zip_tricks 4.1.0 → 4.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f6d3a4df27461f1235e526d7d40eb089f4df5c64
-  data.tar.gz: 179df69ea7d164f9164aabcc0c19d951e8d5748f
+  metadata.gz: 7a529e0fc4dae54675a7ba880475ec6860ae6c4e
+  data.tar.gz: e5ef83a503a377bfa504a9daeeb415367c9c680e
 SHA512:
-  metadata.gz: 68131f0f180074731223f145f06d42f65d7ee327bfcc73c7445a9ae2be198ba8ed2372cffb9deba8729c7b3af46eb4cacdeb3ae408fd37a202c848933ce93ffa
-  data.tar.gz: 9e38d0ce079b7e367b75db3b6ebd032fef11802f12926cf586f061bdb7f059c1087505b2556cfd76062e288601923d51e4c7a1ca5ca5bb928fcae385ee92807b
+  metadata.gz: 46d2a64d61873cf3b32889ef99408fab97aeb25eecc7cd76690f40c328c7bdcec9aa6f9d981726a775b79d1746709a35817156221aaf339dc7cda885e58796bc
+  data.tar.gz: 458b3a982c1e533d321b2fffebd086125aeb29e0b5e687cfc187e340847200e946ce7944ee237298dae1c1702ef8e3a971ceb53b439e7156f12ae9c7ff995842

data/lib/zip_tricks.rb

@@ -1,5 +1,5 @@
 module ZipTricks
-  VERSION = '4.1.0'
+  VERSION = '4.2.0'
   
   # Require all the sub-components except myself
   Dir.glob(__dir__ + '/**/*.rb').sort.each {|p| require p unless p == __FILE__ }

data/lib/zip_tricks/file_reader.rb

@@ -199,10 +199,22 @@ class ZipTricks::FileReader
     log { 'Located the central directory start at %d' % cdir_location }
     seek(io, cdir_location)
 
-    # Read the entire central directory in one fell swoop
-    central_directory_str = read_n(io, cdir_size)
+    # Read the entire central directory AND anything behind it, in one fell swoop.
+    # Strictly speaking, we should be able to read `cdir_size` bytes and not a byte more.
+    # However, we know for a fact that in some of our files the central directory size
+    # is in fact misreported. `zipinfo` then says:
+    #
+    #    warning [ktsglobal-2b03bc.zip]:  1 extra byte at beginning or within zipfile
+    #      (attempting to process anyway)
+    #    error [ktsglobal-2b03bc.zip]:  reported length of central directory is
+    #      -1 bytes too long (Atari STZip zipfile?  J.H.Holm ZIPSPLIT 1.1
+    #      zipfile?).  Compensating...
+    #
+    # Since the EOCD is not that big anyway, we just read the entire "tail" of the ZIP ignoring
+    # the central directory size alltogether.
+    central_directory_str = io.read # and not read_n(io, cdir_size), see above
     central_directory_io = StringIO.new(central_directory_str)
-    log { 'Read %d bytes with central directory entries' % cdir_size }
+    log { 'Read %d bytes with central directory + EOCD record and locator' % central_directory_str.bytesize }
 
     entries = (0...num_files).map do |entry_n|
       log { 'Reading the central directory entry %d starting at offset %d' % [entry_n, cdir_location + central_directory_io.tell] }

data/lib/zip_tricks/streamer.rb

@@ -70,16 +70,18 @@ class ZipTricks::Streamer
   #
   # @param stream [IO] the destination IO for the ZIP (should respond to `tell` and `<<`)
   # @yield [Streamer] the streamer that can be written to
-  def self.open(stream)
-    archive = new(stream)
+  def self.open(stream, **kwargs_for_new)
+    archive = new(stream, **kwargs_for_new)
     yield(archive)
     archive.close
   end
 
   # Creates a new Streamer on top of the given IO-ish object.
   #
-  # @param stream [IO] the destination IO for the ZIP (should respond to `<<`)
-  def initialize(stream)
+  # @param stream[IO] the destination IO for the ZIP (should respond to `<<`)
+  # @param writer[ZipTricks::ZipWriter] the object to be used as the writer.
+  #    Defaults to an instance of ZipTricks::ZipWriter, normally you won't need to override it
+  def initialize(stream, writer: create_writer)
     raise InvalidOutput, "The stream must respond to #<<" unless stream.respond_to?(:<<)
     unless stream.respond_to?(:tell) && stream.respond_to?(:advance_position_by)
       stream = ZipTricks::WriteAndTell.new(stream) 
@@ -88,7 +90,7 @@ class ZipTricks::Streamer
     @out = stream
     @files = []
     @local_header_offsets = []
-    @writer = create_writer
+    @writer = writer
   end
 
   # Writes a part of a zip entry body (actual binary data of the entry) into the output stream.

data/spec/zip_tricks/file_reader_spec.rb

@@ -1,7 +1,7 @@
 require 'spec_helper'
 describe ZipTricks::FileReader do
   
-  describe 'with a file without EOCD' do
+  context 'with a file without EOCD' do
     it 'raises the MissingEOCD exception and refuses to read' do
       f = StringIO.new
       10.times { f << ('A' * 1024 ) }
@@ -72,8 +72,47 @@ describe ZipTricks::FileReader do
       }.to raise_error(described_class::UnsupportedFeature)
     end
   end
-  
-  describe 'with an end-to-end ZIP file to read' do
+
+  context 'with a ZIP file where the size of the central directory is recorded incorrectly, and has a wrong value' do
+    it 'is still able to read the entries' do
+      # Purposefully create a ZIP that we will damage after
+      zipfile = StringIO.new
+      tolstoy = File.read(__dir__ + '/war-and-peace.txt')
+      tolstoy.force_encoding(Encoding::BINARY)
+      
+      # Make a one-off Writer that corrupts the size of the central directory and says there is more data
+      # in it than there actually is
+      class EvilWriter < ZipTricks::ZipWriter
+        def write_end_of_central_directory(**kwargs)
+          kwargs[:central_directory_size] = kwargs[:central_directory_size] + 64 # Pretend there has to be more data
+          super(**kwargs)
+        end
+      end
+        
+      ZipTricks::Streamer.open(zipfile, writer: EvilWriter.new) do |zip|
+        zip.write_deflated_file('text-1.txt') { |sink| sink << tolstoy }
+        zip.write_deflated_file('text-2.txt') { |sink| sink << tolstoy }
+      end
+      
+      # Find the start of the EOCD record (signature, then the information about disk numbers and the information
+      # about the file counts
+      eocd_start_marker = [0x06054b50, 0, 0, 2, 2].pack('Vvvvv')
+      eocd_offset = zipfile.string.index(eocd_start_marker)
+      expect(eocd_offset).not_to be_nil
+      
+      # Seek to the offset where the central directory size is going to be (just after the string we looked for)
+      zipfile.seek(eocd_offset + eocd_start_marker.bytesize)
+      # and overwrite it.
+      zipfile.write([118].pack('V'))
+      zipfile.rewind
+      
+      entries = ZipTricks::FileReader.read_zip_structure(io: zipfile)
+      
+      expect(entries.length).to eq(2)
+    end
+  end
+
+  context 'with an end-to-end ZIP file to read' do
     it 'reads and uncompresses the file written deflated with data descriptors' do
       zipfile = StringIO.new
       tolstoy = File.read(__dir__ + '/war-and-peace.txt')

data/spec/zip_tricks/streamer_spec.rb

@@ -24,7 +24,21 @@ describe ZipTricks::Streamer do
       described_class.new(nil)
     }.to raise_error(ZipTricks::Streamer::InvalidOutput)
   end
-
+  
+  it 'allows the writer to be injectable' do
+    fake_writer = double('ZipWriter')
+    expect(fake_writer).to receive(:write_local_file_header)
+    expect(fake_writer).to receive(:write_data_descriptor)
+    expect(fake_writer).to receive(:write_central_directory_file_header)
+    expect(fake_writer).to receive(:write_end_of_central_directory)
+    
+    described_class.open('', writer: fake_writer) do |zip|
+      zip.write_deflated_file('stored.txt') do |sink|
+        sink << File.read(__dir__ + '/war-and-peace.txt')
+      end
+    end
+  end
+  
   it 'returns the position in the IO at every call' do
     io = StringIO.new
     zip = described_class.new(io)

data/zip_tricks.gemspec

@@ -2,16 +2,16 @@
 # DO NOT EDIT THIS FILE DIRECTLY
 # Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
 # -*- encoding: utf-8 -*-
-# stub: zip_tricks 4.1.0 ruby lib
+# stub: zip_tricks 4.2.0 ruby lib
 
 Gem::Specification.new do |s|
   s.name = "zip_tricks"
-  s.version = "4.1.0"
+  s.version = "4.2.0"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.require_paths = ["lib"]
   s.authors = ["Julik Tarkhanov"]
-  s.date = "2016-09-14"
+  s.date = "2016-09-17"
   s.description = "Stream out ZIP files from Ruby"
   s.email = "me@julik.nl"
   s.extra_rdoc_files = [

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: zip_tricks
 version: !ruby/object:Gem::Version
-  version: 4.1.0
+  version: 4.2.0
 platform: ruby
 authors:
 - Julik Tarkhanov
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-09-14 00:00:00.000000000 Z
+date: 2016-09-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip