Created
June 21, 2012 07:21
-
-
Save barlino/2964376 to your computer and use it in GitHub Desktop.
divide the lyrics into sync and unsync lyrics
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| <?php | |
| /** | |
| 目的：分流歌詞成同步歌詞與非同步歌詞。 | |
| step1 將文件內容轉換為UTF-8編碼 | |
| step2 針對文件內容每一行，判斷是否存在timecode，若有則為同步歌詞，反之為非同步 | |
| step3 若unsync長度少於十行，應從sync中過濾出非同步歌詞 | |
| step4 儲存 | |
| */ | |
| require_once("encoding.php"); | |
| $list = array("640708.txt", | |
| "640709.txt", | |
| "640999.txt"); | |
| foreach ($list as $lyrics) { | |
| //step1 | |
| $content = file_get_contents($lyrics); | |
| $encoding = getFileEncoding($content); | |
| $utf8 = iconv($encoding, "UTF-8", $content); | |
| //step2 | |
| $lines = explode("\r\n", $utf8); | |
| $sync = array(); | |
| $sync_without_timecode = array(); | |
| $unsync = array(); | |
| $remainder = array(); | |
| $regexp = "/([[0-9a-z]+:[^]]+])/"; | |
| foreach ($lines as $line) { | |
| if (preg_match($regexp, $line)) { | |
| $sync []= $line; | |
| $sync_without_timecode []= preg_replace($regexp, "", $line); | |
| } else { | |
| $remainder []= $line; | |
| } | |
| } | |
| //step3 | |
| if (count($remainder) <= 10) { | |
| $unsync = $sync_without_timecode; | |
| } else { | |
| $unsync = $remainder; | |
| } | |
| //step4 | |
| file_put_contents(basename($lyrics) . "_sync.lrc", implode("\r\n", $sync)); | |
| file_put_contents(basename($lyrics) . "_unsync.lrc", implode("\r\n", $unsync)); | |
| echo "\n[SYNC] => \n" . file_get_contents(basename($lyrics) . "_sync.lrc"); | |
| echo "\n[UNSYNC] => \n" . file_get_contents(basename($lyrics) . "_unsync.lrc"); | |
| } | |
| ?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment