format_parser 1.0.0 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 04e71e127d550feb0a5aaa54a27cb68c1671e034a5d309c520e4b81ea385e865
-  data.tar.gz: 4617b5ea41651af01635d16dfba8de00f9765d1f3a092c7ec56170dd0d607495
+  metadata.gz: 9127e98631d7e02c8972809990709a409778faafcc2fed8df4a01cba417a3637
+  data.tar.gz: 6705fd3d1fab6789b8d61e438191e3ba0a2db6a9f15747998647d489abcdb9a2
 SHA512:
-  metadata.gz: f6d059459bcc4813a657bbe6b4eebdbd667d7fb15497ea1cfad2e92e355a68388fd558cc28af4e383f8d909e4a4735d4a485e34d26f1bef7b02e2420650ee0a9
-  data.tar.gz: 990f6e2490a1c38b60e1ce0fcc8f9b3e0b5471ac429a04277171e59a61b0d60d2998834792a7ea124fe474f94446f411620539018ee15bfe176a4d767e1d5919
+  metadata.gz: 95a1dd99683f3ebc60f0ccf9ed5a5715c9299979233b13712fe71f56f87a6feeb6cf0102cc256d5c0f0b3346b4a5c9b889709621c6afeb664640b881d703de7d
+  data.tar.gz: df71c70633550a9b99ed38c0e53049f39d58e4c6d1ade33882317e326da74bb3f3e1665b931205c4aed59482cc1bb2f9c227db429987259eab45e6e48ee036e7

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 1.2.1
+* Resolve bug when `stts` atom is `nil`
+
+## 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`

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '1.0.0'
+  VERSION = '1.2.1'
 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).dig(0, :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/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

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 1.0.0
+  version: 1.2.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2022-01-11 00:00:00.000000000 Z
+date: 2022-04-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -315,7 +315,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.6
+rubygems_version: 3.3.4
 signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata