Deveaud Romain / mirimiri

Download as
Browse Code ยป

Commit bc18b961bdd99fd9f3bb51dc8fd6e88757de3eb8

Authored by Romain Deveaud
1 parent 3e81fa06a9
Exists in master

more doc

Showing 25 changed files with 316 additions and 85 deletions Inline Diff

doc/classes/RIR.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>Module: RIR [RDoc Documentation]</title> 5 <title>Module: RIR [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="classHeader"> 45 <div id="classHeader">
46 <table class="header-table"> 46 <table class="header-table">
47 <tr class="top-aligned-row"> 47 <tr class="top-aligned-row">
48 <td><strong>Module</strong></td> 48 <td><strong>Module</strong></td>
49 <td class="class-name-in-header">RIR</td> 49 <td class="class-name-in-header">RIR</td>
50 </tr> 50 </tr>
51 <tr class="top-aligned-row"> 51 <tr class="top-aligned-row">
52 <td><strong>In:</strong></td> 52 <td><strong>In:</strong></td>
53 <td> 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 </a> 60 </a>
61 61
62 62
63 <br /> 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 </a> 70 </a>
71 71
72 72
73 <br /> 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 </td> 85 </td>
76 </tr> 86 </tr>
77 87
78 88
79 </table> 89 </table>
80 </div> 90 </div>
81 <!-- banner header --> 91 <!-- banner header -->
82 92
83 <div id="bodyContent"> 93 <div id="bodyContent">
84 94
85 <div id="contextContent"> 95 <div id="contextContent">
86 96
87 <div id="description"> 97 <div id="description">
88 <p> 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 </p> 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 <hr size="1"></hr><p> 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 </p> 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 </div> 168 </div>
96 169
97 </div> 170 </div>
98 171
99 172
100 </div> 173 </div>
101 174
102 <!-- if includes --> 175 <!-- if includes -->
103 176
104 <div id="section"> 177 <div id="section">
105 178
106 <div id="class-list"> 179 <div id="class-list">
107 <h3 class="section-bar">Classes and Modules</h3> 180 <h3 class="section-bar">Classes and Modules</h3>
108 181
109 Class <a href="RIR/Document.html" class="link">RIR::Document</a><br /> 182 Module <a href="RIR/Indri.html" class="link">RIR::Indri</a><br />
110 Class <a href="RIR/WebDocument.html" class="link">RIR::WebDocument</a><br /> 183 Class <a href="RIR/Corpus.html" class="link">RIR::Corpus</a><br />
111 Class <a href="RIR/WikipediaPage.html" class="link">RIR::WikipediaPage</a><br /> 184 Class <a href="RIR/Query.html" class="link">RIR::Query</a><br />
112 185
113 </div> 186 </div>
114 187
115 <div id="constants-list"> 188 <div id="constants-list">
116 <h3 class="section-bar">Constants</h3> 189 <h3 class="section-bar">Constants</h3>
117 190
118 <div class="name-list"> 191 <div class="name-list">
119 <table summary="Constants"> 192 <table summary="Constants">
120 193
121 <tr class="top-aligned-row context-row"> 194 <tr class="top-aligned-row context-row">
122 <td class="context-item-name">Stoplist</td> 195 <td class="context-item-name">Stoplist</td>
123 <td>=</td> 196 <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> 197 <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>
125 198
126 <td>&nbsp;</td> 199 <td>&nbsp;</td>
127 <td class="context-item-desc"> 200 <td class="context-item-desc">
128 These are the default stopwords provided by Lemur. 201 These are the default stopwords provided by Lemur.
129 202
130 </td> 203 </td>
131 204
132 </tr> 205 </tr>
133 206
134 </table> 207 </table>
135 </div> 208 </div>
136 </div> 209 </div>
137 210
138 211
139 212
140 213
141 <!-- if method_list --> 214 <!-- if method_list -->
142 215
143 216
144 217
145 218
146 </div> 219 </div>
147 220
148 <div id="validator-badges"> 221 <div id="validator-badges">
149 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 222 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
150 </div> 223 </div>
151 224
152 </body> 225 </body>
153 </html> 226 </html>
154 227
doc/classes/RIR/Document.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>Class: RIR::Document [RDoc Documentation]</title> 5 <title>Class: RIR::Document [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="classHeader"> 45 <div id="classHeader">
46 <table class="header-table"> 46 <table class="header-table">
47 <tr class="top-aligned-row"> 47 <tr class="top-aligned-row">
48 <td><strong>Class</strong></td> 48 <td><strong>Class</strong></td>
49 <td class="class-name-in-header">RIR::Document</td> 49 <td class="class-name-in-header">RIR::Document</td>
50 </tr> 50 </tr>
51 <tr class="top-aligned-row"> 51 <tr class="top-aligned-row">
52 <td><strong>In:</strong></td> 52 <td><strong>In:</strong></td>
53 <td> 53 <td>
54 54
55 55
56 <a href="../../files/lib/rir/document_rb.html"> 56 <a href="../../files/lib/rir/document_rb.html">
57 57
58 lib/rir/document.rb 58 lib/rir/document.rb
59 59
60 </a> 60 </a>
61 61
62 62
63 <br /> 63 <br />
64 64
65 </td> 65 </td>
66 </tr> 66 </tr>
67 67
68 68
69 <tr class="top-aligned-row"> 69 <tr class="top-aligned-row">
70 <td><strong>Parent:</strong></td> 70 <td><strong>Parent:</strong></td>
71 <td> 71 <td>
72 72
73 Object 73 Object
74 74
75 </td> 75 </td>
76 </tr> 76 </tr>
77 77
78 </table> 78 </table>
79 </div> 79 </div>
80 <!-- banner header --> 80 <!-- banner header -->
81 81
82 <div id="bodyContent"> 82 <div id="bodyContent">
83 83
84 <div id="contextContent"> 84 <div id="contextContent">
85 85
86 <div id="description"> 86 <div id="description">
87 <p> 87 <p>
88 A <a href="Document.html">Document</a> is a bag of words and is constructed 88 A <a href="Document.html">Document</a> is a bag of words and is constructed
89 from a string. 89 from a string.
90 </p> 90 </p>
91 91
92 </div> 92 </div>
93 93
94 </div> 94 </div>
95 95
96 96
97 <div id="method-list"> 97 <div id="method-list">
98 <h3 class="section-bar">Methods</h3> 98 <h3 class="section-bar">Methods</h3>
99 99
100 <div class="name-list"> 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 </div> 112 </div>
113 </div> 113 </div>
114 114
115 </div> 115 </div>
116 116
117 <!-- if includes --> 117 <!-- if includes -->
118 118
119 <div id="section"> 119 <div id="section">
120 120
121 121
122 122
123 <div id="attribute-list"> 123 <div id="attribute-list">
124 <h3 class="section-bar">Attributes</h3> 124 <h3 class="section-bar">Attributes</h3>
125 125
126 <div class="name-list"> 126 <div class="name-list">
127 <table> 127 <table>
128 128
129 <tr class="top-aligned-row context-row"> 129 <tr class="top-aligned-row context-row">
130 <td class="context-item-name">doc_content</td> 130 <td class="context-item-name">doc_content</td>
131 131
132 <td class="context-item-value">&nbsp;[R]&nbsp;</td> 132 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
133 133
134 <td class="context-item-desc"></td> 134 <td class="context-item-desc"></td>
135 </tr> 135 </tr>
136 136
137 <tr class="top-aligned-row context-row"> 137 <tr class="top-aligned-row context-row">
138 <td class="context-item-name">words</td> 138 <td class="context-item-name">words</td>
139 139
140 <td class="context-item-value">&nbsp;[R]&nbsp;</td> 140 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
141 141
142 <td class="context-item-desc"></td> 142 <td class="context-item-desc"></td>
143 </tr> 143 </tr>
144 144
145 </table> 145 </table>
146 </div> 146 </div>
147 </div> 147 </div>
148 148
149 149
150 <!-- if method_list --> 150 <!-- if method_list -->
151 151
152 <div id="methods"> 152 <div id="methods">
153 153
154 <h3 class="section-bar">Public Class methods</h3> 154 <h3 class="section-bar">Public Class methods</h3>
155 155
156 156
157 <div id="method-M000014" class="method-detail"> 157 <div id="method-M000023" class="method-detail">
158 <a name="M000014"></a> 158 <a name="M000023"></a>
159 159
160 <div class="method-heading"> 160 <div class="method-heading">
161 161
162 <a href="Document.src/M000014.html" target="Code" class="method-signature" 162 <a href="Document.src/M000023.html" target="Code" class="method-signature"
163 onclick="popupCode('Document.src/M000014.html');return false;"> 163 onclick="popupCode('Document.src/M000023.html');return false;">
164 164
165 <span class="method-name">new</span><span class="method-args">(content)</span> 165 <span class="method-name">new</span><span class="method-args">(content)</span>
166 166
167 </a> 167 </a>
168 168
169 </div> 169 </div>
170 170
171 <div class="method-description"> 171 <div class="method-description">
172 172
173 </div> 173 </div>
174 </div> 174 </div>
175 175
176 176
177 <h3 class="section-bar">Public Instance methods</h3> 177 <h3 class="section-bar">Public Instance methods</h3>
178 178
179 179
180 <div id="method-M000012" class="method-detail"> 180 <div id="method-M000021" class="method-detail">
181 <a name="M000012"></a> 181 <a name="M000021"></a>
182 182
183 <div class="method-heading"> 183 <div class="method-heading">
184 184
185 <a href="Document.src/M000012.html" target="Code" class="method-signature" 185 <a href="Document.src/M000021.html" target="Code" class="method-signature"
186 onclick="popupCode('Document.src/M000012.html');return false;"> 186 onclick="popupCode('Document.src/M000021.html');return false;">
187 187
188 <span class="method-name">count_words</span><span class="method-args">()</span> 188 <span class="method-name">count_words</span><span class="method-args">()</span>
189 189
190 </a> 190 </a>
191 191
192 </div> 192 </div>
193 193
194 <div class="method-description"> 194 <div class="method-description">
195 195
196 <p> 196 <p>
197 Returns a Hash containing the words and their associated counts in the 197 Returns a Hash containing the words and their associated counts in the
198 current <a href="Document.html">Document</a>. 198 current <a href="Document.html">Document</a>.
