Rev 223 | 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"> |
||
5 | <title>Modern Golic Vulcan – Federation Standard English Dictionary</title> |
||
6 | <style type="text/css"> |
||
7 | ol { |
||
8 | padding-left: 0; |
||
9 | list-style-type: none; |
||
10 | } |
||
11 | |||
12 | ol li { |
||
13 | margin-left: 0; |
||
14 | } |
||
15 | |||
16 | ol ol { |
||
17 | padding-left: 1em; |
||
18 | } |
||
19 | </style> |
||
20 | </head> |
||
21 | |||
22 | <body> |
||
23 | <h1>Modern Golic Vulcan – Federation Standard English Dictionary</h1> |
||
24 | <?php |
||
25 | define('REGEXP_PREFIX_EXAMPLE', '/^ex\s*=\s*/'); |
||
26 | |||
27 | $source_lang = 'vuh-Latn-Gol-modern'; |
||
28 | $target_lang = 'en-Latn-Federation'; |
||
29 | $lines = file('vul-gol-en.dict'); |
||
30 | |||
31 | if ($lines) |
||
32 | { |
||
33 | $last_indent = -1; |
||
34 | $last_phrases = array(); |
||
35 | |||
36 | foreach ($lines as $line) |
||
37 | { |
||
38 | preg_match('/^(?<lws>\s*)(?<phrase>[^:]+)\s*:\s*(?<transl>.+)/u', $line, $matches); |
||
39 | // var_dump($matches); |
||
40 | if ($matches) |
||
41 | { |
||
42 | $phrase = $matches['phrase']; |
||
43 | |||
44 | if (mb_strpos($phrase, '#') === false) |
||
45 | { |
||
46 | $indent = mb_strlen($matches['lws']) / 2; |
||
47 | |||
48 | if ($indent > $last_indent) |
||
49 | { |
||
50 | echo '<ol>'; |
||
51 | } |
||
52 | else |
||
53 | { |
||
54 | echo str_repeat('</ol>', $last_indent - $indent); |
||
55 | } |
||
56 | |||
57 | echo '<li>'; |
||
58 | |||
59 | $is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase); |
||
60 | if ($is_example) |
||
61 | { |
||
62 | $phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase); |
||
63 | } |
||
64 | |||
65 | if ($indent > $last_indent) |
||
66 | { |
||
67 | $last_phrases[] = $phrase; |
||
68 | } |
||
69 | else if ($indent < $last_indent) |
||
70 | { |
||
71 | $last_phrases = array_slice($last_phrases, 0, $indent + 1); |
||
72 | } |
||
73 | |||
74 | if ($indent <= $last_indent) |
||
75 | { |
||
76 | $last_phrases[count($last_phrases) - 1] = $phrase; |
||
77 | } |
||
78 | |||
79 | $phrase = preg_replace( |
||
80 | array( |
||
81 | '/~/', |
||
82 | '/[()]/', |
||
83 | ), |
||
84 | array( |
||
85 | '=', |
||
86 | '|', |
||
87 | ), |
||
88 | $phrase); |
||
89 | |||
90 | if ($last_phrases) |
||
91 | { |
||
92 | end($last_phrases); |
||
93 | |||
94 | while (($last_phrase = prev($last_phrases)) !== false) |
||
95 | { |
||
96 | while (mb_strlen($last_phrase) > 1) |
||
97 | { |
||
98 | if (preg_match('/' . preg_quote($last_phrase) . '/i', |
||
99 | $phrase, $last_sub_matches)) |
||
100 | { |
||
101 | $phrase = preg_replace('/' . $last_sub_matches[0] . '/i', |
||
102 | '<u>\\0</u>', $phrase); |
||
103 | break 2; |
||
104 | } |
||
105 | |||
106 | $last_phrase = mb_strcut($last_phrase, 0, mb_strlen($last_phrase) - 1); |
||
107 | } |
||
108 | } |
||
109 | } |
||
110 | |||
111 | $transl = preg_replace( |
||
112 | array( |
||
113 | '/"([^"]+)"/', |
||
114 | '/\\/([\\s\\w\'()-]+)\\//u', |
||
115 | '/\|(.*)(?<!\|)/', |
||
116 | '/\\s+~/', |
||
117 | ), |
||
118 | array( |
||
119 | '“\\1”', |
||
120 | '<i lang="' . $source_lang . '">\\1</i>', |
||
121 | '/\\1', |
||
122 | ' ~', |
||
123 | ), |
||
224 | PointedEar | 124 | $matches['transl']); |
223 | PointedEar | 125 | |
126 | echo ($is_example ? "<i lang='$source_lang'>" : "<b lang='$source_lang'>") |
||
127 | . $phrase |
||
128 | . ($is_example ? '</i>' : '</b>') |
||
129 | . " <span lang='$target_lang'>" . $transl . '</span>'; |
||
130 | |||
131 | $last_indent = $indent; |
||
132 | } |
||
133 | } |
||
134 | } |
||
135 | ?> |
||
136 | </ol> |
||
137 | <?php } ?> |
||
138 | </body> |
||
139 | </html> |