public function testFinalsegCut() { $case_array = array("怜香惜", "玉", "也", "得", "要", "看", "对象", "啊"); $seg_list = Finalseg::cut("怜香惜玉也得要看对象啊!"); $this->assertEquals($case_array, $seg_list); }
/** * Static method __cutDAG * * @param string $sentence # input sentence * @param array $options # other options * * @return array $words */ public static function __cutDAG($sentence, $options = array()) { $defaults = array('mode' => 'default'); $options = array_merge($defaults, $options); $words = array(); $N = mb_strlen($sentence, 'UTF-8'); $DAG = self::getDAG($sentence); self::calc($sentence, $DAG); $x = 0; $buf = ''; while ($x < $N) { $current_route_keys = array_keys(self::$route[$x]); $y = $current_route_keys[0] + 1; $l_word = mb_substr($sentence, $x, $y - $x, 'UTF-8'); if ($y - $x == 1) { $buf = $buf . $l_word; } else { if (mb_strlen($buf, 'UTF-8') > 0) { if (mb_strlen($buf, 'UTF-8') == 1) { array_push($words, $buf); $buf = ''; } else { $regognized = Finalseg::cut($buf); foreach ($regognized as $key => $word) { array_push($words, $word); } $buf = ''; } } array_push($words, $l_word); } $x = $y; } if (mb_strlen($buf, 'UTF-8') > 0) { if (mb_strlen($buf, 'UTF-8') == 1) { array_push($words, $buf); } else { $regognized = Finalseg::cut($buf); foreach ($regognized as $key => $word) { array_push($words, $word); } } } return $words; }