Commit 81ed24dd04a9524e59c08248af3647dae5830d56
1 parent
4b35d22277
Exists in
master
modules revamp.
Showing 63 changed files with 2301 additions and 669 deletions Inline Diff
- doc/classes/Corpus.html
- doc/classes/Corpus.src/M000001.html
- doc/classes/Corpus.src/M000002.html
- doc/classes/Indri.html
- doc/classes/Indri/IndriQuery.html
- doc/classes/Indri/IndriQuery.src/M000020.html
- doc/classes/Indri/IndriQuery.src/M000021.html
- doc/classes/Indri/Parameters.html
- doc/classes/Indri/Parameters.src/M000018.html
- doc/classes/Indri/Parameters.src/M000019.html
- doc/classes/Query.html
- doc/classes/RIR.html
- doc/classes/RIR/Document.src/M000022.html
- doc/classes/RIR/Document.src/M000023.html
- doc/classes/RIR/Document.src/M000024.html
- doc/classes/RIR/Document.src/M000025.html
- doc/classes/RIR/Document.src/M000026.html
- doc/classes/RIR/Document.src/M000027.html
- doc/classes/RIR/WebDocument.src/M000028.html
- doc/classes/RIR/WebDocument.src/M000029.html
- doc/classes/RIR/WikipediaPage.src/M000030.html
- doc/classes/RIR/WikipediaPage.src/M000031.html
- doc/classes/RIR/WikipediaPage.src/M000032.html
- doc/classes/Regexp.html
- doc/classes/Regexp.src/M000003.html
- doc/classes/String.html
- doc/classes/String.src/M000004.html
- doc/classes/String.src/M000005.html
- doc/classes/String.src/M000006.html
- doc/classes/String.src/M000007.html
- doc/classes/String.src/M000008.html
- doc/classes/String.src/M000009.html
- doc/classes/String.src/M000010.html
- doc/classes/String.src/M000011.html
- doc/classes/String.src/M000012.html
- doc/classes/String.src/M000013.html
- doc/classes/String.src/M000014.html
- doc/classes/TreeTagger.html
- doc/classes/TreeTagger/Chunk.html
- doc/classes/TreeTagger/Chunk.src/M000017.html
- doc/classes/TreeTagger/TaggerChunker.html
- doc/classes/TreeTagger/TaggerChunker.src/M000015.html
- doc/classes/TreeTagger/TaggerChunker.src/M000016.html
- doc/classes/TreeTagger/TaggerChunkerEnglish.html
- doc/classes/TreeTagger/TaggerChunkerFrench.html
- doc/classes/TreeTagger/TaggerChunkerGerman.html
- doc/created.rid
- doc/files/lib/rir/corpus_rb.html
- doc/files/lib/rir/document_rb.html
- doc/files/lib/rir/query_rb.html
- doc/files/lib/rir/regexp_rb.html
- doc/files/lib/rir/string_rb.html
- doc/files/lib/rir/ttagger_rb.html
- doc/fr_class_index.html
- doc/fr_file_index.html
- doc/fr_method_index.html
- doc/index.html
- lib/rir/corpus.rb
- lib/rir/document.rb
- lib/rir/query.rb
- lib/rir/regexp.rb
- lib/rir/string.rb
- lib/rir/ttagger.rb
doc/classes/Corpus.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: Corpus [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">Corpus</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../files/lib/rir/corpus_rb.html"> | ||
57 | |||
58 | lib/rir/corpus.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | Object | ||
74 | |||
75 | </td> | ||
76 | </tr> | ||
77 | |||
78 | </table> | ||
79 | </div> | ||
80 | <!-- banner header --> | ||
81 | |||
82 | <div id="bodyContent"> | ||
83 | |||
84 | <div id="contextContent"> | ||
85 | |||
86 | </div> | ||
87 | |||
88 | |||
89 | <div id="method-list"> | ||
90 | <h3 class="section-bar">Methods</h3> | ||
91 | |||
92 | <div class="name-list"> | ||
93 | |||
94 | <a href="#M000002">files</a> | ||
95 | |||
96 | <a href="#M000001">new</a> | ||
97 | |||
98 | </div> | ||
99 | </div> | ||
100 | |||
101 | </div> | ||
102 | |||
103 | <!-- if includes --> | ||
104 | |||
105 | <div id="section"> | ||
106 | |||
107 | |||
108 | |||
109 | <div id="attribute-list"> | ||
110 | <h3 class="section-bar">Attributes</h3> | ||
111 | |||
112 | <div class="name-list"> | ||
113 | <table> | ||
114 | |||
115 | <tr class="top-aligned-row context-row"> | ||
116 | <td class="context-item-name">path</td> | ||
117 | |||
118 | <td class="context-item-value"> [RW] </td> | ||
119 | |||
120 | <td class="context-item-desc"></td> | ||
121 | </tr> | ||
122 | |||
123 | </table> | ||
124 | </div> | ||
125 | </div> | ||
126 | |||
127 | |||
128 | <!-- if method_list --> | ||
129 | |||
130 | <div id="methods"> | ||
131 | |||
132 | <h3 class="section-bar">Public Class methods</h3> | ||
133 | |||
134 | |||
135 | <div id="method-M000001" class="method-detail"> | ||
136 | <a name="M000001"></a> | ||
137 | |||
138 | <div class="method-heading"> | ||
139 | |||
140 | <a href="Corpus.src/M000001.html" target="Code" class="method-signature" | ||
141 | onclick="popupCode('Corpus.src/M000001.html');return false;"> | ||
142 | |||
143 | <span class="method-name">new</span><span class="method-args">(path)</span> | ||
144 | |||
145 | </a> | ||
146 | |||
147 | </div> | ||
148 | |||
149 | <div class="method-description"> | ||
150 | |||
151 | </div> | ||
152 | </div> | ||
153 | |||
154 | |||
155 | <h3 class="section-bar">Public Instance methods</h3> | ||
156 | |||
157 | |||
158 | <div id="method-M000002" class="method-detail"> | ||
159 | <a name="M000002"></a> | ||
160 | |||
161 | <div class="method-heading"> | ||
162 | |||
163 | <a href="Corpus.src/M000002.html" target="Code" class="method-signature" | ||
164 | onclick="popupCode('Corpus.src/M000002.html');return false;"> | ||
165 | |||
166 | <span class="method-name">files</span><span class="method-args">()</span> | ||
167 | |||
168 | </a> | ||
169 | |||
170 | </div> | ||
171 | |||
172 | <div class="method-description"> | ||
173 | |||
174 | <p> | ||
175 | Recursively outputs all files in <tt>self.path</tt>. WARNING ! This | ||
176 | function may take a lot of time if many files are in subdirectories. | ||
177 | </p> | ||
178 | <pre> | ||
179 | c = Corpus.new "my/path" | ||
180 | c.files # => ["README.txt", "lib/code.rb"] | ||
181 | </pre> | ||
182 | |||
183 | </div> | ||
184 | </div> | ||
185 | |||
186 | |||
187 | |||
188 | </div> | ||
189 | |||
190 | |||
191 | |||
192 | |||
193 | </div> | ||
194 | |||
195 | <div id="validator-badges"> | ||
196 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
197 | </div> | ||
198 | |||
199 | </body> | ||
200 | </html> | ||
201 |
doc/classes/Corpus.src/M000001.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>new (Corpus)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/corpus.rb, line 25</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">path</span>) | ||
12 | <span class="ruby-ivar">@path</span> = <span class="ruby-identifier">path</span>.<span class="ruby-identifier">chomp</span> <span class="ruby-value str">"/"</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/Corpus.src/M000002.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>files (Corpus)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/corpus.rb, line 35</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">files</span> | ||
12 | <span class="ruby-constant">Dir</span>[<span class="ruby-node">"#{@path}/**/*.*"</span>] | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/Indri.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Module: Indri [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Module</strong></td> | ||
49 | <td class="class-name-in-header">Indri</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../files/lib/rir/query_rb.html"> | ||
57 | |||
58 | lib/rir/query.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | </table> | ||
70 | </div> | ||
71 | <!-- banner header --> | ||
72 | |||
73 | <div id="bodyContent"> | ||
74 | |||
75 | <div id="contextContent"> | ||
76 | |||
77 | </div> | ||
78 | |||
79 | |||
80 | </div> | ||
81 | |||
82 | <!-- if includes --> | ||
83 | |||
84 | <div id="section"> | ||
85 | |||
86 | <div id="class-list"> | ||
87 | <h3 class="section-bar">Classes and Modules</h3> | ||
88 | |||
89 | Class <a href="Indri/IndriQuery.html" class="link">Indri::IndriQuery</a><br /> | ||
90 | Class <a href="Indri/Parameters.html" class="link">Indri::Parameters</a><br /> | ||
91 | |||
92 | </div> | ||
93 | |||
94 | |||
95 | |||
96 | |||
97 | <!-- if method_list --> | ||
98 | |||
99 | |||
100 | |||
101 | |||
102 | </div> | ||
103 | |||
104 | <div id="validator-badges"> | ||
105 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
106 | </div> | ||
107 | |||
108 | </body> | ||
109 | </html> | ||
110 |
doc/classes/Indri/IndriQuery.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: Indri::IndriQuery [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">Indri::IndriQuery</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/query_rb.html"> | ||
57 | |||
58 | lib/rir/query.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | <a href="../Query.html"> | ||
74 | |||
75 | Query | ||
76 | |||
77 | </a> | ||
78 | |||
79 | </td> | ||
80 | </tr> | ||
81 | |||
82 | </table> | ||
83 | </div> | ||
84 | <!-- banner header --> | ||
85 | |||
86 | <div id="bodyContent"> | ||
87 | |||
88 | <div id="contextContent"> | ||
89 | |||
90 | </div> | ||
91 | |||
92 | |||
93 | <div id="method-list"> | ||
94 | <h3 class="section-bar">Methods</h3> | ||
95 | |||
96 | <div class="name-list"> | ||
97 | |||
98 | <a href="#M000020">new</a> | ||
99 | |||
100 | <a href="#M000021">to_s</a> | ||
101 | |||
102 | </div> | ||
103 | </div> | ||
104 | |||
105 | </div> | ||
106 | |||
107 | <!-- if includes --> | ||
108 | |||
109 | <div id="section"> | ||
110 | |||
111 | |||
112 | |||
113 | <div id="attribute-list"> | ||
114 | <h3 class="section-bar">Attributes</h3> | ||
115 | |||
116 | <div class="name-list"> | ||
117 | <table> | ||
118 | |||
119 | <tr class="top-aligned-row context-row"> | ||
120 | <td class="context-item-name">id</td> | ||
121 | |||
122 | <td class="context-item-value"> [RW] </td> | ||
123 | |||
124 | <td class="context-item-desc"></td> | ||
125 | </tr> | ||
126 | |||
127 | <tr class="top-aligned-row context-row"> | ||
128 | <td class="context-item-name">params</td> | ||
129 | |||
130 | <td class="context-item-value"> [RW] </td> | ||
131 | |||
132 | <td class="context-item-desc"></td> | ||
133 | </tr> | ||
134 | |||
135 | <tr class="top-aligned-row context-row"> | ||
136 | <td class="context-item-name">query</td> | ||
137 | |||
138 | <td class="context-item-value"> [RW] </td> | ||
139 | |||
140 | <td class="context-item-desc"></td> | ||
141 | </tr> | ||
142 | |||
143 | <tr class="top-aligned-row context-row"> | ||
144 | <td class="context-item-name">rule</td> | ||
145 | |||
146 | <td class="context-item-value"> [RW] </td> | ||
147 | |||
148 | <td class="context-item-desc"></td> | ||
149 | </tr> | ||
150 | |||
151 | </table> | ||
152 | </div> | ||
153 | </div> | ||
154 | |||
155 | |||
156 | <!-- if method_list --> | ||
157 | |||
158 | <div id="methods"> | ||
159 | |||
160 | <h3 class="section-bar">Public Class methods</h3> | ||
161 | |||
162 | |||
163 | <div id="method-M000020" class="method-detail"> | ||
164 | <a name="M000020"></a> | ||
165 | |||
166 | <div class="method-heading"> | ||
167 | |||
168 | <a href="IndriQuery.src/M000020.html" target="Code" class="method-signature" | ||
169 | onclick="popupCode('IndriQuery.src/M000020.html');return false;"> | ||
170 | |||
171 | <span class="method-name">new</span><span class="method-args">(id,query,params)</span> | ||
172 | |||
173 | </a> | ||
174 | |||
175 | </div> | ||
176 | |||
177 | <div class="method-description"> | ||
178 | |||
179 | </div> | ||
180 | </div> | ||
181 | |||
182 | |||
183 | <h3 class="section-bar">Public Instance methods</h3> | ||
184 | |||
185 | |||
186 | <div id="method-M000021" class="method-detail"> | ||
187 | <a name="M000021"></a> | ||
188 | |||
189 | <div class="method-heading"> | ||
190 | |||
191 | <a href="IndriQuery.src/M000021.html" target="Code" class="method-signature" | ||
192 | onclick="popupCode('IndriQuery.src/M000021.html');return false;"> | ||
193 | |||
194 | <span class="method-name">to_s</span><span class="method-args">()</span> | ||
195 | |||
196 | </a> | ||
197 | |||
198 | </div> | ||
199 | |||
200 | <div class="method-description"> | ||
201 | |||
202 | </div> | ||
203 | </div> | ||
204 | |||
205 | |||
206 | |||
207 | </div> | ||
208 | |||
209 | |||
210 | |||
211 | |||
212 | </div> | ||
213 | |||
214 | <div id="validator-badges"> | ||
215 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
216 | </div> | ||
217 | |||
218 | </body> | ||
219 | </html> | ||
220 |
doc/classes/Indri/IndriQuery.src/M000020.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>new (Indri::IndriQuery)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 62</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">id</span>,<span class="ruby-identifier">query</span>,<span class="ruby-identifier">params</span>) | ||
12 | <span class="ruby-ivar">@params</span> = <span class="ruby-identifier">params</span> | ||
13 | <span class="ruby-comment cmt"># Here we set the default retrieval model as Language Modeling</span> | ||
14 | <span class="ruby-comment cmt"># with a Dirichlet smoothing at 2500.</span> | ||
15 | <span class="ruby-comment cmt"># TODO: maybe a Rule class...</span> | ||
16 | <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">rule</span> = <span class="ruby-value str">'method:dirichlet,mu:2500'</span> <span class="ruby-keyword kw">if</span> <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">rule</span>.<span class="ruby-identifier">nil?</span> | ||
17 | |||
18 | <span class="ruby-ivar">@id</span> = <span class="ruby-identifier">id</span> | ||
19 | <span class="ruby-ivar">@query</span> = <span class="ruby-identifier">query</span> | ||
20 | <span class="ruby-keyword kw">end</span></pre> | ||
21 | </body> | ||
22 | </html> | ||
23 |
doc/classes/Indri/IndriQuery.src/M000021.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>to_s (Indri::IndriQuery)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 73</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">to_s</span> | ||
12 | <span class="ruby-identifier">h</span> = <span class="ruby-ivar">@params</span>.<span class="ruby-identifier">to_s</span> | ||
13 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">"<query>\n"</span> | ||
14 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<number>#{@id}</number>\n"</span> | ||
15 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<text>#{@query}</text>\n"</span> | ||
16 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">"</query>\n"</span> | ||
17 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-value str">"</parameters>"</span> | ||
18 | |||
19 | <span class="ruby-identifier">h</span> | ||
20 | <span class="ruby-keyword kw">end</span></pre> | ||
21 | </body> | ||
22 | </html> | ||
23 |
doc/classes/Indri/Parameters.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: Indri::Parameters [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">Indri::Parameters</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/query_rb.html"> | ||
57 | |||
58 | lib/rir/query.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | Object | ||
74 | |||
75 | </td> | ||
76 | </tr> | ||
77 | |||
78 | </table> | ||
79 | </div> | ||
80 | <!-- banner header --> | ||
81 | |||
82 | <div id="bodyContent"> | ||
83 | |||
84 | <div id="contextContent"> | ||
85 | |||
86 | </div> | ||
87 | |||
88 | |||
89 | <div id="method-list"> | ||
90 | <h3 class="section-bar">Methods</h3> | ||
91 | |||
92 | <div class="name-list"> | ||
93 | |||
94 | <a href="#M000018">new</a> | ||
95 | |||
96 | <a href="#M000019">to_s</a> | ||
97 | |||
98 | </div> | ||
99 | </div> | ||
100 | |||
101 | </div> | ||
102 | |||
103 | <!-- if includes --> | ||
104 | |||
105 | <div id="section"> | ||
106 | |||
107 | |||
108 | |||
109 | <div id="attribute-list"> | ||
110 | <h3 class="section-bar">Attributes</h3> | ||
111 | |||
112 | <div class="name-list"> | ||
113 | <table> | ||
114 | |||
115 | <tr class="top-aligned-row context-row"> | ||
116 | <td class="context-item-name">baseline</td> | ||
117 | |||
118 | <td class="context-item-value"> [RW] </td> | ||
119 | |||
120 | <td class="context-item-desc"></td> | ||
121 | </tr> | ||
122 | |||
123 | <tr class="top-aligned-row context-row"> | ||
124 | <td class="context-item-name">count</td> | ||
125 | |||
126 | <td class="context-item-value"> [RW] </td> | ||
127 | |||
128 | <td class="context-item-desc"></td> | ||
129 | </tr> | ||
130 | |||
131 | <tr class="top-aligned-row context-row"> | ||
132 | <td class="context-item-name">index_path</td> | ||
133 | |||
134 | <td class="context-item-value"> [RW] </td> | ||
135 | |||
136 | <td class="context-item-desc"></td> | ||
137 | </tr> | ||
138 | |||
139 | <tr class="top-aligned-row context-row"> | ||
140 | <td class="context-item-name">memory</td> | ||
141 | |||
142 | <td class="context-item-value"> [RW] </td> | ||
143 | |||
144 | <td class="context-item-desc"></td> | ||
145 | </tr> | ||
146 | |||
147 | <tr class="top-aligned-row context-row"> | ||
148 | <td class="context-item-name">offset</td> | ||
149 | |||
150 | <td class="context-item-value"> [RW] </td> | ||
151 | |||
152 | <td class="context-item-desc"></td> | ||
153 | </tr> | ||
154 | |||
155 | <tr class="top-aligned-row context-row"> | ||
156 | <td class="context-item-name">print_docs</td> | ||
157 | |||
158 | <td class="context-item-value"> [RW] </td> | ||
159 | |||
160 | <td class="context-item-desc"></td> | ||
161 | </tr> | ||
162 | |||
163 | <tr class="top-aligned-row context-row"> | ||
164 | <td class="context-item-name">print_query</td> | ||
165 | |||
166 | <td class="context-item-value"> [RW] </td> | ||
167 | |||
168 | <td class="context-item-desc"></td> | ||
169 | </tr> | ||
170 | |||
171 | <tr class="top-aligned-row context-row"> | ||
172 | <td class="context-item-name">rule</td> | ||
173 | |||
174 | <td class="context-item-value"> [RW] </td> | ||
175 | |||
176 | <td class="context-item-desc"></td> | ||
177 | </tr> | ||
178 | |||
179 | <tr class="top-aligned-row context-row"> | ||
180 | <td class="context-item-name">run_id</td> | ||
181 | |||
182 | <td class="context-item-value"> [RW] </td> | ||
183 | |||
184 | <td class="context-item-desc"></td> | ||
185 | </tr> | ||
186 | |||
187 | </table> | ||
188 | </div> | ||
189 | </div> | ||
190 | |||
191 | |||
192 | <!-- if method_list --> | ||
193 | |||
194 | <div id="methods"> | ||
195 | |||
196 | <h3 class="section-bar">Public Class methods</h3> | ||
197 | |||
198 | |||
199 | <div id="method-M000018" class="method-detail"> | ||
200 | <a name="M000018"></a> | ||
201 | |||
202 | <div class="method-heading"> | ||
203 | |||
204 | <a href="Parameters.src/M000018.html" target="Code" class="method-signature" | ||
205 | onclick="popupCode('Parameters.src/M000018.html');return false;"> | ||
206 | |||
207 | <span class="method-name">new</span><span class="method-args">(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false)</span> | ||
208 | |||
209 | </a> | ||
210 | |||
211 | </div> | ||
212 | |||
213 | <div class="method-description"> | ||
214 | |||
215 | </div> | ||
216 | </div> | ||
217 | |||
218 | |||
219 | <h3 class="section-bar">Public Instance methods</h3> | ||
220 | |||
221 | |||
222 | <div id="method-M000019" class="method-detail"> | ||
223 | <a name="M000019"></a> | ||
224 | |||
225 | <div class="method-heading"> | ||
226 | |||
227 | <a href="Parameters.src/M000019.html" target="Code" class="method-signature" | ||
228 | onclick="popupCode('Parameters.src/M000019.html');return false;"> | ||
229 | |||
230 | <span class="method-name">to_s</span><span class="method-args">()</span> | ||
231 | |||
232 | </a> | ||
233 | |||
234 | </div> | ||
235 | |||
236 | <div class="method-description"> | ||
237 | |||
238 | </div> | ||
239 | </div> | ||
240 | |||
241 | |||
242 | |||
243 | </div> | ||
244 | |||
245 | |||
246 | |||
247 | |||
