format_parser 0.21.1 → 0.24.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 916f22d0efd27a6e32065b50c51a4a482664c344669aa1f9586769ccf2be7b06
-  data.tar.gz: 3fd1b2ba7285ca69bb8d4c14c9f83e4001b55fee7e85332d97cbdbd36620597f
+  metadata.gz: cef6e8b3f4c3914ef022e7ff0e92d38357670315c0804efe8a2967f7f4228f53
+  data.tar.gz: '09a817b4fc688a3695800f4602a5901613b591d7a30ba26b86988720da7e13a9'
 SHA512:
-  metadata.gz: df680824b240f15df52fbc6c14d44f9b5fb99a93fb69cf191db6027a9871115f5e3e5bbaec48751853683b01b8e87b4266b0bbfb23700901910f2ce0f8da1137
-  data.tar.gz: d944a5db3fb2e1d06435b10bfc6aa0651312b45393180b08cf7a7f0b6237a0804b90a216cdeaf770e50de1af5bf31234f987e6fabc0e72bcb682e59a87cf2e7a
+  metadata.gz: 979804c2a7381d09e1f4952396321e185a917587d44409b1f7d45be0e05b466601eb7281e3d463785c6c18d79ba48ff3858bcd60c0f6791e2d394c4fa40ed684
+  data.tar.gz: a58cd8cab20fa8b8b7886a36479bd03fb6f5a4afbf9435d09318da502de50f6f257e45b012a56c79b4309dbaaf96feedb6b2b12016979bffa1336c528a591e3b

data/.gitignore

@@ -58,3 +58,6 @@ Gemfile.lock
 
 # OSX Files
 .DS_Store
+
+# rspec examples
+spec/examples.txt

data/CHANGELOG.md

@@ -1,3 +1,23 @@
+## 0.24.0
+* The TIFF parser will now return :arw as format for Sony ARW files insted of :tif so that the caller can decide whether it
+  wants to deal with RAW processing or not
+
+## 0.23.1
+* Updated gem exifr to fix problems related to jpeg files from Olympos microscopes, which often have bad thumbnail data
+
+## 0.23.0
+* Add ActiveStorage analyzer which can analyze ActiveStorage blobs. Enable it by setting
+  `config.active_storage.analyzers.prepend FormatParser::ActiveStorage::BlobAnalyzer`
+* Ignore empty ID3 tags and do not allow them to overwrite others
+* Update the id3tag dependency so that we can fallback to UTF8 instead of raising an error when parsing
+  MP3 files
+
+## 0.22.1
+* Fix Zip parser to not raise error for invalid zip files, with an invalid central directory
+
+## 0.22.0
+* Adds option `stringify_keys: true` to #as_json methods (fix #151)
+
 ## 0.21.1
 * MPEG: Ensure parsing does not inadvertently return an Integer instead of Result|nil
 * MPEG: Scan further into the MPEG file than previously (scan 32 1KB chunks)

data/CONTRIBUTING.md

@@ -234,4 +234,9 @@ This provision also applies to the test files you include with the changed code
 
 ## Changelog
 
-When creating a new release you must add an entry in the `CHANGELOG.md`.
+When creating a new release you must add an entry in the `CHANGELOG.md`.
+
+## Testing locally
+
+It's possible to run `exe/format_parser_inspect FILE_NAME` or `exe/format_parser_inspect FILE_URI`
+to test the new code without the necessity of installing the gem.

data/README.md

@@ -75,6 +75,17 @@ img_info = FormatParser.parse(File.open("myimage.jpg", "rb"))
 JSON.pretty_generate(img_info) #=> ...
 ```
 
+To convert the result to a Hash or a structure suitable for JSON serialization
+
+```ruby
+img_info = FormatParser.parse(File.open("myimage.jpg", "rb"))
+img_info.as_json
+
+# it's also possible to convert all keys to string
+img_info.as_json(stringify_keys: true)
+```
+
+
 ## Creating your own parsers
 
 See the [section on writing parsers in CONTRIBUTING.md](CONTRIBUTING.md#so-you-want-to-contribute-a-new-parser)
@@ -188,7 +199,7 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 
 ## Copyright
 
-Copyright (c) 2019 WeTransfer. 
+Copyright (c) 2020 WeTransfer.
 
 `format_parser` is distributed under the conditions of the [Hippocratic License](https://firstdonoharm.dev/version/1/2/license.html)
   - See LICENSE.txt for further details.

data/format_parser.gemspec

@@ -31,15 +31,14 @@ Gem::Specification.new do |spec|
   spec.require_paths = ['lib']
 
   spec.add_dependency 'ks', '~> 0.0'
-  spec.add_dependency 'exifr', '~> 1', '>= 1.3.4'
-  spec.add_dependency 'id3tag', '~> 0.10', '>= 0.10.1'
+  spec.add_dependency 'exifr', '~> 1', '>= 1.3.7'
+  spec.add_dependency 'id3tag', '~> 0.13'
   spec.add_dependency 'faraday', '~> 0.13'
   spec.add_dependency 'measurometer', '~> 1'
 
   spec.add_development_dependency 'rspec', '~> 3.0'
   spec.add_development_dependency 'rake', '~> 12'
   spec.add_development_dependency 'simplecov', '~> 0.15'
-  spec.add_development_dependency 'pry', '~> 0.11'
   spec.add_development_dependency 'yard', '~> 0.9'
   spec.add_development_dependency 'wetransfer_style', '0.5.0'
   spec.add_development_dependency 'parallel_tests'

data/lib/active_storage/blob_analyzer.rb

@@ -0,0 +1,35 @@
+require_relative 'blob_io'
+
+# An analyzer class that can be hooked to ActiveStorage, in order to enable
+# FormatParser to do the blob analysis instead of ActiveStorage builtin-analyzers.
+# Invoked if properly integrated in Rails initializer.
+
+module FormatParser
+  module ActiveStorage
+    class BlobAnalyzer
+      # Format parser is able to handle a lot of format so by default it will accept all files
+      #
+      # @return [Boolean, true] always return true
+      def self.accept?(_blob)
+        true
+      end
+
+      def initialize(blob)
+        @blob = blob
+      end
+
+      # @return [Hash] file metadatas
+      def metadata
+        io = BlobIO.new(@blob)
+        parsed_file = FormatParser.parse(io)
+
+        if parsed_file
+          # We symbolize keys because of existing output hash format of ImageAnalyzer
+          parsed_file.as_json.symbolize_keys
+        else
+          logger.info "Skipping file analysis because FormatParser doesn't support the file"
+        end
+      end
+    end
+  end
+end

data/lib/active_storage/blob_io.rb

@@ -0,0 +1,51 @@
+# Acts as a proxy to turn ActiveStorage file into IO object
+
+module FormatParser
+  module ActiveStorage
+    class BlobIO
+      # @param blob[ActiveStorage::Blob] the file with linked service
+      # @return [BlobIO]
+      def initialize(blob)
+        @blob = blob
+        @service = blob.service
+        @pos = 0
+      end
+
+      # Emulates IO#read, but requires the number of bytes to read.
+      # Rely on `ActiveStorage::Service.download_chunk` of each hosting type (local, S3, Azure, etc)
+      #
+      # @param n_bytes[Integer] how many bytes to read
+      # @return [String] the read bytes
+      def read(n_bytes)
+        # HTTP ranges are exclusive.
+        http_range = (@pos..(@pos + n_bytes - 1))
+        body = @service.download_chunk(@blob.key, http_range)
+        @pos += body.bytesize
+        body.force_encoding(Encoding::ASCII_8BIT)
+      end
+
+      # Emulates IO#seek
+      #
+      # @param [Integer] offset size
+      # @return [Integer] always return 0, `seek` only mutates `pos` attribute
+      def seek(offset)
+        @pos = offset
+        0
+      end
+
+      # Emulates IO#size.
