| 1 | <?php |
| 2 | /* |
| 3 | * $Id$ |
| 4 | * |
| 5 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS |
| 6 | * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT |
| 7 | * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR |
| 8 | * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT |
| 9 | * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 10 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT |
| 11 | * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, |
| 12 | * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY |
| 13 | * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
| 14 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE |
| 15 | * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 16 | * |
| 17 | * This software consists of voluntary contributions made by many individuals |
| 18 | * and is licensed under the LGPL. For more information, see |
| 19 | * <http://www.phpdoctrine.org>. |
| 20 | */ |
| 21 | |
| 22 | /** |
| 23 | * Doctrine_Search_Analyzer_Standard |
| 24 | * |
| 25 | * @package Doctrine |
| 26 | * @subpackage Search |
| 27 | * @author Konsta Vesterinen <kvesteri@cc.hut.fi> |
| 28 | * @license http://www.opensource.org/licenses/lgpl-license.php LGPL |
| 29 | * @version $Revision$ |
| 30 | * @link www.phpdoctrine.org |
| 31 | * @since 1.0 |
| 32 | */ |
| 33 | class Doctrine_Search_Analyzer_Standard implements Doctrine_Search_Analyzer_Interface |
| 34 | { |
| 35 | protected static $_stopwords = array( |
| 36 | '0', |
| 37 | '1', |
| 38 | '2', |
| 39 | '3', |
| 40 | '4', |
| 41 | '5', |
| 42 | '6', |
| 43 | '7', |
| 44 | '8', |
| 45 | '9', |
| 46 | '10', |
| 47 | 'a', |
| 48 | 'about', |
| 49 | 'after', |
| 50 | 'all', |
| 51 | 'almost', |
| 52 | 'along', |
| 53 | 'also', |
| 54 | 'although', |
| 55 | 'amp', |
| 56 | 'an', |
| 57 | 'and', |
| 58 | 'another', |
| 59 | 'any', |
| 60 | 'are', |
| 61 | 'area', |
| 62 | 'arent', |
| 63 | 'around', |
| 64 | 'as', |
| 65 | 'at', |
| 66 | 'available', |
| 67 | 'back', |
| 68 | 'be', |
| 69 | 'because', |
| 70 | 'been', |
| 71 | 'before', |
| 72 | 'being', |
| 73 | 'best', |
| 74 | 'better', |
| 75 | 'big', |
| 76 | 'bit', |
| 77 | 'both', |
| 78 | 'but', |
| 79 | 'by', |
| 80 | 'c', |
| 81 | 'came', |
| 82 | 'can', |
| 83 | 'capable', |
| 84 | 'control', |
| 85 | 'could', |
| 86 | 'course', |
| 87 | 'd', |
| 88 | 'dan', |
| 89 | 'day', |
| 90 | 'decided', |
| 91 | 'did', |
| 92 | 'didn', |
| 93 | 'different', |
| 94 | 'div', |
| 95 | 'do', |
| 96 | 'doesn', |
| 97 | 'don', |
| 98 | 'down', |
| 99 | 'drive', |
| 100 | 'e', |
| 101 | 'each', |
| 102 | 'easily', |
| 103 | 'easy', |
| 104 | 'edition', |
| 105 | 'either', |
| 106 | 'end', |
| 107 | 'enough', |
| 108 | 'even', |
| 109 | 'every', |
| 110 | 'example', |
| 111 | 'few', |
| 112 | 'find', |
| 113 | 'first', |
| 114 | 'for', |
| 115 | 'found', |
| 116 | 'from', |
| 117 | 'get', |
| 118 | 'go', |
| 119 | 'going', |
| 120 | 'good', |
| 121 | 'got', |
| 122 | 'gt', |
| 123 | 'had', |
| 124 | 'hard', |
| 125 | 'has', |
| 126 | 'have', |
| 127 | 'he', |
| 128 | 'her', |
| 129 | 'here', |
| 130 | 'how', |
| 131 | 'i', |
| 132 | 'if', |
| 133 | 'in', |
| 134 | 'into', |