248 | </div> | ||
249 | |||
250 | <div id="validator-badges"> | ||
251 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
252 | </div> | ||
253 | |||
254 | </body> | ||
255 | </html> | ||
256 |
doc/classes/Indri/Parameters.src/M000018.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>new (Indri::Parameters)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 30</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">corpus</span>,<span class="ruby-identifier">mem</span>=<span class="ruby-value str">"1g"</span>,<span class="ruby-identifier">count</span>=<span class="ruby-value str">"1000"</span>,<span class="ruby-identifier">offset</span>=<span class="ruby-value str">"1"</span>,<span class="ruby-identifier">run_id</span>=<span class="ruby-value str">"default"</span>,<span class="ruby-identifier">print_query</span>=<span class="ruby-keyword kw">false</span>,<span class="ruby-identifier">print_docs</span>=<span class="ruby-keyword kw">false</span>) | ||
12 | <span class="ruby-ivar">@index_path</span> = <span class="ruby-identifier">corpus</span> | ||
13 | <span class="ruby-ivar">@memory</span> = <span class="ruby-identifier">mem</span> | ||
14 | <span class="ruby-ivar">@count</span> = <span class="ruby-identifier">count</span> | ||
15 | <span class="ruby-ivar">@offset</span> = <span class="ruby-identifier">offset</span> | ||
16 | <span class="ruby-ivar">@run_id</span> = <span class="ruby-identifier">run_id</span> | ||
17 | <span class="ruby-ivar">@print_query</span> = <span class="ruby-identifier">print_query</span> <span class="ruby-value">? </span><span class="ruby-value str">"true"</span> <span class="ruby-operator">:</span> <span class="ruby-value str">"false"</span> | ||
18 | <span class="ruby-ivar">@print_docs</span> = <span class="ruby-identifier">print_docs</span> <span class="ruby-value">? </span><span class="ruby-value str">"true"</span> <span class="ruby-operator">:</span> <span class="ruby-value str">"false"</span> | ||
19 | <span class="ruby-keyword kw">end</span></pre> | ||
20 | </body> | ||
21 | </html> | ||
22 |
doc/classes/Indri/Parameters.src/M000019.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>to_s (Indri::Parameters)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/query.rb, line 40</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">to_s</span> | ||
12 | <span class="ruby-identifier">h</span> = <span class="ruby-value str">"<parameters>\n"</span> | ||
13 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<memory>#{@memory}</memory>\n"</span> | ||
14 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<index>#{@index_path}</index>\n"</span> | ||
15 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<count>#{@count}</count>\n"</span> | ||
16 | <span class="ruby-keyword kw">unless</span> <span class="ruby-ivar">@baseline</span>.<span class="ruby-identifier">nil?</span> | ||
17 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<baseline>#{@baseline}</baseline>\n"</span> | ||
18 | <span class="ruby-keyword kw">else</span> | ||
19 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<rule>#{@rule}</rule>\n"</span> | ||
20 | <span class="ruby-keyword kw">end</span> | ||
21 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<queryOffset>#{@offset}</queryOffset>\n"</span> | ||
22 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<runID>#{@run_id}</runID>\n"</span> | ||
23 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<printQuery>#{@print_query}</printQuery>\n"</span> | ||
24 | <span class="ruby-identifier">h</span> <span class="ruby-operator">+=</span> <span class="ruby-node">"<printDocuments>#{@print_docs}</printDocuments>\n"</span> | ||
25 | |||
26 | <span class="ruby-identifier">h</span> | ||
27 | <span class="ruby-keyword kw">end</span></pre> | ||
28 | </body> | ||
29 | </html> | ||
30 |
doc/classes/Query.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: Query [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">Query</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../files/lib/rir/query_rb.html"> | ||
57 | |||
58 | lib/rir/query.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | Object | ||
74 | |||
75 | </td> | ||
76 | </tr> | ||
77 | |||
78 | </table> | ||
79 | </div> | ||
80 | <!-- banner header --> | ||
81 | |||
82 | <div id="bodyContent"> | ||
83 | |||
84 | <div id="contextContent"> | ||
85 | |||
86 | </div> | ||
87 | |||
88 | |||
89 | </div> | ||
90 | |||
91 | <!-- if includes --> | ||
92 | |||
93 | <div id="section"> | ||
94 | |||
95 | |||
96 | |||
97 | |||
98 | <!-- if method_list --> | ||
99 | |||
100 | |||
101 | |||
102 | |||
103 | </div> | ||
104 | |||
105 | <div id="validator-badges"> | ||
106 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
107 | </div> | ||
108 | |||
109 | </body> | ||
110 | </html> | ||
111 |
doc/classes/RIR.html
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/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | |||
66 | <a href="../files/lib/rir/corpus_rb.html"> | ||
67 | |||
68 | lib/rir/corpus.rb | ||
69 | |||
70 | </a> | ||
71 | |||
72 | |||
73 | <br /> | ||
74 | |||
75 | |||
76 | <a href="../files/lib/rir/query_rb.html"> | ||
77 | |||
78 | lib/rir/query.rb | ||
79 | |||
80 | </a> | ||
81 | |||
82 | |||
83 | <br /> | ||
84 | |||
85 | |||
86 | <a href="../files/lib/rir/string_rb.html"> | 56 | <a href="../files/lib/rir/string_rb.html"> |
87 | 57 | ||
88 | lib/rir/string.rb | 58 | lib/rir/string.rb |
89 | 59 | ||
90 | </a> | 60 | </a> |
91 | 61 | ||
92 | 62 | ||
93 | <br /> | 63 | <br /> |
94 | 64 | ||
95 | 65 | ||
96 | <a href="../files/lib/rir/document_rb.html"> | 66 | <a href="../files/lib/rir/document_rb.html"> |
97 | 67 | ||
98 | lib/rir/document.rb | 68 | lib/rir/document.rb |
99 | 69 | ||
100 | </a> | 70 | </a> |
101 | 71 | ||
102 | 72 | ||
103 | <br /> | 73 | <br /> |
104 | 74 | ||
105 | </td> | 75 | </td> |
106 | </tr> | 76 | </tr> |
107 | 77 | ||
108 | 78 | ||
109 | </table> | 79 | </table> |
110 | </div> | 80 | </div> |
111 | <!-- banner header --> | 81 | <!-- banner header --> |
112 | 82 | ||
113 | <div id="bodyContent"> | 83 | <div id="bodyContent"> |
114 | 84 | ||
115 | <div id="contextContent"> | 85 | <div id="contextContent"> |
116 | 86 | ||
117 | <div id="description"> | 87 | <div id="description"> |
118 | <p> | 88 | <hr size="1"></hr><p> |
119 | This file is a part of an Information Retrieval oriented Ruby library | ||
120 | </p> | ||
121 | <p> | ||
122 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
123 | </p> | ||
124 | <p> | ||
125 | This program is free software: you can redistribute it and/or modify it | ||
126 | under the terms of the GNU General Public License as published by the Free | ||
127 | Software Foundation, either version 3 of the License, or (at your option) | ||
128 | any later version. | ||
129 | </p> | ||
130 | <p> | ||
131 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
132 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
133 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
134 | more details. | ||
135 | </p> | ||
136 | <p> | ||
137 | You should have received a copy of the GNU General Public License along | ||
138 | with this program. If not, see <<a | ||
139 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
140 | </p> | ||
141 | <hr size="1"></hr><p> | ||
142 | This file is a part of an Information Retrieval oriented Ruby library | ||
143 | </p> | ||
144 | <p> | ||
145 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
146 | </p> | ||
147 | <p> | ||
148 | This program is free software: you can redistribute it and/or modify it | ||
149 | under the terms of the GNU General Public License as published by the Free | ||
150 | Software Foundation, either version 3 of the License, or (at your option) | ||
151 | any later version. | ||
152 | </p> | ||
153 | <p> | ||
154 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
155 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
156 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
157 | more details. | ||
158 | </p> | ||
159 | <p> | ||
160 | You should have received a copy of the GNU General Public License along | ||
161 | with this program. If not, see <<a | ||
162 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
163 | </p> | ||
164 | <hr size="1"></hr><p> | ||
165 | This file is a part of an Information Retrieval oriented Ruby library | ||
166 | </p> | ||
167 | <p> | ||
168 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
169 | </p> | ||
170 | <p> | ||
171 | This program is free software: you can redistribute it and/or modify it | ||
172 | under the terms of the GNU General Public License as published by the Free | ||
173 | Software Foundation, either version 3 of the License, or (at your option) | ||
174 | any later version. | ||
175 | </p> | ||
176 | <p> | ||
177 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
178 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
179 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
180 | more details. | ||
181 | </p> | ||
182 | <p> | ||
183 | You should have received a copy of the GNU General Public License along | ||
184 | with this program. If not, see <<a | ||
185 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
186 | </p> | ||
187 | <hr size="1"></hr><p> | ||
188 | This file is a part of an Information Retrieval oriented Ruby library | ||
189 | </p> | ||
190 | <p> | ||
191 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
192 | </p> | ||
193 | <p> | ||
194 | This program is free software: you can redistribute it and/or modify it | ||
195 | under the terms of the GNU General Public License as published by the Free | ||
196 | Software Foundation, either version 3 of the License, or (at your option) | ||
197 | any later version. | ||
198 | </p> | ||
199 | <p> | ||
200 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
201 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
202 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
203 | more details. | ||
204 | </p> | ||
205 | <p> | ||
206 | You should have received a copy of the GNU General Public License along | ||
207 | with this program. If not, see <<a | ||
208 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
209 | </p> | ||
210 | <hr size="1"></hr><p> | ||
211 | General module for many purposes related to Information Retrieval. | 89 | General module for many purposes related to Information Retrieval. |
212 | </p> | 90 | </p> |
213 | 91 | ||
214 | </div> | 92 | </div> |
215 | 93 | ||
216 | </div> | 94 | </div> |
217 | 95 | ||
218 | 96 | ||
219 | </div> | 97 | </div> |
220 | 98 | ||
221 | <!-- if includes --> | 99 | <!-- if includes --> |
222 | 100 | ||
223 | <div id="section"> | 101 | <div id="section"> |
224 | 102 | ||
225 | <div id="class-list"> | 103 | <div id="class-list"> |
226 | <h3 class="section-bar">Classes and Modules</h3> | 104 | <h3 class="section-bar">Classes and Modules</h3> |
227 | 105 | ||
228 | Module <a href="RIR/Indri.html" class="link">RIR::Indri</a><br /> | 106 | Class <a href="RIR/Document.html" class="link">RIR::Document</a><br /> |
229 | Module <a href="RIR/TreeTagger.html" class="link">RIR::TreeTagger</a><br /> | ||
230 | Class <a href="RIR/Corpus.html" class="link">RIR::Corpus</a><br /> | ||
231 | Class <a href="RIR/Document.html" class="link">RIR::Document</a><br /> | ||
232 | Class <a href="RIR/Query.html" class="link">RIR::Query</a><br /> | ||
233 | Class <a href="RIR/WebDocument.html" class="link">RIR::WebDocument</a><br /> | 107 | Class <a href="RIR/WebDocument.html" class="link">RIR::WebDocument</a><br /> |
234 | Class <a href="RIR/WikipediaPage.html" class="link">RIR::WikipediaPage</a><br /> | 108 | Class <a href="RIR/WikipediaPage.html" class="link">RIR::WikipediaPage</a><br /> |
235 | 109 | ||
236 | </div> | 110 | </div> |
237 | 111 | ||
238 | <div id="constants-list"> | 112 | <div id="constants-list"> |
239 | <h3 class="section-bar">Constants</h3> | 113 | <h3 class="section-bar">Constants</h3> |
240 | 114 | ||
241 | <div class="name-list"> | 115 | <div class="name-list"> |
242 | <table summary="Constants"> | 116 | <table summary="Constants"> |
243 | 117 | ||
244 | <tr class="top-aligned-row context-row"> | 118 | <tr class="top-aligned-row context-row"> |
245 | <td class="context-item-name">Stoplist</td> | 119 | <td class="context-item-name">Stoplist</td> |
246 | <td>=</td> | 120 | <td>=</td> |
247 | <td class="context-item-value">[ "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", "yours", "yourself", "yourselves" ]</td> | 121 | <td class="context-item-value">[ "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", "yours", "yourself", "yourselves" ]</td> |
248 | 122 | ||
249 | <td> </td> | 123 | <td> </td> |
250 | <td class="context-item-desc"> | 124 | <td class="context-item-desc"> |
251 | These are the default stopwords provided by Lemur. | 125 | These are the default stopwords provided by Lemur. |
252 | 126 | ||
253 | </td> | 127 | </td> |
254 | 128 | ||
255 | </tr> | 129 | </tr> |
256 | 130 | ||
257 | </table> | 131 | </table> |
258 | </div> | 132 | </div> |
259 | </div> | 133 | </div> |
260 | 134 | ||
261 | 135 | ||
262 | 136 | ||
263 | 137 | ||
264 | <!-- if method_list --> | 138 | <!-- if method_list --> |
265 | 139 | ||
266 | 140 | ||
267 | 141 | ||
268 | 142 | ||
269 | </div> | 143 | </div> |
270 | 144 | ||
271 | <div id="validator-badges"> | 145 | <div id="validator-badges"> |
272 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 146 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
273 | </div> | 147 | </div> |
274 | 148 | ||
275 | </body> | 149 | </body> |
276 | </html> | 150 | </html> |
277 | 151 |
doc/classes/RIR/Document.src/M000022.html
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>format_words (RIR::Document)</title> | 5 | <title>format_words (RIR::Document)</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/document.rb, line 31</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 34</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">format_words</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">format_words</span> |
12 | <span class="ruby-identifier">wo</span> = [] | 12 | <span class="ruby-identifier">wo</span> = [] |
13 | 13 | ||
14 | <span class="ruby-ivar">@doc_content</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> | 14 | <span class="ruby-ivar">@doc_content</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> |
15 | <span class="ruby-identifier">w</span>.<span class="ruby-identifier">split</span>(<span class="ruby-regexp re">/\W/</span>).<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">sw</span><span class="ruby-operator">|</span> | 15 | <span class="ruby-identifier">w</span>.<span class="ruby-identifier">split</span>(<span class="ruby-regexp re">/\W/</span>).<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">sw</span><span class="ruby-operator">|</span> |
16 | <span class="ruby-identifier">wo</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">sw</span>.<span class="ruby-identifier">downcase</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">sw</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/[a-zA-Z]/</span> | 16 | <span class="ruby-identifier">wo</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">sw</span>.<span class="ruby-identifier">downcase</span>) <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">sw</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/[a-zA-Z]/</span> |
17 | <span class="ruby-keyword kw">end</span> | 17 | <span class="ruby-keyword kw">end</span> |
18 | <span class="ruby-keyword kw">end</span> | 18 | <span class="ruby-keyword kw">end</span> |
19 | 19 | ||
20 | <span class="ruby-identifier">wo</span> | 20 | <span class="ruby-identifier">wo</span> |
21 | <span class="ruby-keyword kw">end</span></pre> | 21 | <span class="ruby-keyword kw">end</span></pre> |
22 | </body> | 22 | </body> |
23 | </html> | 23 | </html> |
24 | 24 |
doc/classes/RIR/Document.src/M000023.html
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>ngrams (RIR::Document)</title> | 5 | <title>ngrams (RIR::Document)</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/document.rb, line 46</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 49</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">ngrams</span>(<span class="ruby-identifier">n</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">ngrams</span>(<span class="ruby-identifier">n</span>) |
12 | <span class="ruby-identifier">window</span> = [] | 12 | <span class="ruby-identifier">window</span> = [] |
13 | <span class="ruby-identifier">ngrams_array</span> = [] | 13 | <span class="ruby-identifier">ngrams_array</span> = [] |
14 | 14 | ||
15 | <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> | 15 | <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> |
16 | <span class="ruby-identifier">window</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">w</span>) | 16 | <span class="ruby-identifier">window</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">w</span>) |
17 | <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">size</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">n</span> | 17 | <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">size</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">n</span> |
18 | <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">push</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">" "</span>) | 18 | <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">push</span> <span class="ruby-identifier">window</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">" "</span>) |
19 | <span class="ruby-identifier">window</span>.<span class="ruby-identifier">delete_at</span>(<span class="ruby-value">0</span>) | 19 | <span class="ruby-identifier">window</span>.<span class="ruby-identifier">delete_at</span>(<span class="ruby-value">0</span>) |
20 | <span class="ruby-keyword kw">end</span> | 20 | <span class="ruby-keyword kw">end</span> |
21 | <span class="ruby-keyword kw">end</span> | 21 | <span class="ruby-keyword kw">end</span> |
22 | 22 | ||
23 | <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">uniq</span> | 23 | <span class="ruby-identifier">ngrams_array</span>.<span class="ruby-identifier">uniq</span> |
24 | <span class="ruby-keyword kw">end</span></pre> | 24 | <span class="ruby-keyword kw">end</span></pre> |
25 | </body> | 25 | </body> |
26 | </html> | 26 | </html> |
27 | 27 |
doc/classes/RIR/Document.src/M000024.html
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>count_words (RIR::Document)</title> | 5 | <title>count_words (RIR::Document)</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/document.rb, line 64</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 67</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">count_words</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">count_words</span> |
12 | <span class="ruby-identifier">counts</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">h</span>,<span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">h</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-value">0</span> } | 12 | <span class="ruby-identifier">counts</span> = <span class="ruby-constant">Hash</span>.<span class="ruby-identifier">new</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">h</span>,<span class="ruby-identifier">k</span><span class="ruby-operator">|</span> <span class="ruby-identifier">h</span>[<span class="ruby-identifier">k</span>] = <span class="ruby-value">0</span> } |