+      #
+      # @return [Integer] the size of the blob size from ActiveStorage
+      def size
+        @blob.byte_size
+      end
+
+      # Emulates IO#pos
+      #
+      # @return [Integer] the current offset (in bytes) of the io
+      def pos
+        @pos
+      end
+    end
+  end
+end

data/lib/attributes_json.rb

@@ -15,7 +15,12 @@ module FormatParser::AttributesJSON
 
   # Implements a sane default `as_json` for an object
   # that accessors defined
-  def as_json(root: false)
+  #
+  # @param root[Bool] if true, it surrounds the result in a hash with a key
+  #  `format_parser_file_info`
+  # @param stringify_keys[Bool] if true, it transforms all the hash keys to a string.
+  #   The default value is false for backward compatibility
+  def as_json(root: false, stringify_keys: false, **)
     h = {}
     h['nature'] = nature if respond_to?(:nature) # Needed for file info structs
     methods.grep(/\w\=$/).each_with_object(h) do |attr_writer_method_name, h|
@@ -27,6 +32,9 @@ module FormatParser::AttributesJSON
       sanitized_value = _sanitize_json_value(unwrapped_attribute_value)
       h[reader_method_name] = sanitized_value
     end
+
+    h = FormatParser::HashUtils.deep_transform_keys(h, &:to_s) if stringify_keys
+
     if root
       {'format_parser_file_info' => h}
     else

data/lib/format_parser.rb

@@ -5,6 +5,7 @@ require 'measurometer'
 # top-level methods of the library.
 module FormatParser
   require_relative 'format_parser/version'
+  require_relative 'hash_utils'
   require_relative 'attributes_json'
   require_relative 'image'
   require_relative 'audio'
@@ -17,6 +18,7 @@ module FormatParser
   require_relative 'remote_io'
   require_relative 'io_constraint'
   require_relative 'care'
+  require_relative 'active_storage/blob_analyzer'
 
   # Define Measurometer in the internal namespace as well
   # so that we stay compatible for the applications that use it

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.21.1'
+  VERSION = '0.24.0'
 end

data/lib/hash_utils.rb

@@ -0,0 +1,19 @@
+# based on https://github.com/rails/rails/blob/master/activesupport/lib/active_support/core_ext/hash/keys.rb#L116
+# I chose to copy this method instead of adding activesupport as a dependency
+# because we want to have the least number of dependencies
+module FormatParser
+  class HashUtils
+    def self.deep_transform_keys(object, &block)
+      case object
+      when Hash
+        object.each_with_object({}) do |(key, value), result|
+          result[yield(key)] = deep_transform_keys(value, &block)
+        end
+      when Array
+        object.map { |e| deep_transform_keys(e, &block) }
+      else
+        object
+      end
+    end
+  end
+end

data/lib/parsers/mp3_parser.rb

@@ -44,13 +44,9 @@ class FormatParser::MP3Parser
       tag = __getobj__
       MEMBERS.each_with_object({}) do |k, h|
         value = tag.public_send(k)
-        h[k] = value if value
+        h[k] = value if value && !value.empty?
       end
     end
-
-    def as_json(*)
-      to_h
-    end
   end
 
   def likely_match?(filename)
@@ -85,7 +81,7 @@ class FormatParser::MP3Parser
 
     first_frame = initial_frames.first
 
-    id3tags_hash = blend_id3_tags_into_hash(*tags)
+    id3tags_hash = with_id3tag_local_configs { blend_id3_tags_into_hash(*tags) }
 
     file_info = FormatParser::Audio.new(
       format: :mp3,
@@ -297,5 +293,14 @@ class FormatParser::MP3Parser
     attrs
   end
 
+  def with_id3tag_local_configs
+    ID3Tag.local_configuration do |c|
+      c.string_encode_options = { invalid: :replace, undef: :replace }
+      c.source_encoding_fallback = Encoding::UTF_8
+
+      yield
+    end
+  end
+
   FormatParser.register_parser new, natures: :audio, formats: :mp3, priority: 99
 end

data/lib/parsers/tiff_parser.rb

@@ -26,7 +26,7 @@ class FormatParser::TIFFParser
     h = exif_data.height || exif_data.pixel_y_dimension
 
     FormatParser::Image.new(
-      format: :tif,
+      format: arw?(exif_data) ? :arw : :tif, # Specify format as arw for Sony ARW format images, else tif
       width_px: w,
       height_px: h,
       display_width_px: exif_data.rotated? ? h : w,
@@ -43,5 +43,11 @@ class FormatParser::TIFFParser
     safe_read(io, 2) == 'CR'
   end
 
+  # 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'
+  end
+
   FormatParser.register_parser new, natures: :image, formats: :tif
 end

data/lib/parsers/zip_parser/file_reader.rb

@@ -18,6 +18,7 @@ class FormatParser::ZIPParser::FileReader
       'Could not find the EOCD signature in the buffer - maybe a malformed ZIP file'
     end
   end
+  InvalidCentralDirectory = Class.new(Error)
 
   C_UINT32LE = 'V'
   C_UINT16LE = 'v'
@@ -175,6 +176,8 @@ class FormatParser::ZIPParser::FileReader
     # BUT! in format_parser we avoid unbounded reads, as a matter of fact they are forbidden.
     # So we will again limit ouselves to cdir_size, and we will take cushion of 1 KB.
     central_directory_str = io.read(cdir_size + 1024)
+    raise InvalidCentralDirectory if central_directory_str.nil?
+
     central_directory_io = StringIO.new(central_directory_str)
     log do
       format(

data/spec/active_storage/blob_io_spec.rb

@@ -0,0 +1,36 @@
+require 'spec_helper'
+
+describe FormatParser::ActiveStorage::BlobIO do
+  let(:blob_service) { double }
+  let(:blob) { double(key: 'blob_key', service: blob_service, byte_size: 43000) }
+  let(:io) { described_class.new(blob) }
+  let(:fixture_path) { fixtures_dir + '/test.png' }
+
+  it_behaves_like 'an IO object compatible with IOConstraint'
+
+  describe '#read' do
+    it 'reads io using download_chunk from ActiveStorage#Service' do
+      allow(blob_service).to receive(:download_chunk) { 'a' }
+
+      expect(io.read(1)).to eq('a')
+    end
+
+    it 'updates #pos on read' do
+      allow(blob_service).to receive(:download_chunk) { 'a' }
+
+      expect { io.read(1) }.to change { io.pos }.from(0).to(1)
+    end
+  end
+
+  describe '#seek' do
+    it 'updates @pos' do
+      expect { io.seek(10) }.to change { io.pos }.from(0).to(10)
+    end
+  end
+
+  describe '#size' do
+    it 'returns the size of the blob byte_size' do
+      expect(io.size).to eq(blob.byte_size)
+    end
+  end
+end

data/spec/active_storage/rails_app_spec.rb

@@ -0,0 +1,58 @@
+require 'spec_helper'
+
+def skip_reason
+  if RUBY_ENGINE == 'jruby'
+    'Skipping because JRuby have randon failing issue'
+  elsif RUBY_VERSION.to_f < 2.5
+    'Skipping because Rails testing script use Rails 6, who does not support Ruby bellow 2.5'
+  else
+    false
+  end
+end
+
+describe 'Rails app with ActiveStorage and format-parser', skip: skip_reason do
+  describe 'local hosting with ActiveStorage disk adapter' do
+    it 'parse local file with format_parser' do
+      clean_env do
+        cmd = 'ruby spec/integration/active_storage/rails_app.rb'
+        cmd_status = ruby_script_runner(cmd)
+        expect(cmd_status[:stdout].last).to match(/1 runs, 3 assertions, 0 failures, 0 errors, 0 skips/)
+        expect(cmd_status[:exitstatus]).to eq(0)
+      end
+    end
+  end
+