199 </p> 199 </p>
200 <pre> 200 <pre>
201 count_words #=&gt; { &quot;guitar&quot;=&gt;1, &quot;bass&quot;=&gt;3, &quot;album&quot;=&gt;20, ... } 201 count_words #=&gt; { &quot;guitar&quot;=&gt;1, &quot;bass&quot;=&gt;3, &quot;album&quot;=&gt;20, ... }
202 </pre> 202 </pre>
203 203
204 </div> 204 </div>
205 </div> 205 </div>
206 206
207 207
208 <div id="method-M000013" class="method-detail"> 208 <div id="method-M000022" class="method-detail">
209 <a name="M000013"></a> 209 <a name="M000022"></a>
210 210
211 <div class="method-heading"> 211 <div class="method-heading">
212 212
213 <a href="Document.src/M000013.html" target="Code" class="method-signature" 213 <a href="Document.src/M000022.html" target="Code" class="method-signature"
214 onclick="popupCode('Document.src/M000013.html');return false;"> 214 onclick="popupCode('Document.src/M000022.html');return false;">
215 215
216 <span class="method-name">entropy</span><span class="method-args">(s)</span> 216 <span class="method-name">entropy</span><span class="method-args">(s)</span>
217 217
218 </a> 218 </a>
219 219
220 </div> 220 </div>
221 221
222 <div class="method-description"> 222 <div class="method-description">
223 223
224 <p> 224 <p>
225 Computes the entropy of a given string <tt>s</tt> inside the document. 225 Computes the entropy of a given string <tt>s</tt> inside the document.
226 </p> 226 </p>
227 <p> 227 <p>
228 If the string parameter is composed of many words (i.e. tokens separated by 228 If the string parameter is composed of many words (i.e. tokens separated by
229 whitespace(s)), it is considered as an ngram. 229 whitespace(s)), it is considered as an ngram.
230 </p> 230 </p>
231 <pre> 231 <pre>
232 entropy(&quot;guitar&quot;) #=&gt; 0.00389919463243839 232 entropy(&quot;guitar&quot;) #=&gt; 0.00389919463243839
233 </pre> 233 </pre>
234 234
235 </div> 235 </div>
236 </div> 236 </div>
237 237
238 238
239 <div id="method-M000011" class="method-detail"> 239 <div id="method-M000020" class="method-detail">
240 <a name="M000011"></a> 240 <a name="M000020"></a>
241 241
242 <div class="method-heading"> 242 <div class="method-heading">
243 243
244 <a href="Document.src/M000011.html" target="Code" class="method-signature" 244 <a href="Document.src/M000020.html" target="Code" class="method-signature"
245 onclick="popupCode('Document.src/M000011.html');return false;"> 245 onclick="popupCode('Document.src/M000020.html');return false;">
246 246
247 <span class="method-name">ngrams</span><span class="method-args">(n)</span> 247 <span class="method-name">ngrams</span><span class="method-args">(n)</span>
248 248
249 </a> 249 </a>
250 250
251 </div> 251 </div>
252 252
253 <div class="method-description"> 253 <div class="method-description">
254 254
255 <p> 255 <p>
256 Returns an Array containing the <tt>n</tt>-grams (words) from the current 256 Returns an Array containing the <tt>n</tt>-grams (words) from the current
257 <a href="Document.html">Document</a>. 257 <a href="Document.html">Document</a>.
258 </p> 258 </p>
259 <pre> 259 <pre>
260 ngrams(2) #=&gt; [&quot;the free&quot;, &quot;free encyclopedia&quot;, &quot;encyclopedia var&quot;, &quot;var skin&quot;, ...] 260 ngrams(2) #=&gt; [&quot;the free&quot;, &quot;free encyclopedia&quot;, &quot;encyclopedia var&quot;, &quot;var skin&quot;, ...]
261 </pre> 261 </pre>
262 262
263 </div> 263 </div>
264 </div> 264 </div>
265 265
266 266
267 <h3 class="section-bar">Protected Instance methods</h3> 267 <h3 class="section-bar">Protected Instance methods</h3>
268 268
269 269
270 <div id="method-M000010" class="method-detail"> 270 <div id="method-M000019" class="method-detail">
271 <a name="M000010"></a> 271 <a name="M000019"></a>
272 272
273 <div class="method-heading"> 273 <div class="method-heading">
274 274
275 <a href="Document.src/M000010.html" target="Code" class="method-signature" 275 <a href="Document.src/M000019.html" target="Code" class="method-signature"
276 onclick="popupCode('Document.src/M000010.html');return false;"> 276 onclick="popupCode('Document.src/M000019.html');return false;">
277 277
278 <span class="method-name">format_words</span><span class="method-args">()</span> 278 <span class="method-name">format_words</span><span class="method-args">()</span>
279 279
280 </a> 280 </a>
281 281
282 </div> 282 </div>
283 283
284 <div class="method-description"> 284 <div class="method-description">
285 285
286 <p> 286 <p>
287 Any non-word characters are removed from the words (see <a 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> 288 href="http://perldoc.perl.org/perlre.html">perldoc.perl.org/perlre.html</a>
289 and the W special escape). 289 and the W special escape).
290 </p> 290 </p>
291 <p> 291 <p>
292 Protected function, only meant to by called at the initialization. 292 Protected function, only meant to by called at the initialization.
293 </p> 293 </p>
294 294
295 </div> 295 </div>
296 </div> 296 </div>
297 297
298 298
299 299
300 </div> 300 </div>
301 301
302 302
303 303
304 304
305 </div> 305 </div>
306 306
307 <div id="validator-badges"> 307 <div id="validator-badges">
308 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 308 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
309 </div> 309 </div>
310 310
311 </body> 311 </body>
312 </html> 312 </html>
313 313
doc/classes/RIR/WebDocument.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>Class: RIR::WebDocument [RDoc Documentation]</title> 5 <title>Class: RIR::WebDocument [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="classHeader"> 45 <div id="classHeader">
46 <table class="header-table"> 46 <table class="header-table">
47 <tr class="top-aligned-row"> 47 <tr class="top-aligned-row">
48 <td><strong>Class</strong></td> 48 <td><strong>Class</strong></td>
49 <td class="class-name-in-header">RIR::WebDocument</td> 49 <td class="class-name-in-header">RIR::WebDocument</td>
50 </tr> 50 </tr>
51 <tr class="top-aligned-row"> 51 <tr class="top-aligned-row">
52 <td><strong>In:</strong></td> 52 <td><strong>In:</strong></td>
53 <td> 53 <td>
54 54
55 55
56 <a href="../../files/lib/rir/document_rb.html"> 56 <a href="../../files/lib/rir/document_rb.html">
57 57
58 lib/rir/document.rb 58 lib/rir/document.rb
59 59
60 </a> 60 </a>
61 61
62 62
63 <br /> 63 <br />
64 64
65 </td> 65 </td>
66 </tr> 66 </tr>
67 67
68 68
69 <tr class="top-aligned-row"> 69 <tr class="top-aligned-row">
70 <td><strong>Parent:</strong></td> 70 <td><strong>Parent:</strong></td>
71 <td> 71 <td>
72 72
73 <a href="Document.html"> 73 <a href="Document.html">
74 74
75 RIR::Document 75 RIR::Document
76 76
77 </a> 77 </a>
78 78
79 </td> 79 </td>
80 </tr> 80 </tr>
81 81
82 </table> 82 </table>
83 </div> 83 </div>
84 <!-- banner header --> 84 <!-- banner header -->
85 85
86 <div id="bodyContent"> 86 <div id="bodyContent">
87 87
88 <div id="contextContent"> 88 <div id="contextContent">
89 89
90 <div id="description"> 90 <div id="description">
91 <p> 91 <p>
92 A <a href="WebDocument.html">WebDocument</a> is a <a 92 A <a href="WebDocument.html">WebDocument</a> is a <a
93 href="Document.html">Document</a> with a <tt>url</tt>. 93 href="Document.html">Document</a> with a <tt>url</tt>.
