rdoc/classes/Porter2.html

   1 <?xml version="1.0" encoding="iso-8859-1"?>
   2 <!DOCTYPE html
   3      PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
   4      "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
   5
   6 <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
   7 <head>
   8   <title>Module: Porter2</title>
   9   <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1" />
  10   <meta http-equiv="Content-Script-Type" content="text/javascript" />
  11   <link rel="stylesheet" href=".././rdoc-style.css" type="text/css" media="screen" />
  12   <script type="text/javascript">
  13   // <![CDATA[
  14
  15   function popupCode( url ) {
  16     window.open(url, "Code", "resizable=yes,scrollbars=yes,toolbar=no,status=no,height=150,width=400")
  17   }
  18
  19   function toggleCode( id ) {
  20     if ( document.getElementById )
  21       elem = document.getElementById( id );
  22     else if ( document.all )
  23       elem = eval( "document.all." + id );
  24     else
  25       return false;
  26
  27     elemStyle = elem.style;
  28
  29     if ( elemStyle.display != "block" ) {
  30       elemStyle.display = "block"
  31     } else {
  32       elemStyle.display = "none"
  33     }
  34
  35     return true;
  36   }
  37
  38   // Make codeblocks hidden by default
  39   document.writeln( "<style type=\"text/css\">div.method-source-code { display: none }</style>" )
  40
  41   // ]]>
  42   </script>
  43
  44 </head>
  45 <body>
  46
  47
  48
  49     <div id="classHeader">
  50         <table class="header-table">
  51         <tr class="top-aligned-row">
  52           <td><strong>Module</strong></td>
  53           <td class="class-name-in-header">Porter2</td>
  54         </tr>
  55         <tr class="top-aligned-row">
  56             <td><strong>In:</strong></td>
  57             <td>
  58                 <a href="../files/lib/porter2stemmer/constants_rb.html">
  59                 lib/porter2stemmer/constants.rb
  60                 </a>
  61         <br />
  62             </td>
  63         </tr>
  64
  65         </table>
  66     </div>
  67   <!-- banner header -->
  68
  69   <div id="bodyContent">
  70
  71
  72
  73   <div id="contextContent">
  74
  75     <div id="description">
  76       <p>
  77 Constants for the Porter 2 stemmer
  78 </p>
  79
  80     </div>
  81
  82
  83    </div>
  84
  85
  86   </div>
  87
  88
  89     <!-- if includes -->
  90
  91     <div id="section">
  92
  93
  94     <div id="constants-list">
  95       <h3 class="section-bar">Constants</h3>
  96
  97       <div class="name-list">
  98         <table summary="Constants">
  99         <tr class="top-aligned-row context-row">
 100           <td class="context-item-name">C</td>
 101           <td>=</td>
 102           <td class="context-item-value">&quot;[^aeiouy]&quot;</td>
 103           <td width="3em">&nbsp;</td>
 104           <td class="context-item-desc">
 105 A non-vowel
 106
 107 </td>
 108         </tr>
 109         <tr class="top-aligned-row context-row">
 110           <td class="context-item-name">V</td>
 111           <td>=</td>
 112           <td class="context-item-value">&quot;[aeiouy]&quot;</td>
 113           <td width="3em">&nbsp;</td>
 114           <td class="context-item-desc">
 115 A vowel: a e i o u y
 116
 117 </td>
 118         </tr>
 119         <tr class="top-aligned-row context-row">
 120           <td class="context-item-name">CW</td>
 121           <td>=</td>
 122           <td class="context-item-value">&quot;[^aeiouywxY]&quot;</td>
 123           <td width="3em">&nbsp;</td>
 124           <td class="context-item-desc">
 125 A non-vowel other than w, x, or Y
 126
 127 </td>
 128         </tr>
 129         <tr class="top-aligned-row context-row">
 130           <td class="context-item-name">Double</td>
 131           <td>=</td>
 132           <td class="context-item-value">&quot;(bb|dd|ff|gg|mm|nn|pp|rr|tt)&quot;</td>
 133           <td width="3em">&nbsp;</td>
 134           <td class="context-item-desc">
 135 Doubles created when adding a suffix: these are undoubled when stemmed
 136
 137 </td>
 138         </tr>
 139         <tr class="top-aligned-row context-row">
 140           <td class="context-item-name">Valid_LI</td>
 141           <td>=</td>
 142           <td class="context-item-value">&quot;[cdeghkmnrt]&quot;</td>
 143           <td width="3em">&nbsp;</td>
 144           <td class="context-item-desc">
 145 A valid letter that can come before &#8216;li&#8217; (or &#8216;ly&#8217;)
 146
 147 </td>
 148         </tr>
 149         <tr class="top-aligned-row context-row">
 150           <td class="context-item-name">SHORT_SYLLABLE</td>
 151           <td>=</td>
 152           <td class="context-item-value">&quot;((#{C}#{V}#{CW})|(^#{V}#{C}))&quot;</td>
