Last active
August 21, 2016 13:58
-
-
Save withmorten/11b22a271c84ced9231e80be5ae243d3 to your computer and use it in GitHub Desktop.
merges duplicate lines in a subtitle file that are meant to be one with proper timings
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 | |
define('SRT_STATE_SUBNUMBER', 0); | |
define('SRT_STATE_TIME', 1); | |
define('SRT_STATE_TEXT', 2); | |
define('SRT_STATE_BLANK', 3); | |
function parseSrt($lines) { | |
$subs = array(); | |
$state = SRT_STATE_SUBNUMBER; | |
$subNum = 0; | |
$subText = ''; | |
$subTime = ''; | |
foreach($lines as $line) { | |
switch($state) { | |
case SRT_STATE_SUBNUMBER: | |
$subNum = trim($line); | |
$state = SRT_STATE_TIME; | |
break; | |
case SRT_STATE_TIME: | |
$subTime = trim($line); | |
$state = SRT_STATE_TEXT; | |
break; | |
case SRT_STATE_TEXT: | |
if (trim($line) == '') { | |
$sub = new stdClass; | |
$sub->number = $subNum; | |
list($sub->startTime, $sub->stopTime) = explode(' --> ', $subTime); | |
$sub->text = $subText; | |
$subText = ''; | |
$state = SRT_STATE_SUBNUMBER; | |
$subs[] = $sub; | |
} else { | |
$subText .= $line; | |
} | |
break; | |
} | |
} | |
return $subs; | |
} | |
$input = file($argv[1]); | |
$input_srt = parseSrt($input); | |
$input_lines = count($input_srt); | |
$sametext = 0; | |
$offset = 0; | |
for($i = 0; $i < $input_lines; $i++) { | |
if($i+1 < $input_lines) { | |
if($input_srt[$i]->text == $input_srt[$i+1]->text) { | |
$sametext = 1; | |
$offset++; | |
} else { | |
$sametext = 0; | |
} | |
} | |
if($sametext === 0) { | |
echo $input_srt[$i]->number."\r\n"; | |
echo $input_srt[$i-$offset]->startTime." --> ".$input_srt[$i]->stopTime."\r\n"; | |
echo $input_srt[$i]->text."\r\n"; | |
$offset = 0; | |
} | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment