/** * Static method cut * * @param string $sentence # input sentence * @param boolean $cut_all # cut_all or not * @param array $options # other options * * @return array $seg_list */ public static function cut($sentence, $cut_all = false, $options = array()) { $defaults = array('mode' => 'default'); $options = array_merge($defaults, $options); $seg_list = array(); $re_han_pattern = '([\\x{4E00}-\\x{9FA5}]+)'; $re_skip_pattern = '([a-zA-Z0-9+#\\n]+)'; preg_match_all('/(' . $re_han_pattern . '|' . $re_skip_pattern . ')/u', $sentence, $matches, PREG_PATTERN_ORDER); $blocks = $matches[0]; foreach ($blocks as $blk) { if (preg_match('/' . $re_han_pattern . '/u', $blk)) { if ($cut_all) { $words = Jieba::__cutAll($blk); } else { $words = Jieba::__cutDAG($blk); } foreach ($words as $word) { array_push($seg_list, $word); } } else { array_push($seg_list, $blk); } // end else (preg_match('/'.$re_han_pattern.'/u', $blk)) } // end foreach ($blocks as $blk) return $seg_list; }
#!/usr/bin/php <?php /** * demo_extract_tags.php * * PHP version 5 * * @category PHP * @package /src/cmd/ * @author Fukuball Lin <*****@*****.**> * @license MIT Licence * @version GIT: <fukuball/jieba-php> * @link https://github.com/fukuball/jieba-php */ ini_set('memory_limit', '600M'); require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/MultiArray.php"; require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/Factory/MultiArrayFactory.php"; require_once dirname(dirname(__FILE__)) . "/class/Jieba.php"; require_once dirname(dirname(__FILE__)) . "/class/Finalseg.php"; require_once dirname(dirname(__FILE__)) . "/class/JiebaAnalyse.php"; use Fukuball\Jieba; use Fukuball\Finalseg; use Fukuball\JiebaAnalyse; Jieba::init(array('mode' => 'test', 'dict' => 'samll')); Finalseg::init(); JiebaAnalyse::init(); $top_k = 10; $content = file_get_contents(dirname(dirname(__FILE__)) . "/dict/lyric.txt", "r"); $tags = JiebaAnalyse::extractTags($content, $top_k); var_dump($tags);
/** * demo.php * * PHP version 5 * * @category PHP * @package /src/cmd/ * @author Fukuball Lin <*****@*****.**> * @license MIT Licence * @version GIT: <fukuball/jieba-php> * @link https://github.com/fukuball/jieba-php */ ini_set('memory_limit', '600M'); require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/MultiArray.php"; require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/Factory/MultiArrayFactory.php"; require_once dirname(dirname(__FILE__)) . "/class/Jieba.php"; require_once dirname(dirname(__FILE__)) . "/class/Finalseg.php"; use Fukuball\Jieba; use Fukuball\Finalseg; Jieba::init(array('mode' => 'test', 'dict' => 'samll')); Finalseg::init(); $seg_list = Jieba::cut("怜香惜玉也得要看对象啊!"); var_dump($seg_list); echo "Full Mode: \n"; $seg_list = Jieba::cut("我来到北京清华大学", true); var_dump($seg_list); echo "Default Mode: \n"; $seg_list = Jieba::cut("我来到北京清华大学", false); var_dump($seg_list); $seg_list = Jieba::cut("他来到了网易杭研大厦"); var_dump($seg_list);
public function testJiebaCutAll() { $case_array = array("我", "来", "来到", "到", "北", "北京", "京", "清", "清华", "清华大学", "华", "华大", "大", "大学", "学"); $seg_list = Jieba::cut("我来到北京清华大学", true); $this->assertEquals($case_array, $seg_list); }
<?php ini_set('memory_limit', '1024M'); require_once dirname(dirname(__FILE__)) . "/src/vendor/multi-array/MultiArray.php"; require_once dirname(dirname(__FILE__)) . "/src/vendor/multi-array/Factory/MultiArrayFactory.php"; require_once dirname(dirname(__FILE__)) . "/src/class/Jieba.php"; require_once dirname(dirname(__FILE__)) . "/src/class/Finalseg.php"; require_once dirname(dirname(__FILE__)) . "/src/class/JiebaAnalyse.php"; use Fukuball\Jieba; use Fukuball\Finalseg; use Fukuball\JiebaAnalyse; Jieba::init(); Finalseg::init(); JiebaAnalyse::init(); function loader($class) { $file = $class . '.php'; if (file_exists($file)) { require_once $file; } } spl_autoload_register('loader');
$count = 0; socket_set_nonblock($sock); //Accept incoming connection - This is a blocking call // $client = socket_accept($sock); while ($count < 1) { if ($new_client = socket_accept($sock)) { echo '<br/>'; echo "Client {$new_client} has connected <br/>"; $clients[] = $new_client; //display information about the client who is connected if (socket_getpeername($new_client, $address, $port)) { echo "Client {$address} : {$port} is now connected to us. <br/>"; //read input sentence from the incoming socket $input_sentence = socket_read($new_client, 1024000); $t1 = microtime(true); $seg_list = Jieba::cut($input_sentence); echo "cut cost " . (microtime(true) - $t1) . " seconds.<br/>"; echo '<br/>'; ob_flush(); flush(); $words = ""; for ($i = 0; $i < count($seg_list); $i++) { $words .= $seg_list[$i] . '/'; } // Display output back to client socket_write($new_client, $words); socket_close($new_client); $count++; } } }
#!/usr/bin/php <?php /** * demo_user_dict.php * * PHP version 5 * * @category PHP * @package /src/cmd/ * @author Fukuball Lin <*****@*****.**> * @license MIT Licence * @version GIT: <fukuball/jieba-php> * @link https://github.com/fukuball/jieba-php */ ini_set('memory_limit', '600M'); require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/MultiArray.php"; require_once dirname(dirname(__FILE__)) . "/vendor/multi-array/Factory/MultiArrayFactory.php"; require_once dirname(dirname(__FILE__)) . "/class/Jieba.php"; require_once dirname(dirname(__FILE__)) . "/class/Finalseg.php"; use Fukuball\Jieba; use Fukuball\Finalseg; Jieba::init(array('mode' => 'test', 'dict' => 'samll')); Finalseg::init(); $seg_list = Jieba::cut("李小福是创新办主任也是云计算方面的专家"); var_dump($seg_list); Jieba::loadUserDict(dirname(dirname(__FILE__)) . '/dict/user_dict.txt'); $seg_list = Jieba::cut("李小福是创新办主任也是云计算方面的专家"); var_dump($seg_list);