94 </p> 94 </p>
95 95
96 </div> 96 </div>
97 97
98 </div> 98 </div>
99 99
100 100
101 <div id="method-list"> 101 <div id="method-list">
102 <h3 class="section-bar">Methods</h3> 102 <h3 class="section-bar">Methods</h3>
103 103
104 <div class="name-list"> 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 </div> 110 </div>
111 </div> 111 </div>
112 112
113 </div> 113 </div>
114 114
115 <!-- if includes --> 115 <!-- if includes -->
116 116
117 <div id="section"> 117 <div id="section">
118 118
119 119
120 120
121 <div id="attribute-list"> 121 <div id="attribute-list">
122 <h3 class="section-bar">Attributes</h3> 122 <h3 class="section-bar">Attributes</h3>
123 123
124 <div class="name-list"> 124 <div class="name-list">
125 <table> 125 <table>
126 126
127 <tr class="top-aligned-row context-row"> 127 <tr class="top-aligned-row context-row">
128 <td class="context-item-name">url</td> 128 <td class="context-item-name">url</td>
129 129
130 <td class="context-item-value">&nbsp;[R]&nbsp;</td> 130 <td class="context-item-value">&nbsp;[R]&nbsp;</td>
131 131
132 <td class="context-item-desc"></td> 132 <td class="context-item-desc"></td>
133 </tr> 133 </tr>
134 134
135 </table> 135 </table>
136 </div> 136 </div>
137 </div> 137 </div>
138 138
139 139
140 <!-- if method_list --> 140 <!-- if method_list -->
141 141
142 <div id="methods"> 142 <div id="methods">
143 143
144 <h3 class="section-bar">Public Class methods</h3> 144 <h3 class="section-bar">Public Class methods</h3>
145 145
146 146
147 <div id="method-M000015" class="method-detail"> 147 <div id="method-M000024" class="method-detail">
148 <a name="M000015"></a> 148 <a name="M000024"></a>
149 149
150 <div class="method-heading"> 150 <div class="method-heading">
151 151
152 <a href="WebDocument.src/M000015.html" target="Code" class="method-signature" 152 <a href="WebDocument.src/M000024.html" target="Code" class="method-signature"
153 onclick="popupCode('WebDocument.src/M000015.html');return false;"> 153 onclick="popupCode('WebDocument.src/M000024.html');return false;">
154 154
155 <span class="method-name">get_content</span><span class="method-args">(url)</span> 155 <span class="method-name">get_content</span><span class="method-args">(url)</span>
156 156
157 </a> 157 </a>
158 158
159 </div> 159 </div>
160 160
161 <div class="method-description"> 161 <div class="method-description">
162 162
163 <p> 163 <p>
164 Returns the HTML text from the page of a given <tt>url</tt>. 164 Returns the HTML text from the page of a given <tt>url</tt>.
165 </p> 165 </p>
166 166
167 </div> 167 </div>
168 </div> 168 </div>
169 169
170 170
171 <div id="method-M000016" class="method-detail"> 171 <div id="method-M000025" class="method-detail">
172 <a name="M000016"></a> 172 <a name="M000025"></a>
173 173
174 <div class="method-heading"> 174 <div class="method-heading">
175 175
176 <a href="WebDocument.src/M000016.html" target="Code" class="method-signature" 176 <a href="WebDocument.src/M000025.html" target="Code" class="method-signature"
177 onclick="popupCode('WebDocument.src/M000016.html');return false;"> 177 onclick="popupCode('WebDocument.src/M000025.html');return false;">
178 178
179 <span class="method-name">new</span><span class="method-args">(url)</span> 179 <span class="method-name">new</span><span class="method-args">(url)</span>
180 180
181 </a> 181 </a>
182 182
183 </div> 183 </div>
184 184
185 <div class="method-description"> 185 <div class="method-description">
186 186
187 <p> 187 <p>
188 <a href="WebDocument.html">WebDocument</a> constructor, the content of the 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. 189 <a href="Document.html">Document</a> is the HTML page without the tags.
190 </p> 190 </p>
191 191
192 </div> 192 </div>
193 </div> 193 </div>
194 194
195 195
196 196
197 </div> 197 </div>
198 198
199 199
200 200
201 201
202 </div> 202 </div>
203 203
204 <div id="validator-badges"> 204 <div id="validator-badges">
205 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 205 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
206 </div> 206 </div>
207 207
208 </body> 208 </body>
209 </html> 209 </html>
210 210
doc/classes/RIR/WikipediaPage.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>Class: RIR::WikipediaPage [RDoc Documentation]</title> 5 <title>Class: RIR::WikipediaPage [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="classHeader"> 45 <div id="classHeader">
46 <table class="header-table"> 46 <table class="header-table">
47 <tr class="top-aligned-row"> 47 <tr class="top-aligned-row">
48 <td><strong>Class</strong></td> 48 <td><strong>Class</strong></td>
49 <td class="class-name-in-header">RIR::WikipediaPage</td> 49 <td class="class-name-in-header">RIR::WikipediaPage</td>
50 </tr> 50 </tr>
51 <tr class="top-aligned-row"> 51 <tr class="top-aligned-row">
52 <td><strong>In:</strong></td> 52 <td><strong>In:</strong></td>
53 <td> 53 <td>
54 54
55 55
56 <a href="../../files/lib/rir/document_rb.html"> 56 <a href="../../files/lib/rir/document_rb.html">
57 57
58 lib/rir/document.rb 58 lib/rir/document.rb
59 59
60 </a> 60 </a>
61 61
62 62
63 <br /> 63 <br />
64 64
65 </td> 65 </td>
66 </tr> 66 </tr>
67 67
68 68
69 <tr class="top-aligned-row"> 69 <tr class="top-aligned-row">
70 <td><strong>Parent:</strong></td> 70 <td><strong>Parent:</strong></td>
71 <td> 71 <td>
72 72
73 <a href="WebDocument.html"> 73 <a href="WebDocument.html">
74 74
75 RIR::WebDocument 75 RIR::WebDocument
76 76
77 </a> 77 </a>
78 78
79 </td> 79 </td>
80 </tr> 80 </tr>
81 81
82 </table> 82 </table>
83 </div> 83 </div>
84 <!-- banner header --> 84 <!-- banner header -->
85 85
86 <div id="bodyContent"> 86 <div id="bodyContent">
87 87
88 <div id="contextContent"> 88 <div id="contextContent">
89 89
90 <div id="description"> 90 <div id="description">
91 <p> 91 <p>
92 A <a href="WikipediaPage.html">WikipediaPage</a> is a <a 92 A <a href="WikipediaPage.html">WikipediaPage</a> is a <a
93 href="WebDocument.html">WebDocument</a>. 93 href="WebDocument.html">WebDocument</a>.
94 </p> 94 </p>
95 95
96 </div> 96 </div>
97 97
98 </div> 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 </div> 115 </div>
102 116
103 <!-- if includes --> 117 <!-- if includes -->
104 118
105 <div id="section"> 119 <div id="section">
106 120
107 121
108 122
109 123
110 <!-- if method_list --> 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
114 196
115 </div> 197 </div>
116 198
117 <div id="validator-badges"> 199 <div id="validator-badges">
118 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 200 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
119 </div> 201 </div>
120 202
121 </body> 203 </body>
122 </html> 204 </html>
123 205
doc/classes/String.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>Class: String [RDoc Documentation]</title> 5 <title>Class: String [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="classHeader"> 45 <div id="classHeader">
46 <table class="header-table"> 46 <table class="header-table">
47 <tr class="top-aligned-row"> 47 <tr class="top-aligned-row">
48 <td><strong>Class</strong></td> 48 <td><strong>Class</strong></td>
49 <td class="class-name-in-header">String</td> 49 <td class="class-name-in-header">String</td>
50 </tr> 50 </tr>
51 <tr class="top-aligned-row"> 51 <tr class="top-aligned-row">
52 <td><strong>In:</strong></td> 52 <td><strong>In:</strong></td>
53 <td> 53 <td>
54 54
55 55
56 <a href="../files/lib/rir/string_rb.html"> 56 <a href="../files/lib/rir/string_rb.html">
57 57
58 lib/rir/string.rb 58 lib/rir/string.rb
59 59
60 </a> 60 </a>
61 61
62 62
63 <br /> 63 <br />
64 64
65 </td> 65 </td>
66 </tr> 66 </tr>
67 67
68 68
69 <tr class="top-aligned-row"> 69 <tr class="top-aligned-row">
70 <td><strong>Parent:</strong></td> 70 <td><strong>Parent:</strong></td>
71 <td> 71 <td>
72 72
73 Object 73 Object
74 74
75 </td> 75 </td>
76 </tr> 76 </tr>
77 77
78 </table> 78 </table>
79 </div> 79 </div>
80 <!-- banner header --> 80 <!-- banner header -->
81 81
82 <div id="bodyContent"> 82 <div id="bodyContent">
83 83
84 <div id="contextContent"> 84 <div id="contextContent">
85 85
86 <div id="description"> 86 <div id="description">
87 <p> 87 <p>
88 Extention of the standard class <a href="String.html">String</a> with 88 Extention of the standard class <a href="String.html">String</a> with
89 useful function. 89 useful function.
90 </p> 90 </p>
91 91
92 </div> 92 </div>
93 93
94 </div> 94 </div>
95 95
96 96
97 <div id="method-list"> 97 <div id="method-list">
98 <h3 class="section-bar">Methods</h3> 98 <h3 class="section-bar">Methods</h3>
99 99
100 <div class="name-list"> 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 <a href="#M000001">is_stopword?</a>&nbsp;&nbsp; 104 <a href="#M000001">is_stopword?</a>&nbsp;&nbsp;
105 105
106 <a href="#M000002">remove_special_characters</a>&nbsp;&nbsp; 106 <a href="#M000002">remove_special_characters</a>&nbsp;&nbsp;
107 107
108 <a href="#M000006">strip_javascripts</a>&nbsp;&nbsp; 108 <a href="#M000006">strip_javascripts</a>&nbsp;&nbsp;
109 109
110 <a href="#M000005">strip_javascripts!</a>&nbsp;&nbsp; 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 <a href="#M000008">strip_stylesheets</a>&nbsp;&nbsp; 116 <a href="#M000008">strip_stylesheets</a>&nbsp;&nbsp;
113 117
114 <a href="#M000007">strip_stylesheets!</a>&nbsp;&nbsp; 118 <a href="#M000007">strip_stylesheets!</a>&nbsp;&nbsp;
115 119
116 <a href="#M000004">strip_xml_tags</a>&nbsp;&nbsp; 120 <a href="#M000004">strip_xml_tags</a>&nbsp;&nbsp;
117 121
118 <a href="#M000003">strip_xml_tags!</a>&nbsp;&nbsp; 122 <a href="#M000003">strip_xml_tags!</a>&nbsp;&nbsp;
119 123
120 </div> 124 </div>
121 </div> 125 </div>
122 126
123 </div> 127 </div>
124 128
125 <!-- if includes --> 129 <!-- if includes -->
126 130
127 <div id="includes"> 131 <div id="includes">
128 <h3 class="section-bar">Included Modules</h3> 132 <h3 class="section-bar">Included Modules</h3>
129 133
130 <div id="includes-list"> 134 <div id="includes-list">
131 135
132 <span class="include-name"><a href="RIR.html">RIR</a></span> 136 <span class="include-name"><a href="RIR.html">RIR</a></span>
133 137
134 </div> 138 </div>
135 </div> 139 </div>
136 140
137 <div id="section"> 141 <div id="section">
138 142
139 143
140 144
141 145
142 <!-- if method_list --> 146 <!-- if method_list -->
143 147
144 <div id="methods"> 148 <div id="methods">
145 149
146 <h3 class="section-bar">Public Instance methods</h3> 150 <h3 class="section-bar">Public Instance methods</h3>
147 151
148 152
149 <div id="method-M000009" class="method-detail"> 153 <div id="method-M000011" class="method-detail">
150 <a name="M000009"></a> 154 <a name="M000011"></a>
151 155
152 <div class="method-heading"> 156 <div class="method-heading">
153 157
154 <a href="String.src/M000009.html" target="Code" class="method-signature" 158 <a href="String.src/M000011.html" target="Code" class="method-signature"
155 onclick="popupCode('String.src/M000009.html');return false;"> 159 onclick="popupCode('String.src/M000011.html');return false;">
156 160
157 <span class="method-name">extract_xmltags_values</span><span class="method-args">(tag_name)</span> 161 <span class="method-name">extract_xmltags_values</span><span class="method-args">(tag_name)</span>
158 162
159 </a> 163 </a>
160 164
161 </div> 165 </div>
162 166
163 <div class="method-description"> 167 <div class="method-description">
164 168
165 <p> 169 <p>
166 Returns the text values inside all occurences of a XML tag in <tt>self</tt> 170 Returns the text values inside all occurences of a XML tag in <tt>self</tt>
167 </p> 171 </p>
168 <pre> 172 <pre>
169 s = &quot;four-piece in &lt;a href='#'&gt;Indianapolis&lt;/a&gt;, &lt;a href='#'&gt;Indiana&lt;/a&gt; at the Murat Theatre&quot; 173 s = &quot;four-piece in &lt;a href='#'&gt;Indianapolis&lt;/a&gt;, &lt;a href='#'&gt;Indiana&lt;/a&gt; at the Murat Theatre&quot;
170 s.extract_xmltags_values 'a' #=&gt; [&quot;Indianapolis&quot;, &quot;Indiana&quot;] 174 s.extract_xmltags_values 'a' #=&gt; [&quot;Indianapolis&quot;, &quot;Indiana&quot;]
171 </pre> 175 </pre>
172 176
173 </div> 177 </div>
174 </div> 178 </div>
175 179
176 180
177 <div id="method-M000001" class="method-detail"> 181 <div id="method-M000001" class="method-detail">
178 <a name="M000001"></a> 182 <a name="M000001"></a>
179 183
180 <div class="method-heading"> 184 <div class="method-heading">
181 185
182 <a href="String.src/M000001.html" target="Code" class="method-signature" 186 <a href="String.src/M000001.html" target="Code" class="method-signature"
183 onclick="popupCode('String.src/M000001.html');return false;"> 187 onclick="popupCode('String.src/M000001.html');return false;">
184 188
185 <span class="method-name">is_stopword?</span><span class="method-args">()</span> 189 <span class="method-name">is_stopword?</span><span class="method-args">()</span>
186 190
187 </a> 191 </a>
188 192
189 </div> 193 </div>
190 194
191 <div class="method-description"> 195 <div class="method-description">
192 196
193 <p> 197 <p>
194 Returns <tt>true</tt> if <tt>self</tt> belongs to Rir::Stoplist, 198 Returns <tt>true</tt> if <tt>self</tt> belongs to Rir::Stoplist,
195 <tt>false</tt> otherwise. 199 <tt>false</tt> otherwise.
196 </p> 200 </p>
197 201
198 </div> 202 </div>
199 </div> 203 </div>
200 204
201 205
202 <div id="method-M000002" class="method-detail"> 206 <div id="method-M000002" class="method-detail">
203 <a name="M000002"></a> 207 <a name="M000002"></a>
204 208
205 <div class="method-heading"> 209 <div class="method-heading">
206 210
207 <a href="String.src/M000002.html" target="Code" class="method-signature" 211 <a href="String.src/M000002.html" target="Code" class="method-signature"
208 onclick="popupCode('String.src/M000002.html');return false;"> 212 onclick="popupCode('String.src/M000002.html');return false;">
209 213
210 <span class="method-name">remove_special_characters</span><span class="method-args">()</span> 214 <span class="method-name">remove_special_characters</span><span class="method-args">()</span>
211 215
212 </a> 216 </a>
213 217
214 </div> 218 </div>
215 219
216 <div class="method-description"> 220 <div class="method-description">
217 221
218 <p> 222 <p>
219 Do not use. TODO: rewamp. find why this function is here. 223 Do not use. TODO: rewamp. find why this function is here.
220 </p> 224 </p>
221 225
222 </div> 226 </div>
223 </div> 227 </div>
224 228
225 229
226 <div id="method-M000006" class="method-detail"> 230 <div id="method-M000006" class="method-detail">
227 <a name="M000006"></a> 231 <a name="M000006"></a>
228 232
229 <div class="method-heading"> 233 <div class="method-heading">
230 234
231 <a href="String.src/M000006.html" target="Code" class="method-signature" 235 <a href="String.src/M000006.html" target="Code" class="method-signature"
232 onclick="popupCode('String.src/M000006.html');return false;"> 236 onclick="popupCode('String.src/M000006.html');return false;">
233 237
234 <span class="method-name">strip_javascripts</span><span class="method-args">()</span> 238 <span class="method-name">strip_javascripts</span><span class="method-args">()</span>
235 239
236 </a> 240 </a>
237 241
238 </div> 242 </div>
239 243
240 <div class="method-description"> 244 <div class="method-description">
241 245
242 <p> 246 <p>
243 Removes all Javascript sources from <tt>self</tt>. 247 Removes all Javascript sources from <tt>self</tt>.
244 </p> 248 </p>
245 <pre> 249 <pre>
246 s = &quot;&lt;script type='text/javascript'&gt; 250 s = &quot;&lt;script type='text/javascript'&gt;
247 var skin='vector', 251 var skin='vector',
248 stylepath='http://bits.wikimedia.org/skins-1.5' 252 stylepath='http://bits.wikimedia.org/skins-1.5'
249 &lt;/script&gt; 253 &lt;/script&gt;
250 254
251 test&quot; 255 test&quot;
252 s.strip_javascripts #=&gt; &quot;test&quot; 256 s.strip_javascripts #=&gt; &quot;test&quot;
253 </pre> 257 </pre>
254 258
255 </div> 259 </div>
256 </div> 260 </div>
257 261
258 262
259 <div id="method-M000005" class="method-detail"> 263 <div id="method-M000005" class="method-detail">
260 <a name="M000005"></a> 264 <a name="M000005"></a>
261 265
262 <div class="method-heading"> 266 <div class="method-heading">
263 267
264 <a href="String.src/M000005.html" target="Code" class="method-signature" 268 <a href="String.src/M000005.html" target="Code" class="method-signature"
265 onclick="popupCode('String.src/M000005.html');return false;"> 269 onclick="popupCode('String.src/M000005.html');return false;">
266 270
267 <span class="method-name">strip_javascripts!</span><span class="method-args">()</span> 271 <span class="method-name">strip_javascripts!</span><span class="method-args">()</span>
268 272
269 </a> 273 </a>
270 274
271 </div> 275 </div>
272 276
273 <div class="method-description"> 277 <div class="method-description">
274 278
275 <p> 279 <p>
276 Removes all Javascript sources from <tt>self</tt>. 280 Removes all Javascript sources from <tt>self</tt>.
277 </p> 281 </p>
278 <pre> 282 <pre>
279 s = &quot;&lt;script type='text/javascript'&gt; 283 s = &quot;&lt;script type='text/javascript'&gt;
280 var skin='vector', 284 var skin='vector',
281 stylepath='http://bits.wikimedia.org/skins-1.5' 285 stylepath='http://bits.wikimedia.org/skins-1.5'
282 &lt;/script&gt; 286 &lt;/script&gt;
283 287
284 test&quot; 288 test&quot;
285 s.strip_javascripts! 289 s.strip_javascripts!
