英文分句/分段落
时间：2021-07-01 10:21:17
帮助过：42人阅读
php环境，指出一个原本分句的时候的误区，分句不用考虑小数点，不用考虑域名，因为标准的句子是句号后面加空格的，唯一要考虑的就是Mr. Li 这种。
先采用分段落的方式是考虑到有些引用采用冒号结尾。
- /*TWWY'S ART*/
- function break_passage($text){ //分割段落
- return preg_split("/(\r|\n|\r\n)/", $text, -1, PREG_SPLIT_NO_EMPTY);
- }
- function break_sentence($text){ //分割句子 英文的句号后面必须有空格
- $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.
- (? 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){ //先分割段落再分割句子 [推荐]
- $passage = break_passage($text);
- $return = array();
- foreach ($passage as $key => $value) $return = array_merge($return, break_sentence($value));
- return $return;
- }
- ?>
|
