├── .gitignore
├── .travis.yml
├── tests
    ├── files
    │   └── SampleCaptions.srt
    ├── TimeTest.php
    ├── CaptionTest.php
    └── ParserTest.php
├── phpunit.xml
├── src
    └── SrtParser
    │   ├── Exceptions
    │       └── FileNotFoundException.php
    │   ├── Caption.php
    │   ├── Time.php
    │   └── Parser.php
├── composer.json
├── LICENSE
└── README.md


/.gitignore:
--------------------------------------------------------------------------------
1 | vendor/
2 | composer.lock
3 | .DS_Store
4 | .idea/


--------------------------------------------------------------------------------
/.travis.yml:
--------------------------------------------------------------------------------
1 | language: php
2 | 
3 | php:
4 |   - 7.0
5 |   - 7.1
6 | 
7 | install:
8 |   - composer install
9 | 


--------------------------------------------------------------------------------
/tests/files/SampleCaptions.srt:
--------------------------------------------------------------------------------
 1 | 1
 2 | 00:00:00,000 --> 00:00:03,000
 3 | Type Caption Text HereCar is backing up a little bit
 4 | 
 5 | 2
 6 | 00:00:03,000 --> 00:00:04,000
 7 | Yep there it goes
 8 | 
 9 | 3
10 | 00:00:04,000 --> 00:00:05,000
11 | Don't hit it!
12 | Testing Multi
13 | 


--------------------------------------------------------------------------------
/phpunit.xml:
--------------------------------------------------------------------------------
 1 | <phpunit 	bootstrap="vendor/autoload.php"			
 2 | 			colors="true"
 3 | 			convertErrorsToExceptions="true"
 4 | 			convertNoticesToExceptions="true"
 5 | 			convertWarningsToExceptions="true"
 6 | 			stopOnFailure="true">
 7 | 			<testsuites>
 8 | 				<testsuite name="Unit Tests">
 9 | 					<directory>tests</directory>
10 | 				</testsuite>
11 | 			</testsuites>
12 | </phpunit>


--------------------------------------------------------------------------------
/src/SrtParser/Exceptions/FileNotFoundException.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Benlipp\SrtParser\Exceptions;
 4 | 
 5 | 
 6 | use Throwable;
 7 | 
 8 | class FileNotFoundException extends \Exception
 9 | {
10 | 
11 |     public function __construct($file_location)
12 |     {
13 |         $message = "Could not find file: " . $file_location;
14 |         parent::__construct($message);
15 |     }
16 | }


--------------------------------------------------------------------------------
/composer.json:
--------------------------------------------------------------------------------
 1 | {
 2 |     "name": "benlipp/srt-parser",
 3 |     "description": "Easily Parse SRT Subtitle Files",
 4 |     "keywords": ["srt", "subtitles", "parser"],
 5 |     "license": "DBAD",
 6 |     "authors": [
 7 |         {
 8 |             "name": "Ben Lippincott",
 9 |             "email": "ben@benlipp.com"
10 |         }
11 |     ],
12 |     "type": "project",
13 |     "require": {
14 | 		"php": ">=7.0"
15 |     },
16 | 	"require-dev": {
17 | 		"phpunit/phpunit": "6.0.*"
18 |     },
19 | 	"autoload": {
20 |         "psr-4": {
21 |             "Benlipp\\SrtParser\\": "src/SrtParser/"
22 |         }
23 |     }
24 | }
25 | 


--------------------------------------------------------------------------------
/tests/TimeTest.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | use Benlipp\SrtParser\Time;
 4 | use PHPUnit\Framework\TestCase;
 5 | 
 6 | class TimeTest extends TestCase
 7 | {
 8 | 
 9 |     /**
10 |      * Check for possible syntax errors
11 |      */
12 |     public function testSyntax()
13 |     {
14 |         $var = new Time();
15 |         $this->assertTrue(is_object($var));
16 |         unset($var);
17 |     }
18 | 
19 |     /**
20 |      * @dataProvider timeProvider
21 |      */
22 |     public function testTimes($time, $expected)
23 |     {
24 |         $this->assertEquals(Time::get($time), $expected);
25 |     }
26 | 
27 |     public function timeProvider()
28 |     {
29 |         return [
30 |             ['00:00:00,000', 0],
31 |             ['00:04:30,000', 270],
32 |             ['01:20:30,999', 4830.999],
33 |         ];
34 |     }
35 | }