 153           <td width="3em">&nbsp;</td>
 154           <td class="context-item-desc">
 155 A specification for a short syllable.
 156
 157 <p>
 158 A short syllable in a word is either:
 159 </p>
 160 <ol>
 161 <li>a vowel followed by a non-vowel other than w, x or Y and preceded by a
 162 non-vowel, or
 163
 164 </li>
 165 <li>a vowel at the beginning of the word followed by a non-vowel.
 166
 167 </li>
 168 </ol>
 169 <p>
 170 (The original document is silent on whether sequences of two or more
 171 non-vowels make a syllable long. But as this specification is only used to
 172 find sequences of non-vowel - vowel - non-vowel - end-of-word, this
 173 ambiguity does not have an effect.)
 174 </p>
 175 </td>
 176         </tr>
 177         <tr class="top-aligned-row context-row">
 178           <td class="context-item-name">STEP_2_MAPS</td>
 179           <td>=</td>
 180           <td class="context-item-value">{&quot;tional&quot; =&gt; &quot;tion&quot;,
                  &quot;enci&quot; =&gt; &quot;ence&quot;,
                  &quot;anci&quot; =&gt; &quot;ance&quot;,
                  &quot;abli&quot; =&gt; &quot;able&quot;,
                  &quot;entli&quot; =&gt; &quot;ent&quot;,
                  &quot;ization&quot; =&gt; &quot;ize&quot;,
                  &quot;izer&quot; =&gt; &quot;ize&quot;,
                  &quot;ational&quot; =&gt; &quot;ate&quot;,
                  &quot;ation&quot; =&gt; &quot;ate&quot;,
                  &quot;ator&quot; =&gt; &quot;ate&quot;,
                  &quot;alism&quot; =&gt; &quot;al&quot;,
                  &quot;aliti&quot; =&gt; &quot;al&quot;,
                  &quot;alli&quot; =&gt; &quot;al&quot;,
                  &quot;fulness&quot; =&gt; &quot;ful&quot;,
                  &quot;ousli&quot; =&gt; &quot;ous&quot;,
                  &quot;ousness&quot; =&gt; &quot;ous&quot;,
                  &quot;iveness&quot; =&gt; &quot;ive&quot;,
                  &quot;iviti&quot; =&gt; &quot;ive&quot;,
                  &quot;biliti&quot; =&gt; &quot;ble&quot;,
                  &quot;bli&quot; =&gt; &quot;ble&quot;,
                  &quot;fulli&quot; =&gt; &quot;ful&quot;,
                  &quot;lessli&quot; =&gt; &quot;less&quot; }</td>
 181           <td width="3em">&nbsp;</td>
 182           <td class="context-item-desc">
 183 Suffix transformations used in porter2_step2. (ogi, li endings dealt with
 184 in procedure)
 185
 186 </td>
 187         </tr>
 188         <tr class="top-aligned-row context-row">
 189           <td class="context-item-name">STEP_3_MAPS</td>
 190           <td>=</td>
 191           <td class="context-item-value">{&quot;tional&quot; =&gt; &quot;tion&quot;,
                  &quot;ational&quot; =&gt; &quot;ate&quot;,
                  &quot;alize&quot; =&gt; &quot;al&quot;,
                  &quot;icate&quot; =&gt; &quot;ic&quot;,
                  &quot;iciti&quot; =&gt; &quot;ic&quot;,
                  &quot;ical&quot; =&gt; &quot;ic&quot;,
                  &quot;ful&quot; =&gt; &quot;&quot;,
                  &quot;ness&quot; =&gt; &quot;&quot; }</td>
 192           <td width="3em">&nbsp;</td>
 193           <td class="context-item-desc">
 194 Suffix transformations used in porter2_step3. (ative ending dealt with in
 195 procedure)
 196
 197 </td>
 198         </tr>
 199         <tr class="top-aligned-row context-row">
 200           <td class="context-item-name">STEP_4_MAPS</td>
 201           <td>=</td>