286 s #=&gt; &quot;test&quot; 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 </pre> 348 </pre>
288 349
289 </div> 350 </div>
290 </div> 351 </div>
291 352
292 353
293 <div id="method-M000008" class="method-detail"> 354 <div id="method-M000008" class="method-detail">
294 <a name="M000008"></a> 355 <a name="M000008"></a>
295 356
296 <div class="method-heading"> 357 <div class="method-heading">
297 358
298 <a href="String.src/M000008.html" target="Code" class="method-signature" 359 <a href="String.src/M000008.html" target="Code" class="method-signature"
299 onclick="popupCode('String.src/M000008.html');return false;"> 360 onclick="popupCode('String.src/M000008.html');return false;">
300 361
301 <span class="method-name">strip_stylesheets</span><span class="method-args">()</span> 362 <span class="method-name">strip_stylesheets</span><span class="method-args">()</span>
302 363
303 </a> 364 </a>
304 365
305 </div> 366 </div>
306 367
307 <div class="method-description"> 368 <div class="method-description">
308 369
309 </div> 370 </div>
310 </div> 371 </div>
311 372
312 373
313 <div id="method-M000007" class="method-detail"> 374 <div id="method-M000007" class="method-detail">
314 <a name="M000007"></a> 375 <a name="M000007"></a>
315 376
316 <div class="method-heading"> 377 <div class="method-heading">
317 378
318 <a href="String.src/M000007.html" target="Code" class="method-signature" 379 <a href="String.src/M000007.html" target="Code" class="method-signature"
319 onclick="popupCode('String.src/M000007.html');return false;"> 380 onclick="popupCode('String.src/M000007.html');return false;">
320 381
321 <span class="method-name">strip_stylesheets!</span><span class="method-args">()</span> 382 <span class="method-name">strip_stylesheets!</span><span class="method-args">()</span>
322 383
323 </a> 384 </a>
324 385
325 </div> 386 </div>
326 387
327 <div class="method-description"> 388 <div class="method-description">
328 389
329 </div> 390 </div>
330 </div> 391 </div>
331 392
332 393
333 <div id="method-M000004" class="method-detail"> 394 <div id="method-M000004" class="method-detail">
334 <a name="M000004"></a> 395 <a name="M000004"></a>
335 396
336 <div class="method-heading"> 397 <div class="method-heading">
337 398
338 <a href="String.src/M000004.html" target="Code" class="method-signature" 399 <a href="String.src/M000004.html" target="Code" class="method-signature"
339 onclick="popupCode('String.src/M000004.html');return false;"> 400 onclick="popupCode('String.src/M000004.html');return false;">
340 401
341 <span class="method-name">strip_xml_tags</span><span class="method-args">()</span> 402 <span class="method-name">strip_xml_tags</span><span class="method-args">()</span>
342 403
343 </a> 404 </a>
344 405
345 </div> 406 </div>
346 407
347 <div class="method-description"> 408 <div class="method-description">
348 409
349 <p> 410 <p>
350 Removes all XML-like tags from <tt>self</tt>. 411 Removes all XML-like tags from <tt>self</tt>.
351 </p> 412 </p>
352 <pre> 413 <pre>
353 s = &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot; 414 s = &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot;
354 s.strip_xml_tags #=&gt; &quot;test&quot; 415 s.strip_xml_tags #=&gt; &quot;test&quot;
355 s #=&gt; &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot; 416 s #=&gt; &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot;
356 </pre> 417 </pre>
357 418
358 </div> 419 </div>
359 </div> 420 </div>
360 421
361 422
362 <div id="method-M000003" class="method-detail"> 423 <div id="method-M000003" class="method-detail">
363 <a name="M000003"></a> 424 <a name="M000003"></a>
364 425
365 <div class="method-heading"> 426 <div class="method-heading">
366 427
367 <a href="String.src/M000003.html" target="Code" class="method-signature" 428 <a href="String.src/M000003.html" target="Code" class="method-signature"
368 onclick="popupCode('String.src/M000003.html');return false;"> 429 onclick="popupCode('String.src/M000003.html');return false;">
369 430
370 <span class="method-name">strip_xml_tags!</span><span class="method-args">()</span> 431 <span class="method-name">strip_xml_tags!</span><span class="method-args">()</span>
371 432
372 </a> 433 </a>
373 434
374 </div> 435 </div>
375 436
376 <div class="method-description"> 437 <div class="method-description">
377 438
378 <p> 439 <p>
379 Removes all XML-like tags from <tt>self</tt>. 440 Removes all XML-like tags from <tt>self</tt>.
380 </p> 441 </p>
381 <pre> 442 <pre>
382 s = &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot; 443 s = &quot;&lt;html&gt;&lt;body&gt;test&lt;/body&gt;&lt;/html&gt;&quot;
383 s.strip_xml_tags! 444 s.strip_xml_tags!
384 s #=&gt; &quot;test&quot; 445 s #=&gt; &quot;test&quot;
385 </pre> 446 </pre>
386 447
387 </div> 448 </div>
388 </div> 449 </div>
389 450
390 451
391 452
392 </div> 453 </div>
393 454
394 455
395 456
396 457
397 </div> 458 </div>
398 459
399 <div id="validator-badges"> 460 <div id="validator-badges">
400 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 461 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
401 </div> 462 </div>
402 463
403 </body> 464 </body>
404 </html> 465 </html>
405 466
doc/classes/String.src/M000001.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>is_stopword? (String)</title> 5 <title>is_stopword? (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">is_stopword?</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">is_stopword?</span>
12 <span class="ruby-constant">Stoplist</span>.<span class="ruby-identifier">include?</span>(<span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">downcase</span>) 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 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000002.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>remove_special_characters (String)</title> 5 <title>remove_special_characters (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">remove_special_characters</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">remove_special_characters</span>
12 <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">w</span>.<span class="ruby-identifier">gsub</span>(<span class="ruby-regexp re">/\W/</span>,<span class="ruby-value str">' '</span>).<span class="ruby-identifier">split</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">w</span>.<span class="ruby-identifier">gsub</span>(<span class="ruby-regexp re">/\W/</span>,<span class="ruby-value str">' '</span>).<span class="ruby-identifier">strip</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/\A.\z/</span>, <span class="ruby-value str">''</span>)}.<span class="ruby-identifier">join</span>(<span class="ruby-value str">' '</span>).<span class="ruby-identifier">strip</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/\A.\z/</span>, <span class="ruby-value str">''</span>)}.<span class="ruby-identifier">join</span>(<span class="ruby-value str">' '</span>) 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 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000003.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_xml_tags! (String)</title> 5 <title>strip_xml_tags! (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span>
12 <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/?[^&gt;]*&gt;/</span> 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 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000004.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_xml_tags (String)</title> 5 <title>strip_xml_tags (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span>
12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_xml_tags!</span> 12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_xml_tags!</span>
13 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000005.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_javascripts! (String)</title> 5 <title>strip_javascripts! (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span>
12 <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">script</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/javascript&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/script&gt;/</span><span class="ruby-identifier">m</span> 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 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000006.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_javascripts (String)</title> 5 <title>strip_javascripts (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</span>
12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_javascripts!</span> 12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_javascripts!</span>
13 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000007.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_stylesheets! (String)</title> 5 <title>strip_stylesheets! (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span>
12 <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</span> 12 <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</span>
13 <span class="ruby-identifier">replace</span> <span class="ruby-identifier">strip_with_pattern</span> <span class="ruby-operator">/</span><span class="ruby-operator">&lt;</span><span class="ruby-identifier">style</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">&quot;text\/css&quot;</span><span class="ruby-operator">&gt;</span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator">&lt;</span>\<span class="ruby-regexp re">/style&gt;/</span><span class="ruby-identifier">m</span> 13 <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>
14 <span class="ruby-keyword kw">end</span></pre> 14 <span class="ruby-keyword kw">end</span></pre>
15 </body> 15 </body>
16 </html> 16 </html>
17 17
doc/classes/String.src/M000008.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>strip_stylesheets (String)</title> 5 <title>strip_stylesheets (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 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 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</span> 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</span>
12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_stylesheets!</span> 12 <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_stylesheets!</span>
13 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
doc/classes/String.src/M000009.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>extract_xmltags_values (String)</title> 5 <title>strip_punctuation! (String)</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 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" /> 7 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
8 </head> 8 </head>
9 <body class="standalone-code"> 9 <body class="standalone-code">
10 <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 145</span> 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>) 11 <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation!</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> 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 <span class="ruby-keyword kw">end</span></pre> 13 <span class="ruby-keyword kw">end</span></pre>
14 </body> 14 </body>
15 </html> 15 </html>
16 16
1 Fri, 05 Nov 2010 15:06:41 +0100 1 Tue, 23 Nov 2010 18:20:46 +0100
2 2
doc/files/lib/rir/document_rb.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>File: document.rb [RDoc Documentation]</title> 5 <title>File: document.rb [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="fileHeader"> 45 <div id="fileHeader">
46 <h1>document.rb</h1> 46 <h1>document.rb</h1>
47 <table class="header-table"> 47 <table class="header-table">
48 <tr class="top-aligned-row"> 48 <tr class="top-aligned-row">
49 <td><strong>Path:</strong></td> 49 <td><strong>Path:</strong></td>
50 <td>lib/rir/document.rb 50 <td>lib/rir/document.rb
51 51
52 </td> 52 </td>
53 </tr> 53 </tr>
54 <tr class="top-aligned-row"> 54 <tr class="top-aligned-row">
55 <td><strong>Last Update:</strong></td> 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 </tr> 57 </tr>
58 </table> 58 </table>
59 </div> 59 </div>
60 <!-- banner header --> 60 <!-- banner header -->
61 61
62 <div id="bodyContent"> 62 <div id="bodyContent">
63 63
64 <div id="contextContent"> 64 <div id="contextContent">
65 65
66 <div id="description"> 66 <div id="description">
67 <p> 67 <p>
68 This file is a part of an Information Retrieval oriented Ruby library 68 This file is a part of an Information Retrieval oriented Ruby library
69 </p> 69 </p>
70 <p> 70 <p>
71 Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> 71 Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72 </p> 72 </p>
73 <p> 73 <p>
74 This program is free software: you can redistribute it and/or modify it 74 This program is free software: you can redistribute it and/or modify it
75 under the terms of the GNU General Public License as published by the Free 75 under the terms of the GNU General Public License as published by the Free
76 Software Foundation, either version 3 of the License, or (at your option) 76 Software Foundation, either version 3 of the License, or (at your option)
77 any later version. 77 any later version.
78 </p> 78 </p>
79 <p> 79 <p>
80 This program is distributed in the hope that it will be useful, but WITHOUT 80 This program is distributed in the hope that it will be useful, but WITHOUT
81 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 81 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for 82 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83 more details. 83 more details.
84 </p> 84 </p>
85 <p> 85 <p>
86 You should have received a copy of the GNU General Public License along 86 You should have received a copy of the GNU General Public License along
87 with this program. If not, see <<a 87 with this program. If not, see <<a
88 href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. 88 href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89 </p> 89 </p>
90 90
91 </div> 91 </div>
92 92
93 <div id="requires-list"> 93 <div id="requires-list">
94 <h3 class="section-bar">Required files</h3> 94 <h3 class="section-bar">Required files</h3>
95 95
96 <div class="name-list"> 96 <div class="name-list">
97 97
98 net/http&nbsp;&nbsp; 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 </div> 106 </div>
101 </div> 107 </div>
102 108
103 </div> 109 </div>
104 110
105 111
106 </div> 112 </div>
107 113
108 <!-- if includes --> 114 <!-- if includes -->
109 115
110 <div id="section"> 116 <div id="section">
111 117
112 118
113 119
114 120
115 <!-- if method_list --> 121 <!-- if method_list -->
116 122
117 123
118 124
119 125
120 </div> 126 </div>
121 127
122 <div id="validator-badges"> 128 <div id="validator-badges">
123 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 129 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
124 </div> 130 </div>
125 131
126 </body> 132 </body>
127 </html> 133 </html>
128 134
doc/files/lib/rir/string_rb.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>File: string.rb [RDoc Documentation]</title> 5 <title>File: string.rb [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="fileHeader"> 45 <div id="fileHeader">
46 <h1>string.rb</h1> 46 <h1>string.rb</h1>
47 <table class="header-table"> 47 <table class="header-table">
48 <tr class="top-aligned-row"> 48 <tr class="top-aligned-row">
49 <td><strong>Path:</strong></td> 49 <td><strong>Path:</strong></td>
50 <td>lib/rir/string.rb 50 <td>lib/rir/string.rb
51 51
52 </td> 52 </td>
53 </tr> 53 </tr>
54 <tr class="top-aligned-row"> 54 <tr class="top-aligned-row">
55 <td><strong>Last Update:</strong></td> 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 </tr> 57 </tr>
58 </table> 58 </table>
59 </div> 59 </div>
60 <!-- banner header --> 60 <!-- banner header -->
61 61
62 <div id="bodyContent"> 62 <div id="bodyContent">
63 63
64 <div id="contextContent"> 64 <div id="contextContent">
65 65
66 <div id="description"> 66 <div id="description">
67 <p> 67 <p>
68 This file is a part of an Information Retrieval oriented Ruby library 68 This file is a part of an Information Retrieval oriented Ruby library
69 </p> 69 </p>
70 <p> 70 <p>
71 Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> 71 Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
72 </p> 72 </p>
73 <p> 73 <p>
74 This program is free software: you can redistribute it and/or modify it 74 This program is free software: you can redistribute it and/or modify it
75 under the terms of the GNU General Public License as published by the Free 75 under the terms of the GNU General Public License as published by the Free
76 Software Foundation, either version 3 of the License, or (at your option) 76 Software Foundation, either version 3 of the License, or (at your option)
77 any later version. 77 any later version.
78 </p> 78 </p>
79 <p> 79 <p>
80 This program is distributed in the hope that it will be useful, but WITHOUT 80 This program is distributed in the hope that it will be useful, but WITHOUT
81 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or 81 ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
82 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for 82 FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
83 more details. 83 more details.
84 </p> 84 </p>
85 <p> 85 <p>
86 You should have received a copy of the GNU General Public License along 86 You should have received a copy of the GNU General Public License along
87 with this program. If not, see <<a 87 with this program. If not, see <<a
88 href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. 88 href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>.
89 </p> 89 </p>
90 90
91 </div> 91 </div>
92 92
93 <div id="requires-list"> 93 <div id="requires-list">
94 <h3 class="section-bar">Required files</h3> 94 <h3 class="section-bar">Required files</h3>
95 95
96 <div class="name-list"> 96 <div class="name-list">
97 97
98 cgi&nbsp;&nbsp; 98 cgi&nbsp;&nbsp;
99 99
100 kconv&nbsp;&nbsp; 100 kconv&nbsp;&nbsp;
101 101
102 </div> 102 </div>
103 </div> 103 </div>
104 104
105 </div> 105 </div>
106 106
107 107
108 </div> 108 </div>
109 109
110 <!-- if includes --> 110 <!-- if includes -->
111 111
112 <div id="section"> 112 <div id="section">
113 113
114 114
115 115
116 116
117 <!-- if method_list --> 117 <!-- if method_list -->
118 118
119 119
120 120
121 121
122 </div> 122 </div>
123 123
124 <div id="validator-badges"> 124 <div id="validator-badges">
125 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 125 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
126 </div> 126 </div>
127 127
128 </body> 128 </body>
129 </html> 129 </html>
130 130
doc/files/lib/rir_rb.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <head> 4 <head>
5 <title>File: rir.rb [RDoc Documentation]</title> 5 <title>File: rir.rb [RDoc Documentation]</title>
6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 6 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
7 <meta http-equiv="Content-Script-Type" content="text/javascript" /> 7 <meta http-equiv="Content-Script-Type" content="text/javascript" />
8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> 8 <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" />
9 <script type="text/javascript"> 9 <script type="text/javascript">
10 // <![CDATA[ 10 // <![CDATA[
11 11
12 function popupCode( url ) { 12 function popupCode( url ) {
13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") 13 window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
14 } 14 }
15 15
16 function toggleCode( id ) { 16 function toggleCode( id ) {
17 if ( document.getElementById ) 17 if ( document.getElementById )
18 elem = document.getElementById( id ); 18 elem = document.getElementById( id );
19 else if ( document.all ) 19 else if ( document.all )
20 elem = eval( "document.all." + id ); 20 elem = eval( "document.all." + id );
21 else 21 else
22 return false; 22 return false;
23 23
24 elemStyle = elem.style; 24 elemStyle = elem.style;
25 25
26 if ( elemStyle.display != "block" ) { 26 if ( elemStyle.display != "block" ) {
27 elemStyle.display = "block" 27 elemStyle.display = "block"
28 } else { 28 } else {
29 elemStyle.display = "none" 29 elemStyle.display = "none"
30 } 30 }
31 31
32 return true; 32 return true;
33 } 33 }
34 34
35 // Make codeblocks hidden by default 35 // Make codeblocks hidden by default
36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) 36 document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" )
37 37
38 // ]]> 38 // ]]>
39 </script> 39 </script>
40 40
41 </head> 41 </head>
42 <body> 42 <body>
43 43
44 44
45 <div id="fileHeader"> 45 <div id="fileHeader">
46 <h1>rir.rb</h1> 46 <h1>rir.rb</h1>
47 <table class="header-table"> 47 <table class="header-table">
48 <tr class="top-aligned-row"> 48 <tr class="top-aligned-row">
49 <td><strong>Path:</strong></td> 49 <td><strong>Path:</strong></td>
50 <td>lib/rir.rb 50 <td>lib/rir.rb
51 51
52 </td> 52 </td>
53 </tr> 53 </tr>
54 <tr class="top-aligned-row"> 54 <tr class="top-aligned-row">
55 <td><strong>Last Update:</strong></td> 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 </tr> 57 </tr>
58 </table> 58 </table>
59 </div> 59 </div>
60 <!-- banner header --> 60 <!-- banner header -->
61 61
62 <div id="bodyContent"> 62 <div id="bodyContent">
63 63
64 <div id="contextContent"> 64 <div id="contextContent">
65 65
66 <div id="requires-list"> 66 <div id="requires-list">
67 <h3 class="section-bar">Required files</h3> 67 <h3 class="section-bar">Required files</h3>
68 68
69 <div class="name-list"> 69 <div class="name-list">
70 70
71 rir/document&nbsp;&nbsp; 71 rir/document&nbsp;&nbsp;
72 72
73 rir/string&nbsp;&nbsp; 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 </div> 81 </div>
76 </div> 82 </div>
77 83
78 </div> 84 </div>
79 85
80 86
81 </div> 87 </div>
82 88
83 <!-- if includes --> 89 <!-- if includes -->
84 90
85 <div id="section"> 91 <div id="section">
86 92
87 93
88 94
89 95
90 <!-- if method_list --> 96 <!-- if method_list -->
91 97
92 98
93 99
94 100
95 </div> 101 </div>
96 102
97 <div id="validator-badges"> 103 <div id="validator-badges">
98 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> 104 <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
99 </div> 105 </div>
100 106
101 </body> 107 </body>
102 </html> 108 </html>
103 109
doc/fr_class_index.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <!-- 4 <!--
5 5
6 Classes [RDoc Documentation] 6 Classes [RDoc Documentation]
7 7
8 --> 8 -->
9 <head> 9 <head>
10 <title>Classes [RDoc Documentation]</title> 10 <title>Classes [RDoc Documentation]</title>
11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" /> 12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" />
13 <base target="docwin" /> 13 <base target="docwin" />
14 </head> 14 </head>
15 <body> 15 <body>
16 <div class="index"> 16 <div class="index">
17 <h1 class="section-bar">Classes</h1> 17 <h1 class="section-bar">Classes</h1>
18 <div id="index-entries"> 18 <div id="index-entries">
19 19
20 <a href="classes/RIR.html">RIR</a><br /> 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 <a href="classes/String.html">String</a><br /> 32 <a href="classes/String.html">String</a><br />
29 33
30 </div> 34 </div>
31 </div> 35 </div>
32 </body> 36 </body>
33 </html> 37 </html>
34 38
doc/fr_file_index.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <!-- 4 <!--
5 5
6 Files [RDoc Documentation] 6 Files [RDoc Documentation]
7 7
8 --> 8 -->
9 <head> 9 <head>
10 <title>Files [RDoc Documentation]</title> 10 <title>Files [RDoc Documentation]</title>
11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" /> 12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" />
13 <base target="docwin" /> 13 <base target="docwin" />
14 </head> 14 </head>
15 <body> 15 <body>
16 <div class="index"> 16 <div class="index">
17 <h1 class="section-bar">Files</h1> 17 <h1 class="section-bar">Files</h1>
18 <div id="index-entries"> 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 </div> 26 </div>
27 </div> 27 </div>
28 </body> 28 </body>
29 </html> 29 </html>
30 30
doc/fr_method_index.html
Diff comments   View file @ bc18b96
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> 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"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <!-- 4 <!--
5 5
6 Methods [RDoc Documentation] 6 Methods [RDoc Documentation]
7 7
8 --> 8 -->
9 <head> 9 <head>
10 <title>Methods [RDoc Documentation]</title> 10 <title>Methods [RDoc Documentation]</title>
11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" /> 12 <link rel="stylesheet" href="rdoc-style.css" type="text/css" />
13 <base target="docwin" /> 13 <base target="docwin" />
14 </head> 14 </head>
15 <body> 15 <body>
16 <div class="index"> 16 <div class="index">
17 <h1 class="section-bar">Methods</h1> 17 <h1 class="section-bar">Methods</h1>
18 <div id="index-entries"> 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 <a href="classes/String.html#M000001">is_stopword? (String)</a><br /> 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 <a href="classes/String.html#M000002">remove_special_characters (String)</a><br /> 32 <a href="classes/String.html#M000002">remove_special_characters (String)</a><br />
39 33
40 <a href="classes/String.html#M000006">strip_javascripts (String)</a><br /> 34 <a href="classes/String.html#M000006">strip_javascripts (String)</a><br />
41 35
42 <a href="classes/String.html#M000005">strip_javascripts! (String)</a><br /> 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 <a href="classes/String.html#M000008">strip_stylesheets (String)</a><br /> 42 <a href="classes/String.html#M000008">strip_stylesheets (String)</a><br />
45 43
46 <a href="classes/String.html#M000007">strip_stylesheets! (String)</a><br /> 44 <a href="classes/String.html#M000007">strip_stylesheets! (String)</a><br />
47 45
48 <a href="classes/String.html#M000004">strip_xml_tags (String)</a><br /> 46 <a href="classes/String.html#M000004">strip_xml_tags (String)</a><br />
49 47
50 <a href="classes/String.html#M000003">strip_xml_tags! (String)</a><br /> 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 />
1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN" 1 <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN"
2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd"> 2 "http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd">
3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> 3 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
4 <!-- 4 <!--
5 5
6 RDoc Documentation 6 RDoc Documentation
7 7
8 --> 8 -->
9 <head> 9 <head>
10 <title>RDoc Documentation</title> 10 <title>RDoc Documentation</title>
11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> 11 <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
12 </head> 12 </head>
13 <frameset rows="20%, 80%"> 13 <frameset rows="20%, 80%">
14 <frameset cols="25%,35%,45%"> 14 <frameset cols="25%,35%,45%">
15 <frame src="fr_file_index.html" title="Files" name="Files" /> 15 <frame src="fr_file_index.html" title="Files" name="Files" />
16 <frame src="fr_class_index.html" name="Classes" /> 16 <frame src="fr_class_index.html" name="Classes" />
17 <frame src="fr_method_index.html" name="Methods" /> 17 <frame src="fr_method_index.html" name="Methods" />
18 </frameset> 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 </frameset> 20 </frameset>
21 </html> 21 </html>
22 22
1 #!/usr/bin/env ruby 1 #!/usr/bin/env ruby
2 2
3 # This file is a part of an Information Retrieval oriented Ruby library 3 # This file is a part of an Information Retrieval oriented Ruby library
4 # 4 #
5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> 5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 # 6 #
7 # This program is free software: you can redistribute it and/or modify 7 # This program is free software: you can redistribute it and/or modify
8 # it under the terms of the GNU General Public License as published by 8 # it under the terms of the GNU General Public License as published by
9 # the Free Software Foundation, either version 3 of the License, or 9 # the Free Software Foundation, either version 3 of the License, or
10 # (at your option) any later version. 10 # (at your option) any later version.
11 # 11 #
12 # This program is distributed in the hope that it will be useful, 12 # This program is distributed in the hope that it will be useful,
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU General Public License for more details. 15 # GNU General Public License for more details.
16 # 16 #
17 # You should have received a copy of the GNU General Public License 17 # You should have received a copy of the GNU General Public License
18 # along with this program. If not, see <http://www.gnu.org/licenses/>. 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 module RIR 20 module RIR
22 21
23 class Corpus 22 class Corpus
24 attr_accessor :path 23 attr_accessor :path
25 24
26 def initialize(path) 25 def initialize(path)
27 @path = path.chomp "/" 26 @path = path.chomp "/"
28 end 27 end
29 28
30 # Recursively outputs all files in +self.path+. 29 # Recursively outputs all files in +self.path+.
31 # WARNING ! This function may take a lot of time if many 30 # WARNING ! This function may take a lot of time if many
32 # files are in subdirectories. 31 # files are in subdirectories.
33 # 32 #
34 # c = Corpus.new "my/path" 33 # c = Corpus.new "my/path"
35 # c.files # => ["README.txt", "lib/code.rb"] 34 # c.files # => ["README.txt", "lib/code.rb"]
36 def files 35 def files
37 Dir["#{@path}/**/*.*"] 36 Dir["#{@path}/**/*.*"]
38 end 37 end
39 end 38 end
40 39
41 end 40 end
42 41
1 #!/usr/bin/env ruby 1 #!/usr/bin/env ruby
2 2
3 # This file is a part of an Information Retrieval oriented Ruby library 3 # This file is a part of an Information Retrieval oriented Ruby library
4 # 4 #
5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> 5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 # 6 #
7 # This program is free software: you can redistribute it and/or modify 7 # This program is free software: you can redistribute it and/or modify
8 # it under the terms of the GNU General Public License as published by 8 # it under the terms of the GNU General Public License as published by
9 # the Free Software Foundation, either version 3 of the License, or 9 # the Free Software Foundation, either version 3 of the License, or
10 # (at your option) any later version. 10 # (at your option) any later version.
11 # 11 #
12 # This program is distributed in the hope that it will be useful, 12 # This program is distributed in the hope that it will be useful,
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU General Public License for more details. 15 # GNU General Public License for more details.
16 # 16 #
17 # You should have received a copy of the GNU General Public License 17 # You should have received a copy of the GNU General Public License
18 # along with this program. If not, see <http://www.gnu.org/licenses/>. 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 module RIR 20 module RIR
22 21
23 class Query 22 class Query
24 end 23 end
25 24
26 module Indri 25 module Indri
27 26
28 class Parameters 27 class Parameters
29 attr_accessor :corpus, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline 28 attr_accessor :corpus, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline
30 29
31 def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) 30 def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false)
32 @corpus = corpus 31 @corpus = corpus
33 @memory = mem 32 @memory = mem
34 @count = count 33 @count = count
35 @offset = offset 34 @offset = offset
36 @run_id = run_id 35 @run_id = run_id
37 @print_query = print_query ? "true" : "false" 36 @print_query = print_query ? "true" : "false"
38 @print_docs = print_docs ? "true" : "false" 37 @print_docs = print_docs ? "true" : "false"
39 end 38 end
40 39
41 def to_s 40 def to_s
42 h = "<parameters>\n" 41 h = "<parameters>\n"
43 h += "<memory>#{@memory}</memory>\n" 42 h += "<memory>#{@memory}</memory>\n"
44 h += "<index>#{@corpus}</index>\n" 43 h += "<index>#{@corpus}</index>\n"
45 h += "<count>#{@count}</count>\n" 44 h += "<count>#{@count}</count>\n"
46 unless @baseline.nil? 45 unless @baseline.nil?
47 h += "<baseline>#{@baseline}</baseline>\n" 46 h += "<baseline>#{@baseline}</baseline>\n"
48 else 47 else
49 h += "<rule>#{@rule}</rule>\n" 48 h += "<rule>#{@rule}</rule>\n"
50 end 49 end
51 h += "<queryOffset>#{@offset}</queryOffset>\n" 50 h += "<queryOffset>#{@offset}</queryOffset>\n"
52 h += "<runID>#{@run_id}</runID>\n" 51 h += "<runID>#{@run_id}</runID>\n"
53 h += "<printQuery>#{@print_query}</printQuery>\n" 52 h += "<printQuery>#{@print_query}</printQuery>\n"
54 h += "<printDocuments>#{@print_docs}</printDocuments>\n" 53 h += "<printDocuments>#{@print_docs}</printDocuments>\n"
55 54
56 h 55 h
57 end 56 end
58 end 57 end
59 58
60 class IndriQuery < Query 59 class IndriQuery < Query
61 attr_accessor :id, :query, :params, :rule 60 attr_accessor :id, :query, :params, :rule
62 61
63 def initialize(id,query,params) 62 def initialize(id,query,params)
64 @params = params 63 @params = params
65 # Here we set the default retrieval model as Language Modeling 64 # Here we set the default retrieval model as Language Modeling
66 # with a Dirichlet smoothing at 2500. 65 # with a Dirichlet smoothing at 2500.