--------------------------------------------------------------------------------
/src/SrtParser/Caption.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Benlipp\SrtParser;
 4 | 
 5 | use Benlipp\SrtParser\Time;
 6 | 
 7 | class Caption
 8 | {
 9 | 
10 |     public $startTime;
11 |     public $endTime;
12 |     public $text;
13 | 
14 |     public function __construct($startTime = null, $endTime = null, $text = null)
15 |     {
16 |         $this->startTime = Time::get($startTime);
17 |         $this->endTime = Time::get($endTime);
18 |         $this->text = $text;
19 |     }
20 | 
21 |     /**
22 |      * @param mixed $text
23 |      * @return Caption
24 |      */
25 |     public function setText($text)
26 |     {
27 |         $this->text = $text;
28 | 
29 |         return $this;
30 |     }
31 | 
32 |     /**
33 |      * Returns an array with snake_case formatted keys for Laravel
34 |      * @return array
35 |      */
36 |     public function toArray()
37 |     {
38 |         return [
39 |             'start_time' => $this->startTime,
40 |             'end_time' => $this->endTime,
41 |             'text' => $this->text
42 |         ];
43 |     }
44 | }


--------------------------------------------------------------------------------
/src/SrtParser/Time.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Benlipp\SrtParser;
 4 | 
 5 | 
 6 | class Time
 7 | {
 8 | 
 9 |     public static function get($time)
10 |     {
11 |         if (isset($time)) {
12 |             $parsed = self::parseTime($time);
13 | 
14 |             return self::formatTime($parsed);
15 |         }
16 | 
17 |         return null;
18 |     }
19 | 
20 |     /**
21 |      * Get the formatted time.
22 |      * @param $times
23 |      * @return float
24 |      */
25 |     private static function formatTime($times)
26 |     {
27 |         $seconds = 0;
28 |         $seconds += $times['hours'] * 3600;
29 |         $seconds += $times['minutes'] * 60;
30 |         $seconds += $times['seconds'];
31 |         $milliseconds = $times['milliseconds'] / 1000;
32 | 
33 |         return $seconds + $milliseconds;
34 |     }
35 | 
36 |     private static function parseTime($time)
37 |     {
38 |         $time = explode(',', $time, 2);
39 |         $milliseconds = $time[1];
40 |         $splitTime = explode(':', $time[0], 3);
41 | 
42 |         $times = [];
43 |         $times['hours'] = (int)$splitTime[0];
44 |         $times['minutes'] = (int)$splitTime[1];
45 |         $times['seconds'] = (int)$splitTime[2];
46 |         $times['milliseconds'] = (int)$milliseconds;
47 | 
48 |         return $times;
49 |     }
50 | }


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
 1 | The code contained in this repository is owned wholly by LiveTech, LLC.
 2 | All code, unless otherwise noted, is Copyright (C) 2017 LiveTech, LLC.
 3 | 
 4 | 
 5 | DON'T BE A DICK PUBLIC LICENSE
 6 | 
 7 | Version 1, December 2009
 8 | 
 9 | Copyright (C) 2009 Philip Sturgeon email@philsturgeon.co.uk
10 | 
11 | Everyone is permitted to copy and distribute verbatim or modified copies of this license document, and changing it is allowed as long as the name is changed.
12 | 
13 | DON'T BE A DICK PUBLIC LICENSE TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
14 | 
15 | Do whatever you like with the original work, just don't be a dick.
16 | 
17 | Being a dick includes - but is not limited to - the following instances:
18 | 
19 | 1a. Outright copyright infringement - Don't just copy this and change the name.
20 | 1b. Selling the unmodified original with no work done what-so-ever, that's REALLY being a dick.
21 | 1c. Modifying the original work to contain hidden harmful content. That would make you a PROPER dick.
22 | 
23 | If you become rich through modifications, related works/services, or supporting the original work, share the love. Only a dick would make loads off this work and not buy the original works creator(s) a pint.
24 | 
25 | Code is provided with no warranty. Using somebody else's code and bitching when it goes wrong makes you a DONKEY dick. Fix the problem yourself. A non-dick would submit the fix back.
26 | 


