format_parser 2.7.0 → 2.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: f7b8b37e26143e2ea941db88183475e70c90ab658adcdad362b32b457a7d19ac
-  data.tar.gz: 50758e107065e1a2ab4fbca7775359d928cd1a62942277a94fcbabfefa1bfe10
+  metadata.gz: 5d2679a365f7c735d2b8c962765c4783b6336bf23461ffde1705ab141d250591
+  data.tar.gz: e1e4b4caa2956cbf1653d39498a9db84589cd0c9c979c6d84e9f3b3027427274
 SHA512:
-  metadata.gz: d34bcd7b0162fe6f911bdd8c3b626dd9ce35b98139bca6ec1b54e653bc7e50453af734c74134745a46e91fbc3528d88f1663fabdbd35e06ae908a41f8e81dcd7
-  data.tar.gz: 2ebbc65f373a3e34a2e8300d40bb239df6d2003dab54b9c461a8cc75f651800d93273aa73bfb4f1a14f195e65f348c218b90b4c1bae860c8269e024ebb2e890c
+  metadata.gz: 52e775ae2a4ced22d2879fff48108974bfe4087333b70d74c5c0910229aa7298826664bbd474dd9b4221777637cc51bf969735a830df976f58f0ff7302dd69c5
+  data.tar.gz: 31b8f95ff8fbcba01d60fe2377699a9abebc61a28d74afc05aa8456d6660f786ee268c2a621c0dc83490e3f9b04dc5e1a60319ae6f4c54503b3dfab9d39d520e

data/README.md

@@ -217,7 +217,7 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 - NEF examples are downloaded from http://www.rawsamples.ch/ and are Creative Common Licensed.
 
 ### OGG
-- `hi.ogg`,  `vorbis.ogg`, `with_confusing_magic_string.ogg`, `with_garbage_at_the_end.ogg` have been generated by the project contributors
+- `hi.ogg`,  `vorbis.ogg`, `with_confusing_magic_string.ogg`, `invalid_with_garbage_at_the_end.ogg` have been generated by the project contributors
 
 ### PDF
 - PDF 2.0 files downloaded from the [PDF Association public Github repository](https://github.com/pdf-association/pdf20examples). These files are licensed under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license.
@@ -236,7 +236,7 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 ### WAV
 - c_11k16bitpcm.wav and c_8kmp316.wav are from [Wikipedia WAV](https://en.wikipedia.org/wiki/WAV#Comparison_of_coding_schemes), retrieved January 7, 2018
 - c_39064__alienbomb__atmo-truck.wav is from [freesound](https://freesound.org/people/alienbomb/sounds/39064/) and is CC0 licensed
-- c_M1F1-Alaw-AFsp.wav and d_6_Channel_ID.wav are from a [McGill Engineering site](http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples.html)
+- c_M1F1-Alaw-AFsp.wav and invalid_d_6_Channel_ID.wav are from a [McGill Engineering site](http://www-mmsp.ece.mcgill.ca/Documents/AudioFormats/WAVE/Samples.html)
 
 ### WEBP
 - With the exception of extended-animation.webp, which was obtained from Wikimedia Commons and is Creative Commons

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '2.7.0'
+  VERSION = '2.7.1'
 end

data/lib/format_parser.rb

@@ -36,6 +36,9 @@ module FormatParser
   # The value will ensure the parser having it will be applied to the file last.
   LEAST_PRIORITY = 99
 
+  @registered_natures = []
+  @registered_formats = []
+
   # Register a parser object to be used to perform file format detection. Each parser FormatParser
   # provides out of the box registers itself using this method.
   #
@@ -68,9 +71,20 @@ module FormatParser
       end
       @parser_priorities ||= {}
       @parser_priorities[callable_parser] = priority
+
+      @registered_natures |= parser_provided_natures
+      @registered_formats |= parser_provided_formats
     end
   end
 
+  def self.registered_natures
+    @registered_natures
+  end
+
+  def self.registered_formats
+    @registered_formats
+  end
+
   # Deregister a parser object (makes FormatParser forget this parser existed). Is mostly used in
   # tests, but can also be used to forcibly disable some formats completely.
   #

data/lib/parsers/mp3_parser.rb

@@ -76,6 +76,11 @@ class FormatParser::MP3Parser
     io.seek(0)
     return if TIFF_HEADER_BYTES.include?(safe_read(io, 4))
 
+    # Prevention against parsing WAV files.
+    io.seek(0)
+    wav_chunk_id, _wav_size, wav_riff_type = safe_read(io, 12).unpack('a4la4')
+    return if wav_chunk_id == 'RIFF' || wav_riff_type == 'WAVE'
+
     # Read all the ID3 tags (or at least attempt to)
     io.seek(0)
     id3v1 = ID3Extraction.attempt_id3_v1_extraction(io)
@@ -315,5 +320,5 @@ class FormatParser::MP3Parser
     end
   end
 
