Rev 230 | Go to most recent revision | Details | Compare with Previous | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 223 | PointedEar | 1 | <!DOCTYPE html> |
| 2 | <html lang="en""> |
||
| 3 | <head> |
||
| 4 | <meta charset="UTF-8"> |
||
| 232 | PointedEar | 5 | <title>Golic Vulcan – Federation Standard English Dictionary</title> |
| 223 | PointedEar | 6 | <style type="text/css"> |
| 230 | PointedEar | 7 | body { |
| 8 | font-family: serif; |
||
| 9 | } |
||
| 10 | |||
| 11 | ol |
||
| 12 | { |
||
| 223 | PointedEar | 13 | padding-left: 0; |
| 14 | list-style-type: none; |
||
| 15 | } |
||
| 16 | |||
| 230 | PointedEar | 17 | ol li |
| 18 | { |
||
| 223 | PointedEar | 19 | margin-left: 0; |
| 20 | } |
||
| 21 | |||
| 230 | PointedEar | 22 | ol ol |
| 23 | { |
||
| 223 | PointedEar | 24 | padding-left: 1em; |
| 25 | } |
||
| 230 | PointedEar | 26 | |
| 27 | .type-or-context { |
||
| 28 | font-family: sans-serif; |
||
| 29 | font-size: small; |
||
| 30 | font-weight: bold; |
||
| 31 | } |
||
| 32 | |||
| 33 | i em { |
||
| 34 | font-weight: bold; |
||
| 35 | } |
||
| 223 | PointedEar | 36 | </style> |
| 37 | </head> |
||
| 38 | |||
| 39 | <body> |
||
| 230 | PointedEar | 40 | <?php |
| 232 | PointedEar | 41 | $source_lang = 'vuh-Latn-Gol'; |
| 223 | PointedEar | 42 | $target_lang = 'en-Latn-Federation'; |
| 232 | PointedEar | 43 | $lines = file('vuh-gol-en.dict'); |
| 230 | PointedEar | 44 | ?> |
| 232 | PointedEar | 45 | <h1>Golic Vulcan – Federation Standard English Dictionary</h1> |
| 230 | PointedEar | 46 | <?php |
| 47 | define('REGEXP_PREFIX_EXAMPLE', '/^ex\s*=\s*/'); |
||
| 223 | PointedEar | 48 | |
| 49 | if ($lines) |
||
| 50 | { |
||
| 51 | $last_indent = -1; |
||
| 52 | $last_phrases = array(); |
||
| 53 | |||
| 54 | foreach ($lines as $line) |
||
| 55 | { |
||
| 56 | preg_match('/^(?<lws>\s*)(?<phrase>[^:]+)\s*:\s*(?<transl>.+)/u', $line, $matches); |
||
| 57 | // var_dump($matches); |
||
| 58 | if ($matches) |
||
| 59 | { |
||
| 60 | $phrase = $matches['phrase']; |
||
| 61 | |||
| 62 | if (mb_strpos($phrase, '#') === false) |
||
| 63 | { |
||
| 64 | $indent = mb_strlen($matches['lws']) / 2; |
||
| 65 | |||
| 66 | if ($indent > $last_indent) |
||
| 67 | { |
||
| 68 | echo '<ol>'; |
||
| 69 | } |
||
| 70 | else |
||
| 71 | { |
||
| 72 | echo str_repeat('</ol>', $last_indent - $indent); |
||
| 73 | } |
||
| 74 | |||
| 75 | echo '<li>'; |
||
| 76 | |||
| 77 | $is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase); |
||
| 78 | if ($is_example) |
||
| 79 | { |
||
| 80 | $phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase); |
||
| 81 | } |
||
| 82 | |||
| 83 | if ($indent > $last_indent) |
||
| 84 | { |
||
| 85 | $last_phrases[] = $phrase; |
||
| 86 | } |
||
| 87 | else if ($indent < $last_indent) |
||
| 88 | { |
||
| 89 | $last_phrases = array_slice($last_phrases, 0, $indent + 1); |
||
| 90 | } |
||
| 91 | |||
| 92 | if ($indent <= $last_indent) |
||
| 93 | { |
||
| 94 | $last_phrases[count($last_phrases) - 1] = $phrase; |
||
| 95 | } |
||
| 96 | |||
| 97 | $phrase = preg_replace( |
||
| 98 | array( |
||
| 99 | '/~/', |
||
| 100 | '/[()]/', |
||
| 101 | ), |
||
| 102 | array( |
||
| 103 | '=', |
||
| 104 | '|', |
||
| 105 | ), |
||
| 106 | $phrase); |
||
| 107 | |||
| 108 | if ($last_phrases) |
||
| 109 | { |
||
| 110 | end($last_phrases); |
||
| 111 | |||
| 112 | while (($last_phrase = prev($last_phrases)) !== false) |
||
| 113 | { |
||
| 114 | while (mb_strlen($last_phrase) > 1) |
||
| 115 | { |
||
| 116 | if (preg_match('/' . preg_quote($last_phrase) . '/i', |
||
| 117 | $phrase, $last_sub_matches)) |
||
| 118 | { |
||
| 119 | $phrase = preg_replace('/' . $last_sub_matches[0] . '/i', |
||
| 120 | '<u>\\0</u>', $phrase); |
||
| 121 | break 2; |
||
| 122 | } |
||
| 123 | |||
| 124 | $last_phrase = mb_strcut($last_phrase, 0, mb_strlen($last_phrase) - 1); |
||
| 125 | } |
||
| 126 | } |
||
| 127 | } |
||
| 128 | |||