+  def ruby_script_runner(cmd)
+    require 'open3'
+    cmd_status = { stdout: [], exitstatus: nil }
+    Open3.popen2(cmd) do |_stdin, stdout, wait_thr|
+      frame_stdout do
+        while line = stdout.gets
+          puts "|  #{line}"
+          cmd_status[:stdout] << line
+        end
+      end
+      cmd_status[:exitstatus] = wait_thr.value.exitstatus
+    end
+    cmd_status
+  end
+
+  def frame_stdout
+    puts
+    puts '-' * 50
+    yield
+    puts '-' * 50
+  end
+
+  def clean_env
+    if Bundler.respond_to?(:with_unbundled_env)
+      Bundler.with_unbundled_env do
+        yield
+      end
+    else
+      Bundler.with_clean_env do
+        yield
+      end
+    end
+  end
+end

data/spec/attributes_json_spec.rb

@@ -140,4 +140,30 @@ describe FormatParser::AttributesJSON do
       JSON.pretty_generate(object_with_attributes_module)
     }.to raise_error(/structure too deep/)
   end
+
+  it 'converts all hash keys to string when stringify_keys: true' do
+    fixture_path = fixtures_dir + '/ZIP/arch_few_entries.zip'
+    fi_io = File.open(fixture_path, 'rb')
+
+    result = FormatParser::ZIPParser.new.call(fi_io).as_json(stringify_keys: true)
+
+    result['entries'].each do |entry|
+      entry.each do |key, _value|
+        expect(key).to be_a(String)
+      end
+    end
+  end
+
+  it 'does not convert hash keys to string when stringify_keys: false' do
+    fixture_path = fixtures_dir + '/ZIP/arch_few_entries.zip'
+    fi_io = File.open(fixture_path, 'rb')
+
+    result = FormatParser::ZIPParser.new.call(fi_io).as_json
+
+    result['entries'].each do |entry|
+      entry.each do |key, _value|
+        expect(key).to be_a(Symbol)
+      end
+    end
+  end
 end

data/spec/hash_utils_spec.rb

@@ -0,0 +1,42 @@
+require 'spec_helper'
+
+describe FormatParser::HashUtils do
+  describe '.deep_transform_keys' do
+    it 'transforms all the keys in a hash' do
+      hash = { aa: 1, 'bb' => 2 }
+      result = described_class.deep_transform_keys(hash, &:to_s)
+
+      expect(result).to eq('aa' => 1, 'bb' => 2)
+    end
+
+    it 'transforms all the keys in a array of hashes' do
+      array = [{ aa: 1, bb: 2 }, { cc: 3, dd: [{c: 2, d: 3}] }]
+      result = described_class.deep_transform_keys(array, &:to_s)
+
+      expect(result).to eq(
+        [{'aa' => 1, 'bb' => 2}, {'cc' => 3, 'dd' => [{'c' => 2, 'd' => 3}]}]
+      )
+    end
+
+    it 'transforms all the keys in a hash recursively' do
+      hash = { aa: 1, bb: { cc: 22, dd: 3 } }
+      result = described_class.deep_transform_keys(hash, &:to_s)
+
+      expect(result).to eq('aa' => 1, 'bb' => { 'cc' => 22, 'dd' => 3})
+    end
+
+    it 'does nothing for an non array/hash object' do
+      object = Object.new
+      result = described_class.deep_transform_keys(object, &:to_s)
+
+      expect(result).to eq(object)
+    end
+
+    it 'returns the last value if different keys are transformed into the same one' do
+      hash = { aa: 0, 'bb' => 2, bb: 1 }
+      result = described_class.deep_transform_keys(hash, &:to_s)
+
+      expect(result).to eq('aa' => 0, 'bb' => 1)
+    end
+  end
+end

data/spec/integration/active_storage/rails_app.rb

@@ -0,0 +1,72 @@
+require 'bundler/inline'
+
+gemfile(true) do
+  source 'https://rubygems.org'
+
+  git_source(:github) { |repo| "https://github.com/#{repo}.git" }
+
+  gem 'rails', '6.0.3'
+  gem 'sqlite3'
+  gem 'format_parser', path: './'
+end
+
+require 'active_record/railtie'
+require 'active_storage/engine'
+require 'tmpdir'
+
+class TestApp < Rails::Application
+  config.root = __dir__
+  config.hosts << 'example.org'
+  config.eager_load = false
+  config.session_store :cookie_store, key: 'cookie_store_key'
+  secrets.secret_key_base = 'secret_key_base'
+
+  config.logger = Logger.new('/dev/null')
+
+  config.active_storage.service = :local
+  config.active_storage.service_configurations = {
+    local: {
+      root: Dir.tmpdir,
+      service: 'Disk'
+    }
+  }
+
+  config.active_storage.analyzers.prepend FormatParser::ActiveStorage::BlobAnalyzer
+end
+
+ENV['DATABASE_URL'] = 'sqlite3::memory:'
+
+Rails.application.initialize!
