//词典类
class ch_dictionary {
    var $_id;

    function ch_dictionary($fname = "") {
        if ($fname != "") {
            $this->load($fname);
        }
    }

    // 根据文件名载入字典 (gdbm数据档案)
    function load($fname) {
        $this->_id = dba_popen($fname, "r", "gdbm");
        if (!$this->_id) {
            echo "failed to open the dictionary.($fname)<br>\n";
            exit;
        }
    }

    // 根据词语返回频率, 不存在返回-1
    function find($word) {
        $freq = dba_fetch($word, $this->_id);
        if (is_bool($freq)) $freq = -1;
        return $freq;
    }
}

// 分词类: (逆向)
// 先将输入的字串正向切成句子, 然后一句一句的分词, 返回由词组成的数组.
class ch_word_split {
    var $_mb_mark_list;    // 常见切分句子的全角标点
    var $_word_maxlen;    // 单个词最大可能长度(汉字字数)
    var $_dic;        // 词典...
    var $_ignore_mark;    // true or false
   
    function ch_word_split () {
        $this->_mb_mark_list = array("，","　","。","！","？","：","……","、","“","”","《","》","（","）");
        $this->_word_maxlen  = 12;    // 12个汉字
        $this->_dic = NULL;
        $this->_ignore_mark = true;
    }

    // 设定字典
    function set_dic($fname) {
        $this->_dic = new ch_dictionary($fname);
    }

    function set_ignore_mark($set) {
        if (is_bool($set)) $this->_ignore_mark = $set;
    }

    // 将字串切成句子再加以切分成词
    function string_split($str, $func = "") {       
        $ret = array();
       
        if ($func == "" || !function_exists($func)) $func = "";       
       
        $len = strlen($str);
        $qtr = "";

        for ($i = 0; $i < $len; $i++) {
 &nb