format_parser 0.29.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 75ee83f55840e3031d4d60d8dc07ca038812188613e2b740079e1c965efb2886
-  data.tar.gz: 31c3ee84434560c18e6ea74a23160b909e6f880f52b2ed6f0e888e847c557bd9
+  metadata.gz: d8bdd6daa59e43bbe6033562b804d3b1b9685c6e2aa5ef3f8d527c74516e1f6c
+  data.tar.gz: d6035f0b3c819085ffd23c4988e48145976ba1f98547d16589b2a4b4aa3e7aa7
 SHA512:
-  metadata.gz: 536cfb1bac7926f56ba760959d7c5a0905d3b2b0944b16248b6c81be00b722dad894a8d6d5773134fb0471e42d016a20be15e3d5a01c671f0cc65658f2fc05b4
-  data.tar.gz: cb3f73df051b8612cb6d0e1a4e55c045e461bf2c5e4667dd6e461e779b1f39d01be8d70d084e252e5198a966ac590129286811f5822808a0c980c2ad72a087a1
+  metadata.gz: 1a2f6243d295589972c63e45b719f19a5761c872103c32bfaacaef9cee9b85551c18ddaaf3c4095567c358958e7b7bf78800fc3e5a8e6c9f774eab383dc3160c
+  data.tar.gz: 73ba4f1099ccb4c490b50a8f531be843679159a6417980b2a61b905724905cf6b7e884127b66096e2237982dc6743e7f057bea0062472c1779e4d754dd5388ff

data/.github/workflows/main.yml

@@ -16,9 +16,6 @@ jobs:
           - 2.7
           - 2.6
           - 2.5
-          - 2.4
-          - 2.3
-          - 2.2
           - jruby
     steps:
       - name: Checkout
@@ -65,12 +62,11 @@ jobs:
           - 2.7
           - 2.6
           - 2.5
-          - 2.4
-          - 2.3
-          - 2.2
           - jruby
         experimental: [false]
         include:
+          - ruby: 3.1
+            experimental: true
           - ruby: 3.0
             experimental: true
     steps:

data/CHANGELOG.md

@@ -1,3 +1,13 @@
+## 1.2.0
+* Add support for `codecs` in moov_parser for video metadata
+
+## 1.1.0
+* Add support for `frame_rate` in moov_parser
+
+## 1.0.0
+* Dropping support for Ruby 2.2.X, 2.3.X and 2.4.X
+* MP3: Fix negative length reads in edge cases by bumping `id3tag` version to `v0.14.2`
+
 ## 0.29.1
 * Fix handling of 200 responses with `parse_http` as well as handling of very small responses which do not need range access
 

data/Gemfile

@@ -1,4 +1,9 @@
 source 'https://rubygems.org'
 
+gem 'ruby-debug-ide'
+gem 'debase'
+gem 'solargraph', group: :development
+gem 'pry', group: :development
+
 # Gem dependencies specified in the gemspec
 gemspec

data/format_parser.gemspec

@@ -32,7 +32,7 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency 'ks', '~> 0.0'
   spec.add_dependency 'exifr', '~> 1', '>= 1.3.8'
-  spec.add_dependency 'id3tag', '~> 0.14'
+  spec.add_dependency 'id3tag', '~> 0.14', '>= 0.14.2'
   spec.add_dependency 'faraday', '~> 0.13'
   spec.add_dependency 'faraday_middleware', '~> 0.14'
   spec.add_dependency 'measurometer', '~> 1'

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.29.1'
+  VERSION = '1.2.0'
 end

data/lib/parsers/moov_parser/decoder.rb

@@ -72,6 +72,7 @@ class FormatParser::MOOVParser::Decoder
 
     trak_atoms.find do |trak_atom|
       hdlr_atom = find_first_atom_by_path([trak_atom], 'trak', 'mdia', 'hdlr')
+      next if hdlr_atom.nil?
       hdlr_atom.atom_fields[:component_type] == 'mhlr' && hdlr_atom.atom_fields[:component_subtype] == 'vide'
     end
   end
@@ -111,6 +112,41 @@ class FormatParser::MOOVParser::Decoder
     }
   end
 
+  def parse_stts_atom(io, _)
+    version = read_byte_value(io)
+    is_v1 = version == 1
+    stts = {
+      version: version,
+      flags: read_bytes(io, 3),
+      number_of_entries: is_v1 ? read_64bit_uint(io) : read_32bit_uint(io),
+      entries: []
+    }
+    stts[:number_of_entries].times {
+      stts[:entries] << {
+        sample_count: read_32bit_uint(io),
+        sample_duration: read_32bit_uint(io)
+      }
+    }
+    stts
+  end
+
+  def parse_stsd_atom(io, _)
+    version = read_byte_value(io)
+    is_v1 = version == 1
+    stsd = {
+      version: version,
+      flags: read_bytes(io, 3),
+      number_of_entries: is_v1 ? read_64bit_uint(io) : read_32bit_uint(io),
+      codecs: []
+    }
+    stsd[:number_of_entries].times {
+      codec_length = read_32bit_uint(io)
+      stsd[:codecs] << read_bytes(io, 4)
+      io.seek(io.pos + codec_length - 8) # 8 bytes is the header length containing the codec length and the codec name that we just did read
+    }
+    stsd
+  end
+
   def parse_mdhd_atom(io, _)
     version = read_byte_value(io)
     is_v1 = version == 1

data/lib/parsers/moov_parser.rb

@@ -48,9 +48,9 @@ class FormatParser::MOOVParser
     width, height = parse_dimensions(decoder, atom_tree)
 
     # Try to find the "topmost" duration (respecting edits)
-    if mdhd = decoder.find_first_atom_by_path(atom_tree, 'moov', 'mvhd')
-      timescale = mdhd.field_value(:tscale)
-      duration = mdhd.field_value(:duration)
+    if mvhd = decoder.find_first_atom_by_path(atom_tree, 'moov', 'mvhd')
+      timescale = mvhd.field_value(:tscale)
+      duration = mvhd.field_value(:duration)
       media_duration_s = duration / timescale.to_f
     end
 
@@ -68,9 +68,11 @@ class FormatParser::MOOVParser
         format: format_from_moov_type(file_type),
         width_px: width,
         height_px: height,
+        frame_rate: parse_time_to_sample_atom(decoder, atom_tree)&.truncate(2),
         media_duration_seconds: media_duration_s,
         content_type: MP4_MIXED_MIME_TYPE,
-        intrinsics: atom_tree,
+        codecs: parse_sample_description_atom(decoder, atom_tree),
+        intrinsics: atom_tree
       )
     end
   end
@@ -115,5 +117,51 @@ class FormatParser::MOOVParser
     maybe_atom_size >= minimum_ftyp_atom_size && maybe_ftyp_atom_signature == 'ftyp'
   end
 
+  # Sample information is found in the 'time-to-sample' stts atom.
+  # The media atom mdhd is needed too in order to get the movie timescale
+  def parse_time_to_sample_atom(decoder, atom_tree)
+    video_trak_atom = decoder.find_video_trak_atom(atom_tree)
+
+    stts = if video_trak_atom
+      decoder.find_first_atom_by_path([video_trak_atom], 'trak', 'mdia', 'minf', 'stbl', 'stts')
+    else
+      decoder.find_first_atom_by_path(atom_tree, 'moov', 'trak', 'mdia', 'minf', 'stbl', 'stts')
+    end
+
+    mdhd = if video_trak_atom
+      decoder.find_first_atom_by_path([video_trak_atom], 'trak', 'mdia', 'mdhd')
+    else
+      decoder.find_first_atom_by_path(atom_tree, 'moov', 'trak', 'mdia', 'mdhd')
+    end
+
+    if stts && mdhd
+      timescale = mdhd.atom_fields[:tscale]
+      sample_duration = stts.field_value(:entries).first[:sample_duration]
+      if timescale.nil? || timescale == 0 || sample_duration.nil? || sample_duration == 0
+        nil
+      else
+        timescale.to_f / sample_duration
+      end
+    else
+      nil
+    end
+  end
+
+  def parse_sample_description_atom(decoder, atom_tree)
+    video_trak_atom = decoder.find_video_trak_atom(atom_tree)
+
+    stsd = if video_trak_atom
+      decoder.find_first_atom_by_path([video_trak_atom], 'trak', 'mdia', 'minf', 'stbl', 'stsd')
+    else
+      decoder.find_first_atom_by_path(atom_tree, 'moov', 'trak', 'mdia', 'minf', 'stbl', 'stsd')
+    end
+
+    if stsd
+      stsd.field_value(:codecs)
+    else
+      nil
+    end
+  end
+
   FormatParser.register_parser new, natures: :video, formats: FTYP_MAP.values, priority: 1
 end

data/lib/video.rb

@@ -8,9 +8,13 @@ module FormatParser
 
     attr_accessor :height_px
 
+    attr_accessor :frame_rate
+
     # Type of the file (e.g :mp3)
     attr_accessor :format
 
+    attr_accessor :codecs
+
     # Duration of the media object (be it audio or video) in seconds,
     # as a Float
     attr_accessor :media_duration_seconds

data/spec/integration/active_storage/rails_app.rb

@@ -53,19 +53,22 @@ end
 require 'minitest/autorun'
 require 'open-uri'
 
+fixtures_dir = File.join(File.dirname(__FILE__), '../../fixtures')
+
 describe User do
   describe "profile_picture's metadatas" do
     it 'parse metadatas with format_parser' do
+      fixture_path = fixtures_dir + '/PNG/cat.png'
       user = User.create
       user.profile_picture.attach(
         filename: 'cat.png',
-        io: URI.open('https://freesvg.org/img/1416155153.png')
+        io: File.open(fixture_path, 'rb')
       )
 
       user.profile_picture.analyze
 
-      _(user.profile_picture.metadata[:width_px]).must_equal 500
-      _(user.profile_picture.metadata[:height_px]).must_equal 296
+      _(user.profile_picture.metadata[:width_px]).must_equal 600
+      _(user.profile_picture.metadata[:height_px]).must_equal 600
       _(user.profile_picture.metadata[:color_mode]).must_equal 'rgba'
     end
   end

data/spec/parsers/moov_parser_spec.rb

@@ -94,6 +94,7 @@ describe FormatParser::MOOVParser do
     expect(result.format).to eq(:mov)
     expect(result.width_px).to eq(1920)
     expect(result.height_px).to eq(1080)
+    expect(result.codecs).to eq(['apcn'])
   end
 
   it 'parses an MP4 video file and provides the necessary metadata' do
@@ -106,6 +107,8 @@ describe FormatParser::MOOVParser do
     expect(result.format).to eq(:mov)
     expect(result.width_px).to eq(160)
     expect(result.height_px).to eq(90)
+    expect(result.frame_rate).to eq(14.98)
+    expect(result.codecs).to eq(['avc1'])
   end
 
   it 'provides filename hints' do
@@ -122,6 +125,7 @@ describe FormatParser::MOOVParser do
     expect(result.format).to eq(:mov)
     expect(result.width_px).to eq(640)
     expect(result.height_px).to eq(360)
+    expect(result.frame_rate).to eq(30)
   end
 
   it 'does not raise error when a meta atom has size 0' do

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.29.1
+  version: 1.2.0
 platform: ruby
 authors:
 - Noah Berman
 - Julik Tarkhanov
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2021-09-10 00:00:00.000000000 Z
+date: 2022-04-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -52,6 +52,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.14'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.14.2
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -59,6 +62,9 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.14'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.14.2
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
@@ -294,7 +300,7 @@ licenses:
 - MIT (Hippocratic)
 metadata:
   allowed_push_host: https://rubygems.org
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -309,8 +315,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
-signing_key:
+rubygems_version: 3.3.4
+signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata
 test_files: []