| 135 | 'is', |
| 136 | 'isn', |
| 137 | 'it', |
| 138 | 'just', |
| 139 | 'know', |
| 140 | 'last', |
| 141 | 'left', |
| 142 | 'li', |
| 143 | 'like', |
| 144 | 'little', |
| 145 | 'll', |
| 146 | 'long', |
| 147 | 'look', |
| 148 | 'lot', |
| 149 | 'lt', |
| 150 | 'm', |
| 151 | 'made', |
| 152 | 'make', |
| 153 | 'many', |
| 154 | 'mb', |
| 155 | 'me', |
| 156 | 'menu', |
| 157 | 'might', |
| 158 | 'mm', |
| 159 | 'more', |
| 160 | 'most', |
| 161 | 'much', |
| 162 | 'my', |
| 163 | 'name', |
| 164 | 'nbsp', |
| 165 | 'need', |
| 166 | 'new', |
| 167 | 'no', |
| 168 | 'not', |
| 169 | 'now', |
| 170 | 'number', |
| 171 | 'of', |
| 172 | 'off', |
| 173 | 'old', |
| 174 | 'on', |
| 175 | 'one', |
| 176 | 'only', |
| 177 | 'or', |
| 178 | 'original', |
| 179 | 'other', |
| 180 | 'our', |
| 181 | 'out', |
| 182 | 'over', |
| 183 | 'part', |
| 184 | 'place', |
| 185 | 'point', |
| 186 | 'pretty', |
| 187 | 'probably', |
| 188 | 'problem', |
| 189 | 'put', |
| 190 | 'quite', |
| 191 | 'quot', |
| 192 | 'r', |
| 193 | 're', |
| 194 | 'really', |
| 195 | 'results', |
| 196 | 'right', |
| 197 | 's', |
| 198 | 'same', |
| 199 | 'saw', |
| 200 | 'see', |
| 201 | 'set', |
| 202 | 'several', |
| 203 | 'she', |
| 204 | 'sherree', |
| 205 | 'should', |
| 206 | 'since', |
| 207 | 'size', |
| 208 | 'small', |
| 209 | 'so', |
| 210 | 'some', |
| 211 | 'something', |
| 212 | 'special', |
| 213 | 'still', |
| 214 | 'stuff', |
| 215 | 'such', |
| 216 | 'sure', |
| 217 | 'system', |
| 218 | 't', |
| 219 | 'take', |
| 220 | 'than', |
| 221 | 'that', |
| 222 | 'the', |
| 223 | 'their', |
| 224 | 'them', |
| 225 | 'then', |
| 226 | 'there', |
| 227 | 'these', |
| 228 | 'they', |
| 229 | 'thing', |
| 230 | 'things', |
| 231 | 'think', |
| 232 | 'this', |
| 233 | 'those', |
| 234 | 'though', |
| 235 | 'through', |
| 236 | 'time', |
| 237 | 'to', |
| 238 | 'today', |
| 239 | 'together', |
| 240 | 'too', |
| 241 | 'took', |
| 242 | 'two', |
| 243 | 'up', |
| 244 | 'us', |
| 245 | 'use', |
| 246 | 'used', |
| 247 | 'using', |
| 248 | 've', |
| 249 | 'very', |
| 250 | 'want', |
| 251 | 'was', |
| 252 | 'way', |
| 253 | 'we', |
| 254 | 'well', |
| 255 | 'went', |
| 256 | 'were', |
| 257 | 'what', |
| 258 | 'when', |
| 259 | 'where', |
| 260 | 'which', |
| 261 | 'while', |
| 262 | 'white', |
| 263 | 'who', |
| 264 | 'will', |
| 265 | 'with', |
| 266 | 'would', |
| 267 | 'yet', |
| 268 | 'you', |
| 269 | 'your', |
| 270 | 'yours' |
| 271 | ); |
| 272 | |
| 273 | public function analyze($text) |
| 274 | { |
| 275 | $text = preg_replace('/[\'`´"]/', '', $text); |
| 276 | $text = preg_replace('/[^A-Za-z0-9]/', ' ', $text); |
| 277 | $text = str_replace(' ', ' ', $text); |
| 278 | |
| 279 | $terms = explode(' ', $text); |
| 280 | |
| 281 | $ret = array(); |
| 282 | if ( ! empty($terms)) { |
| 283 | foreach ($terms as $i => $term) { |
| 284 | if (empty($term)) { |
| 285 | continue; |
| 286 | } |
| 287 | $lower = strtolower(trim($term)); |
| 288 | |
| 289 | if (in_array($lower, self::$_stopwords)) { |
| 290 | continue; |
| 291 | } |
| 292 | |
| 293 | $ret[$i] = $lower; |
| 294 | } |
| 295 | } |
| 296 | return $ret; |
| 297 | } |
| 298 | } |