67 # TODO: maybe a Rule class... 66 # TODO: maybe a Rule class...
68 @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? 67 @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil?
69 68
70 @id = id 69 @id = id
71 @query = query 70 @query = query
72 end 71 end
73 72
74 def to_s 73 def to_s
75 h = @params.to_s 74 h = @params.to_s
76 h += "<query>\n" 75 h += "<query>\n"
77 h += "<number>#{@id}</number>\n" 76 h += "<number>#{@id}</number>\n"
78 h += "<text>#{@query}</text>\n" 77 h += "<text>#{@query}</text>\n"
79 h += "</query>\n" 78 h += "</query>\n"
80 h += "</parameters>" 79 h += "</parameters>"
81 80
82 h 81 h
83 end 82 end
84 end 83 end
85 84
86 end 85 end
87 end 86 end
88 87
1 #!/usr/bin/env ruby 1 #!/usr/bin/env ruby
2 2
3 # This file is a part of an Information Retrieval oriented Ruby library 3 # This file is a part of an Information Retrieval oriented Ruby library
4 # 4 #
5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> 5 # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com>
6 # 6 #
7 # This program is free software: you can redistribute it and/or modify 7 # This program is free software: you can redistribute it and/or modify
8 # it under the terms of the GNU General Public License as published by 8 # it under the terms of the GNU General Public License as published by
9 # the Free Software Foundation, either version 3 of the License, or 9 # the Free Software Foundation, either version 3 of the License, or
10 # (at your option) any later version. 10 # (at your option) any later version.
11 # 11 #
12 # This program is distributed in the hope that it will be useful, 12 # This program is distributed in the hope that it will be useful,
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of 13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the 14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU General Public License for more details. 15 # GNU General Public License for more details.
16 # 16 #
17 # You should have received a copy of the GNU General Public License 17 # You should have received a copy of the GNU General Public License
18 # along with this program. If not, see <http://www.gnu.org/licenses/>. 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 module RIR 20 module RIR
22 21
23 # These are the default stopwords provided by Lemur. 22 # These are the default stopwords provided by Lemur.
24 Stoplist = [ 23 Stoplist = [
25 "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", 24 "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av",
26 "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", 25 "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand",
27 "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", 26 "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by",
28 "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", 27 "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu",
29 "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", 28 "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during",
30 "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", 29 "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every",
31 "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", 30 "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting",
32 "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", 31 "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff",
33 "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", 32 "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore",
34 "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", 33 "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he",
35 "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", 34 "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto",
36 "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", 35 "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto",
37 "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", 36 "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include",
38 "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", 37 "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into",
39 "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", 38 "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last",
40 "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", 39 "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe",
41 "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", 40 "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs",
42 "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", 41 "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless",
43 "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", 42 "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing",
44 "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", 43 "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once",
45 "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", 44 "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours",
46 "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", 45 "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite",
47 "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", 46 "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing",
48 "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", 47 "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt",
49 "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", 48 "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote",
50 "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", 49 "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes",
51 "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", 50 "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave",
52 "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", 51 "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them",
53 "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", 52 "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts",
54 "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", 53 "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon",
55 "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", 54 "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru",
56 "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", 55 "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh",
57 "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", 56 "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward",
58 "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", 57 "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week",
59 "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", 58 "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever",
60 "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", 59 "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore",
61 "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", 60 "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto",
62 "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", 61 "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever",
63 "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", 62 "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom",
64 "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", 63 "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within",
65 "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", 64 "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your",
66 "yours", "yourself", "yourselves" 65 "yours", "yourself", "yourselves"
67 ] 66 ]
68 67
69 68
70 end 69 end
71 70
72 # Extention of the standard class String with useful function. 71 # Extention of the standard class String with useful function.
73 class String 72 class String
74 include RIR 73 include RIR
75 74
76 # Returns +true+ if +self+ belongs to Rir::Stoplist, +false+ otherwise. 75 # Returns +true+ if +self+ belongs to Rir::Stoplist, +false+ otherwise.
77 def is_stopword? 76 def is_stopword?
78 Stoplist.include?(self.downcase) 77 Stoplist.include?(self.downcase)
79 end 78 end
80 79
81 # Do not use. 80 # Do not use.
82 # TODO: rewamp. find why this function is here. 81 # TODO: rewamp. find why this function is here.
83 def remove_special_characters 82 def remove_special_characters
84 self.split.collect { |w| w.gsub(/\W/,' ').split.collect { |w| w.gsub(/\W/,' ').strip.sub(/\A.\z/, '')}.join(' ').strip.sub(/\A.\z/, '')}.join(' ') 83 self.split.collect { |w| w.gsub(/\W/,' ').split.collect { |w| w.gsub(/\W/,' ').strip.sub(/\A.\z/, '')}.join(' ').strip.sub(/\A.\z/, '')}.join(' ')
85 end 84 end
86 85
87 # Removes all XML-like tags from +self+. 86 # Removes all XML-like tags from +self+.
88 # 87 #
89 # s = "<html><body>test</body></html>" 88 # s = "<html><body>test</body></html>"
90 # s.strip_xml_tags! 89 # s.strip_xml_tags!
91 # s #=> "test" 90 # s #=> "test"
92 def strip_xml_tags! 91 def strip_xml_tags!
93 replace strip_with_pattern /<\/?[^>]*>/ 92 replace strip_with_pattern /<\/?[^>]*>/
94 end 93 end
95 94
96 # Removes all XML-like tags from +self+. 95 # Removes all XML-like tags from +self+.
97 # 96 #
98 # s = "<html><body>test</body></html>" 97 # s = "<html><body>test</body></html>"
99 # s.strip_xml_tags #=> "test" 98 # s.strip_xml_tags #=> "test"
100 # s #=> "<html><body>test</body></html>" 99 # s #=> "<html><body>test</body></html>"
101 def strip_xml_tags 100 def strip_xml_tags
102 dup.strip_xml_tags! 101 dup.strip_xml_tags!
103 end 102 end
104 103
105 # Removes all Javascript sources from +self+. 104 # Removes all Javascript sources from +self+.
106 # 105 #
107 # s = "<script type='text/javascript'> 106 # s = "<script type='text/javascript'>
108 # var skin='vector', 107 # var skin='vector',
109 # stylepath='http://bits.wikimedia.org/skins-1.5' 108 # stylepath='http://bits.wikimedia.org/skins-1.5'
110 # </script> 109 # </script>
111 # 110 #
112 # test" 111 # test"
113 # s.strip_javascripts! 112 # s.strip_javascripts!
114 # s #=> "test" 113 # s #=> "test"
115 def strip_javascripts! 114 def strip_javascripts!
116 replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m 115 replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m
117 end 116 end
118 117
119 # Removes all Javascript sources from +self+. 118 # Removes all Javascript sources from +self+.
120 # 119 #
121 # s = "<script type='text/javascript'> 120 # s = "<script type='text/javascript'>
122 # var skin='vector', 121 # var skin='vector',
123 # stylepath='http://bits.wikimedia.org/skins-1.5' 122 # stylepath='http://bits.wikimedia.org/skins-1.5'
124 # </script> 123 # </script>
125 # 124 #
126 # test" 125 # test"
127 # s.strip_javascripts #=> "test" 126 # s.strip_javascripts #=> "test"
128 def strip_javascripts 127 def strip_javascripts
129 dup.strip_javascripts! 128 dup.strip_javascripts!
130 end 129 end
131 130
132 def strip_stylesheets! 131 def strip_stylesheets!
133 # TODO: rewamp. dunno what is it. 132 # TODO: rewamp. dunno what is it.
134 replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m 133 replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m
135 end 134 end
136 135
137 def strip_stylesheets 136 def strip_stylesheets
138 dup.strip_stylesheets! 137 dup.strip_stylesheets!
139 end 138 end
140 139
141 # Removes punctuation from +self+. 140 # Removes punctuation from +self+.
142 # 141 #
143 # s = "hello, world. how are you?!" 142 # s = "hello, world. how are you?!"
144 # s.strip_punctuation! 143 # s.strip_punctuation!
145 # s # => "hello world how are you" 144 # s # => "hello world how are you"
146 def strip_punctuation! 145 def strip_punctuation!
147 replace strip_with_pattern /[^a-zA-Z0-9\-\s]/ 146 replace strip_with_pattern /[^a-zA-Z0-9\-\s]/
148 end 147 end
149 148
150 # Removes punctuation from +self+. 149 # Removes punctuation from +self+.
151 # 150 #
152 # s = "hello, world. how are you?!" 151 # s = "hello, world. how are you?!"
153 # s.strip_punctuation # => "hello world how are you" 152 # s.strip_punctuation # => "hello world how are you"
154 def strip_punctuation 153 def strip_punctuation
155 dup.strip_punctuation! 154 dup.strip_punctuation!
156 end 155 end
157 156
158 # Returns the text values inside all occurences of a XML tag in +self+ 157 # Returns the text values inside all occurences of a XML tag in +self+
159 # 158 #
160 # s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre" 159 # s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre"
161 # s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"] 160 # s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"]
162 def extract_xmltags_values(tag_name) 161 def extract_xmltags_values(tag_name)
163 self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten 162 self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten
164 end 163 end
165 164
166 def strip_with_pattern(pattern) 165 def strip_with_pattern(pattern)
167 require 'cgi' 166 require 'cgi'
168 require 'kconv' 167 require 'kconv'
169 CGI::unescapeHTML(self.gsub(pattern,"")).toutf8 168 CGI::unescapeHTML(self.gsub(pattern,"")).toutf8
170 end 169 end
171 170
172 private :strip_with_pattern 171 private :strip_with_pattern
173 end 172 end
174 173