13 | <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> } | 13 | <span class="ruby-ivar">@words</span>.<span class="ruby-identifier">each</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>] <span class="ruby-operator">+=</span> <span class="ruby-value">1</span> } |
14 | 14 | ||
15 | <span class="ruby-identifier">counts</span> | 15 | <span class="ruby-identifier">counts</span> |
16 | <span class="ruby-keyword kw">end</span></pre> | 16 | <span class="ruby-keyword kw">end</span></pre> |
17 | </body> | 17 | </body> |
18 | </html> | 18 | </html> |
19 | 19 |
doc/classes/RIR/Document.src/M000025.html
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>entropy (RIR::Document)</title> | 5 | <title>entropy (RIR::Document)</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/document.rb, line 78</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 81</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">entropy</span>(<span class="ruby-identifier">s</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">entropy</span>(<span class="ruby-identifier">s</span>) |
12 | <span class="ruby-identifier">en</span> = <span class="ruby-value">0</span><span class="ruby-value">.0</span> | 12 | <span class="ruby-identifier">en</span> = <span class="ruby-value">0</span><span class="ruby-value">.0</span> |
13 | <span class="ruby-identifier">counts</span> = <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span> | 13 | <span class="ruby-identifier">counts</span> = <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span> |
14 | 14 | ||
15 | <span class="ruby-identifier">s</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> | 15 | <span class="ruby-identifier">s</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">w</span><span class="ruby-operator">|</span> |
16 | <span class="ruby-identifier">p_wi</span> = <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">count</span>.<span class="ruby-identifier">to_f</span> | 16 | <span class="ruby-identifier">p_wi</span> = <span class="ruby-identifier">counts</span>[<span class="ruby-identifier">w</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">count</span>.<span class="ruby-identifier">to_f</span> |
17 | <span class="ruby-identifier">en</span> <span class="ruby-operator">+=</span> <span class="ruby-identifier">p_wi</span><span class="ruby-operator">*</span><span class="ruby-constant">Math</span>.<span class="ruby-identifier">log2</span>(<span class="ruby-identifier">p_wi</span>) | 17 | <span class="ruby-identifier">en</span> <span class="ruby-operator">+=</span> <span class="ruby-identifier">p_wi</span><span class="ruby-operator">*</span><span class="ruby-constant">Math</span>.<span class="ruby-identifier">log2</span>(<span class="ruby-identifier">p_wi</span>) |
18 | <span class="ruby-keyword kw">end</span> | 18 | <span class="ruby-keyword kw">end</span> |
19 | 19 | ||
20 | <span class="ruby-identifier">en</span> <span class="ruby-operator">*=</span> <span class="ruby-value">-1</span> | 20 | <span class="ruby-identifier">en</span> <span class="ruby-operator">*=</span> <span class="ruby-value">-1</span> |
21 | <span class="ruby-identifier">en</span> | 21 | <span class="ruby-identifier">en</span> |
22 | <span class="ruby-keyword kw">end</span></pre> | 22 | <span class="ruby-keyword kw">end</span></pre> |
23 | </body> | 23 | </body> |
24 | </html> | 24 | </html> |
25 | 25 |
doc/classes/RIR/Document.src/M000026.html
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>tf (RIR::Document)</title> | 5 | <title>tf (RIR::Document)</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/document.rb, line 94</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 97</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">tf</span>(<span class="ruby-identifier">s</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">tf</span>(<span class="ruby-identifier">s</span>) |
12 | <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>[<span class="ruby-identifier">s</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">size</span>.<span class="ruby-identifier">to_f</span> | 12 | <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">count_words</span>[<span class="ruby-identifier">s</span>].<span class="ruby-identifier">to_f</span><span class="ruby-operator">/</span><span class="ruby-ivar">@words</span>.<span class="ruby-identifier">size</span>.<span class="ruby-identifier">to_f</span> |
13 | <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/RIR/Document.src/M000027.html
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>new (RIR::Document)</title> | 5 | <title>new (RIR::Document)</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/document.rb, line 99</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 102</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">content</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">content</span>) |
12 | <span class="ruby-ivar">@doc_content</span> = <span class="ruby-identifier">content</span> | 12 | <span class="ruby-ivar">@doc_content</span> = <span class="ruby-identifier">content</span> |
13 | <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">format_words</span> | 13 | <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">format_words</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/RIR/WebDocument.src/M000028.html
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>get_content (RIR::WebDocument)</title> | 5 | <title>get_content (RIR::WebDocument)</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/document.rb, line 112</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 115</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>) |
12 | <span class="ruby-identifier">require</span> <span class="ruby-value str">'net/http'</span> | 12 | <span class="ruby-identifier">require</span> <span class="ruby-value str">'net/http'</span> |
13 | <span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>(<span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span>(<span class="ruby-identifier">url</span>)) | 13 | <span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>(<span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span>(<span class="ruby-identifier">url</span>)) |
14 | <span class="ruby-keyword kw">end</span></pre> | 14 | <span class="ruby-keyword kw">end</span></pre> |
15 | </body> | 15 | </body> |
16 | </html> | 16 | </html> |
17 | 17 |
doc/classes/RIR/WebDocument.src/M000029.html
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>new (RIR::WebDocument)</title> | 5 | <title>new (RIR::WebDocument)</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/document.rb, line 119</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 122</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">url</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span>(<span class="ruby-identifier">url</span>) |
12 | <span class="ruby-ivar">@url</span> = <span class="ruby-identifier">url</span> | 12 | <span class="ruby-ivar">@url</span> = <span class="ruby-identifier">url</span> |
13 | <span class="ruby-keyword kw">super</span> <span class="ruby-constant">WebDocument</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>).<span class="ruby-identifier">strip_javascripts</span>.<span class="ruby-identifier">strip_stylesheets</span>.<span class="ruby-identifier">strip_xml_tags</span> | 13 | <span class="ruby-keyword kw">super</span> <span class="ruby-constant">WebDocument</span>.<span class="ruby-identifier">get_content</span>(<span class="ruby-identifier">url</span>).<span class="ruby-identifier">strip_javascripts</span>.<span class="ruby-identifier">strip_stylesheets</span>.<span class="ruby-identifier">strip_xml_tags</span> |
14 | <span class="ruby-keyword kw">end</span></pre> | 14 | <span class="ruby-keyword kw">end</span></pre> |
15 | </body> | 15 | </body> |
16 | </html> | 16 | </html> |
17 | 17 |
doc/classes/RIR/WikipediaPage.src/M000030.html
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>search_wikipedia_titles (RIR::WikipediaPage)</title> | 5 | <title>search_wikipedia_titles (RIR::WikipediaPage)</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/document.rb, line 132</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 135</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_wikipedia_titles</span>(<span class="ruby-identifier">name</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_wikipedia_titles</span>(<span class="ruby-identifier">name</span>) |
12 | <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">"Bad encoding"</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span> | 12 | <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">"Bad encoding"</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span> |
13 | 13 | ||
14 | <span class="ruby-identifier">res</span> = <span class="ruby-constant">REXML</span><span class="ruby-operator">::</span><span class="ruby-constant">Document</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>( <span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span> <span class="ruby-node">"http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml"</span> ).<span class="ruby-identifier">toutf8</span>).<span class="ruby-identifier">elements</span>[<span class="ruby-value str">'api/query/search'</span>] | 14 | <span class="ruby-identifier">res</span> = <span class="ruby-constant">REXML</span><span class="ruby-operator">::</span><span class="ruby-constant">Document</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>( <span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span> <span class="ruby-node">"http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml"</span> ).<span class="ruby-identifier">toutf8</span>).<span class="ruby-identifier">elements</span>[<span class="ruby-value str">'api/query/search'</span>] |
15 | 15 | ||
16 | <span class="ruby-identifier">res</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">e</span><span class="ruby-operator">|</span> <span class="ruby-identifier">e</span>.<span class="ruby-identifier">attributes</span>[<span class="ruby-value str">'title'</span>] } <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">res</span>.<span class="ruby-identifier">nil?</span> | 16 | <span class="ruby-identifier">res</span>.<span class="ruby-identifier">collect</span> { <span class="ruby-operator">|</span><span class="ruby-identifier">e</span><span class="ruby-operator">|</span> <span class="ruby-identifier">e</span>.<span class="ruby-identifier">attributes</span>[<span class="ruby-value str">'title'</span>] } <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">res</span>.<span class="ruby-identifier">nil?</span> |
17 | <span class="ruby-keyword kw">end</span></pre> | 17 | <span class="ruby-keyword kw">end</span></pre> |
18 | </body> | 18 | </body> |
19 | </html> | 19 | </html> |
20 | 20 |
doc/classes/RIR/WikipediaPage.src/M000031.html
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>get_url (RIR::WikipediaPage)</title> | 5 | <title>get_url (RIR::WikipediaPage)</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/document.rb, line 140</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 143</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_url</span>(<span class="ruby-identifier">name</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">get_url</span>(<span class="ruby-identifier">name</span>) |
12 | <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">"Bad encoding"</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span> | 12 | <span class="ruby-identifier">raise</span> <span class="ruby-constant">ArgumentError</span>, <span class="ruby-value str">"Bad encoding"</span>, <span class="ruby-identifier">name</span> <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">name</span>.<span class="ruby-identifier">isutf8</span> |
13 | 13 | ||
14 | <span class="ruby-identifier">atts</span> = <span class="ruby-constant">REXML</span><span class="ruby-operator">::</span><span class="ruby-constant">Document</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>( <span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span> <span class="ruby-node">"http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml"</span> ).<span class="ruby-identifier">toutf8</span>).<span class="ruby-identifier">elements</span>[<span class="ruby-value str">'api/query/pages/page'</span>].<span class="ruby-identifier">attributes</span> | 14 | <span class="ruby-identifier">atts</span> = <span class="ruby-constant">REXML</span><span class="ruby-operator">::</span><span class="ruby-constant">Document</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">Net</span><span class="ruby-operator">::</span><span class="ruby-constant">HTTP</span>.<span class="ruby-identifier">get</span>( <span class="ruby-constant">URI</span>.<span class="ruby-identifier">parse</span> <span class="ruby-node">"http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml"</span> ).<span class="ruby-identifier">toutf8</span>).<span class="ruby-identifier">elements</span>[<span class="ruby-value str">'api/query/pages/page'</span>].<span class="ruby-identifier">attributes</span> |
15 | 15 | ||
16 | <span class="ruby-identifier">atts</span>[<span class="ruby-value str">'fullurl'</span>] <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">atts</span>[<span class="ruby-value str">'missing'</span>].<span class="ruby-identifier">nil?</span> | 16 | <span class="ruby-identifier">atts</span>[<span class="ruby-value str">'fullurl'</span>] <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">atts</span>[<span class="ruby-value str">'missing'</span>].<span class="ruby-identifier">nil?</span> |
17 | <span class="ruby-keyword kw">end</span></pre> | 17 | <span class="ruby-keyword kw">end</span></pre> |
18 | </body> | 18 | </body> |
19 | </html> | 19 | </html> |
20 | 20 |
doc/classes/RIR/WikipediaPage.src/M000032.html
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>search_homepage (RIR::WikipediaPage)</title> | 5 | <title>search_homepage (RIR::WikipediaPage)</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/document.rb, line 148</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/document.rb, line 151</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_homepage</span>(<span class="ruby-identifier">name</span>) | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">search_homepage</span>(<span class="ruby-identifier">name</span>) |
12 | <span class="ruby-identifier">title</span> = <span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">search_wikipedia_titles</span> <span class="ruby-identifier">name</span> | 12 | <span class="ruby-identifier">title</span> = <span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">search_wikipedia_titles</span> <span class="ruby-identifier">name</span> |
13 | 13 | ||
14 | <span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">get_url</span> <span class="ruby-identifier">title</span>[<span class="ruby-value">0</span>]) <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">title</span>.<span class="ruby-identifier">nil?</span> <span class="ruby-operator">||</span> <span class="ruby-identifier">title</span>.<span class="ruby-identifier">empty?</span> | 14 | <span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">new</span>(<span class="ruby-constant">WikipediaPage</span>.<span class="ruby-identifier">get_url</span> <span class="ruby-identifier">title</span>[<span class="ruby-value">0</span>]) <span class="ruby-keyword kw">unless</span> <span class="ruby-identifier">title</span>.<span class="ruby-identifier">nil?</span> <span class="ruby-operator">||</span> <span class="ruby-identifier">title</span>.<span class="ruby-identifier">empty?</span> |
15 | <span class="ruby-keyword kw">end</span></pre> | 15 | <span class="ruby-keyword kw">end</span></pre> |
16 | </body> | 16 | </body> |
17 | </html> | 17 | </html> |
18 | 18 |
doc/classes/Regexp.html
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: Regexp [RDoc Documentation]</title> | 5 | <title>Class: Regexp [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">Regexp</td> | 49 | <td class="class-name-in-header">Regexp</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/regexp_rb.html"> | 56 | <a href="../files/lib/rir/regexp_rb.html"> |
57 | 57 | ||
58 | lib/rir/regexp.rb | 58 | lib/rir/regexp.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"> | ||
87 | <p> | ||
88 | This file is a part of an Information Retrieval oriented Ruby library | ||
89 | </p> | ||
90 | <p> | ||
91 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
92 | </p> | ||
93 | <p> | ||
94 | This program is free software: you can redistribute it and/or modify it | ||
95 | under the terms of the GNU General Public License as published by the Free | ||
96 | Software Foundation, either version 3 of the License, or (at your option) | ||
97 | any later version. | ||
98 | </p> | ||
99 | <p> | ||
100 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
101 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
102 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
103 | more details. | ||
104 | </p> | ||
105 | <p> | ||
106 | You should have received a copy of the GNU General Public License along | ||
107 | with this program. If not, see <<a | ||
108 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
109 | </p> | ||
110 | |||
111 | </div> | ||
112 | |||
113 | </div> | 86 | </div> |
114 | 87 | ||
115 | 88 | ||
116 | <div id="method-list"> | 89 | <div id="method-list"> |
117 | <h3 class="section-bar">Methods</h3> | 90 | <h3 class="section-bar">Methods</h3> |
118 | 91 | ||
119 | <div class="name-list"> | 92 | <div class="name-list"> |
120 | 93 | ||
121 | <a href="#M000001">negated</a> | 94 | <a href="#M000003">negated</a> |
122 | 95 | ||
123 | </div> | 96 | </div> |
124 | </div> | 97 | </div> |
125 | 98 | ||
126 | </div> | 99 | </div> |
127 | 100 | ||
128 | <!-- if includes --> | 101 | <!-- if includes --> |
129 | 102 | ||
130 | <div id="section"> | 103 | <div id="section"> |
131 | 104 | ||
132 | 105 | ||
133 | 106 | ||
134 | 107 | ||
135 | <!-- if method_list --> | 108 | <!-- if method_list --> |
136 | 109 | ||
137 | <div id="methods"> | 110 | <div id="methods"> |
138 | 111 | ||
139 | <h3 class="section-bar">Public Instance methods</h3> | 112 | <h3 class="section-bar">Public Instance methods</h3> |
140 | 113 | ||
141 | 114 | ||
142 | <div id="method-M000001" class="method-detail"> | 115 | <div id="method-M000003" class="method-detail"> |
143 | <a name="M000001"></a> | 116 | <a name="M000003"></a> |
144 | 117 | ||
145 | <div class="method-heading"> | 118 | <div class="method-heading"> |
146 | 119 | ||
147 | <a href="Regexp.src/M000001.html" target="Code" class="method-signature" | 120 | <a href="Regexp.src/M000003.html" target="Code" class="method-signature" |
148 | onclick="popupCode('Regexp.src/M000001.html');return false;"> | 121 | onclick="popupCode('Regexp.src/M000003.html');return false;"> |
149 | 122 | ||
150 | <span class="method-name">negated</span><span class="method-args">()</span> | 123 | <span class="method-name">negated</span><span class="method-args">()</span> |
151 | 124 | ||
152 | </a> | 125 | </a> |
153 | 126 | ||
154 | </div> | 127 | </div> |
155 | 128 | ||
156 | <div class="method-description"> | 129 | <div class="method-description"> |
157 | 130 | ||
158 | </div> | 131 | </div> |
159 | </div> | 132 | </div> |
160 | 133 | ||
161 | 134 | ||
162 | 135 | ||
163 | </div> | 136 | </div> |
