format_parser 0.5.0 → 0.5.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7ff294de8e6759d2705cabe93f548ffb6733a121410e1b3c9dc929de52356745
-  data.tar.gz: 663240675efd9e8e5425f27333098e8661ef5e8dbbbd38bab91fff1e605bbefc
+  metadata.gz: db8e4506635f3537372a808c9ab1fae08aba28a80cd5671616be56728f472b15
+  data.tar.gz: 6ba88eeff2cba9e3d77cb2bf3a5af25cc73dbff384a6c92104a2f7f669313c7c
 SHA512:
-  metadata.gz: ed7ea153adf28d2efb9352a880d9f4a146ebdad53e282f75d36c2dee2887740d727c25373d33c83dc8ab863e680e12175bb19109cbecf2347950a6fc0233c385
-  data.tar.gz: cf6d750264fdfe5a9520c3bb9a8a02b856ba825b709435661b3fcd614f118fc3709d3ba88a25bff0a142f1d03d4fc2389f63740606ff5df4e2db837977a66488
+  metadata.gz: 74f4bfce599ad2a9897009b9cb4f443dc00233ac0aff1eec104f71cdb820e5e4b63cfa82ca92ac67c44e3092a307801512fc275af86d60283ea1c9c604175712
+  data.tar.gz: ce6b0972fa92c85d04a8a6c3cfa42d1834a1c3bb63e157021c694a8e390922f8d61d51f7072ed818805a8ac7b1358401a1a1d8ee7866c34c8698446dd6b386ed

data/README.md

@@ -150,6 +150,7 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 
 ### JPEG
 - `divergent_pixel_dimensions_exif.jpg` is used with permission from LiveKom GmbH
+- `extended_reads.jpg` has kindly been made available by Raphaelle Pellerin for use exclusively with format_parser
 
 ### AIFF
 - fixture.aiff was created by one of the project maintainers and is MIT licensed

data/lib/care.rb

@@ -4,7 +4,7 @@
 # is only available via HTTP, for example, we can have less
 # fetches and have them return more data for one fetch
 class Care
-  DEFAULT_PAGE_SIZE = 16 * 1024
+  DEFAULT_PAGE_SIZE = 64 * 1024
 
   class IOWrapper
     def initialize(io, cache = Cache.new(DEFAULT_PAGE_SIZE))

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.5.0'
+  VERSION = '0.5.1'
 end

data/lib/parsers/zip_parser.rb

@@ -1,4 +1,5 @@
 class FormatParser::ZIPParser
+  UNICODE_REPLACEMENT_CHAR = [0xFFFD].pack('U')
   require_relative 'zip_parser/file_reader'
   require_relative 'zip_parser/office_formats'
 
@@ -11,7 +12,7 @@ class FormatParser::ZIPParser
     filenames_set = Set.new
     entries_archive = entries.map do |ze|
       ft = directory?(ze) ? :directory : :file
-      decoded_filename = decode_filename(ze)
+      decoded_filename = decode_filename_of(ze)
       filenames_set << decoded_filename
       FormatParser::Archive::Entry.new(type: ft, size: ze.uncompressed_size, filename: decoded_filename)
     end
@@ -35,13 +36,18 @@ class FormatParser::ZIPParser
     zip_entry.filename.end_with?('/')
   end
 
-  def decode_filename(zip_entry)
+  def decode_filename(filename, likely_unicode:)
+    filename.force_encoding(Encoding::UTF_8) if likely_unicode
+    filename.encode(Encoding::UTF_8, undefined: :replace, replace: UNICODE_REPLACEMENT_CHAR)
+  end
+
+  def decode_filename_of(zip_entry)
     # Check for the EFS bit in the general-purpose flags. If it is set,
     # the entry filename can be treated as UTF-8
     if zip_entry.gp_flags & 0b100000000000 == 0b100000000000
-      zip_entry.filename.unpack('U*').pack('U*')
+      decode_filename(zip_entry.filename, likely_unicode: true)
     else
-      zip_entry.filename.encode(Encoding::UTF_8, undefined: :replace)
+      decode_filename(zip_entry.filename, likely_unicode: false)
     end
   end
 

data/spec/parsers/zip_parser_spec.rb

@@ -89,4 +89,14 @@ describe FormatParser::ZIPParser do
       expect(e[:type]).to be_kind_of(String)
     end
   end
+
+  it 'parses filenames in ZIP encoded in a local DOS encoding' do
+    spanish_zip_path = fixtures_dir + '/ZIP/broken_filename.zip'
+
+    result = subject.call(File.open(spanish_zip_path, 'rb'))
+
+    first_entry = result.entries.first
+    expect(first_entry.filename).to eq('Li��nia Extreme//')
+    expect(first_entry.type).to eq(:directory)
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.5.0
+  version: 0.5.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-04-03 00:00:00.000000000 Z
+date: 2018-04-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks