format_parser 0.25.5 → 0.29.0

data/spec/parsers/mp3_parser_spec.rb

@@ -23,6 +23,7 @@ describe FormatParser::MP3Parser do
 
     expect(parsed.nature).to eq(:audio)
     expect(parsed.format).to eq(:mp3)
+    expect(parsed.content_type).to eq('audio/mpeg')
     expect(parsed.num_audio_channels).to eq(2)
     expect(parsed.audio_sample_rate_hz).to eq(48000)
     expect(parsed.intrinsics).not_to be_nil

data/spec/parsers/ogg_parser_spec.rb

@@ -6,6 +6,7 @@ describe FormatParser::OggParser do
 
     expect(parse_result.nature).to eq(:audio)
     expect(parse_result.format).to eq(:ogg)
+    expect(parse_result.content_type).to eq('audio/ogg')
     expect(parse_result.num_audio_channels).to eq(1)
     expect(parse_result.audio_sample_rate_hz).to eq(16000)
     expect(parse_result.media_duration_seconds).to be_within(0.01).of(2973.95)

data/spec/parsers/pdf_parser_spec.rb

@@ -17,6 +17,7 @@ describe FormatParser::PDFParser do
       expect(parsed_pdf).not_to be_nil
       expect(parsed_pdf.nature).to eq(:document)
       expect(parsed_pdf.format).to eq(:pdf)
+      expect(parsed_pdf.content_type).to eq('application/pdf')
     end
   end
 

data/spec/parsers/png_parser_spec.rb

@@ -15,6 +15,7 @@ describe FormatParser::PNGParser do
 
         expect(parsed.height_px).to be_kind_of(Integer)
         expect(parsed.height_px).to be > 0
+        expect(parsed.content_type).to eq('image/png')
       end
     end
   end

data/spec/parsers/psd_parser_spec.rb

@@ -15,6 +15,7 @@ describe FormatParser::PSDParser do
 
         expect(parsed.height_px).to be_kind_of(Integer)
         expect(parsed.height_px).to be > 0
+        expect(parsed.content_type).to eq('application/x-photoshop')
       end
     end
   end

data/spec/parsers/tiff_parser_spec.rb

@@ -59,6 +59,7 @@ describe FormatParser::TIFFParser do
     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

data/spec/parsers/wav_parser_spec.rb

@@ -9,6 +9,7 @@ describe FormatParser::WAVParser do
 
       expect(parse_result.nature).to eq(:audio)
       expect(parse_result.format).to eq(:wav)
+      expect(parse_result.content_type).to eq('audio/x-wav')
     end
   end
 

data/spec/parsers/zip_parser_spec.rb

@@ -14,6 +14,7 @@ describe FormatParser::ZIPParser do
     expect(result).not_to be_nil
 
     expect(result.format).to eq(:zip)
+    expect(result.content_type).to eq('application/zip')
     expect(result.nature).to eq(:archive)
     expect(result.entries.length).to eq(0xFFFF + 1)
 
@@ -58,6 +59,7 @@ describe FormatParser::ZIPParser do
     result = subject.call(fi_io)
     expect(result.nature).to eq(:document)
     expect(result.format).to eq(:docx)
+    expect(result.content_type).to eq('application/vnd.openxmlformats-officedocument.wordprocessingml.document')
 
     fixture_path = fixtures_dir + '/ZIP/sample-docx.docx'
     fi_io = File.open(fixture_path, 'rb')

data/spec/remote_fetching_spec.rb

@@ -15,6 +15,10 @@ describe 'Fetching data from HTTP remotes' do
     }
     @server = WEBrick::HTTPServer.new(options)
     @server.mount '/', WEBrick::HTTPServlet::FileHandler, fixtures_dir
+    @server.mount_proc '/redirect' do |req, res|
+      res.status = 302
+      res.header['Location'] = req.path.sub('/redirect', '')
+    end
     trap('INT') { @server.stop }
     @server_thread = Thread.new { @server.start }
   end
@@ -91,6 +95,32 @@ describe 'Fetching data from HTTP remotes' do
     end
   end
 
+  context 'when the server responds with a redirect' do
+    it 'follows the redirect' do
+      file_information = FormatParser.parse_http('http://localhost:9399/redirect/TIFF/test.tif')
+      expect(file_information.format).to eq(:tif)
+    end
+  end
+
+  it 'sends provided HTTP headers in the request' do
+    # Faraday is required only after calling .parse_http
+    # This line is just to trigger this require, then it's possible to
+    # add an expectation of how Faraday is initialized after.
+    FormatParser.parse_http('invalid_url') rescue nil
+
+    expect(Faraday)
+      .to receive(:new)
+      .with(headers: {'test-header' => 'test-value'})
+      .and_call_original
+
+    file_information = FormatParser.parse_http(
+      'http://localhost:9399//TIFF/test.tif',
+      headers: {'test-header' => 'test-value'}
+    )
+
+    expect(file_information.format).to eq(:tif)
+  end
+
   after(:all) do
     @server.stop
     @server_thread.join(0.5)

data/spec/remote_io_spec.rb

@@ -7,7 +7,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {'Content-Range' => '10-109/2577'}, status: 206, body: 'This is the response')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=10-109').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=10-109')
 
     rio.seek(10)
     read_result = rio.read(100)
@@ -18,7 +20,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {'Content-Range' => '10-109/2577'}, status: 200, body: 'This is the response')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=10-109').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=10-109')
 
     rio.seek(10)
     read_result = rio.read(100)
@@ -29,7 +33,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {}, status: 403, body: 'Please log in')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
 
     rio.seek(100)
     expect { rio.read(100) }.to raise_error(/replied with a 403 and refused/)
@@ -39,7 +45,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {}, status: 416, body: 'You stepped off the ledge of the range')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
 
     rio.seek(100)
     expect(rio.read(100)).to be_nil
@@ -49,7 +57,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {}, status: 403, body: 'Please log in')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
 
     rio.seek(100)
     # rubocop: disable Lint/AmbiguousBlockAssociation
@@ -60,7 +70,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {}, status: 416, body: 'You jumped off the end of the file maam')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
 
     rio.seek(100)
     expect(rio.read(100)).to be_nil
@@ -69,15 +81,24 @@ describe FormatParser::RemoteIO do
   it 'does not overwrite size when the range cannot be satisfied and the response is 416' do
     rio = described_class.new('https://images.invalid/img.jpg')
 
-    fake_resp = double(headers: {'Content-Range' => 'bytes 0-0/13'}, status: 206, body: 'a')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=0-0').and_return(fake_resp)
+    fake_resp1 = double(headers: {'Content-Range' => 'bytes 0-0/13'}, status: 206, body: 'a')
+    fake_resp2 = double(headers: {}, status: 416, body: 'You jumped off the end of the file maam')
+
+    faraday_conn = instance_double(Faraday::Connection)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get)
+      .with('https://images.invalid/img.jpg', nil, range: 'bytes=0-0')
+      .ordered
+      .and_return(fake_resp1)
+    expect(faraday_conn).to receive(:get)
+      .with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
+      .ordered
+      .and_return(fake_resp2)
+
     rio.read(1)
 
     expect(rio.size).to eq(13)
 
-    fake_resp = double(headers: {}, status: 416, body: 'You jumped off the end of the file maam')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
-
     rio.seek(100)
     expect(rio.read(100)).to be_nil
 
@@ -88,7 +109,9 @@ describe FormatParser::RemoteIO do
     rio = described_class.new('https://images.invalid/img.jpg')
 
     fake_resp = double(headers: {}, status: 502, body: 'Guru meditation')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199')
 
     rio.seek(100)
     expect { rio.read(100) }.to raise_error(/replied with a 502 and we might want to retry/)
@@ -100,7 +123,9 @@ describe FormatParser::RemoteIO do
     expect(rio.pos).to eq(0)
 
     fake_resp = double(headers: {'Content-Range' => 'bytes 0-0/13'}, status: 206, body: 'a')
-    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=0-0').and_return(fake_resp)
+    faraday_conn = instance_double(Faraday::Connection, get: fake_resp)
+    allow(Faraday).to receive(:new).and_return(faraday_conn)
+    expect(faraday_conn).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=0-0')
     rio.read(1)
 
     expect(rio.pos).to eq(1)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.25.5
+  version: 0.29.0
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2020-12-11 00:00:00.000000000 Z
+date: 2021-02-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -73,6 +73,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.13'
+- !ruby/object:Gem::Dependency
+  name: faraday_middleware
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.14'
 - !ruby/object:Gem::Dependency
   name: measurometer
   requirement: !ruby/object:Gem::Requirement
@@ -183,10 +197,10 @@ executables:
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/main.yml"
 - ".gitignore"
 - ".rspec"
 - ".rubocop.yml"
-- ".travis.yml"
 - CHANGELOG.md
 - CODE_OF_CONDUCT.md
 - CONTRIBUTING.md
@@ -219,6 +233,7 @@ files:
 - lib/parsers/flac_parser.rb
 - lib/parsers/gif_parser.rb
 - lib/parsers/jpeg_parser.rb
+- lib/parsers/m3u_parser.rb
 - lib/parsers/moov_parser.rb
 - lib/parsers/moov_parser/decoder.rb
 - lib/parsers/mp3_parser.rb
@@ -236,6 +251,7 @@ files:
 - lib/read_limiter.rb
 - lib/read_limits_config.rb
 - lib/remote_io.rb
+- lib/text.rb
 - lib/video.rb
 - spec/active_storage/blob_io_spec.rb
 - spec/active_storage/rails_app_spec.rb
@@ -257,6 +273,7 @@ files:
 - spec/parsers/flac_parser_spec.rb
 - spec/parsers/gif_parser_spec.rb
 - spec/parsers/jpeg_parser_spec.rb
+- spec/parsers/m3u_parser_spec.rb
 - spec/parsers/moov_parser_spec.rb
 - spec/parsers/mp3_parser_spec.rb
 - spec/parsers/mpeg_parser_spec.rb

data/.travis.yml

@@ -1,12 +0,0 @@
-rvm:
-- 2.2.10
-- 2.3.8
-- 2.4.9
-- 2.5.8
-- 2.6.6
-- 2.7.2
-- jruby
-sudo: false
-cache: bundler
-script:
-  - bundle exec rake