WebSVN - LCARS - Diff - Rev 223 and 224 - /trunk/tools/eazytrans/vul-gol-en.php


<!DOCTYPE html>
<html lang="en"">
  <head>
    <meta charset="UTF-8">
    <title>Modern Golic Vulcan – Federation Standard English Dictionary</title>
    <style type="text/css">
      ol {
        padding-left: 0;
        list-style-type: none;
      }

      ol li {
        margin-left: 0;
      }

      ol ol {
        padding-left: 1em;
      }
    </style>
  </head>

  <body>
    <h1>Modern Golic Vulcan – Federation Standard English Dictionary</h1>
      <?php
        define('REGEXP_PREFIX_EXAMPLE', '/^ex\s*=\s*/');

        $source_lang = 'vuh-Latn-Gol-modern';
        $target_lang = 'en-Latn-Federation';
        $lines = file('vul-gol-en.dict');

        if ($lines)
        {
          $last_indent = -1;
          $last_phrases = array();

          foreach ($lines as $line)
          {
            preg_match('/^(?<lws>\s*)(?<phrase>[^:]+)\s*:\s*(?<transl>.+)/u', $line, $matches);
// var_dump($matches);
            if ($matches)
            {
              $phrase = $matches['phrase'];

              if (mb_strpos($phrase, '#') === false)
              {
                $indent = mb_strlen($matches['lws']) / 2;

                if ($indent > $last_indent)
                {
                  echo '<ol>';
                }
                else
                {
                  echo str_repeat('</ol>', $last_indent - $indent);
                }

                echo '<li>';

                $is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase);
                if ($is_example)
                {
                  $phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase);
                }

                if ($indent > $last_indent)
                {
                  $last_phrases[] = $phrase;
                }
                else if ($indent < $last_indent)
                {
                  $last_phrases = array_slice($last_phrases, 0, $indent + 1);
                }

                if ($indent <= $last_indent)
                {
                  $last_phrases[count($last_phrases) - 1] = $phrase;
                }

                $phrase = preg_replace(
                  array(
                    '/~/',
                    '/[()]/',
                  ),
                  array(
                    '=',
                    '|',
                  ),
                  $phrase);

                if ($last_phrases)
                {
                  end($last_phrases);

                  while (($last_phrase = prev($last_phrases)) !== false)
                  {
                    while (mb_strlen($last_phrase) > 1)
                    {
                      if (preg_match('/' . preg_quote($last_phrase) . '/i',
                            $phrase, $last_sub_matches))
                      {
                        $phrase = preg_replace('/' . $last_sub_matches[0] . '/i',
                          '<u>\\0</u>', $phrase);
                        break 2;
                      }

                      $last_phrase = mb_strcut($last_phrase, 0, mb_strlen($last_phrase) - 1);
                    }
                  }
                }

                $transl = preg_replace(
                  array(
                    '/"([^"]+)"/',
                    '/\\/([\\s\\w\'()-]+)\\//u',
                    '/\|(.*)(?<!\|)/',
                    '/\\s+~/',
                  ),
                  array(
                    '“\\1”',
                    '<i lang="' . $source_lang . '">\\1</i>',
                    '/\\1',
                    '&nbsp;~',
                  ),
                  $matches['transl']);

                echo ($is_example ? "<i lang='$source_lang'>" : "<b lang='$source_lang'>")
                  . $phrase
                  . ($is_example ? '</i>' : '</b>')
                  . " <span lang='$target_lang'>" . $transl . '</span>';

                $last_indent = $indent;
              }
            }
          }
        ?>
    </ol>
  <?php } ?>
  </body>
</html>

Rev 223	Rev 224
1	<!DOCTYPE html>	1	<!DOCTYPE html>
2	<html lang="en"">	2	<html lang="en"">
3	<head>	3	<head>
4	<meta charset="UTF-8">	4	<meta charset="UTF-8">
5	<title>Modern Golic Vulcan – Federation Standard English Dictionary</title>	5	<title>Modern Golic Vulcan – Federation Standard English Dictionary</title>
6	<style type="text/css">	6	<style type="text/css">
7	ol {	7	ol {
8	padding-left: 0;	8	padding-left: 0;
9	list-style-type: none;	9	list-style-type: none;
10	}	10	}
11		11
12	ol li {	12	ol li {
13	margin-left: 0;	13	margin-left: 0;
14	}	14	}
15		15
16	ol ol {	16	ol ol {
17	padding-left: 1em;	17	padding-left: 1em;
18	}	18	}
19	</style>	19	</style>
20	</head>	20	</head>
21		21
22	<body>	22	<body>
23	<h1>Modern Golic Vulcan – Federation Standard English Dictionary</h1>	23	<h1>Modern Golic Vulcan – Federation Standard English Dictionary</h1>
24	<?php	24	<?php
25	define('REGEXP_PREFIX_EXAMPLE', '/^ex\s=\s/');	25	define('REGEXP_PREFIX_EXAMPLE', '/^ex\s=\s/');
26		26
27	$source_lang = 'vuh-Latn-Gol-modern';	27	$source_lang = 'vuh-Latn-Gol-modern';
28	$target_lang = 'en-Latn-Federation';	28	$target_lang = 'en-Latn-Federation';
29	$lines = file('vul-gol-en.dict');	29	$lines = file('vul-gol-en.dict');
30		30
31	if ($lines)	31	if ($lines)
32	{	32	{
33	$last_indent = -1;	33	$last_indent = -1;
34	$last_phrases = array();	34	$last_phrases = array();
35		35
36	foreach ($lines as $line)	36	foreach ($lines as $line)
37	{	37	{
38	preg_match('/^(?<lws>\s)(?<phrase>[^:]+)\s:\s*(?<transl>.+)/u', $line, $matches);	38	preg_match('/^(?<lws>\s)(?<phrase>[^:]+)\s:\s*(?<transl>.+)/u', $line, $matches);
39	// var_dump($matches);	39	// var_dump($matches);
40	if ($matches)	40	if ($matches)
41	{	41	{
42	$phrase = $matches['phrase'];	42	$phrase = $matches['phrase'];
43		43
44	if (mb_strpos($phrase, '#') === false)	44	if (mb_strpos($phrase, '#') === false)
45	{	45	{
46	$indent = mb_strlen($matches['lws']) / 2;	46	$indent = mb_strlen($matches['lws']) / 2;
47		47
48	if ($indent > $last_indent)	48	if ($indent > $last_indent)
49	{	49	{
50	echo '<ol>';	50	echo '<ol>';
51	}	51	}
52	else	52	else
53	{	53	{
54	echo str_repeat('</ol>', $last_indent - $indent);	54	echo str_repeat('</ol>', $last_indent - $indent);
55	}	55	}
56		56
57	echo '<li>';	57	echo '<li>';
58		58
59	$is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase);	59	$is_example = preg_match(REGEXP_PREFIX_EXAMPLE, $phrase);
60	if ($is_example)	60	if ($is_example)
61	{	61	{
62	$phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase);	62	$phrase = preg_replace(REGEXP_PREFIX_EXAMPLE, '', $phrase);
63	}	63	}
64		64
65	if ($indent > $last_indent)	65	if ($indent > $last_indent)
66	{	66	{
67	$last_phrases[] = $phrase;	67	$last_phrases[] = $phrase;
68	}	68	}
69	else if ($indent < $last_indent)	69	else if ($indent < $last_indent)
70	{	70	{
71	$last_phrases = array_slice($last_phrases, 0, $indent + 1);	71	$last_phrases = array_slice($last_phrases, 0, $indent + 1);
72	}	72	}
73		73
74	if ($indent <= $last_indent)	74	if ($indent <= $last_indent)
75	{	75	{
76	$last_phrases[count($last_phrases) - 1] = $phrase;	76	$last_phrases[count($last_phrases) - 1] = $phrase;
77	}	77	}
78		78
79	$phrase = preg_replace(	79	$phrase = preg_replace(
80	array(	80	array(
81	'/~/',	81	'/~/',
82	'/[()]/',	82	'/[()]/',
83	),	83	),
84	array(	84	array(
85	'=',	85	'=',
86	'\|',	86	'\|',
87	),	87	),
88	$phrase);	88	$phrase);
89		89
90	if ($last_phrases)	90	if ($last_phrases)
91	{	91	{
92	end($last_phrases);	92	end($last_phrases);
93		93
94	while (($last_phrase = prev($last_phrases)) !== false)	94	while (($last_phrase = prev($last_phrases)) !== false)
95	{	95	{
96	while (mb_strlen($last_phrase) > 1)	96	while (mb_strlen($last_phrase) > 1)
97	{	97	{
98	if (preg_match('/' . preg_quote($last_phrase) . '/i',	98	if (preg_match('/' . preg_quote($last_phrase) . '/i',
99	$phrase, $last_sub_matches))	99	$phrase, $last_sub_matches))
100	{	100	{
101	$phrase = preg_replace('/' . $last_sub_matches[0] . '/i',	101	$phrase = preg_replace('/' . $last_sub_matches[0] . '/i',
102	'<u>\\0</u>', $phrase);	102	'<u>\\0</u>', $phrase);
103	break 2;	103	break 2;
104	}	104	}
105		105
106	$last_phrase = mb_strcut($last_phrase, 0, mb_strlen($last_phrase) - 1);	106	$last_phrase = mb_strcut($last_phrase, 0, mb_strlen($last_phrase) - 1);
107	}	107	}
108	}	108	}
109	}	109	}
110		110
111	$transl = preg_replace(	111	$transl = preg_replace(
112	array(	112	array(
113	'/"([^"]+)"/',	113	'/"([^"]+)"/',
114	'/\\/([\\s\\w\'()-]+)\\//u',	114	'/\\/([\\s\\w\'()-]+)\\//u',
115	'/\\|(.*)(?<!\\|)/',	115	'/\\|(.*)(?<!\\|)/',
116	'/\\s+~/',	116	'/\\s+~/',
117	),	117	),
118	array(	118	array(
119	'“\\1”',	119	'“\\1”',
120	'<i lang="' . $source_lang . '">\\1</i>',	120	'<i lang="' . $source_lang . '">\\1</i>',
121	'/\\1',	121	'/\\1',
122	' ~',	122	' ~',
123	),	123	),
124	strip_tags($matches['transl']));	124	$matches['transl']);
125		125
126	echo ($is_example ? "<i lang='$source_lang'>" : "<b lang='$source_lang'>")	126	echo ($is_example ? "<i lang='$source_lang'>" : "<b lang='$source_lang'>")
127	. $phrase	127	. $phrase
128	. ($is_example ? '</i>' : '</b>')	128	. ($is_example ? '</i>' : '</b>')
129	. " <span lang='$target_lang'>" . $transl . '</span>';	129	. " <span lang='$target_lang'>" . $transl . '</span>';
130		130
131	$last_indent = $indent;	131	$last_indent = $indent;
132	}	132	}
133	}	133	}
134	}	134	}
135	?>	135	?>
136	</ol>	136	</ol>
137	<?php } ?>	137	<?php } ?>
138	</body>	138	</body>
139	</html>	139	</html>

Subversion Repositories LCARS

(root)/trunk/tools/eazytrans/vul-gol-en.php @ 230 - Rev 223 → 224