format_parser 0.13.4 → 0.13.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f23bfcabe71704fa85eca744312d6b8f48b97087c13cef3129a027b413d2b6ad
-  data.tar.gz: df7d94ff90f305b8a65deb7734718035e86494a5eaf129f437ba603f1b2935c8
+  metadata.gz: 8837741d44c95c25f1b68ae19991bf6b1c1819b17f8a645d5c53a9d9ba97a8bb
+  data.tar.gz: 58dac9d742cf2b59bbf05ae8b810b8a6b15b144035ca625a52e4a9fbed74f93e
 SHA512:
-  metadata.gz: 6beaa829ff6fee1f9a0c83f2ab3478fa1ea64798693d4b1025cb5d225923a0eb65a98c7355a5a15d764b34e51a51cdf8bb43718ea5297b92fc51bb4bceae842b
-  data.tar.gz: 2bad249ebf76f964d2a565daf8ec0cfd47176b85ae12c1e9f804575bacc2af0636c12a4291220b0b1f7ae1e4ee66926d9543d77c5aa97707b98abc919231fa6b
+  metadata.gz: 5be5537ea121c3eff8ec4520d049b1ff0e813f22cc4ea800ad01be7ccb823e0580ea3155d9d561b6854e1f211a98ecd23e6a8de4ef4c2a735b81a6b69a7aa780
+  data.tar.gz: 9b056ff9cb825a4d925a03ad3fcb245e0e93545057a1cf7c3ef778f84955b16b12175c9d8f3c0ab2e04542364c8bb1c5f65e8c0ad39ff70e199774217282a087

data/.travis.yml

@@ -7,5 +7,4 @@ rvm:
 sudo: false
 cache: bundler
 script:
-  - bundle exec rubocop
-  - bundle exec rspec
+  - bundle exec rake

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 0.13.5
+* Use the same TIFF parsing flow for CR2 files as it seems we are not very reliable _yet._ The CR2 parser will need some work.
+
 ## 0.13.4
 * Make sure JSON data never contains NaN, fix the test that was supposed to verify that but didn't
 * Forcibly UTF-8 sanitize all EXIF data when building JSON

data/Rakefile

@@ -1,6 +1,7 @@
 require 'bundler/gem_tasks'
 require 'rspec/core/rake_task'
 require 'yard'
+require 'rubocop/rake_task'
 
 YARD::Rake::YardocTask.new(:doc) do |t|
   # The dash has to be between the two to "divide" the source files and
@@ -8,5 +9,6 @@ YARD::Rake::YardocTask.new(:doc) do |t|
   t.files = ['lib/**/*.rb', '-', 'LICENSE.txt', 'IMPLEMENTATION_DETAILS.md']
 end
 
+RuboCop::RakeTask.new
 RSpec::Core::RakeTask.new(:spec)
-task default: :spec
+task default: [:spec, :rubocop]

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.13.4'
+  VERSION = '0.13.5'
 end

data/lib/parsers/cr2_parser.rb

@@ -1,22 +1,12 @@
+require_relative 'exif_parser'
+
 class FormatParser::CR2Parser
   include FormatParser::IOUtils
+  include FormatParser::EXIFParser
 
   TIFF_HEADER = [0x49, 0x49, 0x2a, 0x00]
   CR2_HEADER  = [0x43, 0x52, 0x02, 0x00]
 
-  PREVIEW_ORIENTATION_TAG = 0x0112
-  PREVIEW_RESOLUTION_TAG = 0x011a
-  PREVIEW_IMAGE_OFFSET_TAG = 0x0111
-  PREVIEW_IMAGE_BYTE_COUNT_TAG = 0x0117
-  EXIF_OFFSET_TAG = 0x8769
-  MAKERNOTE_OFFSET_TAG = 0x927c
-  AFINFO_TAG = 0x0012
-  AFINFO2_TAG = 0x0026
-  CAMERA_MODEL_TAG = 0x0110
-  SHOOT_DATE_TAG = 0x0132
-  EXPOSURE_TAG = 0x829a
-  APERTURE_TAG = 0x829d
-
   def call(io)
     io = FormatParser::IOConstraint.new(io)
 
@@ -28,130 +18,27 @@ class FormatParser::CR2Parser
 
     return if !magic_bytes.eql?(CR2_HEADER) || !tiff_bytes.eql?(TIFF_HEADER)
 
-    # Offset to IFD #0 where the preview image data is located
-    # For more information about CR2 format,
-    # see http://lclevy.free.fr/cr2/
-    # and https://github.com/lclevy/libcraw2/blob/master/docs/cr2_poster.pdf
-    if0_offset = parse_sequence_to_int tiff_header[4..7]
-
-    parse_ifd_0(io, if0_offset)
-    set_orientation(io, if0_offset)
-
-    exif_offset = parse_ifd(io, if0_offset, EXIF_OFFSET_TAG)
+    # The TIFF scanner in EXIFR is plenty good enough,
+    # so why don't we use it? It does all the right skips
+    # in all the right places.
+    exif_data = exif_from_tiff_io(io)
+    return unless exif_data
 
-    set_photo_info(io, exif_offset[0])
-
-    makernote_offset = parse_ifd(io, exif_offset[0], MAKERNOTE_OFFSET_TAG)
-
-    # Old Canon models have CanonAFInfo tags
-    # Newer models have CanonAFInfo2 tags instead
-    # See https://sno.phy.queensu.ca/~phil/exiftool/TagNames/Canon.html
-    af_info = parse_ifd(io, makernote_offset[0], AFINFO2_TAG)
-    unless af_info.nil?
-      parse_dimensions(io, af_info[0], af_info[1], 8, 10)
-    else
-      af_info = parse_ifd(io, makernote_offset[0], AFINFO_TAG)
-      parse_dimensions(io, af_info[0], af_info[1], 4, 6)
-    end
+    w = exif_data.image_width
+    h = exif_data.image_length
 
     FormatParser::Image.new(
       format: :cr2,
-      width_px: @width,
-      height_px: @height,
-      orientation: @orientation,
-      image_orientation: @image_orientation,
-      intrinsics: intrinsics
+      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,
+      intrinsics: {exif: exif_data},
     )
-  end
-
-  private
-
-  def parse_ifd(io, offset, searched_tag)
-    io.seek(offset)
-    entries_count = parse_sequence_to_int safe_read(io, 2)
-    entries_count.times do
-      ifd = ifd_entry safe_read(io, 12)
-      return [ifd[:value], ifd[:length], ifd[:type]].map { |b| parse_sequence_to_int b } if ifd[:tag] == [searched_tag].pack('v')
-    end
+  rescue EXIFR::MalformedTIFF
     nil
   end
 
-  def ifd_entry(binary)
-    { tag: binary[0..1], type: binary[2..3], length: binary[4..7], value: binary[8..11] }
-  end
-
-  def parse_sequence_to_int(sequence)
-    sequence.reverse.unpack('H*').join.hex
-  end
-
-  def parse_dimensions(io, offset, length, w_offset, h_offset)
-    io.seek(offset)
-    items = safe_read(io, length)
-    @width = parse_sequence_to_int items[w_offset..w_offset + 1]
-    @height = parse_sequence_to_int items[h_offset..h_offset + 1]
-  end
-
-  def parse_ifd_0(io, offset)
-    resolution_offset = parse_ifd(io, offset, PREVIEW_RESOLUTION_TAG)
-    resolution_data = read_data(io, resolution_offset[0], resolution_offset[1] * 8, resolution_offset[2])
-    @resolution = resolution_data[0] / resolution_data[1]
-
-    @preview_offset = parse_ifd(io, offset, PREVIEW_IMAGE_OFFSET_TAG).first
-    @preview_byte_count = parse_ifd(io, offset, PREVIEW_IMAGE_BYTE_COUNT_TAG).first
-
-    model_offset = parse_ifd(io, offset, CAMERA_MODEL_TAG)
-    @model = read_data(io, model_offset[0], model_offset[1], model_offset[2])
-
-    shoot_date_offset = parse_ifd(io, offset, SHOOT_DATE_TAG)
-    @shoot_date = read_data(io, shoot_date_offset[0], shoot_date_offset[1], shoot_date_offset[2])
-  end
-
-  def set_orientation(io, offset)
-    orient = parse_ifd(io, offset, PREVIEW_ORIENTATION_TAG).first
-    # Some old models do not have orientation info in TIFF headers
-    return if orient > 8
-    # EXIF orientation is an one based index
-    # http://sylvana.net/jpegcrop/exif_orientation.html
-    @orientation = FormatParser::EXIFParser::ORIENTATIONS[orient - 1]
-    @image_orientation = orient
-  end
-
-  def set_photo_info(io, offset)
-    # Type for exposure, aperture and resolution is unsigned rational
-    # Unsigned rational = 2x unsigned long (4 bytes)
-    exposure_offset = parse_ifd(io, offset, EXPOSURE_TAG)
-    exposure_data = read_data(io, exposure_offset[0], exposure_offset[1] * 8, exposure_offset[2])
-    @exposure = "#{exposure_data[0]}/#{exposure_data[1]}"
-
-    aperture_offset = parse_ifd(io, offset, APERTURE_TAG)
-    aperture_data = read_data(io, aperture_offset[0], aperture_offset[1] * 8, aperture_offset[2])
-    @aperture = "f#{aperture_data[0] / aperture_data[1].to_f}"
-  end
-
-  def read_data(io, offset, length, type)
-    io.seek(offset)
-    data = io.read(length)
-    case type
-    when 5
-      n = parse_sequence_to_int data[0..3]
-      d = parse_sequence_to_int data[4..7]
-      [n, d]
-    else
-      data
-    end
-  end
-
-  def intrinsics
-    {
-      camera_model: @model,
-      shoot_date: @shoot_date,
-      exposure: @exposure,
-      aperture: @aperture,
-      resolution: @resolution,
-      preview_offset: @preview_offset,
-      preview_length: @preview_byte_count
-    }
-  end
-
   FormatParser.register_parser self, natures: :image, formats: :cr2
 end

data/spec/parsers/cr2_parser_spec.rb

@@ -16,40 +16,29 @@ describe FormatParser::CR2Parser do
         expect(parsed.height_px).to be_kind_of(Integer)
         expect(parsed.height_px).to be > 0
 
-        expect(parsed.intrinsics).not_to be_nil
-        expect(parsed.intrinsics[:camera_model]).to be_kind_of(String)
-        expect(parsed.intrinsics[:camera_model]).to match(/Canon \w+/)
-        expect(parsed.intrinsics[:shoot_date]).to be_kind_of(String)
-        expect(parsed.intrinsics[:shoot_date]).to match(/\d{4}:\d{2}:\d{2} \d{2}:\d{2}:\d{2}/)
-        expect(parsed.intrinsics[:exposure]).to be_kind_of(String)
-        expect(parsed.intrinsics[:exposure]).to match(/1\/[0-9]+/)
-        expect(parsed.intrinsics[:aperture]).to be_kind_of(String)
-        expect(parsed.intrinsics[:aperture]).to match(/f[0-9]+\.[0-9]/)
-        expect(parsed.intrinsics[:resolution]).to be_kind_of(Integer)
-        expect(parsed.intrinsics[:resolution]).to be > 0
-        expect(parsed.intrinsics[:preview_offset]).to be_kind_of(Integer)
-        expect(parsed.intrinsics[:preview_offset]).to be > 0
-        expect(parsed.intrinsics[:preview_length]).to be_kind_of(Integer)
-        expect(parsed.intrinsics[:preview_length]).to be > 0
+        expect(parsed.orientation).not_to be_nil
       end
     end
   end
 
-  describe 'is able to parse orientation info in the examples' do
-    it 'is able to parse orientation in RAW_CANON_40D_SRAW_V103.CR2' do
-      file = fixtures_dir + '/CR2/RAW_CANON_40D_SRAW_V103.CR2'
-      parsed = subject.call(File.open(file, 'rb'))
-      expect(parsed.orientation).to be_kind_of(Symbol)
-      expect(parsed.image_orientation).to be_kind_of(Integer)
-      expect(parsed.image_orientation).to be > 0
-    end
+  it 'is able to parse orientation in RAW_CANON_40D_SRAW_V103.CR2' do
+    file = fixtures_dir + '/CR2/RAW_CANON_40D_SRAW_V103.CR2'
 
-    it 'is able to return the orientation nil for the examples from old Canon models' do
-      file = fixtures_dir + '/CR2/_MG_8591.CR2'
-      parsed = subject.call(File.open(file, 'rb'))
-      expect(parsed.orientation).to be_nil
-      expect(parsed.image_orientation).to be_nil
-    end
+    parsed = subject.call(File.open(file, 'rb'))
+
+    expect(parsed.width_px).to eq(1936)
+    expect(parsed.height_px).to eq(1288)
+    expect(parsed.orientation).to be_kind_of(Symbol)
+  end
+
+  it 'is able to return the orientation nil for the examples from old Canon models' do
+    file = fixtures_dir + '/CR2/_MG_8591.CR2'
+
+    parsed = subject.call(File.open(file, 'rb'))
+
+    expect(parsed.width_px).to eq(1536)
+    expect(parsed.height_px).to eq(1024)
+    expect(parsed.orientation).to eq(:top_left)
   end
 
   describe 'is able to return nil unless the examples are CR2' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.13.4
+  version: 0.13.5
 platform: ruby
 authors:
 - Noah Berman