php敏感词过滤使用第三方扩展trie_filter

安装

• ubuntu 14.04
  • 安装 libdatrie

//http://linux.thai.net/~thep/datrie/datrie.html#Download下不下来，只好直接装
sudo apt-get install libdatrie-dev

• 安装 trie_filter 扩展

> git clone https://github.com/wulijun/php-ext-trie-filter.git
> cd php-ext-trie-filter
> phpize
> ./configure --with-php-config=/usr/bin/php-config
> make
> make install
//添加php扩展，extension=trie_filter.so
> service php5-fpm  restart
> php5-fpm -m //查看

使用

• 生成敏感词库

    $arrWord = array('word1', 'word2', 'word3');
    $resTrie = trie_filter_new(); //create an empty trie tree
    foreach ($arrWord as $k => $v) {
        trie_filter_store($resTrie, $v);
    }
    trie_filter_save($resTrie, __DIR__ . '/blackword.tree');
    trie_filter_free($resTrie);

• 使用

    $resTrie = trie_filter_load(__DIR__ . '/blackword.tree');

    $strContent = 'hello word2 word1';
    $arrRet = trie_filter_search($resTrie, $strContent);
    print_r($arrRet); //Array(0 => 6, 1 => 5)
    echo substr($strContent, $arrRet[0], $arrRet[1]); //word2
    $arrRet = trie_filter_search_all($resTrie, $strContent);
    print_r($arrRet); //Array(0 => Array(0 => 6, 1 => 5), 1 => Array(0 => 12, 1 => 5))
    foreach ($arrRet as $item) {
        echo substr($strContent, $item[0], $item[1]); //word2 word1
    }

    $arrRet = trie_filter_search($resTrie, 'hello word');
    print_r($arrRet); //Array()

    trie_filter_free($resTrie);