php 扩展分词,一个中文分词的PHP扩展

根据版本,下载后在php.ini下

extension=php_scws.dll

scws.default.charset = gbk/utf8

然后phpinfo();你会发现有一栏scsw表示安装成功

$sh = scws_open();

scws_set_charset($sh, 'utf8');

scws_set_dict($sh, 'etc/dict.utf8.xdb');

scws_set_rule($sh, 'etc/rules.utf8.ini');

$text = "我是一个中国人陈凯歌，我会C++语言，我也有很多T恤衣服";

scws_send_text($sh, $text);

$top = scws_get_tops($sh, 5);

while ($res = scws_get_result($sh))

{

foreach ($res as $tmp)

{

if ($tmp['len'] == 1 && $tmp['word'] == "\r")

continue;

if ($tmp['len'] == 1 && $tmp['word'] == "\n")

echo $tmp['word'];

else

printf("%s/%s ", $tmp['word'], $tmp['attr']);

}

}

echo "\n\n";

scws_close($sh);