| 129 | $transl = preg_replace( |
||
| 130 | array( |
||
| 131 | '/"([^"]+)"/', |
||
| 230 | PointedEar | 132 | '/\{([^\}]+)\}/', |
| 133 | '/(^|[\\s+\\[])\\/([\\s\\w\'()-]+)\\/(?=[,.;:\\s+\\]]|$)/u', |
||
| 223 | PointedEar | 134 | '/\|(.*)(?<!\|)/', |
| 230 | PointedEar | 135 | '/\*(.+?)\*/', |
| 223 | PointedEar | 136 | '/\\s+~/', |
| 137 | ), |
||
| 138 | array( |
||
| 139 | '“\\1”', |
||
| 230 | PointedEar | 140 | '<abbr class="type-or-context" lang="' . $target_lang . '">\\1</abbr>', |
| 141 | '\\1<i lang="' . $source_lang . '">\\2</i>', |
||
| 223 | PointedEar | 142 | '/\\1', |
| 230 | PointedEar | 143 | '<em>\\1</em>', |
| 223 | PointedEar | 144 | ' ~', |
| 145 | ), |
||
| 224 | PointedEar | 146 | $matches['transl']); |
| 223 | PointedEar | 147 | |
| 148 | echo ($is_example ? "<i lang='$source_lang'>" : "<b lang='$source_lang'>") |
||
| 149 | . $phrase |
||
| 150 | . ($is_example ? '</i>' : '</b>') |
||
| 151 | . " <span lang='$target_lang'>" . $transl . '</span>'; |
||
| 152 | |||
| 153 | $last_indent = $indent; |
||
| 154 | } |
||
| 155 | } |
||
| 156 | } |
||
| 230 | PointedEar | 157 | echo '</ol>'; |
| 158 | |||
| 159 | // $phrases = array(); |
||
| 160 | |||
| 161 | // foreach ($lines as $line) |
||
| 162 | // { |
||
| 163 | // preg_match('/^(?<lws>\s*)(?<phrase>[^:]+)\s*:\s*(?<transl>.+)/u', $line, $matches); |
||
| 164 | // if ($matches) |
||
| 165 | // { |
||
| 166 | // $phrase = $matches['phrase']; |
||
| 167 | |||
| 168 | // /* if not a comment */ |
||
| 169 | // if (mb_strpos($phrase, '#') === false) |
||
| 170 | // { |
||
| 171 | // $transl = $matches['transl']; |
||
| 172 | |||
| 173 | // $is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase); |
||
| 174 | // if ($is_example) |
||
| 175 | // { |
||
| 176 | // /* assign example to previous phrase; indentation irrelevant */ |
||
| 177 | // $phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase); |
||
| 178 | |||
| 179 | // $prev_phrase['examples'][$phrase] = $transl; |
||
| 180 | // } |
||
| 181 | // else |
||
| 182 | // { |
||
| 183 | // /* create new phrase */ |
||
| 184 | // $level = mb_strlen($matches['lws']) / 2; |
||
| 185 | |||
| 186 | // $phrases[$phrase] = array( |
||
| 187 | // 'translation' => $transl, |
||
| 188 | // 'level' => $level |
||
| 189 | // ); |
||
| 190 | // $prev_phrase =& $phrases[$phrase]; |
||
| 191 | // } |
||
| 192 | // } |
||
| 193 | // } |
||
| 194 | // } |
||
| 195 | |||
| 196 | // // var_dump($phrases); |
||
| 197 | |||
| 198 | // if ($phrases) |
||
| 199 | // { |
||
| 200 | // $prev_level = -1; |
||
| 201 | |||
| 202 | // foreach ($phrases as $phrase => $data) |
||
| 203 | // { |
||
| 204 | // $level = $data['level']; |
||
| 205 | |||
| 206 | // if ($level > $prev_level) |
||
| 207 | // { |
||
| 208 | // echo "\n<ol>\n"; |
||
| 209 | // } |
||
| 210 | // else if ($level < $prev_level) |
||
| 211 | // { |
||
| 212 | // echo str_repeat("</ol>\n", $prev_level - $level); |
||
| 213 | // } |
||
| 214 | |||
| 215 | // $translation = $data['translation']; |
||
| 216 | |||
| 217 | // echo "\n<li>$prev_level => $level <b lang='$source_lang'>" . htmlspecialchars($phrase) . '</b>' |
||
| 218 | // . " <span lang='$target_lang'>" . $translation . '</span>'; |
||
| 219 | |||
| 220 | // if (isset($data['examples'])) |
||
| 221 | // { |
||
| 222 | // echo '<ul>'; |
||
| 223 | |||
| 224 | // foreach ($data['examples'] as $original => $translation) |
||
| 225 | // { |
||
| 226 | // echo "<li><i lang='$source_lang'>" . htmlspecialchars($original) . '</i>' |
||
| 227 | // . " <span lang='$target_lang'>" . $translation . '</span></li>'; |
||
| 228 | // } |
||
| 229 | |||
| 230 | // echo '</ul>'; |
||
| 231 | // } |
||
| 232 | |||
| 233 | // $prev_level = $level; |
||
| 234 | // } |
||
| 235 | |||
| 236 | // echo '</ol>'; |
||
| 237 | // } |
||
| 223 | PointedEar | 238 | ?> |
| 230 | PointedEar | 239 | <?php } ?> |
| 223 | PointedEar | 240 | </body> |
| 241 | </html> |