--------------------------------------------------------------------------------
/tests/CaptionTest.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | use Benlipp\SrtParser\Caption;
 4 | use Benlipp\SrtParser\Time;
 5 | use PHPUnit\Framework\TestCase;
 6 | 
 7 | class CaptionTest extends TestCase
 8 | {
 9 | 
10 |     /**
11 |      * Check possible syntax errors
12 |      */
13 |     public function testSyntax()
14 |     {
15 |         $var = new Caption();
16 |         $this->assertTrue(is_object($var));
17 |         unset($var);
18 |     }
19 | 
20 |     public function testFormatting()
21 |     {
22 |         $startTime = "00:00:00,000";
23 |         $endTime = "00:00:05,000";
24 |         $text = "Caption";
25 | 
26 |         $expectedStart = Time::get($startTime);
27 |         $expectedEnd = Time::get($endTime);
28 | 
29 |         $caption = new Caption($startTime, $endTime, $text);
30 |         $this->assertEquals($expectedStart, $caption->startTime);
31 |         $this->assertEquals($expectedEnd, $caption->endTime);
32 |         $this->assertEquals($text, $caption->text);
33 |     }
34 | 
35 |     public function testToArray()
36 |     {
37 |         $startTime = "00:00:00,000";
38 |         $endTime = "00:00:05,000";
39 |         $text = "Caption";
40 | 
41 |         $expectedStart = Time::get($startTime);
42 |         $expectedEnd = Time::get($endTime);
43 | 
44 |         $caption = new Caption($startTime, $endTime, $text);
45 |         $captionArray = $caption->toArray();
46 |         $this->assertTrue(is_array($captionArray));
47 | 
48 |         $expectedArray = [
49 |             'start_time' => $expectedStart,
50 |             'end_time' => $expectedEnd,
51 |             'text' => $text
52 |         ];
53 |         $this->assertEquals($captionArray, $expectedArray);
54 |     }
55 | 
56 | }
57 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | SRT Parser
 2 | =
 3 | [![Build Status](https://travis-ci.org/benlipp/srt-parser.svg?branch=master)](https://travis-ci.org/benlipp/srt-parser)
 4 | 
 5 | A PHP library to parse SRT files.  
 6 | Built by Ben Lippincott for [LiveTech](http://www.liveteched.com/)
 7 | 
 8 | Installation / Requirements
 9 | -
10 | Run 
11 | `composer require "benlipp/srt-parser"`
12 | and let Composer do the work.
13 | 
14 | PHP 7+ is **REQUIRED**! This isn't amateur hour.  
15 | 
16 | Usage
17 | -
18 | Import the `Parser` class: `use Benlipp\SrtParser\Parser;`
19 | 
20 | Use it:
21 | ````
22 | $parser = new Parser();
23 | 
24 | $parser->loadFile('/path/to/srtfile.srt');
25 | 
26 | $captions = $parser->parse();
27 | ````
28 | or
29 | ````
30 | $parser = new Parser();
31 | 
32 | $parser->loadString($formatted_caption_input);
33 | 
34 | $captions = $parser->parse();
35 | ````
36 | 
37 | `parse()` returns an array of captions. Use them like so:
38 | 
39 | ````
40 | foreach($captions as $caption){
41 |     echo "Start Time: " . $caption->startTime;
42 |     echo "End Time: " . $caption->endTime;
43 |     echo "Text: " . $caption->text;
44 | }
45 | ````
46 | A caption can be returned as an array instead of an object, if you prefer. The array is `snake_case` for compatibility with Laravel's attributes.
47 | ````
48 | foreach($captions as $caption){
49 |     $caption = $caption->toArray();
50 |     echo "Start Time: " . $caption['start_time'];
51 |     echo "End Time: " . $caption['end_time'];
52 |     echo "Text: " . $caption['text'];
53 | }
54 | ````
55 | For Laravel usage with a model:
56 | ````
57 | $url = "https://youtu.be/dQw4w9WgXcQ";
58 | $video = new Video($url);
59 | foreach ($captions as $caption) {
60 |     $data = new VideoMetadata($caption->toArray());
61 |     $video->videoMetadata()->save($data);
62 | }
63 | ````
64 | 
65 | You can also chain the `parse()` method:
66 | ````
67 | $parser = new Parser();
68 | $captions = $parser->loadFile($srtPath)->parse();
69 | ````
70 | 
71 | Contributing
72 | -
73 | Run PHPUnit on your changes, pretty please. If you add a new feature, add tests for that feature.
74 | 


--------------------------------------------------------------------------------
/tests/ParserTest.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | use Benlipp\SrtParser\Exceptions\FileNotFoundException;
 4 | use Benlipp\SrtParser\Parser;
 5 | use PHPUnit\Framework\TestCase;
 6 | 
 7 | class ParserTest extends TestCase
 8 | {
 9 | 
10 |     /**
11 |      * Check for possible syntax errors
12 |      */
13 |     public function testSyntax()
14 |     {
15 |         $var = new Parser();
16 |         $this->assertTrue(is_object($var));
17 |         unset($var);
18 |     }
19 | 
20 |     public function testFileNotFound()
21 |     {
22 |         $parser = new Parser();
23 |         $this->expectException(FileNotFoundException::class);
24 |         $result = $parser->loadFile('NotARealFile');
25 |         $this->assertFalse(is_object($result));
26 |     }
27 | 
28 |     public function testReadFile()
29 |     {
30 |         $parser = new Parser();
31 |         $result = $parser->loadFile(__DIR__ . '/files/SampleCaptions.srt');
32 |         $this->assertTrue(is_object($result));
33 |     }
34 | 
35 |     public function testLoadString()
36 |     {
37 |         $captionString = file_get_contents(__DIR__ . '/files/SampleCaptions.srt');
38 |         $parser = new Parser();
39 |         $result = $parser->loadString($captionString);
40 |         $this->assertTrue(is_object($result));
41 |     }
42 | 
43 | 
44 |     public function testParse()
45 |     {
46 |         $testData = $this->captionData();
47 |         $parser = new Parser();
48 |         $parser->loadFile(__DIR__ . '/files/SampleCaptions.srt');
49 |         $captions = $parser->parse();
50 |         foreach ($captions as $key => $caption) {
51 |             $this->assertEquals($testData[$key]['startTime'], $caption->startTime);
52 |             $this->assertEquals($testData[$key]['endTime'], $caption->endTime);
53 |             $this->assertEquals($testData[$key]['text'], $caption->text);
54 |         }
55 |     }
56 | 
57 |     public function captionData()
58 |     {
59 |         return [
60 |             [
61 |                 'startTime' => 0,
62 |                 'endTime'   => 3,
63 |                 'text'      => "Type Caption Text HereCar is backing up a little bit"
64 |             ],
65 |             [
66 |                 'startTime' => 3,
67 |                 'endTime'   => 4,
68 |                 'text'      => "Yep there it goes"
69 |             ],
70 |             [
71 |                 'startTime' => 4,
72 |                 'endTime'   => 5,
73 |                 'text'      => "Don't hit it!\nTesting Multi"
74 |             ],
75 | 
76 |         ];
77 |     }
78 | }


--------------------------------------------------------------------------------
/src/SrtParser/Parser.php:
--------------------------------------------------------------------------------
 1 | <?php
 2 | 
 3 | namespace Benlipp\SrtParser;
 4 | 
 5 | use Benlipp\SrtParser\Exceptions\FileNotFoundException;
 6 | 
 7 | class Parser
 8 | {
 9 | 
10 |     private $data;
11 |     const SRT_REGEX_STRING = '/\d\r\n\r\n((?:.*\r\n)*)\r\n/';
12 | 
13 |     public function loadFile($file)
14 |     {
15 |         try {
16 |             $fileContents = file_get_contents($file);
17 |         } catch (\Exception $e) {
18 |             throw new FileNotFoundException($file);
19 |         }
20 |         $this->data = $fileContents;
21 | 
22 |         return $this;
23 |     }
24 |     
25 |     public function loadString($string)
26 |     {
27 |         $this->data = $string;
28 | 
29 |         return $this;
30 |     }
31 | 
32 |     public function parse()
33 |     {
34 |         $splitData = self::splitData($this->data);
35 |         $captions = self::buildCaptions($splitData);
36 | 
37 |         return $captions;
38 |     }
39 | 
40 |     /**
41 |      * split data into workable chunks
42 |      * @return array
43 |      */
44 |     private static function splitData($data)
45 |     {
46 |         //find digits followed by a single line break and timestamps
47 |         $sections = preg_split('/\d+(?:\r\n|\r|\n)(?=(?:\d\d:\d\d:\d\d,\d\d\d)\s-->\s(?:\d\d:\d\d:\d\d,\d\d\d))/m', $data,-1,PREG_SPLIT_NO_EMPTY);
48 |         $matches = [];
49 |         foreach ($sections as $section) {
50 |             //cleans out control characters, borrowed from https://stackoverflow.com/a/23066553
51 |             $section = preg_replace('/[^\PC\s]/u', '', $section);
52 |             if(trim($section) == '') continue;
53 |             $matches[] = preg_split('/(\r\n|\r|\n)/', $section, 2,PREG_SPLIT_NO_EMPTY);
54 |         }
55 |         return $matches;
56 |     }
57 | 
58 |     private static function buildCaptions($matches)
59 |     {
60 |         $captions = [];
61 |         foreach ($matches as $match) {
62 |             $times = self::timeMatch($match[0]);
63 |             $text = self::textMatch($match[1]);
64 | 
65 |             $captions[] = new Caption($times['start_time'], $times['end_time'], $text);
66 |         }
67 | 
68 |         return $captions;
69 |     }
70 | 
71 |     private static function timeMatch($timeString)
72 |     {
73 |         $matches = [];
74 |         preg_match_all('/(\d\d:\d\d:\d\d,\d\d\d)\s-->\s(\d\d:\d\d:\d\d,\d\d\d)/', $timeString, $matches,
75 |             PREG_SET_ORDER);
76 |         $time = $matches[0];
77 | 
78 |         return [
79 |             'start_time' => $time[1],
80 |             'end_time'   => $time[2]
81 |         ];
82 |     }
83 | 
84 |     private static function textMatch($textString)
85 |     {
86 |         $text = rtrim($textString);
87 |         $text = str_replace("\r\n", "\n", $text);
88 | 
89 |         return $text;
90 |     }
91 | }
92 | 


--------------------------------------------------------------------------------