164 | 137 | ||
165 | 138 | ||
166 | 139 | ||
167 | 140 | ||
168 | </div> | 141 | </div> |
169 | 142 | ||
170 | <div id="validator-badges"> | 143 | <div id="validator-badges"> |
171 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 144 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
172 | </div> | 145 | </div> |
173 | 146 | ||
174 | </body> | 147 | </body> |
175 | </html> | 148 | </html> |
176 | 149 |
doc/classes/Regexp.src/M000003.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>negated (Regexp)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/regexp.rb, line 24</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">negated</span> | ||
12 | <span class="ruby-node">/^((?!#{self}).)*$/</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/String.html
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="#M000012">extract_xmltags_values</a> | 102 | <a href="#M000014">extract_xmltags_values</a> |
103 | 103 | ||
104 | <a href="#M000002">is_stopword?</a> | 104 | <a href="#M000004">is_stopword?</a> |
105 | 105 | ||
106 | <a href="#M000003">remove_special_characters</a> | 106 | <a href="#M000005">remove_special_characters</a> |
107 | 107 | ||
108 | <a href="#M000007">strip_javascripts</a> | 108 | <a href="#M000009">strip_javascripts</a> |
109 | 109 | ||
110 | <a href="#M000006">strip_javascripts!</a> | 110 | <a href="#M000008">strip_javascripts!</a> |
111 | 111 | ||
112 | <a href="#M000011">strip_punctuation</a> | 112 | <a href="#M000013">strip_punctuation</a> |
113 | 113 | ||
114 | <a href="#M000010">strip_punctuation!</a> | 114 | <a href="#M000012">strip_punctuation!</a> |
115 | 115 | ||
116 | <a href="#M000009">strip_stylesheets</a> | 116 | <a href="#M000011">strip_stylesheets</a> |
117 | 117 | ||
118 | <a href="#M000008">strip_stylesheets!</a> | 118 | <a href="#M000010">strip_stylesheets!</a> |
119 | 119 | ||
120 | <a href="#M000005">strip_xml_tags</a> | 120 | <a href="#M000007">strip_xml_tags</a> |
121 | 121 | ||
122 | <a href="#M000004">strip_xml_tags!</a> | 122 | <a href="#M000006">strip_xml_tags!</a> |
123 | 123 | ||
124 | </div> | 124 | </div> |
125 | </div> | 125 | </div> |
126 | 126 | ||
127 | </div> | 127 | </div> |
128 | 128 | ||
129 | <!-- if includes --> | 129 | <!-- if includes --> |
130 | 130 | ||
131 | <div id="includes"> | 131 | <div id="includes"> |
132 | <h3 class="section-bar">Included Modules</h3> | 132 | <h3 class="section-bar">Included Modules</h3> |
133 | 133 | ||
134 | <div id="includes-list"> | 134 | <div id="includes-list"> |
135 | 135 | ||
136 | <span class="include-name"><a href="RIR.html">RIR</a></span> | 136 | <span class="include-name"><a href="RIR.html">RIR</a></span> |
137 | 137 | ||
138 | </div> | 138 | </div> |
139 | </div> | 139 | </div> |
140 | 140 | ||
141 | <div id="section"> | 141 | <div id="section"> |
142 | 142 | ||
143 | 143 | ||
144 | 144 | ||
145 | 145 | ||
146 | <!-- if method_list --> | 146 | <!-- if method_list --> |
147 | 147 | ||
148 | <div id="methods"> | 148 | <div id="methods"> |
149 | 149 | ||
150 | <h3 class="section-bar">Public Instance methods</h3> | 150 | <h3 class="section-bar">Public Instance methods</h3> |
151 | 151 | ||
152 | 152 | ||
153 | <div id="method-M000012" class="method-detail"> | 153 | <div id="method-M000014" class="method-detail"> |
154 | <a name="M000012"></a> | 154 | <a name="M000014"></a> |
155 | 155 | ||
156 | <div class="method-heading"> | 156 | <div class="method-heading"> |
157 | 157 | ||
158 | <a href="String.src/M000012.html" target="Code" class="method-signature" | 158 | <a href="String.src/M000014.html" target="Code" class="method-signature" |
159 | onclick="popupCode('String.src/M000012.html');return false;"> | 159 | onclick="popupCode('String.src/M000014.html');return false;"> |
160 | 160 | ||
161 | <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> |
162 | 162 | ||
163 | </a> | 163 | </a> |
164 | 164 | ||
165 | </div> | 165 | </div> |
166 | 166 | ||
167 | <div class="method-description"> | 167 | <div class="method-description"> |
168 | 168 | ||
169 | <p> | 169 | <p> |
170 | 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> |
171 | </p> | 171 | </p> |
172 | <pre> | 172 | <pre> |
173 | s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre" | 173 | s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre" |
174 | s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"] | 174 | s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"] |
175 | </pre> | 175 | </pre> |
176 | 176 | ||
177 | </div> | 177 | </div> |
178 | </div> | 178 | </div> |
179 | 179 | ||
180 | 180 | ||
181 | <div id="method-M000002" class="method-detail"> | 181 | <div id="method-M000004" class="method-detail"> |
182 | <a name="M000002"></a> | 182 | <a name="M000004"></a> |
183 | 183 | ||
184 | <div class="method-heading"> | 184 | <div class="method-heading"> |
185 | 185 | ||
186 | <a href="String.src/M000002.html" target="Code" class="method-signature" | 186 | <a href="String.src/M000004.html" target="Code" class="method-signature" |
187 | onclick="popupCode('String.src/M000002.html');return false;"> | 187 | onclick="popupCode('String.src/M000004.html');return false;"> |
188 | 188 | ||
189 | <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> |
190 | 190 | ||
191 | </a> | 191 | </a> |
192 | 192 | ||
193 | </div> | 193 | </div> |
194 | 194 | ||
195 | <div class="method-description"> | 195 | <div class="method-description"> |
196 | 196 | ||
197 | <p> | 197 | <p> |
198 | 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, |
199 | <tt>false</tt> otherwise. | 199 | <tt>false</tt> otherwise. |
200 | </p> | 200 | </p> |
201 | 201 | ||
202 | </div> | 202 | </div> |
203 | </div> | 203 | </div> |
204 | 204 | ||
205 | 205 | ||
206 | <div id="method-M000003" class="method-detail"> | 206 | <div id="method-M000005" class="method-detail"> |
207 | <a name="M000003"></a> | 207 | <a name="M000005"></a> |
208 | 208 | ||
209 | <div class="method-heading"> | 209 | <div class="method-heading"> |
210 | 210 | ||
211 | <a href="String.src/M000003.html" target="Code" class="method-signature" | 211 | <a href="String.src/M000005.html" target="Code" class="method-signature" |
212 | onclick="popupCode('String.src/M000003.html');return false;"> | 212 | onclick="popupCode('String.src/M000005.html');return false;"> |
213 | 213 | ||
214 | <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> |
215 | 215 | ||
216 | </a> | 216 | </a> |
217 | 217 | ||
218 | </div> | 218 | </div> |
219 | 219 | ||
220 | <div class="method-description"> | 220 | <div class="method-description"> |
221 | 221 | ||
222 | <p> | 222 | <p> |
223 | Do not use. TODO: rewamp. find why this function is here. | 223 | Do not use. TODO: rewamp. find why this function is here. |
224 | </p> | 224 | </p> |
225 | 225 | ||
226 | </div> | 226 | </div> |
227 | </div> | 227 | </div> |
228 | 228 | ||
229 | 229 | ||
230 | <div id="method-M000007" class="method-detail"> | 230 | <div id="method-M000009" class="method-detail"> |
231 | <a name="M000007"></a> | 231 | <a name="M000009"></a> |
232 | 232 | ||
233 | <div class="method-heading"> | 233 | <div class="method-heading"> |
234 | 234 | ||
235 | <a href="String.src/M000007.html" target="Code" class="method-signature" | 235 | <a href="String.src/M000009.html" target="Code" class="method-signature" |
236 | onclick="popupCode('String.src/M000007.html');return false;"> | 236 | onclick="popupCode('String.src/M000009.html');return false;"> |
237 | 237 | ||
238 | <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> |
239 | 239 | ||
240 | </a> | 240 | </a> |
241 | 241 | ||
242 | </div> | 242 | </div> |
243 | 243 | ||
244 | <div class="method-description"> | 244 | <div class="method-description"> |
245 | 245 | ||
246 | <p> | 246 | <p> |
247 | Removes all Javascript sources from <tt>self</tt>. | 247 | Removes all Javascript sources from <tt>self</tt>. |
248 | </p> | 248 | </p> |
249 | <pre> | 249 | <pre> |
250 | s = "<script type='text/javascript'> | 250 | s = "<script type='text/javascript'> |
251 | var skin='vector', | 251 | var skin='vector', |
252 | stylepath='http://bits.wikimedia.org/skins-1.5' | 252 | stylepath='http://bits.wikimedia.org/skins-1.5' |
253 | </script> | 253 | </script> |
254 | 254 | ||
255 | test" | 255 | test" |
256 | s.strip_javascripts #=> "test" | 256 | s.strip_javascripts #=> "test" |
257 | </pre> | 257 | </pre> |
258 | 258 | ||
259 | </div> | 259 | </div> |
260 | </div> | 260 | </div> |
261 | 261 | ||
262 | 262 | ||
263 | <div id="method-M000006" class="method-detail"> | 263 | <div id="method-M000008" class="method-detail"> |
264 | <a name="M000006"></a> | 264 | <a name="M000008"></a> |
265 | 265 | ||
266 | <div class="method-heading"> | 266 | <div class="method-heading"> |
267 | 267 | ||
268 | <a href="String.src/M000006.html" target="Code" class="method-signature" | 268 | <a href="String.src/M000008.html" target="Code" class="method-signature" |
269 | onclick="popupCode('String.src/M000006.html');return false;"> | 269 | onclick="popupCode('String.src/M000008.html');return false;"> |
270 | 270 | ||
271 | <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> |
272 | 272 | ||
273 | </a> | 273 | </a> |
274 | 274 | ||
275 | </div> | 275 | </div> |
276 | 276 | ||
277 | <div class="method-description"> | 277 | <div class="method-description"> |
278 | 278 | ||
279 | <p> | 279 | <p> |
280 | Removes all Javascript sources from <tt>self</tt>. | 280 | Removes all Javascript sources from <tt>self</tt>. |
281 | </p> | 281 | </p> |
282 | <pre> | 282 | <pre> |
283 | s = "<script type='text/javascript'> | 283 | s = "<script type='text/javascript'> |
284 | var skin='vector', | 284 | var skin='vector', |
285 | stylepath='http://bits.wikimedia.org/skins-1.5' | 285 | stylepath='http://bits.wikimedia.org/skins-1.5' |
286 | </script> | 286 | </script> |
287 | 287 | ||
288 | test" | 288 | test" |
289 | s.strip_javascripts! | 289 | s.strip_javascripts! |
290 | s #=> "test" | 290 | s #=> "test" |
291 | </pre> | 291 | </pre> |
292 | 292 | ||
293 | </div> | 293 | </div> |
294 | </div> | 294 | </div> |
295 | 295 | ||
296 | 296 | ||
297 | <div id="method-M000011" class="method-detail"> | 297 | <div id="method-M000013" class="method-detail"> |
298 | <a name="M000011"></a> | 298 | <a name="M000013"></a> |
299 | 299 | ||
300 | <div class="method-heading"> | 300 | <div class="method-heading"> |
301 | 301 | ||
302 | <a href="String.src/M000011.html" target="Code" class="method-signature" | 302 | <a href="String.src/M000013.html" target="Code" class="method-signature" |
303 | onclick="popupCode('String.src/M000011.html');return false;"> | 303 | onclick="popupCode('String.src/M000013.html');return false;"> |
304 | 304 | ||
305 | <span class="method-name">strip_punctuation</span><span class="method-args">()</span> | 305 | <span class="method-name">strip_punctuation</span><span class="method-args">()</span> |
306 | 306 | ||
307 | </a> | 307 | </a> |
308 | 308 | ||
309 | </div> | 309 | </div> |
310 | 310 | ||
311 | <div class="method-description"> | 311 | <div class="method-description"> |
312 | 312 | ||
313 | <p> | 313 | <p> |
314 | Removes punctuation from <tt>self</tt>. | 314 | Removes punctuation from <tt>self</tt>. |
315 | </p> | 315 | </p> |
316 | <pre> | 316 | <pre> |
317 | s = "hello, world. how are you?!" | 317 | s = "hello, world. how are you?!" |
318 | s.strip_punctuation # => "hello world how are you" | 318 | s.strip_punctuation # => "hello world how are you" |
319 | </pre> | 319 | </pre> |
320 | 320 | ||
321 | </div> | 321 | </div> |
322 | </div> | 322 | </div> |
323 | 323 | ||
324 | 324 | ||
325 | <div id="method-M000010" class="method-detail"> | 325 | <div id="method-M000012" class="method-detail"> |
326 | <a name="M000010"></a> | 326 | <a name="M000012"></a> |
327 | 327 | ||
328 | <div class="method-heading"> | 328 | <div class="method-heading"> |
329 | 329 | ||
330 | <a href="String.src/M000010.html" target="Code" class="method-signature" | 330 | <a href="String.src/M000012.html" target="Code" class="method-signature" |
331 | onclick="popupCode('String.src/M000010.html');return false;"> | 331 | onclick="popupCode('String.src/M000012.html');return false;"> |
332 | 332 | ||
333 | <span class="method-name">strip_punctuation!</span><span class="method-args">()</span> | 333 | <span class="method-name">strip_punctuation!</span><span class="method-args">()</span> |
334 | 334 | ||
335 | </a> | 335 | </a> |
336 | 336 | ||
337 | </div> | 337 | </div> |
338 | 338 | ||
339 | <div class="method-description"> | 339 | <div class="method-description"> |
340 | 340 | ||
341 | <p> | 341 | <p> |
342 | Removes punctuation from <tt>self</tt>. | 342 | Removes punctuation from <tt>self</tt>. |
343 | </p> | 343 | </p> |
344 | <pre> | 344 | <pre> |
345 | s = "hello, world. how are you?!" | 345 | s = "hello, world. how are you?!" |
346 | s.strip_punctuation! | 346 | s.strip_punctuation! |
347 | s # => "hello world how are you" | 347 | s # => "hello world how are you" |
348 | </pre> | 348 | </pre> |
349 | 349 | ||
350 | </div> | 350 | </div> |
351 | </div> | 351 | </div> |
352 | 352 | ||
353 | 353 | ||
354 | <div id="method-M000009" class="method-detail"> | 354 | <div id="method-M000011" class="method-detail"> |
355 | <a name="M000009"></a> | 355 | <a name="M000011"></a> |
356 | 356 | ||
357 | <div class="method-heading"> | 357 | <div class="method-heading"> |
358 | 358 | ||
359 | <a href="String.src/M000009.html" target="Code" class="method-signature" | 359 | <a href="String.src/M000011.html" target="Code" class="method-signature" |
360 | onclick="popupCode('String.src/M000009.html');return false;"> | 360 | onclick="popupCode('String.src/M000011.html');return false;"> |
361 | 361 | ||
362 | <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> |
363 | 363 | ||
364 | </a> | 364 | </a> |
365 | 365 | ||
366 | </div> | 366 | </div> |
367 | 367 | ||
368 | <div class="method-description"> | 368 | <div class="method-description"> |
369 | 369 | ||
370 | </div> | 370 | </div> |
371 | </div> | 371 | </div> |
372 | 372 | ||
373 | 373 | ||
374 | <div id="method-M000008" class="method-detail"> | 374 | <div id="method-M000010" class="method-detail"> |
375 | <a name="M000008"></a> | 375 | <a name="M000010"></a> |
376 | 376 | ||
377 | <div class="method-heading"> | 377 | <div class="method-heading"> |
378 | 378 | ||
379 | <a href="String.src/M000008.html" target="Code" class="method-signature" | 379 | <a href="String.src/M000010.html" target="Code" class="method-signature" |
380 | onclick="popupCode('String.src/M000008.html');return false;"> | 380 | onclick="popupCode('String.src/M000010.html');return false;"> |
381 | 381 | ||
382 | <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> |
383 | 383 | ||
384 | </a> | 384 | </a> |
385 | 385 | ||
386 | </div> | 386 | </div> |
387 | 387 | ||
388 | <div class="method-description"> | 388 | <div class="method-description"> |
389 | 389 | ||
390 | </div> | 390 | </div> |
391 | </div> | 391 | </div> |
392 | 392 | ||
393 | 393 | ||
394 | <div id="method-M000005" class="method-detail"> | 394 | <div id="method-M000007" class="method-detail"> |
395 | <a name="M000005"></a> | 395 | <a name="M000007"></a> |
396 | 396 | ||
397 | <div class="method-heading"> | 397 | <div class="method-heading"> |
398 | 398 | ||
399 | <a href="String.src/M000005.html" target="Code" class="method-signature" | 399 | <a href="String.src/M000007.html" target="Code" class="method-signature" |
400 | onclick="popupCode('String.src/M000005.html');return false;"> | 400 | onclick="popupCode('String.src/M000007.html');return false;"> |
401 | 401 | ||
402 | <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> |
403 | 403 | ||
404 | </a> | 404 | </a> |
405 | 405 | ||
406 | </div> | 406 | </div> |
407 | 407 | ||
408 | <div class="method-description"> | 408 | <div class="method-description"> |
409 | 409 | ||
410 | <p> | 410 | <p> |
411 | Removes all XML-like tags from <tt>self</tt>. | 411 | Removes all XML-like tags from <tt>self</tt>. |
412 | </p> | 412 | </p> |
413 | <pre> | 413 | <pre> |
414 | s = "<html><body>test</body></html>" | 414 | s = "<html><body>test</body></html>" |
415 | s.strip_xml_tags #=> "test" | 415 | s.strip_xml_tags #=> "test" |
416 | s #=> "<html><body>test</body></html>" | 416 | s #=> "<html><body>test</body></html>" |
417 | </pre> | 417 | </pre> |
418 | 418 | ||
419 | </div> | 419 | </div> |
420 | </div> | 420 | </div> |
421 | 421 | ||
422 | 422 | ||
423 | <div id="method-M000004" class="method-detail"> | 423 | <div id="method-M000006" class="method-detail"> |
424 | <a name="M000004"></a> | 424 | <a name="M000006"></a> |
425 | 425 | ||
426 | <div class="method-heading"> | 426 | <div class="method-heading"> |
427 | 427 | ||
428 | <a href="String.src/M000004.html" target="Code" class="method-signature" | 428 | <a href="String.src/M000006.html" target="Code" class="method-signature" |
429 | onclick="popupCode('String.src/M000004.html');return false;"> | 429 | onclick="popupCode('String.src/M000006.html');return false;"> |
430 | 430 | ||
431 | <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> |
432 | 432 | ||
433 | </a> | 433 | </a> |
434 | 434 | ||
435 | </div> | 435 | </div> |
436 | 436 | ||
437 | <div class="method-description"> | 437 | <div class="method-description"> |
438 | 438 | ||
439 | <p> | 439 | <p> |
440 | Removes all XML-like tags from <tt>self</tt>. | 440 | Removes all XML-like tags from <tt>self</tt>. |
441 | </p> | 441 | </p> |
442 | <pre> | 442 | <pre> |
443 | s = "<html><body>test</body></html>" | 443 | s = "<html><body>test</body></html>" |
444 | s.strip_xml_tags! | 444 | s.strip_xml_tags! |
445 | s #=> "test" | 445 | s #=> "test" |
446 | </pre> | 446 | </pre> |
447 | 447 | ||
448 | </div> | 448 | </div> |
449 | </div> | 449 | </div> |
450 | 450 | ||
451 | 451 | ||
452 | 452 | ||
453 | </div> | 453 | </div> |
454 | 454 | ||
455 | 455 | ||
456 | 456 | ||
457 | 457 | ||
458 | </div> | 458 | </div> |
459 | 459 | ||
460 | <div id="validator-badges"> | 460 | <div id="validator-badges"> |
461 | <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> |
462 | </div> | 462 | </div> |
463 | 463 | ||
464 | </body> | 464 | </body> |
465 | </html> | 465 | </html> |
466 | 466 |
doc/classes/String.src/M000004.html
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>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 91</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 78</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags!</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">is_stopword?</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-regexp re">/?[^>]*>/</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/M000005.html
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>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 100</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 84</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_xml_tags</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">remove_special_characters</span> |
12 | <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_xml_tags!</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/M000006.html
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_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 114</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 93</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</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"><</span><span class="ruby-identifier">script</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">"text\/javascript"</span><span class="ruby-operator">></span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator"><</span>\<span class="ruby-regexp re">/script>/</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"><</span>\<span class="ruby-regexp re">/?[^>]*>/</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
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_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 127</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 102</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts</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_javascripts!</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/M000008.html
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_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 131</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 116</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_javascripts!</span> |
12 | <span class="ruby-comment cmt"># TODO: rewamp. dunno what is it.</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">script</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">"text\/javascript"</span><span class="ruby-operator">></span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator"><</span>\<span class="ruby-regexp re">/script>/</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"><</span><span class="ruby-identifier">style</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">"text\/css"</span><span class="ruby-operator">></span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator"><</span>\<span class="ruby-regexp re">/style>/</span><span class="ruby-identifier">m</span> | ||
14 | <span class="ruby-keyword kw">end</span></pre> | 13 | <span class="ruby-keyword kw">end</span></pre> |
15 | </body> | 14 | </body> |
16 | </html> | 15 | </html> |
17 | 16 |
doc/classes/String.src/M000009.html
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_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 136</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 129</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets</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_stylesheets!</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/M000010.html
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_punctuation! (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 145</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 133</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation!</span> | 11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_stylesheets!</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> | 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"><</span><span class="ruby-identifier">style</span> <span class="ruby-identifier">type</span>=<span class="ruby-value str">"text\/css"</span><span class="ruby-operator">></span>(.<span class="ruby-operator">+</span><span class="ruby-value">?)</span><span class="ruby-operator"><</span>\<span class="ruby-regexp re">/style>/</span><span class="ruby-identifier">m</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | 14 | <span class="ruby-keyword kw">end</span></pre> |
14 | </body> | 15 | </body> |
15 | </html> | 16 | </html> |
16 | 17 |
doc/classes/String.src/M000011.html
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_punctuation (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 153</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 138</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation</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_punctuation!</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/M000012.html
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 161</span> | 10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 147</span> |
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">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">/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/</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 |
doc/classes/String.src/M000013.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>strip_punctuation (String)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 155</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">strip_punctuation</span> | ||
12 | <span class="ruby-identifier">dup</span>.<span class="ruby-identifier">strip_punctuation!</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/String.src/M000014.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>extract_xmltags_values (String)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/string.rb, line 163</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">extract_xmltags_values</span>(<span class="ruby-identifier">tag_name</span>) | ||
12 | <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">scan</span>(<span class="ruby-node">/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/</span>).<span class="ruby-identifier">flatten</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/TreeTagger.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Module: TreeTagger [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Module</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | </table> | ||
70 | </div> | ||
71 | <!-- banner header --> | ||
72 | |||
73 | <div id="bodyContent"> | ||
74 | |||
75 | <div id="contextContent"> | ||
76 | |||
77 | <div id="description"> | ||
78 | <p> | ||
79 | TreeTagger-related stuff module. | ||
80 | </p> | ||
81 | <p> | ||
82 | See <a | ||
83 | href="http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html">www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html</a> | ||
84 | </p> | ||
85 | |||
86 | </div> | ||
87 | |||
88 | </div> | ||
89 | |||
90 | |||
91 | </div> | ||
92 | |||
93 | <!-- if includes --> | ||
94 | |||
95 | <div id="section"> | ||
96 | |||
97 | <div id="class-list"> | ||
98 | <h3 class="section-bar">Classes and Modules</h3> | ||
99 | |||
100 | Class <a href="TreeTagger/Chunk.html" class="link">TreeTagger::Chunk</a><br /> | ||
101 | Class <a href="TreeTagger/TaggerChunker.html" class="link">TreeTagger::TaggerChunker</a><br /> | ||
102 | Class <a href="TreeTagger/TaggerChunkerEnglish.html" class="link">TreeTagger::TaggerChunkerEnglish</a><br /> | ||
103 | Class <a href="TreeTagger/TaggerChunkerFrench.html" class="link">TreeTagger::TaggerChunkerFrench</a><br /> | ||
104 | Class <a href="TreeTagger/TaggerChunkerGerman.html" class="link">TreeTagger::TaggerChunkerGerman</a><br /> | ||
105 | |||
106 | </div> | ||
107 | |||
108 | |||
109 | |||
110 | |||
111 | <!-- if method_list --> | ||
112 | |||
113 | |||
114 | |||
115 | |||
116 | </div> | ||
117 | |||
118 | <div id="validator-badges"> | ||
119 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
120 | </div> | ||
121 | |||
122 | </body> | ||
123 | </html> | ||
124 |
doc/classes/TreeTagger/Chunk.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: TreeTagger::Chunk [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger::Chunk</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | Object | ||
74 | |||
75 | </td> | ||
76 | </tr> | ||
77 | |||
78 | </table> | ||
79 | </div> | ||
80 | <!-- banner header --> | ||
81 | |||
82 | <div id="bodyContent"> | ||
83 | |||
84 | <div id="contextContent"> | ||
85 | |||
86 | <div id="description"> | ||
87 | <p> | ||
88 | Represents a <a href="Chunk.html">Chunk</a> extracted when parsing a <a | ||
89 | href="TaggerChunker.html">TaggerChunker</a> file. | ||
90 | </p> | ||
91 | |||
92 | </div> | ||
93 | |||
94 | </div> | ||
95 | |||
96 | |||
97 | <div id="method-list"> | ||
98 | <h3 class="section-bar">Methods</h3> | ||
99 | |||
100 | <div class="name-list"> | ||
101 | |||
102 | <a href="#M000017">new</a> | ||
103 | |||
104 | </div> | ||
105 | </div> | ||
106 | |||
107 | </div> | ||
108 | |||
109 | <!-- if includes --> | ||
110 | |||
111 | <div id="section"> | ||
112 | |||
113 | |||
114 | |||
115 | <div id="attribute-list"> | ||
116 | <h3 class="section-bar">Attributes</h3> | ||
117 | |||
118 | <div class="name-list"> | ||
119 | <table> | ||
120 | |||
121 | <tr class="top-aligned-row context-row"> | ||
122 | <td class="context-item-name">tag</td> | ||
123 | |||
124 | <td class="context-item-value"> [R] </td> | ||
125 | |||
126 | <td class="context-item-desc"></td> | ||
127 | </tr> | ||
128 | |||
129 | <tr class="top-aligned-row context-row"> | ||
130 | <td class="context-item-name">words</td> | ||
131 | |||
132 | <td class="context-item-value"> [R] </td> | ||
133 | |||
134 | <td class="context-item-desc"></td> | ||
135 | </tr> | ||
136 | |||
137 | </table> | ||
138 | </div> | ||
139 | </div> | ||
140 | |||
141 | |||
142 | <!-- if method_list --> | ||
143 | |||
144 | <div id="methods"> | ||
145 | |||
146 | <h3 class="section-bar">Public Class methods</h3> | ||
147 | |||
148 | |||
149 | <div id="method-M000017" class="method-detail"> | ||
150 | <a name="M000017"></a> | ||
151 | |||
152 | <div class="method-heading"> | ||
153 | |||
154 | <a href="Chunk.src/M000017.html" target="Code" class="method-signature" | ||
155 | onclick="popupCode('Chunk.src/M000017.html');return false;"> | ||
156 | |||
157 | <span class="method-name">new</span><span class="method-args">(str,tag)</span> | ||
158 | |||
159 | </a> | ||
160 | |||
161 | </div> | ||
162 | |||
163 | <div class="method-description"> | ||
164 | |||
165 | <p> | ||
166 | Creates a <a href="Chunk.html">Chunk</a>. | ||
167 | </p> | ||
168 | <ul> | ||
169 | <li><tt>str</tt> are whitespace-separated terms. | ||
170 | |||
171 | </li> | ||
172 | <li><tt>tag</tt> see : <a | ||
173 | href="ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt">ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt</a> | ||
174 | |||
175 | </li> | ||
176 | </ul> | ||
177 | |||
178 | </div> | ||
179 | </div> | ||
180 | |||
181 | |||
182 | |||
183 | </div> | ||
184 | |||
185 | |||
186 | |||
187 | |||
188 | </div> | ||
189 | |||
190 | <div id="validator-badges"> | ||
191 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
192 | </div> | ||
193 | |||
194 | </body> | ||
195 | </html> | ||
196 |
doc/classes/TreeTagger/Chunk.src/M000017.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>new (TreeTagger::Chunk)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 89</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span> <span class="ruby-identifier">str</span>,<span class="ruby-identifier">tag</span> | ||
12 | <span class="ruby-ivar">@words</span> = <span class="ruby-identifier">str</span>.<span class="ruby-identifier">split</span> | ||
13 | <span class="ruby-ivar">@tag</span> = <span class="ruby-identifier">tag</span>[<span class="ruby-value">1</span><span class="ruby-operator">..</span><span class="ruby-value">-2</span>] | ||
14 | <span class="ruby-keyword kw">end</span></pre> | ||
15 | </body> | ||
16 | </html> | ||
17 |
doc/classes/TreeTagger/TaggerChunker.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: TreeTagger::TaggerChunker [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger::TaggerChunker</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | Object | ||
74 | |||
75 | </td> | ||
76 | </tr> | ||
77 | |||
78 | </table> | ||
79 | </div> | ||
80 | <!-- banner header --> | ||
81 | |||
82 | <div id="bodyContent"> | ||
83 | |||
84 | <div id="contextContent"> | ||
85 | |||
86 | <div id="description"> | ||
87 | <p> | ||
88 | This class handles generic parsing of tagger-chunker outputs. | ||
89 | </p> | ||
90 | |||
91 | </div> | ||
92 | |||
93 | </div> | ||
94 | |||
95 | |||
96 | <div id="method-list"> | ||
97 | <h3 class="section-bar">Methods</h3> | ||
98 | |||
99 | <div class="name-list"> | ||
100 | |||
101 | <a href="#M000016">new</a> | ||
102 | |||
103 | <a href="#M000015">parse</a> | ||
104 | |||
105 | </div> | ||
106 | </div> | ||
107 | |||
108 | </div> | ||
109 | |||
110 | <!-- if includes --> | ||
111 | |||
112 | <div id="section"> | ||
113 | |||
114 | |||
115 | |||
116 | <div id="attribute-list"> | ||
117 | <h3 class="section-bar">Attributes</h3> | ||
118 | |||
119 | <div class="name-list"> | ||
120 | <table> | ||
121 | |||
122 | <tr class="top-aligned-row context-row"> | ||
123 | <td class="context-item-name">chunks</td> | ||
124 | |||
125 | <td class="context-item-value"> [R] </td> | ||
126 | |||
127 | <td class="context-item-desc"></td> | ||
128 | </tr> | ||
129 | |||
130 | <tr class="top-aligned-row context-row"> | ||
131 | <td class="context-item-name">file</td> | ||
132 | |||
133 | <td class="context-item-value"> [R] </td> | ||
134 | |||
135 | <td class="context-item-desc"></td> | ||
136 | </tr> | ||
137 | |||
138 | </table> | ||
139 | </div> | ||
140 | </div> | ||
141 | |||
142 | |||
143 | <!-- if method_list --> | ||
144 | |||
145 | <div id="methods"> | ||
146 | |||
147 | <h3 class="section-bar">Public Class methods</h3> | ||
148 | |||
149 | |||
150 | <div id="method-M000016" class="method-detail"> | ||
151 | <a name="M000016"></a> | ||
152 | |||
153 | <div class="method-heading"> | ||
154 | |||
155 | <a href="TaggerChunker.src/M000016.html" target="Code" class="method-signature" | ||
156 | onclick="popupCode('TaggerChunker.src/M000016.html');return false;"> | ||
157 | |||
158 | <span class="method-name">new</span><span class="method-args">(chunk_file)</span> | ||
159 | |||
160 | </a> | ||
161 | |||
162 | </div> | ||
163 | |||
164 | <div class="method-description"> | ||
165 | |||
166 | <p> | ||
167 | Initializes parsing. <tt>chunk_file</tt> is the output of | ||
168 | <tt>tagger-chunker-</tt> and must be a valid path to the file. | ||
169 | </p> | ||
170 | <pre> | ||
171 | TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...> | ||
172 | </pre> | ||
173 | |||
174 | </div> | ||
175 | </div> | ||
176 | |||
177 | |||
178 | <div id="method-M000015" class="method-detail"> | ||
179 | <a name="M000015"></a> | ||
180 | |||
181 | <div class="method-heading"> | ||
182 | |||
183 | <a href="TaggerChunker.src/M000015.html" target="Code" class="method-signature" | ||
184 | onclick="popupCode('TaggerChunker.src/M000015.html');return false;"> | ||
185 | |||
186 | <span class="method-name">parse</span><span class="method-args">(chunk_lines)</span> | ||
187 | |||
188 | </a> | ||
189 | |||
190 | </div> | ||
191 | |||
192 | <div class="method-description"> | ||
193 | |||
194 | <p> | ||
195 | Parses a tagger-chunker output and returns an Array of <a | ||
196 | href="Chunk.html">Chunk</a>. | ||
197 | </p> | ||
198 | |||
199 | </div> | ||
200 | </div> | ||
201 | |||
202 | |||
203 | |||
204 | </div> | ||
205 | |||
206 | |||
207 | |||
208 | |||
209 | </div> | ||
210 | |||
211 | <div id="validator-badges"> | ||
212 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
213 | </div> | ||
214 | |||
215 | </body> | ||
216 | </html> | ||
217 |
doc/classes/TreeTagger/TaggerChunker.src/M000015.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>parse (TreeTagger::TaggerChunker)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 34</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-keyword kw">self</span>.<span class="ruby-identifier">parse</span> <span class="ruby-identifier">chunk_lines</span> | ||
12 | <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">false</span> | ||
13 | <span class="ruby-identifier">tag</span> = <span class="ruby-keyword kw">nil</span> | ||
14 | |||
15 | <span class="ruby-identifier">chunks</span> = [] | ||
16 | <span class="ruby-identifier">words</span> = [] | ||
17 | |||
18 | <span class="ruby-identifier">chunk_lines</span>.<span class="ruby-identifier">each</span> <span class="ruby-keyword kw">do</span> <span class="ruby-operator">|</span><span class="ruby-identifier">l</span><span class="ruby-operator">|</span> | ||
19 | <span class="ruby-identifier">l</span>.<span class="ruby-identifier">chomp!</span> | ||
20 | <span class="ruby-keyword kw">if</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/^<\w+>$/</span> | ||
21 | <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">true</span> | ||
22 | <span class="ruby-identifier">tag</span> = <span class="ruby-identifier">l</span> | ||
23 | <span class="ruby-keyword kw">elsif</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">=~</span> <span class="ruby-regexp re">/^<\/\w+>$/</span> | ||
24 | <span class="ruby-keyword kw">if</span> <span class="ruby-operator">!</span><span class="ruby-identifier">words</span>.<span class="ruby-identifier">empty?</span> <span class="ruby-operator">&&</span> <span class="ruby-identifier">open</span> <span class="ruby-operator">&&</span> <span class="ruby-identifier">l</span> <span class="ruby-operator">==</span> <span class="ruby-identifier">tag</span>.<span class="ruby-identifier">sub</span>(<span class="ruby-regexp re">/</</span>, <span class="ruby-value str">'</'</span>) | ||
25 | <span class="ruby-identifier">open</span> = <span class="ruby-keyword kw">false</span> | ||
26 | <span class="ruby-identifier">chunks</span>.<span class="ruby-identifier">push</span> <span class="ruby-constant">Chunk</span>.<span class="ruby-identifier">new</span>(<span class="ruby-identifier">words</span>.<span class="ruby-identifier">join</span>(<span class="ruby-value str">" "</span>), <span class="ruby-identifier">tag</span>) | ||
27 | <span class="ruby-identifier">words</span>.<span class="ruby-identifier">clear</span> | ||
28 | <span class="ruby-keyword kw">else</span> | ||
29 | <span class="ruby-keyword kw">next</span> | ||
30 | <span class="ruby-keyword kw">end</span> | ||
31 | <span class="ruby-keyword kw">else</span> | ||
32 | <span class="ruby-identifier">words</span>.<span class="ruby-identifier">push</span>(<span class="ruby-identifier">l</span>.<span class="ruby-identifier">split</span>.<span class="ruby-identifier">first</span>) | ||
33 | <span class="ruby-keyword kw">end</span> | ||
34 | <span class="ruby-keyword kw">end</span> | ||
35 | |||
36 | <span class="ruby-identifier">chunks</span> | ||
37 | <span class="ruby-keyword kw">end</span></pre> | ||
38 | </body> | ||
39 | </html> | ||
40 |
doc/classes/TreeTagger/TaggerChunker.src/M000016.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>new (TreeTagger::TaggerChunker)</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <link rel="stylesheet" href="../../.././rdoc-style.css" type="text/css" media="screen" /> | ||
8 | </head> | ||
9 | <body class="standalone-code"> | ||
10 | <pre><span class="ruby-comment cmt"># File lib/rir/ttagger.rb, line 66</span> | ||
11 | <span class="ruby-keyword kw">def</span> <span class="ruby-identifier">initialize</span> <span class="ruby-identifier">chunk_file</span> | ||
12 | <span class="ruby-ivar">@chunks</span> = <span class="ruby-constant">TaggerChunker</span>.<span class="ruby-identifier">parse</span> <span class="ruby-constant">File</span>.<span class="ruby-identifier">open</span>(<span class="ruby-identifier">chunk_file</span>).<span class="ruby-identifier">readlines</span> | ||
13 | <span class="ruby-keyword kw">end</span></pre> | ||
14 | </body> | ||
15 | </html> | ||
16 |
doc/classes/TreeTagger/TaggerChunkerEnglish.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: TreeTagger::TaggerChunkerEnglish [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger::TaggerChunkerEnglish</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | <a href="TaggerChunker.html"> | ||
74 | |||
75 | TreeTagger::TaggerChunker | ||
76 | |||
77 | </a> | ||
78 | |||
79 | </td> | ||
80 | </tr> | ||
81 | |||
82 | </table> | ||
83 | </div> | ||
84 | <!-- banner header --> | ||
85 | |||
86 | <div id="bodyContent"> | ||
87 | |||
88 | <div id="contextContent"> | ||
89 | |||
90 | </div> | ||
91 | |||
92 | |||
93 | </div> | ||
94 | |||
95 | <!-- if includes --> | ||
96 | |||
97 | <div id="section"> | ||
98 | |||
99 | |||
100 | |||
101 | |||
102 | <!-- if method_list --> | ||
103 | |||
104 | |||
105 | |||
106 | |||
107 | </div> | ||
108 | |||
109 | <div id="validator-badges"> | ||
110 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
111 | </div> | ||
112 | |||
113 | </body> | ||
114 | </html> | ||
115 |
doc/classes/TreeTagger/TaggerChunkerFrench.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: TreeTagger::TaggerChunkerFrench [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger::TaggerChunkerFrench</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | <a href="TaggerChunker.html"> | ||
74 | |||
75 | TreeTagger::TaggerChunker | ||
76 | |||
77 | </a> | ||
78 | |||
79 | </td> | ||
80 | </tr> | ||
81 | |||
82 | </table> | ||
83 | </div> | ||
84 | <!-- banner header --> | ||
85 | |||
86 | <div id="bodyContent"> | ||
87 | |||
88 | <div id="contextContent"> | ||
89 | |||
90 | </div> | ||
91 | |||
92 | |||
93 | </div> | ||
94 | |||
95 | <!-- if includes --> | ||
96 | |||
97 | <div id="section"> | ||
98 | |||
99 | |||
100 | |||
101 | |||
102 | <!-- if method_list --> | ||
103 | |||
104 | |||
105 | |||
106 | |||
107 | </div> | ||
108 | |||
109 | <div id="validator-badges"> | ||
110 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
111 | </div> | ||
112 | |||
113 | </body> | ||
114 | </html> | ||
115 |
doc/classes/TreeTagger/TaggerChunkerGerman.html
File was created | 1 | <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" | |
2 | "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> | ||
3 | <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"> | ||
4 | <head> | ||
5 | <title>Class: TreeTagger::TaggerChunkerGerman [RDoc Documentation]</title> | ||
6 | <meta http-equiv="Content-Type" content="text/html; charset=utf-8" /> | ||
7 | <meta http-equiv="Content-Script-Type" content="text/javascript" /> | ||
8 | <link rel="stylesheet" href="../.././rdoc-style.css" type="text/css" media="screen" /> | ||
9 | <script type="text/javascript"> | ||
10 | // <![CDATA[ | ||
11 | |||
12 | function popupCode( url ) { | ||
13 | window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400") | ||
14 | } | ||
15 | |||
16 | function toggleCode( id ) { | ||
17 | if ( document.getElementById ) | ||
18 | elem = document.getElementById( id ); | ||
19 | else if ( document.all ) | ||
20 | elem = eval( "document.all." + id ); | ||
21 | else | ||
22 | return false; | ||
23 | |||
24 | elemStyle = elem.style; | ||
25 | |||
26 | if ( elemStyle.display != "block" ) { | ||
27 | elemStyle.display = "block" | ||
28 | } else { | ||
29 | elemStyle.display = "none" | ||
30 | } | ||
31 | |||
32 | return true; | ||
33 | } | ||
34 | |||
35 | // Make codeblocks hidden by default | ||
36 | document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }<\/style>" ) | ||
37 | |||
38 | // ]]> | ||
39 | </script> | ||
40 | |||
41 | </head> | ||
42 | <body> | ||
43 | |||
44 | |||
45 | <div id="classHeader"> | ||
46 | <table class="header-table"> | ||
47 | <tr class="top-aligned-row"> | ||
48 | <td><strong>Class</strong></td> | ||
49 | <td class="class-name-in-header">TreeTagger::TaggerChunkerGerman</td> | ||
50 | </tr> | ||
51 | <tr class="top-aligned-row"> | ||
52 | <td><strong>In:</strong></td> | ||
53 | <td> | ||
54 | |||
55 | |||
56 | <a href="../../files/lib/rir/ttagger_rb.html"> | ||
57 | |||
58 | lib/rir/ttagger.rb | ||
59 | |||
60 | </a> | ||
61 | |||
62 | |||
63 | <br /> | ||
64 | |||
65 | </td> | ||
66 | </tr> | ||
67 | |||
68 | |||
69 | <tr class="top-aligned-row"> | ||
70 | <td><strong>Parent:</strong></td> | ||
71 | <td> | ||
72 | |||
73 | <a href="TaggerChunker.html"> | ||
74 | |||
75 | TreeTagger::TaggerChunker | ||
76 | |||
77 | </a> | ||
78 | |||
79 | </td> | ||
80 | </tr> | ||
81 | |||
82 | </table> | ||
83 | </div> | ||
84 | <!-- banner header --> | ||
85 | |||
86 | <div id="bodyContent"> | ||
87 | |||
88 | <div id="contextContent"> | ||
89 | |||
90 | </div> | ||
91 | |||
92 | |||
93 | </div> | ||
94 | |||
95 | <!-- if includes --> | ||
96 | |||
97 | <div id="section"> | ||
98 | |||
99 | |||
100 | |||
101 | |||
102 | <!-- if method_list --> | ||
103 | |||
104 | |||
105 | |||
106 | |||
107 | </div> | ||
108 | |||
109 | <div id="validator-badges"> | ||
110 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | ||
111 | </div> | ||
112 | |||
113 | </body> | ||
114 | </html> | ||
115 |
doc/created.rid
1 | Thu, 25 Nov 2010 17:10:04 +0100 | 1 | Thu, 25 Nov 2010 17:21:51 +0100 |
2 | 2 |
doc/files/lib/rir/corpus_rb.html
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: corpus.rb [RDoc Documentation]</title> | 5 | <title>File: corpus.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>corpus.rb</h1> | 46 | <h1>corpus.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/corpus.rb | 50 | <td>lib/rir/corpus.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>2010-11-23 18:20:24 +0100</td> | 56 | <td>2010-11-25 17:20:52 +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 | |||
66 | <div id="description"> | ||
67 | <p> | ||
68 | This file is a part of an Information Retrieval oriented Ruby library | ||
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | ||
90 | |||
91 | </div> | ||
92 | 65 | ||
93 | </div> | 66 | </div> |
94 | 67 | ||
95 | 68 | ||
96 | </div> | 69 | </div> |
97 | 70 | ||
98 | <!-- if includes --> | 71 | <!-- if includes --> |
99 | 72 | ||
100 | <div id="section"> | 73 | <div id="section"> |
101 | 74 | ||
102 | 75 | ||
103 | 76 | ||
104 | 77 | ||
105 | <!-- if method_list --> | 78 | <!-- if method_list --> |
106 | 79 | ||
107 | 80 | ||
108 | 81 | ||
109 | 82 | ||
110 | </div> | 83 | </div> |
111 | 84 | ||
112 | <div id="validator-badges"> | 85 | <div id="validator-badges"> |
113 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 86 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
114 | </div> | 87 | </div> |
115 | 88 | ||
116 | </body> | 89 | </body> |
117 | </html> | 90 | </html> |
118 | 91 |
doc/files/lib/rir/document_rb.html
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>2010-11-25 16:04:20 +0100</td> | 56 | <td>2010-11-25 17:20:25 +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 | |||
66 | <div id="description"> | ||
67 | <p> | ||
68 | This file is a part of an Information Retrieval oriented Ruby library | ||
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | ||
90 | |||
91 | </div> | ||
92 | 65 | ||
93 | <div id="requires-list"> | 66 | <div id="requires-list"> |
94 | <h3 class="section-bar">Required files</h3> | 67 | <h3 class="section-bar">Required files</h3> |
95 | 68 | ||
96 | <div class="name-list"> | 69 | <div class="name-list"> |
97 | 70 | ||
98 | net/http | 71 | net/http |
99 | 72 | ||
100 | rexml/document | 73 | rexml/document |
101 | 74 | ||
102 | net/http | 75 | net/http |
103 | 76 | ||
104 | kconv | 77 | kconv |
105 | 78 | ||
106 | </div> | 79 | </div> |
107 | </div> | 80 | </div> |
108 | 81 | ||
109 | </div> | 82 | </div> |
110 | 83 | ||
111 | 84 | ||
112 | </div> | 85 | </div> |
113 | 86 | ||
114 | <!-- if includes --> | 87 | <!-- if includes --> |
115 | 88 | ||
116 | <div id="section"> | 89 | <div id="section"> |
117 | 90 | ||
118 | 91 | ||
119 | 92 | ||
120 | 93 | ||
121 | <!-- if method_list --> | 94 | <!-- if method_list --> |
122 | 95 | ||
123 | 96 | ||
124 | 97 | ||
125 | 98 | ||
126 | </div> | 99 | </div> |
127 | 100 | ||
128 | <div id="validator-badges"> | 101 | <div id="validator-badges"> |
129 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 102 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
130 | </div> | 103 | </div> |
131 | 104 | ||
132 | </body> | 105 | </body> |
133 | </html> | 106 | </html> |
134 | 107 |
doc/files/lib/rir/query_rb.html
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: query.rb [RDoc Documentation]</title> | 5 | <title>File: query.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>query.rb</h1> | 46 | <h1>query.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/query.rb | 50 | <td>lib/rir/query.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>2010-11-25 13:25:18 +0100</td> | 56 | <td>2010-11-25 17:21:14 +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 | |||
66 | <div id="description"> | ||
67 | <p> | ||
68 | This file is a part of an Information Retrieval oriented Ruby library | ||
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | ||
90 | |||
91 | </div> | ||
92 | 65 | ||
93 | </div> | 66 | </div> |
94 | 67 | ||
95 | 68 | ||
96 | </div> | 69 | </div> |
97 | 70 | ||
98 | <!-- if includes --> | 71 | <!-- if includes --> |
99 | 72 | ||
100 | <div id="section"> | 73 | <div id="section"> |
101 | 74 | ||
102 | 75 | ||
103 | 76 | ||
104 | 77 | ||
105 | <!-- if method_list --> | 78 | <!-- if method_list --> |
106 | 79 | ||
107 | 80 | ||
108 | 81 | ||
109 | 82 | ||
110 | </div> | 83 | </div> |
111 | 84 | ||
112 | <div id="validator-badges"> | 85 | <div id="validator-badges"> |
113 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 86 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
114 | </div> | 87 | </div> |
115 | 88 | ||
116 | </body> | 89 | </body> |
117 | </html> | 90 | </html> |
118 | 91 |
doc/files/lib/rir/regexp_rb.html
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: regexp.rb [RDoc Documentation]</title> | 5 | <title>File: regexp.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>regexp.rb</h1> | 46 | <h1>regexp.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/regexp.rb | 50 | <td>lib/rir/regexp.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>2010-11-19 11:27:06 +0100</td> | 56 | <td>2010-11-25 17:19:39 +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 | |||
66 | <div id="description"> | ||
67 | <p> | ||
68 | This file is a part of an Information Retrieval oriented Ruby library | ||
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | ||
90 | |||
91 | </div> | ||
92 | 65 | ||
93 | </div> | 66 | </div> |
94 | 67 | ||
95 | 68 | ||
96 | </div> | 69 | </div> |
97 | 70 | ||
98 | <!-- if includes --> | 71 | <!-- if includes --> |
99 | 72 | ||
100 | <div id="section"> | 73 | <div id="section"> |
101 | 74 | ||
102 | 75 | ||
103 | 76 | ||
104 | 77 | ||
105 | <!-- if method_list --> | 78 | <!-- if method_list --> |
106 | 79 | ||
107 | 80 | ||
108 | 81 | ||
109 | 82 | ||
110 | </div> | 83 | </div> |
111 | 84 | ||
112 | <div id="validator-badges"> | 85 | <div id="validator-badges"> |
113 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 86 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
114 | </div> | 87 | </div> |
115 | 88 | ||
116 | </body> | 89 | </body> |
117 | </html> | 90 | </html> |
118 | 91 |
doc/files/lib/rir/string_rb.html
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>2010-11-23 18:20:41 +0100</td> | 56 | <td>2010-11-25 17:20:14 +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 | <hr size="1"></hr><p> |
68 | This file is a part of an Information Retrieval oriented Ruby library | 68 | General module for many purposes related to Information Retrieval. |
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | 69 | </p> |
90 | 70 | ||
91 | </div> | 71 | </div> |
92 | 72 | ||
93 | <div id="requires-list"> | 73 | <div id="requires-list"> |
94 | <h3 class="section-bar">Required files</h3> | 74 | <h3 class="section-bar">Required files</h3> |
95 | 75 | ||
96 | <div class="name-list"> | 76 | <div class="name-list"> |
97 | 77 | ||
98 | cgi | 78 | cgi |
99 | 79 | ||
100 | kconv | 80 | kconv |
101 | 81 | ||
102 | </div> | 82 | </div> |
103 | </div> | 83 | </div> |
104 | 84 | ||
105 | </div> | 85 | </div> |
106 | 86 | ||
107 | 87 | ||
108 | </div> | 88 | </div> |
109 | 89 | ||
110 | <!-- if includes --> | 90 | <!-- if includes --> |
111 | 91 | ||
112 | <div id="section"> | 92 | <div id="section"> |
113 | 93 | ||
114 | 94 | ||
115 | 95 | ||
116 | 96 | ||
117 | <!-- if method_list --> | 97 | <!-- if method_list --> |
118 | 98 | ||
119 | 99 | ||
120 | 100 | ||
121 | 101 | ||
122 | </div> | 102 | </div> |
123 | 103 | ||
124 | <div id="validator-badges"> | 104 | <div id="validator-badges"> |
125 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 105 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
126 | </div> | 106 | </div> |
127 | 107 | ||
128 | </body> | 108 | </body> |
129 | </html> | 109 | </html> |
130 | 110 |
doc/files/lib/rir/ttagger_rb.html
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: ttagger.rb [RDoc Documentation]</title> | 5 | <title>File: ttagger.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>ttagger.rb</h1> | 46 | <h1>ttagger.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/ttagger.rb | 50 | <td>lib/rir/ttagger.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>2010-11-25 17:01:46 +0100</td> | 56 | <td>2010-11-25 17:21:44 +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 | |||
66 | <div id="description"> | ||
67 | <p> | ||
68 | This file is a part of an Information Retrieval oriented Ruby library | ||
69 | </p> | ||
70 | <p> | ||
71 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
72 | </p> | ||
73 | <p> | ||
74 | This program is free software: you can redistribute it and/or modify it | ||
75 | under the terms of the GNU General Public License as published by the Free | ||
76 | Software Foundation, either version 3 of the License, or (at your option) | ||
77 | any later version. | ||
78 | </p> | ||
79 | <p> | ||
80 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
81 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
82 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
83 | more details. | ||
84 | </p> | ||
85 | <p> | ||
86 | You should have received a copy of the GNU General Public License along | ||
87 | with this program. If not, see <<a | ||
88 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
89 | </p> | ||
90 | <hr size="1"></hr><p> | ||
91 | This file is a part of an Information Retrieval oriented Ruby library | ||
92 | </p> | ||
93 | <p> | ||
94 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
95 | </p> | ||
96 | <p> | ||
97 | This program is free software: you can redistribute it and/or modify it | ||
98 | under the terms of the GNU General Public License as published by the Free | ||
99 | Software Foundation, either version 3 of the License, or (at your option) | ||
100 | any later version. | ||
101 | </p> | ||
102 | <p> | ||
103 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
104 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
105 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
106 | more details. | ||
107 | </p> | ||
108 | <p> | ||
109 | You should have received a copy of the GNU General Public License along | ||
110 | with this program. If not, see <<a | ||
111 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
112 | </p> | ||
113 | <hr size="1"></hr><p> | ||
114 | This file is a part of an Information Retrieval oriented Ruby library | ||
115 | </p> | ||
116 | <p> | ||
117 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
118 | </p> | ||
119 | <p> | ||
120 | This program is free software: you can redistribute it and/or modify it | ||
121 | under the terms of the GNU General Public License as published by the Free | ||
122 | Software Foundation, either version 3 of the License, or (at your option) | ||
123 | any later version. | ||
124 | </p> | ||
125 | <p> | ||
126 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
127 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
128 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
129 | more details. | ||
130 | </p> | ||
131 | <p> | ||
132 | You should have received a copy of the GNU General Public License along | ||
133 | with this program. If not, see <<a | ||
134 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
135 | </p> | ||
136 | <hr size="1"></hr><p> | ||
137 | This file is a part of an Information Retrieval oriented Ruby library | ||
138 | </p> | ||
139 | <p> | ||
140 | Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | ||
141 | </p> | ||
142 | <p> | ||
143 | This program is free software: you can redistribute it and/or modify it | ||
144 | under the terms of the GNU General Public License as published by the Free | ||
145 | Software Foundation, either version 3 of the License, or (at your option) | ||
146 | any later version. | ||
147 | </p> | ||
148 | <p> | ||
149 | This program is distributed in the hope that it will be useful, but WITHOUT | ||
150 | ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or | ||
151 | FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for | ||
152 | more details. | ||
153 | </p> | ||
154 | <p> | ||
155 | You should have received a copy of the GNU General Public License along | ||
156 | with this program. If not, see <<a | ||
157 | href="http://www.gnu.org/licenses/">www.gnu.org/licenses/</a>>. | ||
158 | </p> | ||
159 | <hr size="1"></hr><p> | ||
160 | General module for many purposes related to Information Retrieval. | ||
161 | </p> | ||
162 | |||
163 | </div> | ||
164 | 65 | ||
165 | </div> | 66 | </div> |
166 | 67 | ||
167 | 68 | ||
168 | </div> | 69 | </div> |
169 | 70 | ||
170 | <!-- if includes --> | 71 | <!-- if includes --> |
171 | 72 | ||
172 | <div id="section"> | 73 | <div id="section"> |
173 | 74 | ||
174 | 75 | ||
175 | 76 | ||
176 | 77 | ||
177 | <!-- if method_list --> | 78 | <!-- if method_list --> |
178 | 79 | ||
179 | 80 | ||
180 | 81 | ||
181 | 82 | ||
182 | </div> | 83 | </div> |
183 | 84 | ||
184 | <div id="validator-badges"> | 85 | <div id="validator-badges"> |
185 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> | 86 | <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p> |
186 | </div> | 87 | </div> |
187 | 88 | ||
188 | </body> | 89 | </body> |
189 | </html> | 90 | </html> |
190 | 91 |
doc/fr_class_index.html
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/Corpus.html">Corpus</a><br /> |
21 | 21 | ||
22 | <a href="classes/RIR/Corpus.html">RIR::Corpus</a><br /> | 22 | <a href="classes/Indri.html">Indri</a><br /> |
23 | 23 | ||
24 | <a href="classes/RIR/Document.html">RIR::Document</a><br /> | 24 | <a href="classes/Indri/IndriQuery.html">Indri::IndriQuery</a><br /> |
25 | 25 | ||
26 | <a href="classes/RIR/Indri.html">RIR::Indri</a><br /> | 26 | <a href="classes/Indri/Parameters.html">Indri::Parameters</a><br /> |
27 | 27 | ||
28 | <a href="classes/RIR/Indri/IndriQuery.html">RIR::Indri::IndriQuery</a><br /> | 28 | <a href="classes/Query.html">Query</a><br /> |
29 | 29 | ||
30 | <a href="classes/RIR/Indri/Parameters.html">RIR::Indri::Parameters</a><br /> | 30 | <a href="classes/RIR.html">RIR</a><br /> |
31 | 31 | ||
32 | <a href="classes/RIR/Query.html">RIR::Query</a><br /> | 32 | <a href="classes/RIR/Document.html">RIR::Document</a><br /> |
33 | 33 | ||
34 | <a href="classes/RIR/TreeTagger.html">RIR::TreeTagger</a><br /> | 34 | <a href="classes/RIR/WebDocument.html">RIR::WebDocument</a><br /> |
35 | 35 | ||
36 | <a href="classes/RIR/TreeTagger/Chunk.html">RIR::TreeTagger::Chunk</a><br /> | 36 | <a href="classes/RIR/WikipediaPage.html">RIR::WikipediaPage</a><br /> |
37 | 37 | ||
38 | <a href="classes/RIR/TreeTagger/TaggerChunker.html">RIR::TreeTagger::TaggerChunker</a><br /> | 38 | <a href="classes/Regexp.html">Regexp</a><br /> |
39 | 39 | ||
40 | <a href="classes/RIR/TreeTagger/TaggerChunkerEnglish.html">RIR::TreeTagger::TaggerChunkerEnglish</a><br /> | 40 | <a href="classes/String.html">String</a><br /> |
