webvtt-ruby 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 750601959beae93666af734645757e22a9f8fe2d
-  data.tar.gz: ce85964a436d8459dc409503ff61e8ae12ba33b3
+SHA256:
+  metadata.gz: f4334c8feffaab4ed2438a52554ce17ebd2bd0152622adbd8445c7de99e6e14d
+  data.tar.gz: 6de8052ac1d531bb77630c086425c3f2640295d510cd87546d357a2791d06695
 SHA512:
-  metadata.gz: 9d4c6238c8c843bb83955db872f2b7ad51281e64074e8c1beecb30e9fb1ef930e4f0344d1db7e4243c63f5625b6c575d3d55947d8c8555887a2fcf19ea380081
-  data.tar.gz: f250cac70bf7c1a534f518ca013fe04c8a7d422686d8cb7439ff3621b4410d35b2aab69f7ed3456c2ed7a8db25c8ca2c0e0dd4ce032297e2eedfeddde48680f4
+  metadata.gz: 7cba26291e3f92b889ff2d03246873d44f07c12890dec24201bd4e13e61b286a0a2af4c22e207c37ff976d3056cd38381bd470be9894bf3ebccd3043fdfac0ab
+  data.tar.gz: 7350a1b409e9178eea25526bb0fb2d7167b7348fb4fc19bc96a3edcf353f6aa4ae3c86f3ea31ac988925604da6def8ce621f636d73b66dd02656c0d945fb13a7

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    webvtt-ruby (0.2.5)
+    webvtt-ruby (0.3.0)
 
 GEM
   remote: https://rubygems.org/

data/README.md

@@ -116,6 +116,6 @@ Usage: bin/webvtt-segmenter [--arg]
 
 **Bruno Celeste**
 
-* http://www.heywatchencoding.com
-* bruno@heywatch.com
-* [@sadikzzz](http://twitter.com/sadikzzz)
+* http://coconut.co
+* bruno@coconut.co
+* [@brunoceleste](http://twitter.com/brunoceleste)

data/lib/{parser.rb → webvtt/parser.rb}

@@ -4,14 +4,20 @@ module WebVTT
     File.new(file)
   end
 
+  def self.from_blob(content)
+    Blob.new(content)
+  end
+
   def self.convert_from_srt(srt_file, output=nil)
-    if !::File.exists?(srt_file)
+    if !::File.exist?(srt_file)
       raise InputError, "SRT file not found"
     end
 
     srt = ::File.read(srt_file)
     output ||= srt_file.gsub(".srt", ".vtt")
 
+    # normalize timestamps in srt
+    srt.gsub!(/(:|^)(\d)(,|:)/, '\10\2\3')
     # convert timestamps and save the file
     srt.gsub!(/([0-9]{2}:[0-9]{2}:[0-9]{2})([,])([0-9]{3})/, '\1.\3')
     # normalize new line character
@@ -23,19 +29,20 @@ module WebVTT
     return File.new(output)
   end
 
-  class File
-    attr_reader :header, :path, :filename
+  class Blob
+    attr_reader :header
     attr_accessor :cues
 
-    def initialize(webvtt_file)
-      if !::File.exists?(webvtt_file)
-        raise InputError, "WebVTT file not found"
-      end
+    def initialize(content = nil)
+      @cues = []
 
-      @path = webvtt_file
-      @filename = ::File.basename(@path)
-      @content = ::File.read(webvtt_file).gsub("\r\n", "\n") # normalizing new line character
-      parse
+      if content
+        parse(
+          content.gsub("\r\n", "\n").gsub("\r","\n") # normalizing new line character
+        )
+      else
+        @header = 'WEBVTT'
+      end
     end
 
     def to_webvtt
@@ -50,20 +57,12 @@ module WebVTT
       @cues.last.end_in_sec - @cues.first.start_in_sec
     end
 
-    def save(output=nil)
-      output ||= @path.gsub(".srt", ".vtt")
-
-      ::File.open(output, "w") do |f|
-        f.write(to_webvtt)
-      end
-      return output
-    end
-
-    def parse
+    def parse(content)
       # remove bom first
-      @content.gsub!("\uFEFF", '')
+      content.gsub!("\uFEFF", '')
+
+      cues = content.split(/\n\n+/)
 
-      cues = @content.split("\n\n")
       @header = cues.shift
       header_lines = @header.split("\n").map(&:strip)
       if (header_lines[0] =~ /^WEBVTT/).nil?
@@ -72,7 +71,7 @@ module WebVTT
 
       @cues = []
       cues.each do |cue|
-        cue_parsed = Cue.new(cue.strip)
+        cue_parsed = Cue.parse(cue.strip)
         if !cue_parsed.text.nil?
           @cues << cue_parsed
         end
@@ -81,12 +80,41 @@ module WebVTT
     end
   end
 
+  class File < Blob
+    attr_reader :path, :filename
+
+    def initialize(webvtt_file)
+      if !::File.exist?(webvtt_file)
+        raise InputError, "WebVTT file not found"
+      end
+
+      @path = webvtt_file
+      @filename = ::File.basename(@path)
+      super(::File.read(webvtt_file))
+    end
+
+    def save(output=nil)
+      output ||= @path.gsub(".srt", ".vtt")
+
+      ::File.open(output, "w") do |f|
+        f.write(to_webvtt)
+      end
+      return output
+    end
+  end
+
   class Cue
     attr_accessor :identifier, :start, :end, :style, :text
 
-    def initialize(cue)
+    def initialize(cue = nil)
       @content = cue
-      parse
+      @style = {}
+    end
+
+    def self.parse(cue)
+      cue = Cue.new(cue)
+      cue.parse
+      return cue
     end
 
     def to_webvtt
@@ -136,10 +164,14 @@ module WebVTT
         lines.shift
       end
 
-      if lines[0].match(/([0-9]{2}:[0-9]{2}:[0-9]{2}\.[0-9]{3}) -+> ([0-9]{2}:[0-9]{2}:[0-9]{2}\.[0-9]{3})(.*)/)
+      if lines.empty?
+        return
+      end
+
+      if lines[0].match(/(([0-9]{2}:)?[0-9]{2}:[0-9]{2}\.[0-9]{3}) -+> (([0-9]{2}:)?[0-9]{2}:[0-9]{2}\.[0-9]{3})(.*)/)
         @start = Timestamp.new $1
-        @end = Timestamp.new $2
-        @style = Hash[$3.strip.split(" ").map{|s| s.split(":").map(&:strip) }]
+        @end = Timestamp.new $3
+        @style = Hash[$5.strip.split(" ").map{|s| s.split(":").map(&:strip) }]
       end
       @text = lines[1..-1].join("\n")
     end

data/lib/{segmenter.rb → webvtt/segmenter.rb}

@@ -1,3 +1,5 @@
+require 'fileutils'
+
 module WebVTT
 
   def self.segment(input, options={})
@@ -25,6 +27,25 @@ module WebVTT
       @options[:length] ||= 10
       @options[:output] ||= "fileSequence-%05d.vtt"
       @options[:playlist] ||= "prog_index.m3u8"
+
+      # a dirty hack to check if output and playlist are ending with / (indicating a directory) and if so use the default filename and playlist name and create directory which is required.
+
+      if @options[:output].end_with?('/')
+        @options[:output] = "#{@options[:output]}fileSequence-%05d.vtt"
+      end
+      if @options[:playlist].end_with?('/')
+        @options[:playlist] = "#{@options[:playlist]}prog_index.m3u8"
+      end
+
+      output_dirname = ::File.dirname(@options[:output])
+      playlist_dirname = ::File.dirname(@options[:playlist])
+
+      unless ::File.directory?(output_dirname)
+        ::FileUtils.mkdir_p(output_dirname)
+      end
+      unless ::File.directory?(playlist_dirname)
+        ::FileUtils.mkdir_p(playlist_dirname)
+      end
     end
 
     def find_segment_files(cue)
@@ -123,4 +144,4 @@ module WebVTT
       return filenames.map{|f| File.new(f) }
     end
   end
-end
+end

data/lib/webvtt.rb

@@ -9,5 +9,5 @@ module WebVTT
   class InputError < RuntimeError; end
 end
 
-require "parser"
-require "segmenter"
+require "webvtt/parser"
+require "webvtt/segmenter"

data/tests/parser.rb

@@ -20,6 +20,12 @@ class ParserTest < Minitest::Test
     }
   end
 
+  def test_can_create_empty_webvtt
+    webvtt = WebVTT::Blob.new
+    assert_equal 'WEBVTT', webvtt.header
+    assert_equal [], webvtt.cues
+  end
+
   def test_list_cues
     webvtt = WebVTT.read("tests/subtitles/test.vtt")
     assert_instance_of Array, webvtt.cues
@@ -43,6 +49,16 @@ class ParserTest < Minitest::Test
     assert_equal "English subtitle 15 -Forced- (00:00:27.000)\nline:75%", cue.text
   end
 
+  def test_cue_non_hours
+    webvtt = WebVTT.read("tests/subtitles/test_mmss_format.vtt")
+    cue = webvtt.cues[0]
+    assert_equal "00:00:29.000", cue.start.to_s
+    assert_equal "00:00:31.000", cue.end.to_s
+    assert_instance_of Hash, cue.style
+    assert_equal "75%", cue.style["line"]
+    assert_equal "English subtitle 15 -Forced- (00:00:27.000)\nline:75%", cue.text
+  end
+
   def test_cue_identifier
     webvtt = WebVTT.read("tests/subtitles/test.vtt")
     cue = webvtt.cues[1]
@@ -54,6 +70,11 @@ class ParserTest < Minitest::Test
     assert_equal "English subtitle 16 -Unforced- (00:00:31.000)\nalign:start line:0%", cue.text
   end
 
+  def test_multiple_line_separators
+    webvtt = WebVTT.read("tests/subtitles/test_multiple_line_separators.vtt")
+    assert_equal 2, webvtt.cues.length
+  end
+
   def test_ignore_if_note
     webvtt = WebVTT.read("tests/subtitles/withnote.vtt")
     assert_equal 3, webvtt.cues.size
@@ -129,6 +150,17 @@ The text should change)
     assert_equal 2, webvtt.cues.size
   end
 
+  def test_convert_weird_format_srt_to_webvtt
+    webvtt = WebVTT.convert_from_srt("tests/subtitles/weird_format.srt")
+    correct_webvtt = WebVTT.read("tests/subtitles/weird_format_corrected.vtt")
+
+    converted_cues = webvtt.cues.map { |cue| cue.start.to_s }
+    correct_cues = correct_webvtt.cues.map { |cue| cue.start.to_s }
+
+    assert_instance_of WebVTT::File, webvtt
+    assert_equal correct_cues, converted_cues
+  end
+
   def test_parse_big_file
     return
     webvtt = WebVTT.read("tests/subtitles/big_srt.vtt")
@@ -154,9 +186,9 @@ The text should change)
     assert_equal "00:09:02.373", webvtt.cues[1].end.to_s
     assert_equal "", webvtt.cues[1].text
   end
-  
+
   def test_cue_offset_by
-    cue = WebVTT::Cue.new <<-CUE
+    cue = WebVTT::Cue.parse <<-CUE
     00:00:01.000 --> 00:00:25.432
     Test Cue
     CUE
@@ -195,4 +227,28 @@ The text should change)
     assert_equal "03:39:34.008", ts3.to_s
   end
 
+  def test_build_cue
+    cue = WebVTT::Cue.new
+    cue.start = WebVTT::Timestamp.new 0
+    cue.end = WebVTT::Timestamp.new 12
+    cue.text = "Built from scratch"
+    output = ""
+    output << "00:00:00.000 --> 00:00:12.000\n"
+    output << "Built from scratch"
+    assert_equal output, cue.to_webvtt
+  end
+
+  def test_invalid_cue
+    webvtt = WebVTT.convert_from_srt("tests/subtitles/invalid_cue.srt")
+    assert_equal 1, webvtt.cues.size
+  end
+
+  def test_can_validate_webvtt_with_carriage_returns
+    webvtt = WebVTT::File.new("tests/subtitles/test_carriage_returns.vtt")
+    assert_instance_of Array, webvtt.cues
+    assert !webvtt.cues.empty?, "Cues should not be empty"
+    assert_instance_of WebVTT::Cue, webvtt.cues[0]
+    assert_equal 15, webvtt.cues.size
+  end
+
 end

data/tests/segmenter.rb

@@ -43,7 +43,7 @@ class ParserTest < Minitest::Test
     subs = segmenter.split_to_files
     segmenter.generate_playlist(subs)
 
-    assert File.exists?("test.m3u8")
+    assert File.exist?("test.m3u8")
     # clean up
     subs.each {|f| FileUtils.rm(f.filename)}
     FileUtils.rm("test.m3u8")

data/tests/subtitles/invalid_cue.srt

@@ -0,0 +1,5 @@
+1
+00:00:30,828 --> 00:00:34,894
+
+Captain Phillips (2013)
+

data/tests/subtitles/invalid_cue.vtt

@@ -0,0 +1,6 @@
+WEBVTT
+
+1
+00:00:30.828 --> 00:00:34.894
+
+Captain Phillips (2013)

data/tests/subtitles/test_carriage_returns.vtt

@@ -0,0 +1 @@
+WEBVTT

data/tests/subtitles/test_from_srt.vtt

@@ -6,4 +6,4 @@ Elephant's Dream
 
 2
 00:00:15.000 --> 00:00:18.000
-At the left we can see...
+At the left we can see...

data/tests/subtitles/test_mmss_format.vtt

@@ -0,0 +1,9 @@
+WEBVTT
+
+00:29.000 --> 00:31.000 line:75%
+English subtitle 15 -Forced- (00:00:27.000)
+line:75%
+
+2
+00:31.000 --> 00:33.000 align:start line:0%
+ 

data/tests/subtitles/test_multiple_line_separators.vtt

@@ -0,0 +1,15 @@
+WEBVTT X-TIMESTAMP-MAP=MPEGTS:900000,LOCAL:00:00:00.000
+
+
+
+
+00:00:29.000 --> 00:00:31.000 line:75%
+English subtitle 15 -Forced- (00:00:27.000)
+line:75%
+
+
+
+
+00:00:31.000 --> 00:00:33.000 align:start line:0%
+English subtitle 16 -Unforced- (00:00:31.000)
+align:start line:0%

data/tests/subtitles/weird_format.srt

@@ -0,0 +1,15 @@
+1
+00:00:00,970 --> 00:00:03,000
+Normal formatting
+
+2
+00:00:4,080 --> 00:00:06,080
+Third digit
+
+3
+00:0:09,350 --> 00:00:13,350
+Second digit
+
+4
+0:00:15,000 --> 00:00:16,000
+First digit

data/tests/subtitles/weird_format.vtt

@@ -0,0 +1,17 @@
+WEBVTT
+
+1
+00:00:00.970 --> 00:00:03.000
+Normal formatting
+
+2
+00:00:04.080 --> 00:00:06.080
+Third digit
+
+3
+00:00:09.350 --> 00:00:13.350
+Second digit
+
+4
+00:00:15.000 --> 00:00:16.000
+First digit

data/tests/subtitles/weird_format_corrected.vtt

@@ -0,0 +1,17 @@
+WEBVTT
+
+1
+00:00:00.970 --> 00:00:03.000
+Normal formatting
+
+2
+00:00:04.080 --> 00:00:06.080
+Third digit
+
+3
+00:00:09.350 --> 00:00:13.350
+Second digit
+
+4
+00:00:15.000 --> 00:00:16.000
+First digit

data/webvtt-ruby.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name          = 'webvtt-ruby'
-  s.version       = '0.3.0'
+  s.version       = '0.4.0'
   s.summary       = "WebVTT parser and segmenter in ruby"
   s.description   = "WebVTT parser and segmenter in ruby for HTML5 and HTTP Live Streaming (HLS)."
   s.authors       = ["Bruno Celeste"]

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: webvtt-ruby
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Bruno Celeste
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-15 00:00:00.000000000 Z
+date: 2023-04-06 00:00:00.000000000 Z
 dependencies: []
 description: WebVTT parser and segmenter in ruby for HTML5 and HTTP Live Streaming
   (HLS).
@@ -24,18 +24,26 @@ files:
 - LICENSE
 - README.md
 - bin/webvtt-segmenter
-- lib/parser.rb
-- lib/segmenter.rb
 - lib/webvtt.rb
+- lib/webvtt/parser.rb
+- lib/webvtt/segmenter.rb
 - tests/parser.rb
 - tests/segmenter.rb
 - tests/subtitles/big_srt.srt
 - tests/subtitles/big_srt.vtt
+- tests/subtitles/invalid_cue.srt
+- tests/subtitles/invalid_cue.vtt
 - tests/subtitles/no_text.vtt
 - tests/subtitles/notvalid.vtt
 - tests/subtitles/test.vtt
+- tests/subtitles/test_carriage_returns.vtt
 - tests/subtitles/test_from_srt.srt
 - tests/subtitles/test_from_srt.vtt
+- tests/subtitles/test_mmss_format.vtt
+- tests/subtitles/test_multiple_line_separators.vtt
+- tests/subtitles/weird_format.srt
+- tests/subtitles/weird_format.vtt
+- tests/subtitles/weird_format_corrected.vtt
 - tests/subtitles/withnote.vtt
 - webvtt-ruby.gemspec
 homepage: https://github.com/HeyWatch/webvtt-ruby
@@ -57,8 +65,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.3
+rubygems_version: 3.1.4
 signing_key: 
 specification_version: 4
 summary: WebVTT parser and segmenter in ruby