, &quot;how&quot;, &quot;however&quot;, &quot;howsoever&quot;, &quot;i&quot;, &quot;ie&quot;, &quot;if&quot;, &quot;in&quot;, &quot;inasmuch&quot;, &quot;inc&quot;, &quot;include&quot;, &quot;included&quot;, &quot;including&quot;, &quot;indeed&quot;, &quot;indoors&quot;, &quot;inside&quot;, &quot;insomuch&quot;, &quot;instead&quot;, &quot;into&quot;, &quot;inward&quot;, &quot;inwards&quot;, &quot;is&quot;, &quot;it&quot;, &quot;its&quot;, &quot;itself&quot;, &quot;just&quot;, &quot;kind&quot;, &quot;kg&quot;, &quot;km&quot;, &quot;last&quot;, &quot;latter&quot;, &quot;latterly&quot;, &quot;less&quot;, &quot;lest&quot;, &quot;let&quot;, &quot;like&quot;, &quot;little&quot;, &quot;ltd&quot;, &quot;many&quot;, &quot;may&quot;, &quot;maybe&quot;, &quot;me&quot;, &quot;meantime&quot;, &quot;meanwhile&quot;, &quot;might&quot;, &quot;moreover&quot;, &quot;most&quot;, &quot;mostly&quot;, &quot;more&quot;, &quot;mr&quot;, &quot;mrs&quot;, &quot;ms&quot;, &quot;much&quot;, &quot;must&quot;, &quot;my&quot;, &quot;myself&quot;, &quot;namely&quot;, &quot;need&quot;, &quot;neither&quot;, &quot;never&quot;, &quot;nevertheless&quot;, &quot;next&quot;, &quot;no&quot;, &quot;nobody&quot;, &quot;none&quot;, &quot;nonetheless&quot;, &quot;noone&quot;, &quot;nope&quot;, &quot;nor&quot;, &quot;not&quot;, &quot;nothing&quot;, &quot;notwithstanding&quot;, &quot;now&quot;, &quot;nowadays&quot;, &quot;nowhere&quot;, &quot;of&quot;, &quot;off&quot;, &quot;often&quot;, &quot;ok&quot;, &quot;on&quot;, &quot;once&quot;, &quot;one&quot;, &quot;only&quot;, &quot;onto&quot;, &quot;or&quot;, &quot;other&quot;, &quot;others&quot;, &quot;otherwise&quot;, &quot;ought&quot;, &quot;our&quot;, &quot;ours&quot;, &quot;ourselves&quot;, &quot;out&quot;, &quot;outside&quot;, &quot;over&quot;, &quot;own&quot;, &quot;per&quot;, &quot;perhaps&quot;, &quot;plenty&quot;, &quot;provide&quot;, &quot;quite&quot;, &quot;rather&quot;, &quot;really&quot;, &quot;round&quot;, &quot;said&quot;, &quot;sake&quot;, &quot;same&quot;, &quot;sang&quot;, &quot;save&quot;, &quot;saw&quot;, &quot;see&quot;, &quot;seeing&quot;, &quot;seem&quot;, &quot;seemed&quot;, &quot;seeming&quot;, &quot;seems&quot;, &quot;seen&quot;, &quot;seldom&quot;, &quot;selves&quot;, &quot;sent&quot;, &quot;several&quot;, &quot;shalt&quot;, &quot;she&quot;, &quot;should&quot;, &quot;shown&quot;, &quot;sideways&quot;, &quot;since&quot;, &quot;slept&quot;, &quot;slew&quot;, &quot;slung&quot;, &quot;slunk&quot;, &quot;smote&quot;, &quot;so&quot;, &quot;some&quot;, &quot;somebody&quot;, &quot;somehow&quot;, &quot;someone&quot;, &quot;something&quot;, &quot;sometime&quot;, &quot;sometimes&quot;, &quot;somewhat&quot;, &quot;somewhere&quot;, &quot;spake&quot;, &quot;spat&quot;, &quot;spoke&quot;, &quot;spoken&quot;, &quot;sprang&quot;, &quot;sprung&quot;, &quot;stave&quot;, &quot;staves&quot;, &quot;still&quot;, &quot;such&quot;, &quot;supposing&quot;, &quot;than&quot;, &quot;that&quot;, &quot;the&quot;, &quot;thee&quot;, &quot;their&quot;, &quot;them&quot;, &quot;themselves&quot;, &quot;then&quot;, &quot;thence&quot;, &quot;thenceforth&quot;, &quot;there&quot;, &quot;thereabout&quot;, &quot;thereabouts&quot;, &quot;thereafter&quot;, &quot;thereby&quot;, &quot;therefore&quot;, &quot;therein&quot;, &quot;thereof&quot;, &quot;thereon&quot;, &quot;thereto&quot;, &quot;thereupon&quot;, &quot;these&quot;, &quot;they&quot;, &quot;this&quot;, &quot;those&quot;, &quot;thou&quot;, &quot;though&quot;, &quot;thrice&quot;, &quot;through&quot;, &quot;throughout&quot;, &quot;thru&quot;, &quot;thus&quot;, &quot;thy&quot;, &quot;thyself&quot;, &quot;till&quot;, &quot;to&quot;, &quot;together&quot;, &quot;too&quot;, &quot;toward&quot;, &quot;towards&quot;, &quot;ugh&quot;, &quot;unable&quot;, &quot;under&quot;, &quot;underneath&quot;, &quot;unless&quot;, &quot;unlike&quot;, &quot;until&quot;, &quot;up&quot;, &quot;upon&quot;, &quot;upward&quot;, &quot;upwards&quot;, &quot;us&quot;, &quot;use&quot;, &quot;used&quot;, &quot;using&quot;, &quot;very&quot;, &quot;via&quot;, &quot;vs&quot;, &quot;want&quot;, &quot;was&quot;, &quot;we&quot;, &quot;week&quot;, &quot;well&quot;, &quot;were&quot;, &quot;what&quot;, &quot;whatever&quot;, &quot;whatsoever&quot;, &quot;when&quot;, &quot;whence&quot;, &quot;whenever&quot;, &quot;whensoever&quot;, &quot;where&quot;, &quot;whereabouts&quot;, &quot;whereafter&quot;, &quot;whereas&quot;, &quot;whereat&quot;, &quot;whereby&quot;, &quot;wherefore&quot;, &quot;wherefrom&quot;, &quot;wherein&quot;, &quot;whereinto&quot;, &quot;whereof&quot;, &quot;whereon&quot;, &quot;wheresoever&quot;, &quot;whereto&quot;, &quot;whereunto&quot;, &quot;whereupon&quot;, &quot;wherever&quot;, &quot;wherewith&quot;, &quot;whether&quot;, &quot;whew&quot;, &quot;which&quot;, &quot;whichever&quot;, &quot;whichsoever&quot;, &quot;while&quot;, &quot;whilst&quot;, &quot;whither&quot;, &quot;who&quot;, &quot;whoa&quot;, &quot;whoever&quot;, &quot;whole&quot;, &quot;whom&quot;, &quot;whomever&quot;, &quot;whomsoever&quot;, &quot;whose&quot;, &quot;whosoever&quot;, &quot;why&quot;, &quot;will&quot;, &quot;wilt&quot;, &quot;with&quot;, &quot;within&quot;, &quot;without&quot;, &quot;worse&quot;, &quot;worst&quot;, &quot;would&quot;, &quot;wow&quot;, &quot;ye&quot;, &quot;yet&quot;, &quot;year&quot;, &quot;yippee&quot;, &quot;you&quot;, &quot;your&quot;, &quot;yours&quot;, &quot;yourself&quot;, &quot;yourselves&quot; ]</td>
125
126 <td>&nbsp;</td>
127 <td class="context-item-desc">
128 These are the default stopwords provided by Lemur.
129
130 </td>
131
132 </tr>
133
134 </table>
135 </div>
136 </div>
137
138
139
140
141 <!-- if method_list -->
142
143
144
145
146 </div>
147
148 <div id="validator-badges">
149 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
150 </div>
151
152 </body>
153 </html>
154 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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: Rir::Document [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">Rir::Document</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/document_rb.html">
57
58 lib/rir/document.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 A <a href="Document.html">Document</a> is a bag of words and is constructed
89 from a string.
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="#M000012">count_words</a>&nbsp;&nbsp;
103
104 <a href="#M000013">entropy</a>&nbsp;&nbsp;
105
106 <a href="#M000010">format_words</a>&nbsp;&nbsp;
107
108 <a href="#M000014">new</a>&nbsp;&nbsp;
109
110 <a href="#M000011">ngrams</a>&nbsp;&nbsp;
111
112 </div>
113 </div>
114
115 </div>
116
117 <!-- if includes -->
118
119 <div id="section">
120
121
122
123 <div id="attribute-list">
124 <h3 class="section-bar">Attributes</h3>
125
126 <div class="name-list">
127 <table>
128
129 <tr class="top-aligned-row context-row">
130 <td class="context-item-name">doc_content</td>
131
132 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
133
134 <td class="context-item-desc"></td>
135 </tr>
136
137 <tr class="top-aligned-row context-row">
138 <td class="context-item-name">words</td>
139
140 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
141
142 <td class="context-item-desc"></td>
143 </tr>
144
145 </table>
146 </div>
147 </div>
148
149
150 <!-- if method_list -->
151
152 <div id="methods">
153
154 <h3 class="section-bar">Public Class methods</h3>
155
156
157 <div id="method-M000014" class="method-detail">
158 <a name="M000014"></a>
159
160 <div class="method-heading">
161
162 <a href="Document.src/M000014.html" target="Code" class="method-signature"
163 onclick="popupCode('Document.src/M000014.html');return false;">
164
165 <span class="method-name">new</span><span class="method-args">(content)</span>
166
167 </a>
168
169 </div>
170
171 <div class="method-description">
172
173 </div>
174 </div>
175
176
177 <h3 class="section-bar">Public Instance methods</h3>
178
179
180 <div id="method-M000012" class="method-detail">
181 <a name="M000012"></a>
182
183 <div class="method-heading">
184
185 <a href="Document.src/M000012.html" target="Code" class="method-signature"
186 onclick="popupCode('Document.src/M000012.html');return false;">
187
188 <span class="method-name">count_words</span><span class="method-args">()</span>
189
190 </a>
191
192 </div>
193
194 <div class="method-description">
195
196 <p>
197 Returns a Hash containing the words and their associated counts in the
198 current <a href="Document.html">Document</a>.
199 </p>
200 <pre>
201 count_words #=&gt; { &quot;guitar&quot;=&gt;1, &quot;bass&quot;=&gt;3, &quot;album&quot;=&gt;20, ... }
202 </pre>
203
204 </div>
205 </div>
206
207
208 <div id="method-M000013" class="method-detail">
209 <a name="M000013"></a>
210
211 <div class="method-heading">
212
213 <a href="Document.src/M000013.html" target="Code" class="method-signature"
214 onclick="popupCode('Document.src/M000013.html');return false;">
215
216 <span class="method-name">entropy</span><span class="method-args">(s)</span>
217
218 </a>
219
220 </div>
221
222 <div class="method-description">
223
224 <p>
225 Computes the entropy of a given string <tt>s</tt> inside the document.
226 </p>
227 <p>
228 If the string parameter is composed of many words (i.e. tokens separated by
229 whitespace(s)), it is considered as an ngram.
230 </p>
231 <pre>
232 entropy(&quot;guitar&quot;) #=&gt; 0.00389919463243839
233 </pre>
234
235 </div>
236 </div>
237
238
239 <div id="method-M000011" class="method-detail">
240 <a name="M000011"></a>
241
242 <div class="method-heading">
243
244 <a href="Document.src/M000011.html" target="Code" class="method-signature"
245 onclick="popupCode('Document.src/M000011.html');return false;">
246
247 <span class="method-name">ngrams</span><span class="method-args">(n)</span>
248
249 </a>
250
251 </div>
252
253 <div class="method-description">
254
255 <p>
256 Returns an Array containing the <tt>n</tt>-grams (words) from the current
257 <a href="Document.html">Document</a>.
258 </p>
259 <pre>
260 ngrams(2) #=&gt; [&quot;the free&quot;, &quot;free encyclopedia&quot;, &quot;encyclopedia var&quot;, &quot;var skin&quot;, ...]