+
+require ActiveStorage::Engine.root.join('db/migrate/20170806125915_create_active_storage_tables.rb').to_s
+
+ActiveRecord::Schema.define do
+  CreateActiveStorageTables.new.change
+
+  create_table :users, force: true
+end
+
+class User < ActiveRecord::Base
+  has_one_attached :profile_picture
+end
+
+require 'minitest/autorun'
+require 'open-uri'
+
+describe User do
+  describe "profile_picture's metadatas" do
+    it 'parse metadatas with format_parser' do
+      user = User.create
+      user.profile_picture.attach(
+        filename: 'cat.png',
+        io: URI.open('https://freesvg.org/img/1416155153.png')
+      )
+
+      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[:color_mode]).must_equal 'rgba'
+    end
+  end
+end

data/spec/parsers/mp3_parser_spec.rb

@@ -37,6 +37,14 @@ describe FormatParser::MP3Parser do
         expect(parsed.album).to be_nil
       end
     end
+
+    context 'when has an empty tag' do
+      let(:fpath) { fixtures_dir + '/MP3/id3v2_with_empty_tag.mp3' }
+
+      it 'ignores the empty tags' do
+        expect(parsed.intrinsics[:genre]).to eq('Rock')
+      end
+    end
   end
 
   it 'decodes and estimates duration for a CBR MP3' do
@@ -71,6 +79,17 @@ describe FormatParser::MP3Parser do
     expect(prepped.pos).to eq(3145738)
   end
 
+  it 'does not raise error when a tag frame has unsupported encoding' do
+    fpath = fixtures_dir + '/MP3/id3v2_frame_with_invalid_encoding.mp3'
+
+    parsed = subject.call(File.open(fpath, 'rb'))
+
+    expect(parsed.nature). to eq(:audio)
+    expect(parsed.album).to eq('wetransfer')
+    expect(parsed.artist).to eq('wetransfer')
+    expect(parsed.title).to eq('test')
+  end
+
   it 'parses the Cassy MP3' do
     fpath = fixtures_dir + '/MP3/Cassy.mp3'
     parsed = subject.call(File.open(fpath, 'rb'))
@@ -110,4 +129,32 @@ describe FormatParser::MP3Parser do
       subject.call(StringIO.new(''))
     }.to raise_error(FormatParser::IOUtils::InvalidRead)
   end
+
+  describe '#as_json' do
+    it 'converts all hash keys to string when stringify_keys: true' do
+      fpath = fixtures_dir + '/MP3/Cassy.mp3'
+      result = subject.call(File.open(fpath, 'rb')).as_json(stringify_keys: true)
+
+      expect(
+        result['intrinsics'].keys.map(&:class).uniq
+      ).to eq([String])
+
+      expect(
+        result['intrinsics']['id3tags'].map(&:class).uniq
+      ).to eq([ID3Tag::Tag])
+    end
+
+    it 'does not convert the hash keys to string when stringify_keys: false' do
+      fpath = fixtures_dir + '/MP3/Cassy.mp3'
+      result = subject.call(File.open(fpath, 'rb')).as_json
+
+      expect(
+        result['intrinsics'].keys.map(&:class).uniq
+      ).to eq([Symbol])
+
+      expect(
+        result['intrinsics'][:id3tags].map(&:class).uniq
+      ).to eq([ID3Tag::Tag])
+    end
+  end
 end

data/spec/parsers/tiff_parser_spec.rb

@@ -47,12 +47,15 @@ describe FormatParser::TIFFParser do
     expect(parsed.intrinsics[:exif]).not_to be_nil
   end
 
-  it 'correctly extracts dimensions for a Sony ARW fixture' do
+  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

data/spec/parsers/zip_parser_spec.rb

@@ -103,4 +103,11 @@ describe FormatParser::ZIPParser do