-  FormatParser.register_parser new, natures: :audio, formats: :mp3, priority: 99
+  FormatParser.register_parser new, natures: :audio, formats: :mp3, priority: 101
 end

data/spec/format_parser_spec.rb

@@ -34,6 +34,26 @@ describe FormatParser do
       end
     end
 
+    it "fixtures with 'invalid' in the filename should fail to parse" do
+      Dir.glob(fixtures_dir + '/**/*.*').sort.each do |fixture_path|
+        file_name = File.basename(fixture_path)
+        next unless file_name.include? "invalid"
+        File.open(fixture_path, 'rb') do |file|
+          FormatParser.parse(file)
+        end
+      end
+    end
+
+    it "fixtures without 'invalid' in the filename should be parsed successfully" do
+      Dir.glob(fixtures_dir + '/**/*.*').sort.each do |fixture_path|
+        file_name = File.basename(fixture_path)
+        next if file_name.include? "invalid"
+        File.open(fixture_path, 'rb') do |file|
+          FormatParser.parse(file)
+        end
+      end
+    end
+
     it 'triggers parsers in a certain order that corresponds to the parser priorities' do
       file_contents = StringIO.new('a' * 4096)
 
@@ -189,12 +209,20 @@ describe FormatParser do
         'FormatParser::CR3Parser',
         'FormatParser::DPXParser',
         'FormatParser::FLACParser',
-        'FormatParser::MP3Parser',
         'FormatParser::OggParser',
         'FormatParser::TIFFParser',
-        'FormatParser::WAVParser'
+        'FormatParser::WAVParser',
+        'FormatParser::MP3Parser'
       ])
     end
+
+    it 'ensures that MP3 parser is the last one among all' do
+      natures = FormatParser.registered_natures
+      formats = FormatParser.registered_formats
+      prioritised_parsers = FormatParser.parsers_for(natures, formats)
+      parser_class_names = prioritised_parsers.map { |parser| parser.class.name }
+      expect(parser_class_names.last).to eq 'FormatParser::MP3Parser'
+    end
   end
 
   describe '.register_parser and .deregister_parser' do

data/spec/parsers/flac_parser_spec.rb

@@ -55,7 +55,7 @@ describe FormatParser::FLACParser do
   end
 
   it 'raises an error when sample rate is 0' do
-    fpath = fixtures_dir + 'FLAC/sample_rate_0.flac'
+    fpath = fixtures_dir + 'FLAC/invalid_sample_rate_0.flac'
 
     expect {
       subject.call(File.open(fpath, 'rb'))

data/spec/parsers/json_parser_spec.rb

@@ -99,7 +99,7 @@ describe FormatParser::JSONParser do
 
   describe 'When reading objects invalid JSON files' do
     it "rejects files with corrupted JSON data" do
-      io = load_file 'malformed.json'
+      io = load_file 'invalid_malformed.json'
 
       parsed = subject.call(io)
 
@@ -107,7 +107,7 @@ describe FormatParser::JSONParser do
     end
 
     it "rejects invalid files early without reading the whole content" do
-      io = load_file 'lorem_ipsum.json'
+      io = load_file 'invalid_lorem_ipsum.json'
 
       parsed = subject.call(io)
 

data/spec/parsers/m3u_parser_spec.rb

@@ -11,7 +11,7 @@ describe FormatParser::M3UParser do
   end
 
   describe 'an m3u file with missing header' do
-    let(:m3u_file) { 'plain_text.m3u' }
+    let(:m3u_file) { 'invalid_plain_text.m3u' }
 
     it 'does not parse the file successfully' do
       expect(parsed_m3u).to be_nil

data/spec/parsers/mp3_parser_spec.rb

@@ -36,6 +36,12 @@ describe FormatParser::MP3Parser do
     expect(parsed).to be_nil
   end
 
+  it 'does not misdetect a WAV' do
+    fpath = fixtures_dir + '/WAV/c_SCAM_MIC_SOL001_RUN001.wav'
+    parsed = subject.call(File.open(fpath, 'rb'))
+    expect(parsed).to be_nil
+  end
+
   describe 'title/artist/album attributes' do
     let(:parsed) { subject.call(File.open(fpath, 'rb')) }
 

data/spec/parsers/ogg_parser_spec.rb

@@ -13,7 +13,7 @@ describe FormatParser::OggParser do
   end
 
   it 'skips a file if it contains more than MAX_POSSIBLE_OGG_PAGE_SIZE bytes of garbage at the end' do
-    parse_result = subject.call(File.open(__dir__ + '/../fixtures/Ogg/with_garbage_at_the_end.ogg', 'rb'))
+    parse_result = subject.call(File.open(__dir__ + '/../fixtures/Ogg/invalid_with_garbage_at_the_end.ogg', 'rb'))
     expect(parse_result).to be_nil
   end
 

data/spec/parsers/pdf_parser_spec.rb

@@ -46,17 +46,17 @@ describe FormatParser::PDFParser do
 
   describe 'broken PDF files should not parse' do
     it 'PDF with missing version header' do
-      parsed_pdf = parse_pdf 'not_a.pdf'
+      parsed_pdf = parse_pdf 'invalid_not_a.pdf'
       expect(parsed_pdf).to be_nil
     end
 
     it 'PDF 2.0 with offset start' do
-      parsed_pdf = parse_pdf 'PDF 2.0 with offset start.pdf'
+      parsed_pdf = parse_pdf 'invalid PDF 2.0 with offset start.pdf'
       expect(parsed_pdf).to be_nil
     end
 
     it 'exceeds the PDF read limit' do
-      parsed_pdf = parse_pdf 'exceed_PDF_read_limit.pdf'
+      parsed_pdf = parse_pdf 'invalid_exceed_PDF_read_limit.pdf'
       expect(parsed_pdf).to be_nil
     end
   end

data/spec/parsers/wav_parser_spec.rb

@@ -48,7 +48,7 @@ describe FormatParser::WAVParser do
 
   it "cannot parse file with audio format different from 1 and no 'fact' chunk" do
     expect {
-      subject.call(File.open(__dir__ + '/../fixtures/WAV/d_6_Channel_ID.wav', 'rb'))
+      subject.call(File.open(__dir__ + '/../fixtures/WAV/invalid_d_6_Channel_ID.wav', 'rb'))
     }.to raise_error(FormatParser::IOUtils::InvalidRead)
   end
 end

data/spec/parsers/webp_parser_spec.rb

@@ -7,7 +7,7 @@ describe FormatParser::WebpParser do
   end
 
   it 'does not parse files with an unrecognised variant' do
-    result = subject.call(File.open(fixtures_dir + 'WEBP/unrecognised-variant.webp', 'rb'))
+    result = subject.call(File.open(fixtures_dir + 'WEBP/invalid-unrecognised-variant.webp', 'rb'))
     expect(result).to be_nil
   end
 

data/spec/remote_fetching_spec.rb

@@ -104,6 +104,43 @@ describe 'Fetching data from HTTP remotes' do
     expect(file_information.format).to eq(:png)
   end
 
+  describe 'correctly parses WAV files without falling back to another filetype' do
+    ['c_8kmp316.wav', 'c_SCAM_MIC_SOL001_RUN001.wav'].each do |filename|
+      it "parses WAV file #{filename}" do
+        remote_url = 'http://localhost:9399/WAV/' + filename
+        file_information = FormatParser.parse_http(remote_url)
+        expect(file_information).not_to be_nil
+        expect(file_information.format).to eq(:wav)
+      end
+    end
+  end
+
+  describe "correctly parses files over HTTP without filename hint" do
+    Dir.glob(fixtures_dir + '/**/*.*').sort.each do |fixture_path|
+      file_name = File.basename(fixture_path)
+      next if file_name.include? "invalid"
+
+      file_type_dir = fixture_path.delete_prefix(fixtures_dir).delete_suffix(file_name)
+      file_type_dir.delete_prefix!('/').delete_suffix!('/')
+      next if file_type_dir.empty?
+
+      # skipping this one because it's a special case
+      next if file_name == "arch_many_entries.zip"
+
+      it "parses #{file_type_dir} file: #{file_name}" do
+        url = "http://localhost:9399/#{file_type_dir}/#{file_name}?some_param=test".gsub(' ', '%20')
+        result_with_hint = FormatParser.parse_http(url, filename_hint: file_name)
+        result_no_hint = FormatParser.parse_http(url)
+
+        expect(result_with_hint).not_to be_nil
+        expect(result_no_hint).not_to be_nil
+
+        expect(result_no_hint.nature).to eq(result_with_hint.nature)
+        expect(result_no_hint.format).to eq(result_with_hint.format)
+      end
+    end
+  end
+
   describe 'when parsing remote fixtures' do
     Dir.glob(fixtures_dir + '/**/*.*').sort.each do |fixture_path|
       filename = File.basename(fixture_path)

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 2.7.0
+  version: 2.7.1
 platform: ruby
 authors:
 - Noah Berman
 - Julik Tarkhanov
-autorequire:
+autorequire: 
 bindir: exe
 cert_chain: []
-date: 2023-06-27 00:00:00.000000000 Z
+date: 2023-08-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: exifr
@@ -319,7 +319,7 @@ licenses:
 - MIT (Hippocratic)
 metadata:
   allowed_push_host: https://rubygems.org
-post_install_message:
+post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
@@ -334,8 +334,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
-signing_key:
+rubygems_version: 3.1.6
+signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata
 test_files: []