assembly-image 2.1.4 → 2.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5aa835ae3183f8de14d0e677ded80d0ee5ffd813b2150e9fc4665245964dbab1
-  data.tar.gz: 639cad1edcc8abf76c26598bfd4949085a2fdea49f1acf5802a5a75f6b887c68
+  metadata.gz: fa79dbf8616f62f2ec19a862730b26e6c35151effcfa1a928babed128e7792fd
+  data.tar.gz: 6312f2cca6e2d431e6b20743d7514994a1244c38c253ba9cfe736efedc5d2b3a
 SHA512:
-  metadata.gz: dcc568cc992f74a80e69b6f6bae2eb56a5611a22e848371ce669634037181aae4f735ca2823e35b64037609a4c3b3f473d556fd3830a4d5a33c13d24b6536a59
-  data.tar.gz: f6cdae8947215307048dc439ef76308cb12b3523ed4722258c0d156bdee189c10c5fab6aee444ab09aeb3b3bff59a3ee4c00a3b5cf51619293a9a1ac8b214f7e
+  metadata.gz: adcd39ced78216223ebde02426945048c2f6b28919dee87924736c523d916af196f95879b28518eb80844dbe550fd6f6d10cc83506b7294f58a11d5159e9ed22
+  data.tar.gz: fd104a2b3202efaf3ba7bed7cfbbc816d668b21f27555fed88ff47019d24da745011b66393db4f708fb5d280d3ea9fb421ec8dc2ae483bda616ab56087d70f7d

data/.circleci/config.yml

@@ -1,6 +1,6 @@
 version: 2.1
 orbs:
-  ruby-rails: sul-dlss/ruby-rails@4.6.0
+  ruby-rails: sul-dlss/ruby-rails@4.12.0
 workflows:
   build:
     jobs:

data/.rubocop.yml

@@ -26,7 +26,7 @@ Naming/FileName:
   Exclude:
    - lib/assembly-image.rb
 
-Naming/PredicateName:
+Naming/PredicatePrefix:
   ForbiddenPrefixes:
     - is_
 
@@ -184,7 +184,7 @@ Lint/ConstantOverwrittenInRescue: # new in 1.31
 Lint/NonAtomicFileOperation: # new in 1.31
   Enabled: true
 
-Capybara/SpecificMatcher: # new in 2.12
+Capybara/RSpec/SpecificMatcher: # new in 2.12
   Enabled: true
 RSpecRails/HaveHttpStatus: # new in 2.12
   Enabled: false
@@ -243,9 +243,9 @@ Style/RedundantRegexpConstructor: # new in 1.52
   Enabled: true
 Style/RedundantStringEscape: # new in 1.37
   Enabled: true
-Capybara/MatchStyle: # new in 2.17
+Capybara/RSpec/MatchStyle: # new in 2.17
   Enabled: true
-Capybara/NegationMatcher: # new in 2.14
+Capybara/RSpec/NegationMatcher: # new in 2.14
   Enabled: true
 Capybara/SpecificActions: # new in 2.14
   Enabled: true

