Created
December 26, 2011 12:00
-
-
Save geta6/1520984 to your computer and use it in GitHub Desktop.
日本語/英語から任意文字数の識別子を生成します
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/php | |
<?php | |
// 辞書 | |
$dicts = array( | |
array('jp'=>'英単語', 'en'=>'English Words'), | |
); | |
// 生成する識別子の文字数 | |
$n = 4; | |
foreach ($dicts as $dict) : | |
// n文字の識別子($dict['id'])を作る | |
// 大文字開始文字列に展開 | |
// 母音を出現頻度順(日本語ローマ字)に削って合成 | |
// n文字になった時点で完了する | |
preg_match_all('/[A-Z][a-z]*/', $dict['en'], $reg); | |
$reg = $reg[0]; | |
init: | |
// フィルタリング,なくてもいい | |
// ローマ字を識別子化する時に使えばいい | |
$reg = array_map(function($m){ | |
$m = str_replace('shi','si',$m); | |
// : | |
return $m; | |
},$reg); | |
$regs = str_replace(array('a','e','i','o','u'), '', strtolower(implode($reg))); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
$regs = str_replace(array('a','i','o','u'), '', strtolower(implode($reg))); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
$regs = str_replace(array('a','i','o',), '', strtolower(implode($reg))); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
$regs = str_replace(array('a','i'), '', strtolower(implode($reg))); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
$regs = str_replace(array('a'), '', strtolower(implode($reg))); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
$regs = implode($reg); | |
$dict['id'] = substr($regs,0,$n); | |
if ($n>strlen($dict['id'])) : | |
foreach(json_decode(file_get_contents("http://pipes.yahoo.com/pipes/pipe.run?_id=ohZnaGr92xG36xIFyzUFzw&_render=json&text={$dict['ja']}"))->value->items as $value) : | |
$reg = array(preg_replace('/[^A-Za-z]/','',(string)$value->description)); | |
break; | |
endforeach; | |
goto init; | |
endif; | |
endif; | |
endif; | |
endif; | |
endif; | |
endif; | |
$dict['id'] = strtoupper($dict['id']); | |
$resdict[] = $dict; | |
endforeach; | |
print_r($resdict); | |
/* | |
Array | |
( | |
[0] => Array | |
( | |
[jp] => 英単語 | |
[en] => English Words | |
[dis] => NGLS | |
) | |
) | |
*/ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment