中文分词的php代码_PHP教程
class NLP{
private static $cmd_path;
// 不以'/'结尾
static function set_cmd_path($path){
self::$cmd_path = $path;
}
private function cmd($str){
$descriptorspec = array(
0 => array("pipe", "r"),
1 => array("pipe", "w"),
);
$cmd = self::$cmd_path . "/ictclas";
$process = proc_open($cmd, $descriptorspec, $pipes);
if (is_resource($process)) {
$str = iconv('utf-8', 'gbk', $str);
fwrite($pipes[0], $str);
$output = stream_get_contents($pipes[1]);
fclose($pipes[0]);
fclose($pipes[1]);
$return_value = proc_close($process);
}
/*
$cmd = "printf '$input' | " . self::$cmd_path . "/ictclas";
exec($cmd, $output, $ret);
$output = join("n", $output);
*/
$output = trim($output);
$output = iconv('gbk', 'utf-8', $output);
return $output;
}
/**
* 进行分词, 返回词语列表.
*/
function tokenize($str){
$tokens = array();
$output = self::cmd($input);
if($output){
$ps教程 = preg_split('/s+/', $output);
foreach($ps as $p){
list($seg, $tag) = explode('/', $p);
$item = array(
'seg' => $seg,
'tag' => $tag,
);
$tokens[] = $item;
}
}
return $tokens;
}
}
NLP::set_cmd_path(dirname(__FILE__));
?>用起来很简单(确保 ICTCLAS 编译后的可执行文件和词典在当前目录):
复制代码 代码如下:
require_once('NLP.php');
var_dump(NLP::tokenize('Hello, World!'));
?>
进行中文分词的 PHP 类就在下面了, 用 proc_open() 函数来执行分词程序, 并通过管道和其交互, 输入要进行分词的文本, 读取分词结果。