将聊天记录拆成对应的每句话的role,time,message的格式
<?PHP $data = '[S][04:39:35] [#1][V][04:39:35] 不忈: Hello[V][04:39:35] 不忈: Hello[V][04:39:35] 不忈: Hello[V][04:40:11] 不忈: 你好[A][04:40:38] agent01: 嗯[S][04:40:54] [#8]给你[S][04:40:57] agent03 [#6][S][04:41:00] agent01 [#7][A][04:41:02] agent03: hade [V][04:41:06] 不忈: 一[A][04:41:10] agent03: en [S][04:41:20] [#8]-[S][04:41:22] agent01 [#6][S][04:41:24] agent03 [#7][A][04:41:27] agent01: 32423[V][04:41:29] 不忈: 。[S][04:41:31] [#2]agent01'; preg_match_all('/(\[S\](.*?))(?=\[[SVA]\])|(\[S\](.*?))$|(\[V\](.*?))(?=\[[SVA]\])|(\[V\](.*?))$|(\[A\](.*?))(?=\[[SVA]\])|(\[A\](.*?))$/',$data,$matches); $data1 = $matches[0]; foreach($matches[0] as $k => $v){ preg_match_all('/\[\w\]|\[\d{2}:\d{2}:\d{2}\]/',$v,$vMatch); $res[$k]['role'] = $vMatch[0][0]; $res[$k]['time'] = $vMatch[0][1]; $res[$k]['message'] = preg_filter('/\[(S|A|V)\]|\[\d{2}:\d{2}:\d{2}\]/','',$v); } print_r($res);exit;
拆分出来后:
Array ( [0] => Array ( [role] => [S] [time] => [04:39:35] [message] => [#1] ) [1] => Array ( [role] => [V] [time] => [04:39:35] [message] => 不忈: Hello ) [2] => Array ( [role] => [V] [time] => [04:39:35] [message] => 不忈: Hello ) [3] => Array ( [role] => [V] [time] => [04:39:35] [message] => 不忈: Hello ) [4] => Array ( [role] => [V] [time] => [04:40:11] [message] => 不忈: 你好 ) [5] => Array ( [role] => [A] [time] => [04:40:38] [message] => agent01: 嗯 ) [6] => Array ( [role] => [S] [time] => [04:40:54] [message] => [#8]给你 ) [7] => Array ( [role] => [S] [time] => [04:40:57] [message] => agent03 [#6] ) [8] => Array ( [role] => [S] [time] => [04:41:00] [message] => agent01 [#7] ) [9] => Array ( [role] => [A] [time] => [04:41:02] [message] => agent03: hade ) [10] => Array ( [role] => [V] [time] => [04:41:06] [message] => 不忈: 一 ) [11] => Array ( [role] => [A] [time] => [04:41:10] [message] => agent03: en ) [12] => Array ( [role] => [S] [time] => [04:41:20] [message] => [#8]- ) [13] => Array ( [role] => [S] [time] => [04:41:22] [message] => agent01 [#6] ) [14] => Array ( [role] => [S] [time] => [04:41:24] [message] => agent03 [#7] ) [15] => Array ( [role] => [A] [time] => [04:41:27] [message] => agent01: 32423 ) [16] => Array ( [role] => [V] [time] => [04:41:29] [message] => 不忈: 。 ) [17] => Array ( [role] => [S] [time] => [04:41:31] [message] => [#2]agent01 ) )原文链接:/regex/358367.html