261 </pre>
262
263 </div>
264 </div>
265
266
267 <h3 class="section-bar">Protected Instance methods</h3>
268
269
270 <div id="method-M000010" class="method-detail">
271 <a name="M000010"></a>
272
273 <div class="method-heading">
274
275 <a href="Document.src/M000010.html" target="Code" class="method-signature"
276 onclick="popupCode('Document.src/M000010.html');return false;">
277
278 <span class="method-name">format_words</span><span class="method-args">()</span>
279
280 </a>
281
282 </div>
283
284 <div class="method-description">
285
286 <p>
287 Any non-word characters are removed from the words (see <a
288 href="http://perldoc.perl.org/perlre.html">perldoc.perl.org/perlre.html</a>
289 and the W special escape).
290 </p>
291 <p>
292 Protected function, only meant to by called at the initialization.
293 </p>
294
295 </div>
296 </div>
297
298
299
300 </div>
301
302
303
304
305 </div>
306
307 <div id="validator-badges">
308 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
309 </div>
310
311 </body>
312 </html>
313 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.src/M000010.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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>format_words (Rir::Document)</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/document.rb, line 31</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">format_words</span>
12 <span class="ruby-identifier">wo</span> = []
13
14 <span class="ruby-ivar">@doc_content</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
15 <span class="ruby-identifier">w</span>.<span class="ruby-identifier">split</span>(<span class="ruby-regexp re">/\W/</span>).<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">sw</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">wo</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">sw</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">sw</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/[a-zA-Z]/</span>
17 <span class="ruby-keyword kw">end</span>
18 <span class="ruby-keyword kw">end</span>
19
20 <span class="ruby-identifier">wo</span>
21 <span class="ruby-keyword kw">end</span></pre>
22 </body>
23 </html>
24 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.src/M000011.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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>ngrams (Rir::Document)</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/document.rb, line 46</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">ngrams</span>(<span class="ruby-identifier">n</span>)
12 <span class="ruby-identifier">window</span> = []
13 <span class="ruby-identifier">ngrams_array</span> = []
14
15 <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">window</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">w</span>)
17 <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">size</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">n</span>
18 <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">push</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">&quot; &quot;</span>)
19 <span class="ruby-identifier">window</span>.<span class="ruby-identifier">delete_at</span>(<span class="ruby-value">0</span>)
20 <span class="ruby-keyword kw">end</span>
21 <span class="ruby-keyword kw">end</span>
22
23 <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">uniq</span>
24 <span class="ruby-keyword kw">end</span></pre>
25 </body>
26 </html>
27 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.src/M000012.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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>count_words (Rir::Document)</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/document.rb, line 64</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">count_words</span>
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 <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-identifier">downcase</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> }
14
15 <span class="ruby-identifier">counts</span>
16 <span class="ruby-keyword kw">end</span></pre>
17 </body>
18 </html>
19 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.src/M000013.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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>entropy (Rir::Document)</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/document.rb, line 77</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">entropy</span>(<span class="ruby-identifier">s</span>)
12 <span class="ruby-identifier">en</span> = <span class="ruby-value">0</span><span class="ruby-value">.0</span>
13 <span class="ruby-identifier">counts</span> = <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>
14
15 <span class="ruby-identifier">s</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span>
16 <span class="ruby-identifier">p_wi</span> = <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">count</span>.<span class="ruby-identifier">to_f</span>
17 <span class="ruby-identifier">en</span> <span class="ruby-operator">+=</span> <span class="ruby-identifier">p_wi</span><span class="ruby-operator">*</span><span class="ruby-constant">Math</span>.<span class="ruby-identifier">log2</span>(<span class="ruby-identifier">p_wi</span>)
18 <span class="ruby-keyword kw">end</span>
19
20 <span class="ruby-identifier">en</span> <span class="ruby-operator">*=</span> <span class="ruby-value">-1</span>
21 <span class="ruby-identifier">en</span>
22 <span class="ruby-keyword kw">end</span></pre>
23 </body>
24 </html>
25 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/Document.src/M000014.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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 (Rir::Document)</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/document.rb, line 92</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">content</span>)
12 <span class="ruby-ivar">@doc_content</span> = <span class="ruby-identifier">content</span>
13 <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">format_words</span>
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/WebDocument.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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: Rir::WebDocument [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">Rir::WebDocument</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/document_rb.html">
57
58 lib/rir/document.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="Document.html">
74
75 Rir::Document
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 id="description">
91 <p>
92 A <a href="WebDocument.html">WebDocument</a> is a <a
93 href="Document.html">Document</a> with a <tt>url</tt>.
94 </p>
95
96 </div>
97
98 </div>
99
100
101 <div id="method-list">
102 <h3 class="section-bar">Methods</h3>
103
104 <div class="name-list">
105
106 <a href="#M000015">get_content</a>&nbsp;&nbsp;
107
108 <a href="#M000016">new</a>&nbsp;&nbsp;
109
110 </div>
111 </div>
112
113 </div>
114
115 <!-- if includes -->
116
117 <div id="section">
118
119
120
121 <div id="attribute-list">
122 <h3 class="section-bar">Attributes</h3>
123
124 <div class="name-list">
125 <table>
126
127 <tr class="top-aligned-row context-row">
128 <td class="context-item-name">url</td>
129
130 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
131
132 <td class="context-item-desc"></td>
133 </tr>
134
135 </table>
136 </div>
137 </div>
138
139
140 <!-- if method_list -->
141
142 <div id="methods">
143
144 <h3 class="section-bar">Public Class methods</h3>
145
146
147 <div id="method-M000015" class="method-detail">
148 <a name="M000015"></a>
149
150 <div class="method-heading">
151
152 <a href="WebDocument.src/M000015.html" target="Code" class="method-signature"
153 onclick="popupCode('WebDocument.src/M000015.html');return false;">
154
155 <span class="method-name">get_content</span><span class="method-args">(url)</span>
156
157 </a>
158
159 </div>
160
161 <div class="method-description">
162
163 <p>
164 Returns the HTML text from the page of a given <tt>url</tt>.
165 </p>
166
167 </div>
168 </div>
169
170
171 <div id="method-M000016" class="method-detail">
172 <a name="M000016"></a>
173
174 <div class="method-heading">
175
176 <a href="WebDocument.src/M000016.html" target="Code" class="method-signature"
177 onclick="popupCode('WebDocument.src/M000016.html');return false;">
178
179 <span class="method-name">new</span><span class="method-args">(url)</span>
180
181 </a>
182
183 </div>
184
185 <div class="method-description">
186
187 <p>
188 <a href="WebDocument.html">WebDocument</a> constructor, the content of the
189 <a href="Document.html">Document</a> is the HTML page without the tags.
190 </p>
191
192 </div>
193 </div>
194
195
196
197 </div>
198
199
200
201
202 </div>
203
204 <div id="validator-badges">
205 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
206 </div>
207
208 </body>
209 </html>
210 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/WebDocument.src/M000015.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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>get_content (Rir::WebDocument)</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/document.rb, line 105</span>
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 <span class="ruby-identifier">require</span> <span class="ruby-value str">'net/http'</span>
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>))
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/WebDocument.src/M000016.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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 (Rir::WebDocument)</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/document.rb, line 112</span>
11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">url</span>)
12 <span class="ruby-ivar">@url</span> = <span class="ruby-identifier">url</span>
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>
14 <span class="ruby-keyword kw">end</span></pre>
15 </body>
16 </html>
17 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
doc/classes/Rir/WikipediaPage.html
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" File was deleted
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: Rir::WikipediaPage [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">Rir::WikipediaPage</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/document_rb.html">
57
58 lib/rir/document.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="WebDocument.html">
74
75 Rir::WebDocument
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 id="description">
91 <p>
92 A <a href="WikipediaPage.html">WikipediaPage</a> is a <a
93 href="WebDocument.html">WebDocument</a>.
94 </p>
95
96 </div>
97
98 </div>
99
100
101 </div>
102
103 <!-- if includes -->
104
105 <div id="section">
106
107
108
109
110 <!-- if method_list -->
111
112
113
114
115 </div>
116
117 <div id="validator-badges">
118 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
119 </div>
120
121 </body>
122 </html>
123 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"