41 | 41 | ||
42 | <a href="classes/RIR/TreeTagger/TaggerChunkerFrench.html">RIR::TreeTagger::TaggerChunkerFrench</a><br /> | 42 | <a href="classes/TreeTagger.html">TreeTagger</a><br /> |
43 | 43 | ||
44 | <a href="classes/RIR/TreeTagger/TaggerChunkerGerman.html">RIR::TreeTagger::TaggerChunkerGerman</a><br /> | 44 | <a href="classes/TreeTagger/Chunk.html">TreeTagger::Chunk</a><br /> |
45 | 45 | ||
46 | <a href="classes/RIR/WebDocument.html">RIR::WebDocument</a><br /> | 46 | <a href="classes/TreeTagger/TaggerChunker.html">TreeTagger::TaggerChunker</a><br /> |
47 | 47 | ||
48 | <a href="classes/RIR/WikipediaPage.html">RIR::WikipediaPage</a><br /> | 48 | <a href="classes/TreeTagger/TaggerChunkerEnglish.html">TreeTagger::TaggerChunkerEnglish</a><br /> |
49 | 49 | ||
50 | <a href="classes/Regexp.html">Regexp</a><br /> | 50 | <a href="classes/TreeTagger/TaggerChunkerFrench.html">TreeTagger::TaggerChunkerFrench</a><br /> |
51 | 51 | ||
52 | <a href="classes/String.html">String</a><br /> | 52 | <a href="classes/TreeTagger/TaggerChunkerGerman.html">TreeTagger::TaggerChunkerGerman</a><br /> |
53 | 53 | ||
54 | </div> | 54 | </div> |
55 | </div> | 55 | </div> |
56 | </body> | 56 | </body> |
57 | </html> | 57 | </html> |
58 | 58 |
doc/fr_file_index.html
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_rb.html">lib/rir.rb</a><br /> | ||
21 | |||
22 | <a href="files/lib/rir/corpus_rb.html">lib/rir/corpus.rb</a><br /> | 20 | <a href="files/lib/rir/corpus_rb.html">lib/rir/corpus.rb</a><br /> |
23 | 21 | ||
24 | <a href="files/lib/rir/document_rb.html">lib/rir/document.rb</a><br /> | 22 | <a href="files/lib/rir/document_rb.html">lib/rir/document.rb</a><br /> |
25 | 23 | ||
26 | <a href="files/lib/rir/query_rb.html">lib/rir/query.rb</a><br /> | 24 | <a href="files/lib/rir/query_rb.html">lib/rir/query.rb</a><br /> |
27 | 25 | ||
28 | <a href="files/lib/rir/regexp_rb.html">lib/rir/regexp.rb</a><br /> | 26 | <a href="files/lib/rir/regexp_rb.html">lib/rir/regexp.rb</a><br /> |
29 | 27 | ||
30 | <a href="files/lib/rir/string_rb.html">lib/rir/string.rb</a><br /> | 28 | <a href="files/lib/rir/string_rb.html">lib/rir/string.rb</a><br /> |
31 | 29 | ||
32 | <a href="files/lib/rir/ttagger_rb.html">lib/rir/ttagger.rb</a><br /> | 30 | <a href="files/lib/rir/ttagger_rb.html">lib/rir/ttagger.rb</a><br /> |
33 | 31 | ||
34 | </div> | 32 | </div> |
35 | </div> | 33 | </div> |
36 | </body> | 34 | </body> |
37 | </html> | 35 | </html> |
38 | 36 |
doc/fr_method_index.html
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#M000024">count_words (RIR::Document)</a><br /> | 20 | <a href="classes/RIR/Document.html#M000024">count_words (RIR::Document)</a><br /> |
21 | 21 | ||
22 | <a href="classes/RIR/Document.html#M000025">entropy (RIR::Document)</a><br /> | 22 | <a href="classes/RIR/Document.html#M000025">entropy (RIR::Document)</a><br /> |
23 | 23 | ||
24 | <a href="classes/String.html#M000012">extract_xmltags_values (String)</a><br /> | 24 | <a href="classes/String.html#M000014">extract_xmltags_values (String)</a><br /> |
25 | 25 | ||
26 | <a href="classes/RIR/Corpus.html#M000021">files (RIR::Corpus)</a><br /> | 26 | <a href="classes/Corpus.html#M000002">files (Corpus)</a><br /> |
27 | 27 | ||
28 | <a href="classes/RIR/Document.html#M000022">format_words (RIR::Document)</a><br /> | 28 | <a href="classes/RIR/Document.html#M000022">format_words (RIR::Document)</a><br /> |
29 | 29 | ||
30 | <a href="classes/RIR/WebDocument.html#M000028">get_content (RIR::WebDocument)</a><br /> | 30 | <a href="classes/RIR/WebDocument.html#M000028">get_content (RIR::WebDocument)</a><br /> |
31 | 31 | ||
32 | <a href="classes/RIR/WikipediaPage.html#M000031">get_url (RIR::WikipediaPage)</a><br /> | 32 | <a href="classes/RIR/WikipediaPage.html#M000031">get_url (RIR::WikipediaPage)</a><br /> |
33 | 33 | ||
34 | <a href="classes/String.html#M000002">is_stopword? (String)</a><br /> | 34 | <a href="classes/String.html#M000004">is_stopword? (String)</a><br /> |
35 | 35 | ||
36 | <a href="classes/Regexp.html#M000001">negated (Regexp)</a><br /> | 36 | <a href="classes/Regexp.html#M000003">negated (Regexp)</a><br /> |
37 | 37 | ||
38 | <a href="classes/RIR/Document.html#M000027">new (RIR::Document)</a><br /> | 38 | <a href="classes/RIR/Document.html#M000027">new (RIR::Document)</a><br /> |
39 | 39 | ||
40 | <a href="classes/RIR/WebDocument.html#M000029">new (RIR::WebDocument)</a><br /> | 40 | <a href="classes/RIR/WebDocument.html#M000029">new (RIR::WebDocument)</a><br /> |
41 | 41 | ||
42 | <a href="classes/RIR/Indri/IndriQuery.html#M000018">new (RIR::Indri::IndriQuery)</a><br /> | 42 | <a href="classes/Indri/IndriQuery.html#M000020">new (Indri::IndriQuery)</a><br /> |
43 | 43 | ||
44 | <a href="classes/RIR/Corpus.html#M000020">new (RIR::Corpus)</a><br /> | 44 | <a href="classes/Indri/Parameters.html#M000018">new (Indri::Parameters)</a><br /> |
45 | 45 | ||
46 | <a href="classes/RIR/TreeTagger/TaggerChunker.html#M000014">new (RIR::TreeTagger::TaggerChunker)</a><br /> | 46 | <a href="classes/Corpus.html#M000001">new (Corpus)</a><br /> |
47 | 47 | ||
48 | <a href="classes/RIR/Indri/Parameters.html#M000016">new (RIR::Indri::Parameters)</a><br /> | 48 | <a href="classes/TreeTagger/TaggerChunker.html#M000016">new (TreeTagger::TaggerChunker)</a><br /> |
49 | 49 | ||
50 | <a href="classes/RIR/TreeTagger/Chunk.html#M000015">new (RIR::TreeTagger::Chunk)</a><br /> | 50 | <a href="classes/TreeTagger/Chunk.html#M000017">new (TreeTagger::Chunk)</a><br /> |
51 | 51 | ||
52 | <a href="classes/RIR/Document.html#M000023">ngrams (RIR::Document)</a><br /> | 52 | <a href="classes/RIR/Document.html#M000023">ngrams (RIR::Document)</a><br /> |
53 | 53 | ||
54 | <a href="classes/RIR/TreeTagger/TaggerChunker.html#M000013">parse (RIR::TreeTagger::TaggerChunker)</a><br /> | 54 | <a href="classes/TreeTagger/TaggerChunker.html#M000015">parse (TreeTagger::TaggerChunker)</a><br /> |
55 | 55 | ||
56 | <a href="classes/String.html#M000003">remove_special_characters (String)</a><br /> | 56 | <a href="classes/String.html#M000005">remove_special_characters (String)</a><br /> |
57 | 57 | ||
58 | <a href="classes/RIR/WikipediaPage.html#M000032">search_homepage (RIR::WikipediaPage)</a><br /> | 58 | <a href="classes/RIR/WikipediaPage.html#M000032">search_homepage (RIR::WikipediaPage)</a><br /> |
59 | 59 | ||
60 | <a href="classes/RIR/WikipediaPage.html#M000030">search_wikipedia_titles (RIR::WikipediaPage)</a><br /> | 60 | <a href="classes/RIR/WikipediaPage.html#M000030">search_wikipedia_titles (RIR::WikipediaPage)</a><br /> |
61 | 61 | ||
62 | <a href="classes/String.html#M000007">strip_javascripts (String)</a><br /> | 62 | <a href="classes/String.html#M000009">strip_javascripts (String)</a><br /> |
63 | 63 | ||
64 | <a href="classes/String.html#M000006">strip_javascripts! (String)</a><br /> | 64 | <a href="classes/String.html#M000008">strip_javascripts! (String)</a><br /> |
65 | 65 | ||
66 | <a href="classes/String.html#M000011">strip_punctuation (String)</a><br /> | 66 | <a href="classes/String.html#M000013">strip_punctuation (String)</a><br /> |
67 | 67 | ||
68 | <a href="classes/String.html#M000010">strip_punctuation! (String)</a><br /> | 68 | <a href="classes/String.html#M000012">strip_punctuation! (String)</a><br /> |
69 | 69 | ||
70 | <a href="classes/String.html#M000009">strip_stylesheets (String)</a><br /> | 70 | <a href="classes/String.html#M000011">strip_stylesheets (String)</a><br /> |
71 | 71 | ||
72 | <a href="classes/String.html#M000008">strip_stylesheets! (String)</a><br /> | 72 | <a href="classes/String.html#M000010">strip_stylesheets! (String)</a><br /> |
73 | 73 | ||
74 | <a href="classes/String.html#M000005">strip_xml_tags (String)</a><br /> | 74 | <a href="classes/String.html#M000007">strip_xml_tags (String)</a><br /> |
75 | 75 | ||
76 | <a href="classes/String.html#M000004">strip_xml_tags! (String)</a><br /> | 76 | <a href="classes/String.html#M000006">strip_xml_tags! (String)</a><br /> |
77 | 77 | ||
78 | <a href="classes/RIR/Document.html#M000026">tf (RIR::Document)</a><br /> | 78 | <a href="classes/RIR/Document.html#M000026">tf (RIR::Document)</a><br /> |
79 | 79 | ||
80 | <a href="classes/RIR/Indri/IndriQuery.html#M000019">to_s (RIR::Indri::IndriQuery)</a><br /> | 80 | <a href="classes/Indri/Parameters.html#M000019">to_s (Indri::Parameters)</a><br /> |
81 | 81 | ||
82 | <a href="classes/RIR/Indri/Parameters.html#M000017">to_s (RIR::Indri::Parameters)</a><br /> | 82 | <a href="classes/Indri/IndriQuery.html#M000021">to_s (Indri::IndriQuery)</a><br /> |
83 | 83 | ||
84 | </div> | 84 | </div> |
85 | </div> | 85 | </div> |
86 | </body> | 86 | </body> |
87 | </html> | 87 | </html> |
88 | 88 |
doc/index.html
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_rb.html" name="docwin" /> | 19 | <frame src="files/lib/rir/ttagger_rb.html" name="docwin" /> |
20 | </frameset> | 20 | </frameset> |
21 | </html> | 21 | </html> |
22 | 22 |
lib/rir/corpus.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
19 | 21 | ||
20 | module RIR | 22 | class Corpus |
23 | attr_accessor :path | ||
21 | 24 | ||
22 | class Corpus | 25 | def initialize(path) |
23 | attr_accessor :path | 26 | @path = path.chomp "/" |
24 | |||
25 | def initialize(path) | ||
26 | @path = path.chomp "/" | ||
27 | end | ||
28 | |||
29 | # Recursively outputs all files in +self.path+. | ||
30 | # WARNING ! This function may take a lot of time if many | ||
31 | # files are in subdirectories. | ||
32 | # | ||
33 | # c = Corpus.new "my/path" | ||
34 | # c.files # => ["README.txt", "lib/code.rb"] | ||
35 | def files | ||
36 | Dir["#{@path}/**/*.*"] | ||
37 | end | ||
38 | end | 27 | end |
lib/rir/document.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
21 | |||
19 | 22 | ||
20 | # General module for many purposes related to Information Retrieval. | 23 | # General module for many purposes related to Information Retrieval. |
21 | module RIR | 24 | module RIR |
22 | 25 | ||
23 | # A Document is a bag of words and is constructed from a string. | 26 | # A Document is a bag of words and is constructed from a string. |
24 | class Document | 27 | class Document |
25 | attr_reader :words, :doc_content | 28 | attr_reader :words, :doc_content |
26 | 29 | ||
27 | # Any non-word characters are removed from the words (see http://perldoc.perl.org/perlre.html | 30 | # Any non-word characters are removed from the words (see http://perldoc.perl.org/perlre.html |
28 | # and the \\W special escape). | 31 | # and the \\W special escape). |
29 | # | 32 | # |
30 | # Protected function, only meant to by called at the initialization. | 33 | # Protected function, only meant to by called at the initialization. |
31 | def format_words | 34 | def format_words |
32 | wo = [] | 35 | wo = [] |
33 | 36 | ||
34 | @doc_content.split.each do |w| | 37 | @doc_content.split.each do |w| |
35 | w.split(/\W/).each do |sw| | 38 | w.split(/\W/).each do |sw| |
36 | wo.push(sw.downcase) if sw =~ /[a-zA-Z]/ | 39 | wo.push(sw.downcase) if sw =~ /[a-zA-Z]/ |
37 | end | 40 | end |
38 | end | 41 | end |
39 | 42 | ||
40 | wo | 43 | wo |
41 | end | 44 | end |
42 | 45 | ||
43 | # Returns an Array containing the +n+-grams (words) from the current Document. | 46 | # Returns an Array containing the +n+-grams (words) from the current Document. |
44 | # | 47 | # |
45 | # ngrams(2) #=> ["the free", "free encyclopedia", "encyclopedia var", "var skin", ...] | 48 | # ngrams(2) #=> ["the free", "free encyclopedia", "encyclopedia var", "var skin", ...] |
46 | def ngrams(n) | 49 | def ngrams(n) |
47 | window = [] | 50 | window = [] |
48 | ngrams_array = [] | 51 | ngrams_array = [] |
49 | 52 | ||
50 | @words.each do |w| | 53 | @words.each do |w| |
51 | window.push(w) | 54 | window.push(w) |
52 | if window.size == n | 55 | if window.size == n |
53 | ngrams_array.push window.join(" ") | 56 | ngrams_array.push window.join(" ") |
54 | window.delete_at(0) | 57 | window.delete_at(0) |
55 | end | 58 | end |
56 | end | 59 | end |
57 | 60 | ||
58 | ngrams_array.uniq | 61 | ngrams_array.uniq |
59 | end | 62 | end |
60 | 63 | ||
61 | # Returns a Hash containing the words and their associated counts in the current Document. | 64 | # Returns a Hash containing the words and their associated counts in the current Document. |
62 | # | 65 | # |
63 | # count_words #=> { "guitar"=>1, "bass"=>3, "album"=>20, ... } | 66 | # count_words #=> { "guitar"=>1, "bass"=>3, "album"=>20, ... } |
64 | def count_words | 67 | def count_words |
65 | counts = Hash.new { |h,k| h[k] = 0 } | 68 | counts = Hash.new { |h,k| h[k] = 0 } |
66 | @words.each { |w| counts[w] += 1 } | 69 | @words.each { |w| counts[w] += 1 } |
67 | 70 | ||
68 | counts | 71 | counts |
69 | end | 72 | end |
70 | 73 | ||
71 | # Computes the entropy of a given string +s+ inside the document. | 74 | # Computes the entropy of a given string +s+ inside the document. |
72 | # | 75 | # |
73 | # If the string parameter is composed of many words (i.e. tokens separated | 76 | # If the string parameter is composed of many words (i.e. tokens separated |
74 | # by whitespace(s)), it is considered as an ngram. | 77 | # by whitespace(s)), it is considered as an ngram. |
75 | # | 78 | # |
76 | # entropy("guitar") #=> 0.00432114812727959 | 79 | # entropy("guitar") #=> 0.00432114812727959 |
77 | # entropy("dillinger escape plan") #=> 0.265862076325102 | 80 | # entropy("dillinger escape plan") #=> 0.265862076325102 |
78 | def entropy(s) | 81 | def entropy(s) |
79 | en = 0.0 | 82 | en = 0.0 |
80 | counts = self.count_words | 83 | counts = self.count_words |
81 | 84 | ||
82 | s.split.each do |w| | 85 | s.split.each do |w| |
83 | p_wi = counts[w].to_f/@words.count.to_f | 86 | p_wi = counts[w].to_f/@words.count.to_f |
84 | en += p_wi*Math.log2(p_wi) | 87 | en += p_wi*Math.log2(p_wi) |
85 | end | 88 | end |
86 | 89 | ||
87 | en *= -1 | 90 | en *= -1 |
88 | en | 91 | en |
89 | end | 92 | end |
90 | 93 | ||
91 | # Computes the term frequency of a given *word* +s+. | 94 | # Computes the term frequency of a given *word* +s+. |
92 | # | 95 | # |
93 | # tf("guitar") #=> 0.000380372765310004 | 96 | # tf("guitar") #=> 0.000380372765310004 |
94 | def tf(s) | 97 | def tf(s) |
95 | self.count_words[s].to_f/@words.size.to_f | 98 | self.count_words[s].to_f/@words.size.to_f |
96 | end | 99 | end |
97 | 100 | ||
98 | 101 | ||
99 | def initialize(content) | 102 | def initialize(content) |
100 | @doc_content = content | 103 | @doc_content = content |
101 | @words = format_words | 104 | @words = format_words |
102 | end | 105 | end |
103 | 106 | ||
104 | protected :format_words | 107 | protected :format_words |
105 | end | 108 | end |
106 | 109 | ||
107 | # A WebDocument is a Document with a +url+. | 110 | # A WebDocument is a Document with a +url+. |
108 | class WebDocument < Document | 111 | class WebDocument < Document |
109 | attr_reader :url | 112 | attr_reader :url |
110 | 113 | ||
111 | # Returns the HTML text from the page of a given +url+. | 114 | # Returns the HTML text from the page of a given +url+. |
112 | def self.get_content(url) | 115 | def self.get_content(url) |
113 | require 'net/http' | 116 | require 'net/http' |
114 | Net::HTTP.get(URI.parse(url)) | 117 | Net::HTTP.get(URI.parse(url)) |
115 | end | 118 | end |
116 | 119 | ||
117 | # WebDocument constructor, the content of the Document is the HTML page | 120 | # WebDocument constructor, the content of the Document is the HTML page |
118 | # without the tags. | 121 | # without the tags. |
119 | def initialize(url) | 122 | def initialize(url) |
120 | @url = url | 123 | @url = url |
121 | super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags | 124 | super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags |
122 | end | 125 | end |
123 | end | 126 | end |
124 | 127 | ||
125 | # A WikipediaPage is a WebDocument. | 128 | # A WikipediaPage is a WebDocument. |
126 | class WikipediaPage < WebDocument | 129 | class WikipediaPage < WebDocument |
127 | require 'rexml/document' | 130 | require 'rexml/document' |
128 | require 'net/http' | 131 | require 'net/http' |
129 | require 'kconv' | 132 | require 'kconv' |
130 | 133 | ||
131 | 134 | ||
132 | def self.search_wikipedia_titles(name) | 135 | def self.search_wikipedia_titles(name) |
133 | raise ArgumentError, "Bad encoding", name unless name.isutf8 | 136 | raise ArgumentError, "Bad encoding", name unless name.isutf8 |
134 | 137 | ||
135 | res = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml" ).toutf8).elements['api/query/search'] | 138 | res = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml" ).toutf8).elements['api/query/search'] |
136 | 139 | ||
137 | res.collect { |e| e.attributes['title'] } unless res.nil? | 140 | res.collect { |e| e.attributes['title'] } unless res.nil? |
138 | end | 141 | end |
139 | 142 | ||
140 | def self.get_url(name) | 143 | def self.get_url(name) |
141 | raise ArgumentError, "Bad encoding", name unless name.isutf8 | 144 | raise ArgumentError, "Bad encoding", name unless name.isutf8 |
142 | 145 | ||
143 | atts = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml" ).toutf8).elements['api/query/pages/page'].attributes | 146 | atts = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml" ).toutf8).elements['api/query/pages/page'].attributes |
144 | 147 | ||
145 | atts['fullurl'] if atts['missing'].nil? | 148 | atts['fullurl'] if atts['missing'].nil? |
146 | end | 149 | end |
147 | 150 | ||
148 | def self.search_homepage(name) | 151 | def self.search_homepage(name) |
149 | title = WikipediaPage.search_wikipedia_titles name | 152 | title = WikipediaPage.search_wikipedia_titles name |
150 | 153 | ||
151 | WikipediaPage.new(WikipediaPage.get_url title[0]) unless title.nil? || title.empty? | 154 | WikipediaPage.new(WikipediaPage.get_url title[0]) unless title.nil? || title.empty? |
152 | end | 155 | end |
153 | 156 | ||
154 | # def initialize(name) | 157 | # def initialize(name) |
155 | # title = WikipediaPage.search_wikipedia_titles name | 158 | # title = WikipediaPage.search_wikipedia_titles name |
156 | # raise ArgumentError, "No page found" if title.empty? | 159 | # raise ArgumentError, "No page found" if title.empty? |
157 | # super WikipediaPage.get_url title[0] | 160 | # super WikipediaPage.get_url title[0] |
158 | # end | 161 | # end |
159 | end | 162 | end |
160 | end | 163 | end |
161 | 164 |
lib/rir/query.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
19 | 21 | ||
20 | module RIR | 22 | class Query |
23 | end | ||
21 | 24 | ||
22 | class Query | 25 | module Indri |
23 | end | ||
24 | 26 | ||
25 | module Indri | 27 | class Parameters |
28 | attr_accessor :index_path, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline | ||
26 | 29 | ||
27 | class Parameters | 30 | def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) |
28 | attr_accessor :index_path, :memory, :count, :offset, :run_id, :print_query, :print_docs, :rule, :baseline | 31 | @index_path = corpus |
32 | @memory = mem | ||
33 | @count = count | ||
34 | @offset = offset | ||
35 | @run_id = run_id | ||
36 | @print_query = print_query ? "true" : "false" | ||
37 | @print_docs = print_docs ? "true" : "false" | ||
38 | end | ||
29 | 39 | ||
30 | def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) | 40 | def to_s |
31 | @index_path = corpus | 41 | h = "<parameters>\n" |
32 | @memory = mem | 42 | h += "<memory>#{@memory}</memory>\n" |
33 | @count = count | 43 | h += "<index>#{@index_path}</index>\n" |
34 | @offset = offset | 44 | h += "<count>#{@count}</count>\n" |
35 | @run_id = run_id | 45 | unless @baseline.nil? |
36 | @print_query = print_query ? "true" : "false" | 46 | h += "<baseline>#{@baseline}</baseline>\n" |
37 | @print_docs = print_docs ? "true" : "false" | 47 | else |
48 | h += "<rule>#{@rule}</rule>\n" | ||
38 | end | 49 | end |
50 | h += "<queryOffset>#{@offset}</queryOffset>\n" | ||
51 | h += "<runID>#{@run_id}</runID>\n" | ||
52 | h += "<printQuery>#{@print_query}</printQuery>\n" | ||
53 | h += "<printDocuments>#{@print_docs}</printDocuments>\n" | ||
39 | 54 | ||
40 | def to_s | 55 | h |
41 | h = "<parameters>\n" | ||
42 | h += "<memory>#{@memory}</memory>\n" | ||
43 | h += "<index>#{@index_path}</index>\n" | ||
44 | h += "<count>#{@count}</count>\n" | ||
45 | unless @baseline.nil? | ||
46 | h += "<baseline>#{@baseline}</baseline>\n" | ||
47 | else | ||
48 | h += "<rule>#{@rule}</rule>\n" | ||
49 | end | ||
50 | h += "<queryOffset>#{@offset}</queryOffset>\n" | ||
51 | h += "<runID>#{@run_id}</runID>\n" | ||
52 | h += "<printQuery>#{@print_query}</printQuery>\n" | ||
53 | h += "<printDocuments>#{@print_docs}</printDocuments>\n" | ||
54 | |||
55 | h | ||
56 | end | ||
57 | end | 56 | end |
58 | 57 | end | |
59 | class IndriQuery < Query | 58 | |
60 | attr_accessor :id, :query, :params, :rule | 59 | class IndriQuery < Query |
60 | attr_accessor :id, :query, :params, :rule | ||
61 | 61 | ||
62 | def initialize(id,query,params) | 62 | def initialize(id,query,params) |
63 | @params = params | 63 | @params = params |
64 | # Here we set the default retrieval model as Language Modeling | 64 | # Here we set the default retrieval model as Language Modeling |
65 | # with a Dirichlet smoothing at 2500. | 65 | # with a Dirichlet smoothing at 2500. |
66 | # TODO: maybe a Rule class... | 66 | # TODO: maybe a Rule class... |
67 | @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? | 67 | @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? |
68 | 68 | ||
69 | @id = id | 69 | @id = id |
70 | @query = query | 70 | @query = query |
lib/rir/regexp.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
19 | 21 | ||
20 | class Regexp | 22 | class Regexp |
21 | 23 | ||
22 | def negated | 24 | def negated |
23 | /^((?!#{self}).)*$/ | 25 | /^((?!#{self}).)*$/ |
24 | end | 26 | end |
25 | 27 | ||
26 | end | 28 | end |
27 | 29 |
lib/rir/string.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
19 | 21 | ||
20 | module RIR | 22 | module RIR |
21 | 23 | ||
22 | # These are the default stopwords provided by Lemur. | 24 | # These are the default stopwords provided by Lemur. |
23 | Stoplist = [ | 25 | Stoplist = [ |
24 | "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", | 26 | "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", |
25 | "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", | 27 | "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", |
26 | "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", | 28 | "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", |
27 | "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", | 29 | "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", |
28 | "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", | 30 | "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", |
29 | "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", | 31 | "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", |
30 | "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", | 32 | "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", |
31 | "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", | 33 | "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", |
32 | "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", | 34 | "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", |
33 | "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", | 35 | "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", |
34 | "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", | 36 | "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", |
35 | "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", | 37 | "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", |
36 | "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", | 38 | "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", |
37 | "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", | 39 | "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", |
38 | "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", | 40 | "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", |
39 | "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", | 41 | "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", |
40 | "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", | 42 | "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", |
41 | "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", | 43 | "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", |
42 | "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", | 44 | "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", |
43 | "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", | 45 | "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", |
44 | "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", | 46 | "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", |
45 | "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", | 47 | "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", |
46 | "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", | 48 | "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", |
47 | "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", | 49 | "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", |
48 | "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", | 50 | "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", |
49 | "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", | 51 | "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", |
50 | "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", | 52 | "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", |
51 | "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", | 53 | "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", |
52 | "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", | 54 | "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", |
53 | "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", | 55 | "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", |
54 | "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", | 56 | "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", |
55 | "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", | 57 | "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", |
56 | "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", | 58 | "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", |
57 | "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", | 59 | "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", |
58 | "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", | 60 | "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", |
59 | "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", | 61 | "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", |
60 | "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", | 62 | "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", |
61 | "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", | 63 | "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", |
62 | "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", | 64 | "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", |
63 | "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", | 65 | "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", |
64 | "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", | 66 | "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", |
65 | "yours", "yourself", "yourselves" | 67 | "yours", "yourself", "yourselves" |
66 | ] | 68 | ] |
67 | 69 | ||
68 | 70 | ||
69 | end | 71 | end |
70 | 72 | ||
71 | # Extention of the standard class String with useful function. | 73 | # Extention of the standard class String with useful function. |
72 | class String | 74 | class String |
73 | include RIR | 75 | include RIR |
74 | 76 | ||
75 | # Returns +true+ if +self+ belongs to Rir::Stoplist, +false+ otherwise. | 77 | # Returns +true+ if +self+ belongs to Rir::Stoplist, +false+ otherwise. |
76 | def is_stopword? | 78 | def is_stopword? |
77 | Stoplist.include?(self.downcase) | 79 | Stoplist.include?(self.downcase) |
78 | end | 80 | end |
79 | 81 | ||
80 | # Do not use. | 82 | # Do not use. |
81 | # TODO: rewamp. find why this function is here. | 83 | # TODO: rewamp. find why this function is here. |
82 | def remove_special_characters | 84 | def remove_special_characters |
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 | self.split.collect { |w| w.gsub(/\W/,' ').split.collect { |w| w.gsub(/\W/,' ').strip.sub(/\A.\z/, '')}.join(' ').strip.sub(/\A.\z/, '')}.join(' ') |
84 | end | 86 | end |
85 | 87 | ||
86 | # Removes all XML-like tags from +self+. | 88 | # Removes all XML-like tags from +self+. |
87 | # | 89 | # |
88 | # s = "<html><body>test</body></html>" | 90 | # s = "<html><body>test</body></html>" |
89 | # s.strip_xml_tags! | 91 | # s.strip_xml_tags! |
90 | # s #=> "test" | 92 | # s #=> "test" |
91 | def strip_xml_tags! | 93 | def strip_xml_tags! |
92 | replace strip_with_pattern /<\/?[^>]*>/ | 94 | replace strip_with_pattern /<\/?[^>]*>/ |
93 | end | 95 | end |
94 | 96 | ||
95 | # Removes all XML-like tags from +self+. | 97 | # Removes all XML-like tags from +self+. |
96 | # | 98 | # |
97 | # s = "<html><body>test</body></html>" | 99 | # s = "<html><body>test</body></html>" |
98 | # s.strip_xml_tags #=> "test" | 100 | # s.strip_xml_tags #=> "test" |
99 | # s #=> "<html><body>test</body></html>" | 101 | # s #=> "<html><body>test</body></html>" |
100 | def strip_xml_tags | 102 | def strip_xml_tags |
101 | dup.strip_xml_tags! | 103 | dup.strip_xml_tags! |
102 | end | 104 | end |
103 | 105 | ||
104 | # Removes all Javascript sources from +self+. | 106 | # Removes all Javascript sources from +self+. |
105 | # | 107 | # |
106 | # s = "<script type='text/javascript'> | 108 | # s = "<script type='text/javascript'> |
107 | # var skin='vector', | 109 | # var skin='vector', |
108 | # stylepath='http://bits.wikimedia.org/skins-1.5' | 110 | # stylepath='http://bits.wikimedia.org/skins-1.5' |
109 | # </script> | 111 | # </script> |
110 | # | 112 | # |
111 | # test" | 113 | # test" |
112 | # s.strip_javascripts! | 114 | # s.strip_javascripts! |
113 | # s #=> "test" | 115 | # s #=> "test" |
114 | def strip_javascripts! | 116 | def strip_javascripts! |
115 | replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m | 117 | replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m |
116 | end | 118 | end |
117 | 119 | ||
118 | # Removes all Javascript sources from +self+. | 120 | # Removes all Javascript sources from +self+. |
119 | # | 121 | # |
120 | # s = "<script type='text/javascript'> | 122 | # s = "<script type='text/javascript'> |
121 | # var skin='vector', | 123 | # var skin='vector', |
122 | # stylepath='http://bits.wikimedia.org/skins-1.5' | 124 | # stylepath='http://bits.wikimedia.org/skins-1.5' |
123 | # </script> | 125 | # </script> |
124 | # | 126 | # |
125 | # test" | 127 | # test" |
126 | # s.strip_javascripts #=> "test" | 128 | # s.strip_javascripts #=> "test" |
127 | def strip_javascripts | 129 | def strip_javascripts |
128 | dup.strip_javascripts! | 130 | dup.strip_javascripts! |
129 | end | 131 | end |
130 | 132 | ||
131 | def strip_stylesheets! | 133 | def strip_stylesheets! |
132 | # TODO: rewamp. dunno what is it. | 134 | # TODO: rewamp. dunno what is it. |
133 | replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m | 135 | replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m |
134 | end | 136 | end |
135 | 137 | ||
136 | def strip_stylesheets | 138 | def strip_stylesheets |
137 | dup.strip_stylesheets! | 139 | dup.strip_stylesheets! |
138 | end | 140 | end |
139 | 141 | ||
140 | # Removes punctuation from +self+. | 142 | # Removes punctuation from +self+. |
141 | # | 143 | # |
142 | # s = "hello, world. how are you?!" | 144 | # s = "hello, world. how are you?!" |
143 | # s.strip_punctuation! | 145 | # s.strip_punctuation! |
144 | # s # => "hello world how are you" | 146 | # s # => "hello world how are you" |
145 | def strip_punctuation! | 147 | def strip_punctuation! |
146 | replace strip_with_pattern /[^a-zA-Z0-9\-\s]/ | 148 | replace strip_with_pattern /[^a-zA-Z0-9\-\s]/ |
147 | end | 149 | end |
148 | 150 | ||
149 | # Removes punctuation from +self+. | 151 | # Removes punctuation from +self+. |
150 | # | 152 | # |
151 | # s = "hello, world. how are you?!" | 153 | # s = "hello, world. how are you?!" |
152 | # s.strip_punctuation # => "hello world how are you" | 154 | # s.strip_punctuation # => "hello world how are you" |
153 | def strip_punctuation | 155 | def strip_punctuation |
154 | dup.strip_punctuation! | 156 | dup.strip_punctuation! |
155 | end | 157 | end |
156 | 158 | ||
157 | # Returns the text values inside all occurences of a XML tag in +self+ | 159 | # Returns the text values inside all occurences of a XML tag in +self+ |
158 | # | 160 | # |
159 | # s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre" | 161 | # s = "four-piece in <a href='#'>Indianapolis</a>, <a href='#'>Indiana</a> at the Murat Theatre" |
160 | # s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"] | 162 | # s.extract_xmltags_values 'a' #=> ["Indianapolis", "Indiana"] |
161 | def extract_xmltags_values(tag_name) | 163 | def extract_xmltags_values(tag_name) |
162 | self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten | 164 | self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten |
163 | end | 165 | end |
164 | 166 | ||
165 | def strip_with_pattern(pattern) | 167 | def strip_with_pattern(pattern) |
166 | require 'cgi' | 168 | require 'cgi' |
167 | require 'kconv' | 169 | require 'kconv' |
168 | CGI::unescapeHTML(self.gsub(pattern,"")).toutf8 | 170 | CGI::unescapeHTML(self.gsub(pattern,"")).toutf8 |
169 | end | 171 | end |
170 | 172 | ||
171 | private :strip_with_pattern | 173 | private :strip_with_pattern |
172 | end | 174 | end |
173 | 175 |
lib/rir/ttagger.rb
1 | #!/usr/bin/env ruby | 1 | #!/usr/bin/env ruby |
2 | 2 | ||
3 | #-- | ||
3 | # This file is a part of an Information Retrieval oriented Ruby library | 4 | # This file is a part of an Information Retrieval oriented Ruby library |
4 | # | 5 | # |
5 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> | 6 | # Copyright (C) 2010-2011 Romain Deveaud <romain.deveaud@gmail.com> |
6 | # | 7 | # |
7 | # This program is free software: you can redistribute it and/or modify | 8 | # 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 | 9 | # 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 | 10 | # the Free Software Foundation, either version 3 of the License, or |
10 | # (at your option) any later version. | 11 | # (at your option) any later version. |
11 | # | 12 | # |
12 | # This program is distributed in the hope that it will be useful, | 13 | # This program is distributed in the hope that it will be useful, |
13 | # but WITHOUT ANY WARRANTY; without even the implied warranty of | 14 | # but WITHOUT ANY WARRANTY; without even the implied warranty of |
14 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 15 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15 | # GNU General Public License for more details. | 16 | # GNU General Public License for more details. |
16 | # | 17 | # |
17 | # You should have received a copy of the GNU General Public License | 18 | # 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/>. | 19 | # along with this program. If not, see <http://www.gnu.org/licenses/>. |
20 | #++ | ||
19 | 21 | ||
20 | module RIR | ||
21 | 22 | ||
22 | # TreeTagger-related stuff module. | 23 | # TreeTagger-related stuff module. |
23 | # | 24 | # |
24 | # See http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html | 25 | # See http://www.ims.uni-stuttgart.de/projekte/corplex/TreeTagger/DecisionTreeTagger.html |
25 | module TreeTagger | 26 | module TreeTagger |
26 | 27 | ||
27 | # This class handles generic parsing of tagger-chunker outputs. | 28 | # This class handles generic parsing of tagger-chunker outputs. |
28 | class TaggerChunker | 29 | class TaggerChunker |
29 | attr_reader :chunks, :file | 30 | attr_reader :chunks, :file |
30 | 31 | ||
31 | 32 | ||
32 | # Parses a tagger-chunker output and returns an Array of Chunk. | 33 | # Parses a tagger-chunker output and returns an Array of Chunk. |
33 | def self.parse chunk_lines | 34 | def self.parse chunk_lines |
34 | open = false | 35 | open = false |
35 | tag = nil | 36 | tag = nil |
36 | 37 | ||
37 | chunks = [] | 38 | chunks = [] |
38 | words = [] | 39 | words = [] |
39 | 40 | ||
40 | chunk_lines.each do |l| | 41 | chunk_lines.each do |l| |
41 | l.chomp! | 42 | l.chomp! |
42 | if l =~ /^<\w+>$/ | 43 | if l =~ /^<\w+>$/ |
43 | open = true | 44 | open = true |
44 | tag = l | 45 | tag = l |
45 | elsif l =~ /^<\/\w+>$/ | 46 | elsif l =~ /^<\/\w+>$/ |
46 | if !words.empty? && open && l == tag.sub(/</, '</') | 47 | if !words.empty? && open && l == tag.sub(/</, '</') |
47 | open = false | 48 | open = false |
48 | chunks.push Chunk.new(words.join(" "), tag) | 49 | chunks.push Chunk.new(words.join(" "), tag) |
49 | words.clear | 50 | words.clear |
50 | else | ||
51 | next | ||
52 | end | ||
53 | else | 51 | else |
54 | words.push(l.split.first) | 52 | next |
55 | end | 53 | end |
54 | else | ||
55 | words.push(l.split.first) | ||
56 | end | 56 | end |
57 | |||
58 | chunks | ||
59 | end | 57 | end |
60 | 58 | ||
61 | # Initializes parsing. +chunk_file+ is the output of +tagger-chunker-+ and must | 59 | chunks |
62 | # be a valid path to the file. | ||
63 | # | ||
64 | # TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...> | ||
65 | def initialize chunk_file | ||
66 | @chunks = TaggerChunker.parse File.open(chunk_file).readlines | ||
67 | end | ||
68 | |||
69 | end | 60 | end |
70 | 61 | ||
71 | class TaggerChunkerEnglish < TaggerChunker | 62 | # Initializes parsing. +chunk_file+ is the output of +tagger-chunker-+ and must |
63 | # be a valid path to the file. | ||
64 | # | ||
65 | # TaggerChunker.new("ttout/2010020") #=> #<RIR::TreeTagger::TaggerChunker:0x92fd088 @chunks=[#<RIR::TreeTagger::Chunk:0x8ec5a10 @words=["robert", "schumann"], @tag="NC">, ...] ...> | ||
66 | def initialize chunk_file | ||
67 | @chunks = TaggerChunker.parse File.open(chunk_file).readlines | ||
72 | end | 68 | end |
73 | 69 | ||
74 | class TaggerChunkerFrench < TaggerChunker | 70 | end |
75 | end | ||
76 | 71 | ||
77 | class TaggerChunkerGerman < TaggerChunker | 72 | class TaggerChunkerEnglish < TaggerChunker |
78 | end | 73 | end |
79 | 74 | ||
80 | # Represents a Chunk extracted when parsing a TaggerChunker file. | 75 | class TaggerChunkerFrench < TaggerChunker |
81 | class Chunk | 76 | end |
82 | attr_reader :words, :tag | ||
83 | 77 | ||
84 | # +str+ are whitespace-separated terms. | 78 | class TaggerChunkerGerman < TaggerChunker |
85 | # +tag+ see : ftp://ftp.ims.uni-stuttgart.de/pub/corpora/chunker-tagset-english.txt | 79 | end |
86 | def initialize str,tag | ||
87 | @words = str.split |