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    assembly-image (2.1.4)
+    assembly-image (2.3.0)
       activesupport (> 6.1)
       assembly-objectfile (>= 1.6.4)
       ruby-vips (>= 2.0)
@@ -9,7 +9,7 @@ PATH
 GEM
   remote: http://rubygems.org/
   specs:
-    activesupport (8.1.2)
+    activesupport (8.1.3)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.3.1)
@@ -28,8 +28,8 @@ GEM
       mini_exiftool
     ast (2.4.3)
     base64 (0.3.0)
-    bigdecimal (4.0.1)
-    concurrent-ruby (1.3.6)
+    bigdecimal (4.1.2)
+    concurrent-ruby (1.3.7)
     connection_pool (3.0.2)
     date (3.5.1)
     debug (1.11.1)
@@ -38,51 +38,53 @@ GEM
     diff-lcs (1.6.2)
     docile (1.4.1)
     drb (2.2.3)
-    erb (6.0.1)
-    ffi (1.17.3-arm64-darwin)
-    ffi (1.17.3-x86_64-darwin)
-    ffi (1.17.3-x86_64-linux-gnu)
-    i18n (1.14.8)
+    erb (6.0.4)
+    ffi (1.17.4-arm64-darwin)
+    ffi (1.17.4-x86_64-darwin)
+    ffi (1.17.4-x86_64-linux-gnu)
+    i18n (1.15.2)
       concurrent-ruby (~> 1.0)
     io-console (0.8.2)
-    irb (1.16.0)
+    irb (1.18.0)
       pp (>= 0.6.0)
+      prism (>= 1.3.0)
       rdoc (>= 4.0.0)
       reline (>= 0.4.2)
-    json (2.18.0)
+    json (2.19.9)
     language_server-protocol (3.17.0.5)
     lint_roller (1.1.0)
     logger (1.7.0)
     mime-types (3.7.0)
       logger
       mime-types-data (~> 3.2025, >= 3.2025.0507)
-    mime-types-data (3.2025.0924)
+    mime-types-data (3.2026.0414)
     mini_exiftool (2.14.0)
       ostruct (>= 0.6.0)
       pstore (>= 0.1.3)
-    minitest (6.0.1)
+    minitest (6.0.6)
+      drb (~> 2.0)
       prism (~> 1.5)
     ostruct (0.6.3)
-    parallel (1.27.0)
-    parser (3.3.10.0)
+    parallel (2.1.0)
+    parser (3.3.11.1)
       ast (~> 2.4.1)
       racc
-    pp (0.6.3)
+    pp (0.6.4)
       prettyprint
     prettyprint (0.2.0)
-    prism (1.7.0)
-    pstore (0.2.0)
-    psych (5.3.1)
+    prism (1.9.0)
+    pstore (0.2.1)
+    psych (5.4.0)
       date
       stringio
     racc (1.8.1)
     rainbow (3.1.1)
-    rake (13.3.1)
-    rdoc (7.0.3)
+    rake (13.4.2)
+    rdoc (7.2.0)
       erb
       psych (>= 4.0.0)
       tsort
-    regexp_parser (2.11.3)
+    regexp_parser (2.12.0)
     reline (0.6.3)
       io-console (~> 0.5)
     rspec (3.13.2)
@@ -94,33 +96,34 @@ GEM
     rspec-expectations (3.13.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-mocks (3.13.7)
+    rspec-mocks (3.13.8)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.13.0)
-    rspec-support (3.13.6)
-    rubocop (1.82.1)
+    rspec-support (3.13.7)
+    rubocop (1.88.0)
       json (~> 2.3)
       language_server-protocol (~> 3.17.0.2)
       lint_roller (~> 1.1.0)
-      parallel (~> 1.10)
+      parallel (>= 1.10)
       parser (>= 3.3.0.2)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 2.9.3, < 3.0)
-      rubocop-ast (>= 1.48.0, < 2.0)
+      rubocop-ast (>= 1.49.0, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 4.0)
-    rubocop-ast (1.49.0)
+    rubocop-ast (1.49.1)
       parser (>= 3.3.7.2)
       prism (~> 1.7)
-    rubocop-capybara (2.22.1)
+    rubocop-capybara (2.23.0)
       lint_roller (~> 1.1)
-      rubocop (~> 1.72, >= 1.72.1)
+      rubocop (~> 1.81)
     rubocop-factory_bot (2.28.0)
       lint_roller (~> 1.1)
       rubocop (~> 1.72, >= 1.72.1)
-    rubocop-rspec (3.9.0)
+    rubocop-rspec (3.10.2)
       lint_roller (~> 1.1)
-      rubocop (~> 1.81)
+      regexp_parser (>= 2.0)
+      rubocop (~> 1.86, >= 1.86.2)
     rubocop-rspec_rails (2.32.0)
       lint_roller (~> 1.1)
       rubocop (~> 1.72, >= 1.72.1)
@@ -166,4 +169,4 @@ DEPENDENCIES
   simplecov
 
 BUNDLED WITH
-  4.0.3
+  4.0.14

data/assembly-image.gemspec

@@ -4,7 +4,7 @@ $LOAD_PATH.push File.expand_path('lib', __dir__)
 
 Gem::Specification.new do |s|
   s.name        = 'assembly-image'
-  s.version     = '2.1.4'
+  s.version     = '2.3.0'
   s.authors     = ['Peter Mangiafico', 'Renzo Sanchez-Silva', 'Monty Hindman', 'Tony Calavano']
   s.email       = ['pmangiafico@stanford.edu']
   s.homepage    = ''

data/bin/console

@@ -2,8 +2,8 @@
 # frozen_string_literal: true
 
 require 'rubygems'
-require 'irb'
+require 'pry'
 
 require File.expand_path("#{File.dirname(__FILE__)}/../config/boot")
 
-IRB.start
+Pry.start

data/lib/assembly/image/jp2_creator.rb

@@ -50,6 +50,7 @@ module Assembly
           # KDUcompress doesn’t support arbitrary image types, so we make a temporary tiff
           make_tmp_tiff(tmp_tiff_path)
           make_jp2(tmp_tiff_path)
+          clean_jp2_metadata
         end
 
         # create output response object, which is an Assembly::Image type object
@@ -129,6 +130,18 @@ module Assembly
         FileUtils.rm_rf(output_path)
         raise "JP2 creation command failed: #{jp2_command} with result #{result}"
       end
+
+      # Rebuild all EXIF meta information from scratch
+      # See https://exiftool.sourceforge.net/exiftool_pod.html#exiftool--exif:all--tagsfromfile--all:all--unsafe-bad.jpg
+      def clean_jp2_metadata
+        exif_command = "exiftool -all= -tagsfromfile @ -all:all -unsafe #{Shellwords.escape(output_path)}"
+        result = `#{exif_command}`
+        return if $CHILD_STATUS.success?
+
+        # Clean up any partial result
+        FileUtils.rm_rf(output_path)
+        raise "JP2 clean metadata command failed: #{exif_command} with result #{result}"
+      end
     end
   end
 end

data/lib/assembly/image.rb

@@ -17,6 +17,26 @@ module Assembly
       vips_image.width
     end
 
+    # @return [boolean] true if this image is a multi-page (e.g. a TIFF with multiple pages)
+    def multi_page?
+      return false unless mimetype == 'image/tiff'
+
+      vips_image.get('n-pages').to_i > 1
+    rescue Vips::Error
+      false
+    end
+
+    # Extract and save only the first page from a multi-image TIFF
+    # @param [String] output_path path to save the extracted first page
+    def extract_first_page(output_path)
+      raise "Cannot extract first page from mimetype #{mimetype}" unless mimetype == 'image/tiff'
+
+      first_page = Vips::Image.new_from_file(path, page: 0).autorot
+      first_page.write_to_file(output_path)
+
+      true
+    end
+
     # @return [string] full default jp2 path and filename that will be created from the given image
     # Example:  given original file of '/dir/path_to_file.tif', gives '/dir/path_to_file.jp2'
     def jp2_filename

data/spec/assembly/image/jp2_creator_spec.rb

@@ -401,6 +401,50 @@ RSpec.describe Assembly::Image::Jp2Creator do
     end
   end
 
+  describe '#clean_jp2_metadata' do
+    let(:input_path) { TEST_TIF_INPUT_FILE }
+
+    before do
+      generate_test_image(input_path)
+      FileUtils.touch(jp2_output_file)
+    end
+
+    after { cleanup }
+
+    context 'when the output jp2 has a Coded Character Set IPTC tag' do
+      # Fixture is a real JP2 (created with opj_compress) so exiftool accepts IPTC writes to it.
+      # It lives outside spec/test_data/input/ so cleanup doesn't delete it.
+      let(:coded_charset_jp2) { 'spec/test_data/coded_charset_source.jp2' }
+
+      before do
+        FileUtils.cp(coded_charset_jp2, jp2_output_file)
+        system("exiftool -IPTC:CodedCharacterSet=UTF8 -overwrite_original '#{jp2_output_file}'")
+      end
+
+      it 'removes the Coded Character Set tag from the output file' do
+        expect(`exiftool '#{jp2_output_file}'`).to include('Coded Character Set')
+        jp2creator.send(:clean_jp2_metadata)
+        expect(`exiftool '#{jp2_output_file}'`).not_to include('Coded Character Set')
+      end
+    end
+
+    context 'when the exiftool command fails' do
+      before do
+        allow(jp2creator).to receive(:`).and_invoke(lambda { |_cmd|
+          system('false')
+          'error output'
+        })
+      end
+
+      it 'raises an error and removes the output file' do
+        expect(File).to exist(jp2_output_file)
+        expect { jp2creator.send(:clean_jp2_metadata) }
+          .to raise_error(RuntimeError, /JP2 clean metadata command failed/)
+        expect(File).not_to exist(jp2_output_file)
+      end
+    end
+  end
+
   describe '#make_tmp_tiff' do
     let(:input_path) { 'spec/test_data/color_rgb_srgb_rot90cw.tif' }
     let(:plum) { [94.0, 58.0, 101.0] }

