以下是代码片段: < ?php /** * @version 0.1 * @todo 构造通用的字典算法,并写了一个简易的分词 * @author shjuto@gmail.com * Trie字典树 * */ class Trie { private $trie; function __construct() { $trie = array(’children’ => array(),’isword’=>false); } /** * 把词加入词典 * * @param String $key */ function &setWord($word=’’) { $trienode = &$this->trie; for($i = 0;$i < strlen($word);$i++) { $character = $word[$i]; if(!isset($trienode[’children’][$character])) { $trienode[’children’][$character] = array(’isword’=>false); } if($i == strlen($word)-1) { $trienode[’children’][$character] = array(’isword’=>true); } $trienode = &$trienode[’children’][$character]; } } /** * 判断是否为词典词 * * @param String $word * @return bool true/false */ function & isWord($word) { $trienode = &$this->trie; for($i = 0;$i < strlen($word);$i++) { $character = $word[$i]; if(!isset($trienode[’children’][$character])) { return false; } else { //判断词结束 if($i == (strlen($word)-1) && $trienode[’children’][$character][’isword’] == true) { return true; } elseif($i == (strlen($word)-1) && $trienode[’children’][$character][’isword’] == false) { return false; } $trienode = &$trienode[’children’][$character]; } } } /** * 在文本$text找词出现的位置 * * @param String $text * @return array array(’position’=>$position,’word’ =>$word); */ function search($text="") { $textlen = strlen($text); $trienode = $tree = $this->trie; $find = array(); $wordrootposition = 0;//词根位置 $prenode = false;//回溯参数,当词典ab,在字符串aab中,需要把$i向前回溯一次 $word = ’’; for ($i = 0; $i < $textlen;$i++) { if(isset($trienode[’children’][$text[$i]])) { $word = $word .$text[$i]; $trienode = $trienode[’children’][$text[$i]]; if($prenode == false) { $wordrootposition = $i; } $prenode = true; if($trienode[’isword’]) { $find[] = array(’position’=>$wordrootposition,’word’ =>$word); } } else { $trienode = $tree; $word = ’’; if($prenode) { $i = $i -1; $prenode = false; } } } return $find; } } $trie = new Trie(); $trie->setWord(’中国’); $trie->setWord(’中国人’); $trie->setWord(’伟大’); $trie->setWord(’军队’); $trie->setWord(’中国人民’); $trie->setWord(’中国人民解放军’); $trie->setWord(’解放军’); $trie->setWord(’解放’); $words = $trie->search(’伟大的中国人民解放军解放了全中国,是很伟大的军队’); foreach ($words as $word) { echo ’位置:’.$word[’position’].’-’.(strlen($word[’word’])+$word[’position’]); echo ’ 词:’.$word[’word’]."\n"; } |
|