format_parser 1.6.0 → 1.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 54b56b24c97b2532bc5d7f8521aa38714111a05f2bedd5e15b7391e1005d9795
-  data.tar.gz: e33a026ab2c611a86d6ba7e35fd413455f7b99c423651fa09dcebf08ad543e0a
+  metadata.gz: 8b3cef665ae16efd68e8da952fd4656e2d9403f3899bd58839da3d8026db91f4
+  data.tar.gz: 7b0ec88efc2ea62f526699a4041cb3f1b3062994d2a6e0b24c2cfdf247aaf532
 SHA512:
-  metadata.gz: e27ec936c4b43cc6c82f896846ef3e8044a0639b18c1c2accf7bbdeffd0fe73d9c03fb2f2e9b4a477ef1f98a1043047042b8521f186e3406ca1c482be9a66abd
-  data.tar.gz: a7927cfb5fbf0a41980465186809fb830b322e83db56bab15b5a2ad897031f7269eeae85d7e61f489a5cc2e6737348309e4f93c5dee27238d06a3ed0979f0d43
+  metadata.gz: 24c6379ef4fd3b5a9f061c6fc40fd8c0498ad33213684d08dd27a8b8994ba40a98bf1fa18a6d6b3b8189aa71436ec9bb394e3b8d41a8dd3ca90a5b93d0f1718a
+  data.tar.gz: a2d3df2c17d2559aa99f52f04624032a9243915f2a1b28a6f3626bd3b9112eb8c325b0c9a286864d25c2b4e92a44a8939448a85d1004ac5d48c2f81f747749c1

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+## 1.7.0
+* Add support for `ARW` files.
+
+## 1.6.0
+* Add support for `AAC` files.
+
 ## 1.5.0
 * Add support for `NEF` files.
 

data/README.md

@@ -194,7 +194,7 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 - `IMG_9266_*.tif` and all it's variations were created by the project maintainers
 
 ### ARW
-- ARW example is downloaded from http://www.rawsamples.ch/ and is Creative Common Licensed.
+- ARW examples are downloaded from http://www.rawsamples.ch/ and are Creative Common Licensed.
 
 ### ZIP
 - The .zip fixture files have been created by the project maintainers

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '1.6.0'
+  VERSION = '1.7.0'
 end

data/lib/parsers/arw_parser.rb

@@ -0,0 +1,50 @@
+require_relative 'exif_parser'
+
+class FormatParser::ARWParser
+  include FormatParser::IOUtils
+  include FormatParser::EXIFParser
+
+  # Standard TIFF headers
+  MAGIC_LE = [0x49, 0x49, 0x2A, 0x0].pack('C4')
+  MAGIC_BE = [0x4D, 0x4D, 0x0, 0x2A].pack('C4')
+  HEADER_BYTES = [MAGIC_LE, MAGIC_BE]
+  ARW_MIME_TYPE = 'image/x-sony-arw'
+
+  def likely_match?(filename)
+    filename =~ /\.arw$/i
+  end
+
+  def call(io)
+    io = FormatParser::IOConstraint.new(io)
+
+    return unless HEADER_BYTES.include?(safe_read(io, 4))
+    exif_data = exif_from_tiff_io(io)
+
+    return unless valid?(exif_data)
+
+    w = exif_data.width || exif_data.pixel_x_dimension
+    h = exif_data.height || exif_data.pixel_y_dimension
+
+    FormatParser::Image.new(
+      format: :arw,
+      width_px: w,
+      height_px: h,
+      display_width_px: exif_data.rotated? ? h : w,
+      display_height_px: exif_data.rotated? ? w : h,
+      orientation: exif_data.orientation_sym,
+      intrinsics: { exif: exif_data },
+      content_type: ARW_MIME_TYPE,
+    )
+  rescue EXIFR::MalformedTIFF
+    nil
+  end
+
+  def valid?(exif_data)
+    # taken directly from tiff_parser.rb
+    # Similar to how exiftool determines the image type as ARW, we are implementing a check here
+    # https://github.com/exiftool/exiftool/blob/e969456372fbaf4b980fea8bb094d71033ac8bf7/lib/Image/ExifTool/Exif.pm#L929
+    exif_data.compression == 6 && exif_data.new_subfile_type == 1 && exif_data.make&.start_with?('SONY')
+  end
+
+  FormatParser.register_parser new, natures: :image, formats: :arw
+end

data/lib/parsers/tiff_parser.rb

@@ -6,7 +6,6 @@ class FormatParser::TIFFParser
   MAGIC_BE = [0x4D, 0x4D, 0x0, 0x2A].pack('C4')
   HEADER_BYTES = [MAGIC_LE, MAGIC_BE]
   TIFF_MIME_TYPE = 'image/tiff'
-  ARW_MIME_TYPE = 'image/x-sony-arw'
 
   def likely_match?(filename)
     filename =~ /\.tiff?$/i
@@ -28,20 +27,20 @@ class FormatParser::TIFFParser
     exif_data = exif_from_tiff_io(io)
     return unless exif_data
 
+    return if arw?(exif_data)
+
     w = exif_data.width || exif_data.pixel_x_dimension
     h = exif_data.height || exif_data.pixel_y_dimension
 
-    format = arw?(exif_data) ? :arw : :tif
-    mime_type = arw?(exif_data) ? ARW_MIME_TYPE : TIFF_MIME_TYPE
     FormatParser::Image.new(
-      format: format,
+      format: :tif,
       width_px: w,
       height_px: h,
       display_width_px: exif_data.rotated? ? h : w,
       display_height_px: exif_data.rotated? ? w : h,
       orientation: exif_data.orientation_sym,
       intrinsics: {exif: exif_data},
-      content_type: mime_type,
+      content_type: TIFF_MIME_TYPE,
     )
   rescue EXIFR::MalformedTIFF
     nil
@@ -55,7 +54,7 @@ class FormatParser::TIFFParser
   # Similar to how exiftool determines the image type as ARW, we are implementing a check here
   # https://github.com/exiftool/exiftool/blob/e969456372fbaf4b980fea8bb094d71033ac8bf7/lib/Image/ExifTool/Exif.pm#L929
   def arw?(exif_data)
-    exif_data.compression == 6 && exif_data.new_subfile_type == 1 && exif_data.make == 'SONY'
+    exif_data.compression == 6 && exif_data.new_subfile_type == 1 && exif_data.make&.start_with?('SONY')
   end
 
   FormatParser.register_parser new, natures: :image, formats: :tif

data/spec/parsers/arw_parser_spec.rb

@@ -0,0 +1,119 @@
+require 'spec_helper'
+
+describe FormatParser::ARWParser do
+  shared_examples 'likely_match for file' do |filename_with_extension|
+    it "matches '#{filename_with_extension}'" do
+      expect(subject.likely_match?(filename_with_extension)).to be_truthy
+    end
+  end
+
+  shared_examples 'no likely_match for file' do |filename_with_extension|
+    it "does not match '#{filename_with_extension}'" do
+      expect(subject.likely_match?(filename_with_extension)).to be_falsey
+    end
+  end
+
+  describe 'likely_match' do
+    filenames = ['raw_file', 'another raw file', 'and.another', 'one-more']
+    valid_extensions = ['.arw', '.Arw', '.aRw', '.arW', '.ARw', '.ArW', '.aRW', '.ARW']
+    invalid_extensions = ['.tiff', '.cr2', '.new', '.jpeg']
+    filenames.each do |filename|
+      valid_extensions.each do |extension|
+        include_examples 'likely_match for file', filename + extension
+      end
+      invalid_extensions.each do |extension|
+        include_examples 'no likely_match for file', filename + extension
+      end
+    end
+  end
+
+  describe 'parses Sony ARW fixtures as arw format file' do
+    expected_parsed_dimensions = {
+      'RAW_SONY_A100.ARW' => {
+        width_px: 3872,
+        height_px: 2592,
+        display_width_px: 3872,
+        display_height_px: 2592,
+        orientation: :top_left
+      },
+      'RAW_SONY_A700.ARW' => {
+        width_px: 4288,
+        height_px: 2856,
+        display_width_px: 4288,
+        display_height_px: 2856,
+        orientation: :top_left
+      },
+      'RAW_SONY_A900.ARW' => {
+        width_px: 6080,
+        height_px: 4048,
+        display_width_px: 6080,
+        display_height_px: 4048,
+        orientation: :top_left
+      },
+      # rotated 90 degree image
+      'RAW_SONY_DSC-RX100M2.ARW' => {
+        width_px: 5472,
+        height_px: 3648,
+        display_width_px: 3648,
+        display_height_px: 5472,
+        orientation: :right_top,
+      },
+      'RAW_SONY_ILCE-7RM2.ARW' => {
+        width_px: 7952,
+        height_px: 5304,
+        display_width_px: 7952,
+        display_height_px: 5304,
+        orientation: :top_left,
+      },
+      'RAW_SONY_NEX7.ARW' => {
+        width_px: 6000,
+        height_px: 4000,
+        display_width_px: 6000,
+        display_height_px: 4000,
+        orientation: :top_left,
+      },
+      'RAW_SONY_SLTA55V.ARW' => {
+        width_px: 4928,
+        height_px: 3280,
+        display_width_px: 4928,
+        display_height_px: 3280,
+        orientation: :top_left,
+      },
+    }
+
+    Dir.glob(fixtures_dir + '/ARW/*.ARW').each do |arw_path|
+      it "is able to parse #{File.basename(arw_path)}" do
+        expected_dimension = expected_parsed_dimensions[File.basename(arw_path)]
+        # error if a new .arw test file is added without specifying the expected dimensions
+        expect(expected_dimension).not_to be_nil
+
+        parsed = subject.call(File.open(arw_path, 'rb'))
+        expect(parsed).not_to be_nil
+        expect(parsed.nature).to eq(:image)
+        expect(parsed.format).to eq(:arw)
+        expect(parsed.intrinsics[:exif]).not_to be_nil
+        expect(parsed.content_type).to eq('image/x-sony-arw')
+
+        expect(parsed.width_px).to eq(expected_dimension[:width_px])
+        expect(parsed.height_px).to eq(expected_dimension[:height_px])
+        expect(parsed.display_width_px).to eq(expected_dimension[:display_width_px])
+        expect(parsed.display_height_px).to eq(expected_dimension[:display_height_px])
+        expect(parsed.orientation).to eq(expected_dimension[:orientation])
+      end
+    end
+
+    shared_examples 'invalid filetype' do |filetype, fixture_path|
+      it "should fail to parse #{filetype}" do
+        file_path = fixtures_dir + fixture_path
+        parsed = subject.call(File.open(file_path, 'rb'))
+        expect(parsed).to be_nil
+      end
+    end
+
+    include_examples 'invalid filetype', 'NEF', '/NEF/RAW_NIKON_1S2.NEF'
+    include_examples 'invalid filetype', 'TIFF', '/TIFF/Shinbutsureijoushuincho.tiff'
+    include_examples 'invalid filetype', 'JPG', '/JPEG/orient_6.jpg'
+    include_examples 'invalid filetype', 'PNG', '/PNG/cat.png'
+    include_examples 'invalid filetype', 'CR2', '/CR2/RAW_CANON_1DM2.CR2'
+  end
+end

data/spec/parsers/tiff_parser_spec.rb

@@ -47,21 +47,6 @@ describe FormatParser::TIFFParser do
     expect(parsed.intrinsics[:exif]).not_to be_nil
   end
 
-  it 'parses Sony ARW fixture as arw format file' do
-    arw_path = fixtures_dir + '/ARW/RAW_SONY_ILCE-7RM2.ARW'
-
-    parsed = subject.call(File.open(arw_path, 'rb'))
-
-    expect(parsed).not_to be_nil
-    expect(parsed.nature).to eq(:image)
-    expect(parsed.format).to eq(:arw)
-
-    expect(parsed.width_px).to eq(7952)
-    expect(parsed.height_px).to eq(5304)
-    expect(parsed.intrinsics[:exif]).not_to be_nil
-    expect(parsed.content_type).to eq('image/x-sony-arw')
-  end
-
   describe 'correctly extracts dimensions from various TIFF flavors of the same file' do
     Dir.glob(fixtures_dir + '/TIFF/IMG_9266*.tif').each do |tiff_path|
       it "is able to parse #{File.basename(tiff_path)}" do
@@ -100,4 +85,13 @@ describe FormatParser::TIFFParser do
       end
     end
   end
+
+  describe 'bails out on ARW files, such as' do
+    Dir.glob(fixtures_dir + '/ARW/*.ARW').each do |arw_path|
+      it "skips #{File.basename(arw_path)}" do
+        parsed = subject.call(File.open(arw_path, 'rb'))
+        expect(parsed).to be_nil
+      end
+    end
+  end
 end

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 1.6.0
+  version: 1.7.0
 platform: ruby
 authors:
 - Noah Berman
 - Julik Tarkhanov
-autorequire: 
+autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-09-21 00:00:00.000000000 Z
+date: 2022-10-05 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -232,6 +232,7 @@ files:
 - lib/parsers/aac_parser.rb
 - lib/parsers/aac_parser/adts_header_info.rb
 - lib/parsers/aiff_parser.rb
+- lib/parsers/arw_parser.rb
 - lib/parsers/bmp_parser.rb
 - lib/parsers/cr2_parser.rb
 - lib/parsers/dpx_parser.rb
@@ -278,6 +279,7 @@ files:
 - spec/parsers/aac_parser_spec.rb
 - spec/parsers/adts_header_info_spec.rb
 - spec/parsers/aiff_parser_spec.rb
+- spec/parsers/arw_parser_spec.rb
 - spec/parsers/bmp_parser_spec.rb
 - spec/parsers/cr2_parser_spec.rb
 - spec/parsers/dpx_parser_spec.rb
@@ -310,7 +312,7 @@ licenses:
 - MIT (Hippocratic)
 metadata:
   allowed_push_host: https://rubygems.org
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -325,8 +327,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.6
-signing_key: 
+rubygems_version: 3.3.7
+signing_key:
 specification_version: 4
 summary: A library for efficient parsing of file metadata
 test_files: []