data/spec/assembly/image_spec.rb

@@ -22,4 +22,91 @@ RSpec.describe Assembly::Image do
       end
     end
   end
+
+  describe '#multi_page?' do
+    context 'with a single page TIFF' do
+      before { generate_test_image(input_path) }
+
+      it 'returns false' do
+        expect(assembly_image.multi_page?).to be false
+      end
+    end
+
+    context 'with a multi-page TIFF' do
+      let(:input_path) { TEST_MULTIPAGE_TIF_FILE } # this image exists and is in our checked in codebase
+
+      it 'returns true' do
+        expect(assembly_image.multi_page?).to be true
+      end
+    end
+
+    context 'with a non-TIFF image' do
+      before { generate_test_image(input_path) }
+
+      let(:input_path) { TEST_JPEG_INPUT_FILE }
+
+      it 'returns false (JPEG cannot have multiple pages)' do
+        expect(assembly_image.multi_page?).to be false
+      end
+    end
+
+    context 'when Vips raises an error' do
+      before { generate_test_image(input_path) }
+
+      let(:input_path) { TEST_TIF_INPUT_FILE }
+
+      it 'rescues the error and returns false' do
+        allow(assembly_image.vips_image).to receive(:get).and_raise(Vips::Error, 'Test error')
+        expect(assembly_image.multi_page?).to be false
+      end
+    end
+  end
+
+  describe '#extract_first_page' do
+    let(:output_path) { File.join(TEST_OUTPUT_DIR, 'extracted.tif') }
+
+    after { FileUtils.rm_f(output_path) }
+
+    context 'with a single page TIFF' do
+      let(:input_path) { TEST_TIF_INPUT_FILE }
+
+      before { generate_test_image(input_path) }
+
+      it 'extracts and saves the first page' do
+        expect(assembly_image.multi_page?).to be false
+        result = assembly_image.extract_first_page(output_path)
+        expect(result).to be true
+        expect(File.exist?(output_path)).to be true
+        extracted = described_class.new(output_path)
+        expect(extracted.width).to eq assembly_image.width
+        expect(extracted.height).to eq assembly_image.height
+        expect(extracted.multi_page?).to be false
+      end
+    end
+
+    context 'with a multi-page TIFF' do
+      let(:input_path) { TEST_MULTIPAGE_TIF_FILE } # this is a test multi-page image that exists and is in our checked in codebase
+
+      it 'extracts only the first page' do
+        expect(assembly_image.multi_page?).to be true
+        result = assembly_image.extract_first_page(output_path)
+        expect(result).to be true
+        expect(File.exist?(output_path)).to be true
+        extracted = described_class.new(output_path)
+        expect(extracted.width).to eq assembly_image.width
+        expect(extracted.height).to eq assembly_image.height
+        expect(extracted.multi_page?).to be false
+      end
+    end
+
+    context 'with different image formats' do
+      before { generate_test_image(input_path) }
+
+      let(:input_path) { TEST_JPEG_INPUT_FILE }
+
+      it 'raises an error' do
+        expect { assembly_image.extract_first_page(output_path) }.to raise_error(RuntimeError, 'Cannot extract first page from mimetype image/jpeg')
+      end
+    end
+  end
 end

data/spec/spec_helper.rb

@@ -19,6 +19,7 @@ TEST_INPUT_DIR       = File.join(Assembly::PATH_TO_IMAGE_GEM, 'spec', 'test_data
 TEST_OUTPUT_DIR      = File.join(Assembly::PATH_TO_IMAGE_GEM, 'spec', 'test_data', 'output')
 TEST_TIF_INPUT_FILE  = File.join(TEST_INPUT_DIR, 'test.tif')
 TEST_JPEG_INPUT_FILE = File.join(TEST_INPUT_DIR, 'test.jpg')
+TEST_MULTIPAGE_TIF_FILE = File.join(Assembly::PATH_TO_IMAGE_GEM, 'spec', 'test_data', 'shapes_multi_size.tif')
 
 RSpec.configure do |config|
   # rspec-expectations config goes here. You can use an alternate

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: assembly-image
 version: !ruby/object:Gem::Version
-  version: 2.1.4
+  version: 2.3.0
 platform: ruby
 authors:
 - Peter Mangiafico
@@ -10,7 +10,7 @@ authors:
 - Tony Calavano
 bindir: exe
 cert_chain: []
-date: 2026-01-09 00:00:00.000000000 Z
+date: 1980-01-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -213,9 +213,11 @@ files:
 - spec/assembly/image/jp2_creator_spec.rb
 - spec/assembly/image_spec.rb
 - spec/spec_helper.rb
+- spec/test_data/coded_charset_source.jp2
 - spec/test_data/color_rgb_srgb_rot90cw.tif
 - spec/test_data/input/.empty
 - spec/test_data/output/.empty
+- spec/test_data/shapes_multi_size.tif
 homepage: ''
 licenses: []
 metadata:
@@ -234,7 +236,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.2
+rubygems_version: 4.0.6
 specification_version: 4
 summary: Ruby implementation of image services needed to prepare objects to be accessioned
   in SULAIR digital library