     expect(first_entry.filename).to eq('Li��nia Extreme//')
     expect(first_entry.type).to eq(:directory)
   end
+
+  it 'is able to handle files with invalid central directory position' do
+    invalid_zip_path = fixtures_dir + '/ZIP/invalid_central_directory.zip'
+
+    expect { subject.call(File.open(invalid_zip_path, 'rb')) }
+      .to_not raise_error
+  end
 end

data/spec/spec_helper.rb

@@ -8,7 +8,6 @@ $LOAD_PATH.unshift(File.dirname(__FILE__))
 
 require 'rspec'
 require 'format_parser'
-require 'pry'
 
 module SpecHelpers
   def fixtures_dir
@@ -19,6 +18,8 @@ end
 RSpec.configure do |c|
   c.include SpecHelpers
   c.extend SpecHelpers # makes fixtures_dir available for example groups too
+  # https://relishapp.com/rspec/rspec-core/docs/command-line/only-failures
+  c.example_status_persistence_file_path = 'spec/examples.txt'
 end
 
 RSpec.shared_examples 'an IO object compatible with IOConstraint' do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.21.1
+  version: 0.24.0
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-04-20 00:00:00.000000000 Z
+date: 2020-09-15 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -34,7 +34,7 @@ dependencies:
         version: '1'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.4
+        version: 1.3.7
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -44,27 +44,21 @@ dependencies:
         version: '1'
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.3.4
+        version: 1.3.7
 - !ruby/object:Gem::Dependency
   name: id3tag
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.10'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 0.10.1
+        version: '0.13'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.10'
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: 0.10.1
+        version: '0.13'
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
@@ -135,20 +129,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.15'
-- !ruby/object:Gem::Dependency
-  name: pry
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.11'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '0.11'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
@@ -216,6 +196,8 @@ files:
 - Rakefile
 - exe/format_parser_inspect
 - format_parser.gemspec
+- lib/active_storage/blob_analyzer.rb
+- lib/active_storage/blob_io.rb
 - lib/archive.rb
 - lib/attributes_json.rb
 - lib/audio.rb
@@ -223,6 +205,7 @@ files:
 - lib/document.rb
 - lib/format_parser.rb
 - lib/format_parser/version.rb
+- lib/hash_utils.rb
 - lib/image.rb
 - lib/io_constraint.rb
 - lib/io_utils.rb
@@ -254,12 +237,16 @@ files:
 - lib/read_limits_config.rb
 - lib/remote_io.rb
 - lib/video.rb
+- spec/active_storage/blob_io_spec.rb
+- spec/active_storage/rails_app_spec.rb
 - spec/attributes_json_spec.rb
 - spec/care_spec.rb
 - spec/esoteric_formats_spec.rb
 - spec/file_information_spec.rb
 - spec/format_parser_inspect_spec.rb
 - spec/format_parser_spec.rb
+- spec/hash_utils_spec.rb
+- spec/integration/active_storage/rails_app.rb
 - spec/io_utils_spec.rb
 - spec/parsers/aiff_parser_spec.rb
 - spec/parsers/bmp_parser_spec.rb
@@ -305,7 +292,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.3
+rubygems_version: 3.0.6
 signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata