ttml 0.0.5 → 0.1.0

data/.gitignore

@@ -15,3 +15,4 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+*~

data/README.md

@@ -2,9 +2,19 @@
 
 Very simple Timed Text Markup Language parsing - I needed to parse a ttml file
 and couldn't find a ruby implementation (probably because you don't really
-need one!), so I wrote one. In the future I may support writing a ttml file
+need one!), so I wrote it. In the future I may support writing a ttml file
 and/or a better, richer API.
 
+Also, I needed to convert ttml to SubRip, so a little binary was born, ttml2srt;
+It's run like
+
+    $ ttml2srt filename
+
+and outputs some .srt formatted subtitles to standard output.
+**Please note that it does a very (my)application dependent stripping of
+html tags from the input, so you may have to check the source to get
+out valid SubRip output.**
+
 ## Installation
 
 Add this line to your application's Gemfile:

data/bin/ttml2srt

@@ -0,0 +1,28 @@
+#!/usr/bin/env ruby
+
+require 'rubygems'
+require 'ttml'
+
+raise "Please pass filename[s] to parse" if ARGV.empty?
+
+def self.conv2srt fname
+  doc = Ttml::Document.new(fname) || raise("No doc at #{ fname }")
+  counter = 1
+  doc.subtitle_stream.each do |sub|
+    # Avoid outputing empty lines
+    cleaned = sub.content.sub(/.+00">([^<]*)<.+/, '\1')
+    next if cleaned.empty?
+    puts <<EOS
+#{ counter }
+#{ Ttml::Util.smpte_time(sub['begin']) } --> #{ Ttml::Util.smpte_time(sub['end']) }
+
+#{ cleaned }
+
+EOS
+    counter += 1
+  end
+end
+
+while fname = ARGV.shift
+  conv2srt(fname)
+end

data/lib/ttml.rb

@@ -2,6 +2,23 @@ require "ttml/version"
 require "nokogiri"
 
 module Ttml
+
+  # Some stuff that helps but is not directly about getting nodes out of it
+  class Util
+    # takes a string offset (as found in ttml nodes) and returns smpte string;
+    # Used in converting to SubRip.
+    #
+    # Ex: 0.0s => 00:00:00.0
+    # Ex: 63.5s => 00:01:03.500
+    def self.smpte_time offset
+      hours = minutes = seconds = millisecs = 0
+      f_off = offset.to_s.sub(/s$/, '').to_f
+      millisecs = ((f_off - f_off.to_i) * 1000).to_i
+      minutes, seconds = f_off.divmod(60)
+      hours, minutes = minutes.divmod(60)
+      "#{ sprintf('%02d', hours) }:#{ sprintf('%02d', minutes) }:#{ sprintf('%02d', seconds) },#{ millisecs }"
+    end
+  end
   # Minimal Timed Text Markup Language parsing and extraction.
   #
   # Example:
@@ -9,9 +26,9 @@ module Ttml
   #   => [Ttml::Document]
   #   >> doc.copyright
   #   => '(c) 2012 loop23'
-  #   >> doc.subtitles
-  #   => [All subtitles]
-  #   >> doc.subtitles(0.0, 100.0)
+  #   >> doc.subtitle_stream
+  #   => [All subtitles as Nokogiri::Node instances]
+  #   >> doc.subtitle_stream(0.0, 100.0)
   #   => [Subtitles from beginning to 100 seconds]
   class Document
 

