「PHPの学習」phpで英文のセンテンス/段落に分けるサンプルプログラム

2014年7月23日

PHPコード：
<?php

function break_passage($text){ //段落を分割
return preg_split(“/(\r|\n|\r\n)/", $text, -1, PREG_SPLIT_NO_EMPTY);
}

function break_sentence($text){ //センテンスを分割
$re = '/# Split sentences on whitespace between them.
(?<= # Begin positive lookbehind.
[.!?] # Either an end of sentence punct,
| [.!?][\'"] # or end of sentence punct and quote.
) # End positive lookbehind.
(?<! # Begin negative lookbehind.
Mr\. # Skip either “Mr."
| Mrs\. # or “Mrs.",
| Ms\. # or “Ms.",
| Jr\. # or “Jr.",
| Dr\. # or “Dr.",
| Prof\. # or “Prof.",
| Sr\. # or “Sr.",
# or… (you get the idea).
) # End negative lookbehind.
\s+ # Split on whitespace between sentences.
/ix’;
$sentences = preg_split($re, $text, -1, PREG_SPLIT_NO_EMPTY);
return $sentences;
}

function get_sentence($text){ //先に段落を分割してまたセンテンスを分割 [推奨]
$passage = break_passage($text);
$return = array();
foreach ($passage as $key => $value) $return = array_merge($return, break_sentence($value));
return $return;
}

?>