webvtt 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +4 -0
- data/Gemfile +6 -0
- data/Guardfile +9 -0
- data/LICENSE +20 -0
- data/README.md +58 -0
- data/Rakefile +12 -0
- data/lib/webvtt/cue.rb +18 -0
- data/lib/webvtt/file.rb +72 -0
- data/lib/webvtt/version.rb +4 -0
- data/lib/webvtt.rb +9 -0
- data/test/cue_test.rb +27 -0
- data/test/examples/tolson.vtt +10 -0
- data/test/file_test.rb +64 -0
- data/test/test_helper.rb +5 -0
- data/webvtt.gemspec +22 -0
- metadata +93 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Guardfile
ADDED
@@ -0,0 +1,9 @@
|
|
1
|
+
# A sample Guardfile
|
2
|
+
# More info at https://github.com/guard/guard#readme
|
3
|
+
|
4
|
+
guard :test do
|
5
|
+
watch(%r{^lib/webvtt/(.+)\.rb$}) { |m| "test/#{m[1]}_test.rb" }
|
6
|
+
watch(%r{^test/.+_test\.rb$})
|
7
|
+
watch('test/test_helper.rb') { "test" }
|
8
|
+
callback(:run_on_changes_begin) { puts "\n", '='*70, "\n" }
|
9
|
+
end
|
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright 2012 North Carolina State University
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
# WEBVTT FILE parser for Ruby
|
2
|
+
|
3
|
+
Parse WebVTT files with Ruby.
|
4
|
+
The main goal is just to extract the text out with start and end times.
|
5
|
+
The parsing does not conform the [WebVTT specification](http://dev.w3.org/html5/webvtt/) at this point.
|
6
|
+
|
7
|
+
|
8
|
+
# Story
|
9
|
+
|
10
|
+
We were creating WebVTT files to enable closed captions for HTML5 video.
|
11
|
+
We wanted to reuse this work to embed the transcript in the video player
|
12
|
+
page to increase SEO and allow for jumping to sections of the video.
|
13
|
+
|
14
|
+
# Install
|
15
|
+
|
16
|
+
```
|
17
|
+
git clone
|
18
|
+
rake build
|
19
|
+
gem install pkg/webvtt.x.x.x.gem
|
20
|
+
```
|
21
|
+
|
22
|
+
# Usage
|
23
|
+
|
24
|
+
Based on this WebVTT:
|
25
|
+
|
26
|
+
```
|
27
|
+
WEBVTT
|
28
|
+
|
29
|
+
1
|
30
|
+
00:00:00 --> 00:00:03.000 D:vertical A:start
|
31
|
+
I grew up in Eastern North Carolina, <b>Edgecombe</b> County
|
32
|
+
|
33
|
+
2
|
34
|
+
00:00:03.300 --> 00:00:07.800 A:start
|
35
|
+
on a tobacco and dairy farm outside of Tarboro.
|
36
|
+
```
|
37
|
+
|
38
|
+
You can do the following:
|
39
|
+
|
40
|
+
|
41
|
+
```
|
42
|
+
require 'webvtt'
|
43
|
+
vtt = Webvtt::File.new('path/to/file.vtt')
|
44
|
+
vtt.cues.class #=> Webvtt::Cue
|
45
|
+
vtt.cues[0].start #=> '00:00:00'
|
46
|
+
vtt.cues[0].end #=> '00:00:03.000'
|
47
|
+
vtt.cues[0].identifier #=> '1'
|
48
|
+
vtt.cues[0].settings #=> 'D:vertical A:start'
|
49
|
+
vtt.cues[0].text #=> 'I grew up in Eastern North Carolina, <b>Edgecombe</b> County'
|
50
|
+
```
|
51
|
+
|
52
|
+
# Author
|
53
|
+
|
54
|
+
Jason Ronallo
|
55
|
+
|
56
|
+
# License
|
57
|
+
|
58
|
+
See LICENSE
|
data/Rakefile
ADDED
data/lib/webvtt/cue.rb
ADDED
@@ -0,0 +1,18 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
module Webvtt
|
3
|
+
class Cue
|
4
|
+
attr_accessor :identifier, :start, :end, :settings, :text
|
5
|
+
def initialize(opts={})
|
6
|
+
if !opts.empty?
|
7
|
+
@identifier = opts[:identifier]
|
8
|
+
@text = opts[:text]
|
9
|
+
cue_parts = opts[:cue_line].split('-->')
|
10
|
+
@start = cue_parts.first.strip
|
11
|
+
remaining_cue_parts = cue_parts.last.split(" ")
|
12
|
+
@end = remaining_cue_parts.shift.strip
|
13
|
+
@settings = remaining_cue_parts.join(' ')
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
data/lib/webvtt/file.rb
ADDED
@@ -0,0 +1,72 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
module Webvtt
|
3
|
+
class File
|
4
|
+
|
5
|
+
attr_accessor :file, :cues
|
6
|
+
|
7
|
+
def initialize(input_file)
|
8
|
+
if input_file.is_a?(String)
|
9
|
+
input_file = input_file.encode('UTF-8')
|
10
|
+
if ::File.exist?(input_file)
|
11
|
+
@file = ::File.read(input_file)
|
12
|
+
else
|
13
|
+
@file = input_file
|
14
|
+
end
|
15
|
+
elsif input_file.is_a?(::File)
|
16
|
+
@file = input_file.read
|
17
|
+
else
|
18
|
+
raise
|
19
|
+
end
|
20
|
+
@cues = []
|
21
|
+
parse
|
22
|
+
end
|
23
|
+
|
24
|
+
def parse
|
25
|
+
remove_bom
|
26
|
+
if !webvtt_line?(file.lines.first)
|
27
|
+
raise Webvtt::MalformedError
|
28
|
+
end
|
29
|
+
collected_lines = []
|
30
|
+
file_lines = file.dup.lines.to_a
|
31
|
+
|
32
|
+
file_lines.each_with_index do |line,index|
|
33
|
+
line.chomp!
|
34
|
+
|
35
|
+
next if webvtt_line?(line)
|
36
|
+
if line.empty?
|
37
|
+
add_a_cue(collected_lines) if !collected_lines.empty?
|
38
|
+
collected_lines = []
|
39
|
+
elsif !line.empty? and file_lines.length == (index + 1)
|
40
|
+
collected_lines << line
|
41
|
+
add_a_cue(collected_lines)
|
42
|
+
else
|
43
|
+
collected_lines << line
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
def webvtt_line?(line)
|
49
|
+
line[0,6] == 'WEBVTT'
|
50
|
+
end
|
51
|
+
|
52
|
+
def remove_bom
|
53
|
+
file.gsub!("\uFEFF", '')
|
54
|
+
end
|
55
|
+
|
56
|
+
private
|
57
|
+
|
58
|
+
def add_a_cue(collected_lines)
|
59
|
+
cue_opts = {}
|
60
|
+
if collected_lines.first.include?('-->')
|
61
|
+
cue_opts[:identifier] = nil
|
62
|
+
cue_opts[:cue_line] = collected_lines.first
|
63
|
+
elsif collected_lines[1].include?('-->')
|
64
|
+
cue_opts[:identifier] = collected_lines.first
|
65
|
+
cue_opts[:cue_line] = collected_lines[1]
|
66
|
+
end
|
67
|
+
cue_opts[:text] = collected_lines[2..-1].join('')
|
68
|
+
cues << Cue.new(cue_opts)
|
69
|
+
end
|
70
|
+
|
71
|
+
end
|
72
|
+
end
|
data/lib/webvtt.rb
ADDED
data/test/cue_test.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
# -*- encoding : utf-8 -*-
|
2
|
+
require 'test_helper'
|
3
|
+
|
4
|
+
class WebvttCueTest < Test::Unit::TestCase
|
5
|
+
test "should have a Cue class" do
|
6
|
+
assert Webvtt::Cue
|
7
|
+
end
|
8
|
+
|
9
|
+
test "should respond to identifier, start, end, settings, and text" do
|
10
|
+
cue = Webvtt::Cue.new
|
11
|
+
assert cue.respond_to?(:identifier)
|
12
|
+
assert cue.respond_to?(:start)
|
13
|
+
assert cue.respond_to?(:end)
|
14
|
+
assert cue.respond_to?(:settings)
|
15
|
+
assert cue.respond_to?(:text)
|
16
|
+
end
|
17
|
+
|
18
|
+
test "parses an individual cue" do
|
19
|
+
cue = Webvtt::Cue.new(:identifier => "1", :cue_line => "00:00:00 --> 00:00:03.000 D:vertical A:start", :text => "I grew up in Eastern North Carolina, <b>Edgecombe</b> County")
|
20
|
+
assert_equal '1', cue.identifier
|
21
|
+
assert_equal '00:00:00', cue.start
|
22
|
+
assert_equal '00:00:03.000', cue.end
|
23
|
+
assert_equal 'D:vertical A:start', cue.settings
|
24
|
+
assert_equal 'I grew up in Eastern North Carolina, <b>Edgecombe</b> County', cue.text
|
25
|
+
end
|
26
|
+
|
27
|
+
end
|
data/test/file_test.rb
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
|
3
|
+
class WebvttFileTest < Test::Unit::TestCase
|
4
|
+
|
5
|
+
setup do
|
6
|
+
path = File.expand_path(File.dirname(__FILE__))
|
7
|
+
@file_path = File.join(path, 'examples', 'tolson.vtt')
|
8
|
+
@vtt = Webvtt::File.new(@file_path)
|
9
|
+
end
|
10
|
+
|
11
|
+
test "should have a File class" do
|
12
|
+
assert Webvtt::File
|
13
|
+
end
|
14
|
+
|
15
|
+
test "should create a new File with file path" do
|
16
|
+
assert Webvtt::File.new(@file_path)
|
17
|
+
end
|
18
|
+
|
19
|
+
test "should create a new File with a File object" do
|
20
|
+
file = File.open(@file_path)
|
21
|
+
assert Webvtt::File.new(file)
|
22
|
+
end
|
23
|
+
|
24
|
+
test "should create a new File with a String as the contents of the WEBVTT file" do
|
25
|
+
file = "WEBVTT FILE\n\n1\n00:00:00 --> 00:00:05\nIt was a frightening time but it also was a time of great student intrigue"
|
26
|
+
assert Webvtt::File.new(file)
|
27
|
+
end
|
28
|
+
|
29
|
+
test "should handle files with a BOM and different line endings" do
|
30
|
+
file = "\uFEFFWEBVTT FILE\r\n\r\n1\r\n00:00:00 --> 00:00:05\r\nIt was a frightening time but it also was a time of great student intrigue"
|
31
|
+
assert Webvtt::File.new(file)
|
32
|
+
end
|
33
|
+
|
34
|
+
test "should have a file method" do
|
35
|
+
assert @vtt.respond_to?(:file)
|
36
|
+
end
|
37
|
+
|
38
|
+
test "should have a file method with the contents of the original file" do
|
39
|
+
assert @vtt.file.include?('WEBVTT')
|
40
|
+
end
|
41
|
+
|
42
|
+
test "should have a list of cues" do
|
43
|
+
assert @vtt.respond_to?(:cues)
|
44
|
+
assert @vtt.cues.is_a?(Array)
|
45
|
+
end
|
46
|
+
|
47
|
+
test "should have 2 cues" do
|
48
|
+
assert_equal 2, @vtt.cues.length
|
49
|
+
end
|
50
|
+
|
51
|
+
test "first cue should be correct" do
|
52
|
+
first_cue = @vtt.cues.first
|
53
|
+
assert_equal "1", first_cue.identifier
|
54
|
+
assert_equal "00:00:00", first_cue.start
|
55
|
+
assert_equal "00:00:03.000", first_cue.end
|
56
|
+
assert_equal "D:vertical A:start", first_cue.settings
|
57
|
+
assert_equal "I grew up in Eastern North Carolina, <b>Edgecombe</b> County", first_cue.text
|
58
|
+
end
|
59
|
+
|
60
|
+
test "multiline cue text should be correct" do
|
61
|
+
assert_equal "on a tobacco and dairy farm outside of Tarboro.", @vtt.cues.last.text
|
62
|
+
end
|
63
|
+
|
64
|
+
end
|
data/test/test_helper.rb
ADDED
data/webvtt.gemspec
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "webvtt/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = "webvtt"
|
7
|
+
s.version = Webvtt::VERSION
|
8
|
+
s.authors = ["Jason Ronallo"]
|
9
|
+
s.email = ["jronallo@gmail.com"]
|
10
|
+
s.homepage = ""
|
11
|
+
s.summary = %q{WEBVTT file parser in Ruby}
|
12
|
+
s.description = %q{WEBVTT file parser in Ruby}
|
13
|
+
|
14
|
+
s.rubyforge_project = "webvtt"
|
15
|
+
|
16
|
+
s.files = `git ls-files`.split("\n")
|
17
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
18
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
19
|
+
s.require_paths = ["lib"]
|
20
|
+
s.add_development_dependency "test-unit", [">= 2.5.0"]
|
21
|
+
s.add_development_dependency "guard-test", [">= 0.5.0"]
|
22
|
+
end
|
metadata
ADDED
@@ -0,0 +1,93 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: webvtt
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Jason Ronallo
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2012-12-09 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: test-unit
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
none: false
|
18
|
+
requirements:
|
19
|
+
- - ! '>='
|
20
|
+
- !ruby/object:Gem::Version
|
21
|
+
version: 2.5.0
|
22
|
+
type: :development
|
23
|
+
prerelease: false
|
24
|
+
version_requirements: !ruby/object:Gem::Requirement
|
25
|
+
none: false
|
26
|
+
requirements:
|
27
|
+
- - ! '>='
|
28
|
+
- !ruby/object:Gem::Version
|
29
|
+
version: 2.5.0
|
30
|
+
- !ruby/object:Gem::Dependency
|
31
|
+
name: guard-test
|
32
|
+
requirement: !ruby/object:Gem::Requirement
|
33
|
+
none: false
|
34
|
+
requirements:
|
35
|
+
- - ! '>='
|
36
|
+
- !ruby/object:Gem::Version
|
37
|
+
version: 0.5.0
|
38
|
+
type: :development
|
39
|
+
prerelease: false
|
40
|
+
version_requirements: !ruby/object:Gem::Requirement
|
41
|
+
none: false
|
42
|
+
requirements:
|
43
|
+
- - ! '>='
|
44
|
+
- !ruby/object:Gem::Version
|
45
|
+
version: 0.5.0
|
46
|
+
description: WEBVTT file parser in Ruby
|
47
|
+
email:
|
48
|
+
- jronallo@gmail.com
|
49
|
+
executables: []
|
50
|
+
extensions: []
|
51
|
+
extra_rdoc_files: []
|
52
|
+
files:
|
53
|
+
- .gitignore
|
54
|
+
- Gemfile
|
55
|
+
- Guardfile
|
56
|
+
- LICENSE
|
57
|
+
- README.md
|
58
|
+
- Rakefile
|
59
|
+
- lib/webvtt.rb
|
60
|
+
- lib/webvtt/cue.rb
|
61
|
+
- lib/webvtt/file.rb
|
62
|
+
- lib/webvtt/version.rb
|
63
|
+
- test/cue_test.rb
|
64
|
+
- test/examples/tolson.vtt
|
65
|
+
- test/file_test.rb
|
66
|
+
- test/test_helper.rb
|
67
|
+
- webvtt.gemspec
|
68
|
+
homepage: ''
|
69
|
+
licenses: []
|
70
|
+
post_install_message:
|
71
|
+
rdoc_options: []
|
72
|
+
require_paths:
|
73
|
+
- lib
|
74
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
75
|
+
none: false
|
76
|
+
requirements:
|
77
|
+
- - ! '>='
|
78
|
+
- !ruby/object:Gem::Version
|
79
|
+
version: '0'
|
80
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
81
|
+
none: false
|
82
|
+
requirements:
|
83
|
+
- - ! '>='
|
84
|
+
- !ruby/object:Gem::Version
|
85
|
+
version: '0'
|
86
|
+
requirements: []
|
87
|
+
rubyforge_project: webvtt
|
88
|
+
rubygems_version: 1.8.24
|
89
|
+
signing_key:
|
90
|
+
specification_version: 3
|
91
|
+
summary: WEBVTT file parser in Ruby
|
92
|
+
test_files: []
|
93
|
+
has_rdoc:
|