data/lib/ttml/version.rb

@@ -1,3 +1,3 @@
 module Ttml
-  VERSION = "0.0.5"
+  VERSION = "0.1.0"
 end

data/test/sample_2.xml

@@ -1,17 +1,17 @@
-<?xml version='1.0'?><ns2:tt xmlns:ns4="http://www.w3.org/2006/10/ttaf1#parameter" xmlns:ns3="http://www.w3.org/2006/10/ttaf1#style" xmlns:ns2="http://www.w3.org/2006/10/ttaf1" xmlns:ns1="http://www.w3.org/2006/10/ttaf1#metadata" xml:lang="it"><ns2:head><ns1:title>Timed Text DFPX</ns1:title>
-<ns1:copyright>2010 (c) PerVoice S.p.A.</ns1:copyright>
-<ns2:styling><ns2:style xml:id="s1" ns3:textAlign="left" ns3:fontSize="22px" ns3:fontFamily="proportionalSansSerif" ns3:color="yellow"/>
-<ns2:style xml:id="s2" ns3:color="yellow" style="s1"/>
-<ns2:style xml:id="s1Right" ns3:textAlign="end" style="s1"/>
-<ns2:style xml:id="s2Left" ns3:textAlign="start" style="s2"/>
-</ns2:styling>
-<ns2:layout><ns2:region ns3:padding="5px 3px" ns3:extent="560px 62px" ns3:displayAlign="after" ns3:backgroundColor="black" style="s1" xml:id="subtitleArea"/>
-</ns2:layout>
-</ns2:head>
-<ns2:body region="subtitleArea"><ns2:div><ns2:p end="104.34s" begin="104.34s"><![CDATA[<p align="left" ><font color="#ffa500">Sono</font></p>]]></ns2:p>
-<ns2:p end="107.76s" begin="104.34s"><![CDATA[<p align="left" ><font color="#ffa500"></font></p>]]></ns2:p>
-<ns2:p end="117.8s" begin="107.76s"><![CDATA[<p align="left" ><font color="#ffa500">presenti 25</font></p>]]></ns2:p>
-<ns2:p end="117.8s" begin="117.8s"><![CDATA[<p align="left" ><font color="#ffa500">Consiglieri,</font></p>]]></ns2:p>
-</ns2:div>
-</ns2:body>
-</ns2:tt>
+<?xml version='1.0'?><ns2:tt xmlns:ns4="http://www.w3.org/2006/10/ttaf1#parameter" xmlns:ns3="http://www.w3.org/2006/10/ttaf1#style" xmlns:ns2="http://www.w3.org/2006/10/ttaf1" xmlns:ns1="http://www.w3.org/2006/10/ttaf1#metadata" xml:lang="it"><ns2:head><ns1:title>Timed Text DFPX</ns1:title>
+<ns1:copyright>2010 (c) PerVoice S.p.A.</ns1:copyright>
+<ns2:styling><ns2:style xml:id="s1" ns3:textAlign="left" ns3:fontSize="22px" ns3:fontFamily="proportionalSansSerif" ns3:color="yellow"/>
+<ns2:style xml:id="s2" ns3:color="yellow" style="s1"/>
+<ns2:style xml:id="s1Right" ns3:textAlign="end" style="s1"/>
+<ns2:style xml:id="s2Left" ns3:textAlign="start" style="s2"/>
+</ns2:styling>
+<ns2:layout><ns2:region ns3:padding="5px 3px" ns3:extent="560px 62px" ns3:displayAlign="after" ns3:backgroundColor="black" style="s1" xml:id="subtitleArea"/>
+</ns2:layout>
+</ns2:head>
+<ns2:body region="subtitleArea"><ns2:div><ns2:p end="104.34s" begin="104.34s"><![CDATA[<p align="left" ><font color="#ffa500">Sono</font></p>]]></ns2:p>
+<ns2:p end="107.76s" begin="104.34s"><![CDATA[<p align="left" ><font color="#ffa500"></font></p>]]></ns2:p>
+<ns2:p end="117.8s" begin="107.76s"><![CDATA[<p align="left" ><font color="#ffa500">presenti 25</font></p>]]></ns2:p>
+<ns2:p end="117.8s" begin="117.8s"><![CDATA[<p align="left" ><font color="#ffa500">Consiglieri,</font></p>]]></ns2:p>
+</ns2:div>
+</ns2:body>
+</ns2:tt>

data/test/util_test.rb

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+require 'test/unit'
+require 'ttml'
+
+class UtilTest < Test::Unit::TestCase
+
+  def test_smpte
+    assert_equal "00:00:00,0", Ttml::Util.smpte_time('0s')
+    assert_equal "00:00:00,0", Ttml::Util.smpte_time('0.0s')
+    assert_equal "00:01:00,0", Ttml::Util.smpte_time('60.0s')
+    assert_equal "00:01:01,0", Ttml::Util.smpte_time('61.0s')
+    assert_equal "00:00:00,500", Ttml::Util.smpte_time('0.5s')
+  end
+
+end

metadata

@@ -1,75 +1,94 @@
---- !ruby/object:Gem::Specification
+--- !ruby/object:Gem::Specification 
 name: ttml
-version: !ruby/object:Gem::Version
-  version: 0.0.5
+version: !ruby/object:Gem::Version 
+  hash: 27
   prerelease: 
+  segments: 
+  - 0
+  - 1
+  - 0
+  version: 0.1.0
 platform: ruby
-authors:
+authors: 
 - Luca S.G. de Marinis
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-09-14 00:00:00.000000000 Z
-dependencies:
-- !ruby/object:Gem::Dependency
+
+date: 2013-12-26 00:00:00 Z
+dependencies: 
+- !ruby/object:Gem::Dependency 
   name: nokogiri
-  requirement: !ruby/object:Gem::Requirement
-    none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :runtime
   prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
+  requirement: &id001 !ruby/object:Gem::Requirement 
     none: false
-    requirements:
-    - - ! '>='
-      - !ruby/object:Gem::Version
-        version: '0'
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        hash: 3
+        segments: 
+        - 0
+        version: "0"
+  type: :runtime
+  version_requirements: *id001
 description: Parse a ttml file
-email:
+email: 
 - loop23@gmail.com
-executables: []
+executables: 
+- ttml2srt
 extensions: []
+
 extra_rdoc_files: []
-files:
+
+files: 
 - .gitignore
 - Gemfile
 - LICENSE
 - README.md
 - Rakefile
+- bin/ttml2srt
 - lib/ttml.rb
 - lib/ttml/version.rb
 - test/sample.xml
 - test/sample_2.xml
-- test/test_ttml.rb
+- test/ttml_test.rb
+- test/util_test.rb
 - ttml.gemspec
 homepage: http://github.com/loop23/ttml
 licenses: []
+
 post_install_message: 
 rdoc_options: []
-require_paths:
+
+require_paths: 
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement
+required_ruby_version: !ruby/object:Gem::Requirement 
   none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
-required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
   none: false
-  requirements:
-  - - ! '>='
-    - !ruby/object:Gem::Version
-      version: '0'
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      hash: 3
+      segments: 
+      - 0
+      version: "0"
 requirements: []
+
 rubyforge_project: 
 rubygems_version: 1.8.24
 signing_key: 
 specification_version: 3
 summary: Minimal parsing for timed text markup language (http://www.w3.org/TR/ttaf1-dfxp/)
-test_files:
+test_files: 
 - test/sample.xml
 - test/sample_2.xml
-- test/test_ttml.rb
+- test/ttml_test.rb
+- test/util_test.rb