 202           <td class="context-item-value">{&quot;al&quot; =&gt; &quot;&quot;,
                  &quot;ance&quot; =&gt; &quot;&quot;,
                  &quot;ence&quot; =&gt; &quot;&quot;,
                  &quot;er&quot; =&gt; &quot;&quot;,
                  &quot;ic&quot; =&gt; &quot;&quot;,
                  &quot;able&quot; =&gt; &quot;&quot;,
                  &quot;ible&quot; =&gt; &quot;&quot;,
                  &quot;ant&quot; =&gt; &quot;&quot;,
                  &quot;ement&quot; =&gt; &quot;&quot;,
                  &quot;ment&quot; =&gt; &quot;&quot;,
                  &quot;ent&quot; =&gt; &quot;&quot;,
                  &quot;ism&quot; =&gt; &quot;&quot;,
                  &quot;ate&quot; =&gt; &quot;&quot;,
                  &quot;iti&quot; =&gt; &quot;&quot;,
                  &quot;ous&quot; =&gt; &quot;&quot;,
                  &quot;ive&quot; =&gt; &quot;&quot;,
                  &quot;ize&quot; =&gt; &quot;&quot; }</td>
 203           <td width="3em">&nbsp;</td>
 204           <td class="context-item-desc">
 205 Suffix transformations used in porter2_step4. (ion ending dealt with in
 206 procedure)
 207
 208 </td>
 209         </tr>
 210         <tr class="top-aligned-row context-row">
 211           <td class="context-item-name">SPECIAL_CASES</td>
 212           <td>=</td>
 213           <td class="context-item-value">{&quot;skis&quot; =&gt; &quot;ski&quot;,
                    &quot;skies&quot; =&gt; &quot;sky&quot;,
                     
                    &quot;dying&quot; =&gt; &quot;die&quot;,
                    &quot;lying&quot; =&gt; &quot;lie&quot;,
                    &quot;tying&quot; =&gt; &quot;tie&quot;,
                    &quot;idly&quot; =&gt;  &quot;idl&quot;,
                    &quot;gently&quot; =&gt; &quot;gentl&quot;,
                    &quot;ugly&quot; =&gt; &quot;ugli&quot;,
                    &quot;early&quot; =&gt; &quot;earli&quot;,
                    &quot;only&quot; =&gt; &quot;onli&quot;,
                    &quot;singly&quot; =&gt;&quot;singl&quot;,
                     
                    &quot;sky&quot; =&gt; &quot;sky&quot;,
                    &quot;news&quot; =&gt; &quot;news&quot;,
                    &quot;howe&quot; =&gt; &quot;howe&quot;,
                    &quot;atlas&quot; =&gt; &quot;atlas&quot;,
                    &quot;cosmos&quot; =&gt; &quot;cosmos&quot;,
                    &quot;bias&quot; =&gt; &quot;bias&quot;,
                    &quot;andes&quot; =&gt; &quot;andes&quot; }</td>
 214           <td width="3em">&nbsp;</td>
 215           <td class="context-item-desc">
 216 Special-case stemmings
 217
 218 </td>
 219         </tr>
 220         <tr class="top-aligned-row context-row">
 221           <td class="context-item-name">STEP_1A_SPECIAL_CASES</td>
 222           <td>=</td>
 223           <td class="context-item-value">%w[ inning outing canning herring earring proceed exceed succeed ]</td>
 224           <td width="3em">&nbsp;</td>
 225           <td class="context-item-desc">
 226 Special case words to stop processing after step 1a.
 227
 228 </td>
 229         </tr>
 230         </table>
 231       </div>
 232     </div>
 233
 234
 235
 236
 237
 238
 239     <!-- if method_list -->
 240
 241
 242   </div>
 243
 244
 245 <div id="validator-badges">
 246   <p><small><a href="http://validator.w3.org/check/referer">[Validate]</a></small></p>
 247 </div>
 248
 249 </body>
 250 </html>