rubyzip 1.2.0 → 2.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 4af5fd26173e16759a74f190b293f84cc02d605b
-  data.tar.gz: 05666235e929fdb9bd6abe6807d3bf9583e65244
+SHA256:
+  metadata.gz: 8ffab0e42187d7bbd5b732ff0b9395a6215587a18ce5dd9d64da46d1c628a69c
+  data.tar.gz: 3032ae5d4f62644c1a19d5de25d515844ecb8da0f59c774fcaa6b16904f496b7
 SHA512:
-  metadata.gz: 2f4b82040f81e517ddb65660bea4a3368ec5e150bd094051d0ae3a515184c2eef55e32bcf5f49877bd432b3331a809402977e1c4b2a045695c8d2f45ab86f43c
-  data.tar.gz: 31fdb0e8c66d737d341161d02faf343786d0a0d1beca058cff4532886a2cfe268b738c6307b042c22a3186909953cd6879656a7660ef607eea906f407f1aada1
+  metadata.gz: 218f77b0c4ae423f2baed702bf56bb598e2c3d22a01fc9af8c2fa33432580e2706a820474fa1222480370517a9f28bda692a2f296d89620459d9c6239fcfff37
+  data.tar.gz: a4ffa820bb2272b07bd918827d03751261f87d694966ef6c88f74f4ec569c94b0420c9288a92e5370653d00790478bdd85d3e89a9ef42ccd94834facb622c336

data/README.md

@@ -1,4 +1,5 @@
 # rubyzip
+
 [![Gem Version](https://badge.fury.io/rb/rubyzip.svg)](http://badge.fury.io/rb/rubyzip)
 [![Build Status](https://secure.travis-ci.org/rubyzip/rubyzip.svg)](http://travis-ci.org/rubyzip/rubyzip)
 [![Code Climate](https://codeclimate.com/github/rubyzip/rubyzip.svg)](https://codeclimate.com/github/rubyzip/rubyzip)
@@ -19,9 +20,10 @@ gem 'zip-zip' # will load compatibility for old rubyzip API.
 
 ## Requirements
 
-* Ruby 1.9.2 or greater
+- Ruby 2.4 or greater (for rubyzip 2.0; use 1.x for older rubies)
 
 ## Installation
+
 Rubyzip is available on RubyGems:
 
 ```
@@ -52,30 +54,29 @@ Zip::File.open(zipfile_name, Zip::File::CREATE) do |zipfile|
     # Two arguments:
     # - The name of the file as it will appear in the archive
     # - The original file, including the path to find it
-    zipfile.add(filename, folder + '/' + filename)
+    zipfile.add(filename, File.join(folder, filename))
   end
-  zipfile.get_output_stream("myFile") { |os| os.write "myFile contains just this" }
+  zipfile.get_output_stream("myFile") { |f| f.write "myFile contains just this" }
 end
 ```
 
 ### Zipping a directory recursively
-Copy from [here](https://github.com/rubyzip/rubyzip/blob/05916bf89181e1955118fd3ea059f18acac28cc8/samples/example_recursive.rb )
+
+Copy from [here](https://github.com/rubyzip/rubyzip/blob/9d891f7353e66052283562d3e252fe380bb4b199/samples/example_recursive.rb)
 
 ```ruby
-require 'rubygems'
 require 'zip'
+
 # This is a simple example which uses rubyzip to
 # recursively generate a zip file from the contents of
 # a specified directory. The directory itself is not
 # included in the archive, rather just its contents.
 #
 # Usage:
-# require /path/to/the/ZipFileGenerator/Class
-# directoryToZip = "/tmp/input"
-# outputFile = "/tmp/out.zip"
-# zf = ZipFileGenerator.new(directoryToZip, outputFile)
-# zf.write()
-
+#   directory_to_zip = "/tmp/input"
+#   output_file = "/tmp/out.zip"
+#   zf = ZipFileGenerator.new(directory_to_zip, output_file)
+#   zf.write()
 class ZipFileGenerator
   # Initialize with the directory to zip and the location of the output archive.
   def initialize(input_dir, output_file)
@@ -85,40 +86,37 @@ class ZipFileGenerator
 
   # Zip the input directory.
   def write
-    entries = Dir.entries(@input_dir) - %w(. ..)
+    entries = Dir.entries(@input_dir) - %w[. ..]
 
-    ::Zip::File.open(@output_file, ::Zip::File::CREATE) do |io|
-      write_entries entries, '', io
+    ::Zip::File.open(@output_file, ::Zip::File::CREATE) do |zipfile|
+      write_entries entries, '', zipfile
     end
   end
 
   private
 
   # A helper method to make the recursion work.
-  def write_entries(entries, path, io)
+  def write_entries(entries, path, zipfile)
     entries.each do |e|
-      zip_file_path = path == '' ? e : File.join(path, e)
-      disk_file_path = File.join(@input_dir, zip_file_path)
-      puts "Deflating #{disk_file_path}"
+      zipfile_path = path == '' ? e : File.join(path, e)
+      disk_file_path = File.join(@input_dir, zipfile_path)
 
       if File.directory? disk_file_path
-        recursively_deflate_directory(disk_file_path, io, zip_file_path)
+        recursively_deflate_directory(disk_file_path, zipfile, zipfile_path)
       else
-        put_into_archive(disk_file_path, io, zip_file_path)
+        put_into_archive(disk_file_path, zipfile, zipfile_path)
       end
     end
   end
 
-  def recursively_deflate_directory(disk_file_path, io, zip_file_path)
-    io.mkdir zip_file_path
-    subdir = Dir.entries(disk_file_path) - %w(. ..)
-    write_entries subdir, zip_file_path, io
+  def recursively_deflate_directory(disk_file_path, zipfile, zipfile_path)
+    zipfile.mkdir zipfile_path
+    subdir = Dir.entries(disk_file_path) - %w[. ..]
+    write_entries subdir, zipfile_path, zipfile
   end
 
-  def put_into_archive(disk_file_path, io, zip_file_path)
-    io.get_output_stream(zip_file_path) do |f|
-      f.puts(File.open(disk_file_path, 'rb').read)
-    end
+  def put_into_archive(disk_file_path, zipfile, zipfile_path)
+    zipfile.add(zipfile_path, disk_file_path)
   end
 end
 ```
@@ -154,12 +152,15 @@ When modifying a zip archive the file permissions of the archive are preserved.
 ### Reading a Zip file
 
 ```ruby
+MAX_SIZE = 1024**2 # 1MiB (but of course you can increase this)
 Zip::File.open('foo.zip') do |zip_file|
   # Handle entries one by one
   zip_file.each do |entry|
-    # Extract to file/directory/symlink
     puts "Extracting #{entry.name}"
-    entry.extract(dest_file)
+    raise 'File too large when extracted' if entry.size > MAX_SIZE
+
+    # Extract to file or directory based on name in the archive
+    entry.extract
 
     # Read into memory
     content = entry.get_input_stream.read
@@ -167,6 +168,7 @@ Zip::File.open('foo.zip') do |zip_file|
 
   # Find specific entry
   entry = zip_file.glob('*.csv').first
+  raise 'File too large when extracted' if entry.size > MAX_SIZE
   puts entry.get_input_stream.read
 end
 ```
@@ -177,9 +179,7 @@ end
 
 But there is one exception when it is not working - General Purpose Flag Bit 3.
 
-```
-If bit 3 (0x08) of the general-purpose flags field is set, then the CRC-32 and file sizes are not known when the header is written. The fields in the local header are filled with zero, and the CRC-32 and size are appended in a 12-byte structure (optionally preceded by a 4-byte signature) immediately after the compressed data
-```
+> If bit 3 (0x08) of the general-purpose flags field is set, then the CRC-32 and file sizes are not known when the header is written. The fields in the local header are filled with zero, and the CRC-32 and size are appended in a 12-byte structure (optionally preceded by a 4-byte signature) immediately after the compressed data
 
 If `::Zip::InputStream` finds such entry in the zip archive it will raise an exception.
 
@@ -218,12 +218,14 @@ buffer = Zip::OutputStream.write_buffer do |out|
   out.write rels.to_xml(:indent => 0).gsub("\n","")
 end
 
-File.open(new_path, "w") {|f| f.write(buffer.string) }
+File.open(new_path, "wb") {|f| f.write(buffer.string) }
 ```
 
 ## Configuration
 
-By default, rubyzip will not overwrite files if they already exist inside of the extracted path.  To change this behavior, you may specify a configuration option like so:
+### Existing Files
+
+By default, rubyzip will not overwrite files if they already exist inside of the extracted path. To change this behavior, you may specify a configuration option like so:
 
 ```ruby
 Zip.on_exists_proc = true
@@ -237,25 +239,77 @@ Additionally, if you want to configure rubyzip to overwrite existing files while
 Zip.continue_on_exists_proc = true
 ```
 
+### Non-ASCII Names
+
 If you want to store non-english names and want to open them on Windows(pre 7) you need to set this option:
 
 ```ruby
 Zip.unicode_names = true
 ```
 
+Sometimes file names inside zip contain non-ASCII characters. If you can assume which encoding was used for such names and want to be able to find such entries using `find_entry` then you can force assumed encoding like so:
+
+```ruby
+Zip.force_entry_names_encoding = 'UTF-8'
+```
+
+Allowed encoding names are the same as accepted by `String#force_encoding`
+
+### Date Validation
+
 Some zip files might have an invalid date format, which will raise a warning. You can hide this warning with the following setting:
 
 ```ruby
 Zip.warn_invalid_date = false
 ```
 
+### Size Validation
+
+By default (in rubyzip >= 2.0), rubyzip's `extract` method checks that an entry's reported uncompressed size is not (significantly) smaller than its actual size. This is to help you protect your application against [zip bombs](https://en.wikipedia.org/wiki/Zip_bomb). Before `extract`ing an entry, you should check that its size is in the range you expect. For example, if your application supports processing up to 100 files at once, each up to 10MiB, your zip extraction code might look like:
+
+```ruby
+MAX_FILE_SIZE = 10 * 1024**2 # 10MiB
+MAX_FILES = 100
+Zip::File.open('foo.zip') do |zip_file|
+  num_files = 0
+  zip_file.each do |entry|
+    num_files += 1 if entry.file?
+    raise 'Too many extracted files' if num_files > MAX_FILES
+    raise 'File too large when extracted' if entry.size > MAX_FILE_SIZE
+    entry.extract
+  end
+end
+```
+
+If you need to extract zip files that report incorrect uncompressed sizes and you really trust them not too be too large, you can disable this setting with
+```ruby
+Zip.validate_entry_sizes = false
+```
+
+Note that if you use the lower level `Zip::InputStream` interface, `rubyzip` does *not* check the entry `size`s. In this case, the caller is responsible for making sure it does not read more data than expected from the input stream.
+
+### Default Compression
+
 You can set the default compression level like so:
 
 ```ruby
 Zip.default_compression = Zlib::DEFAULT_COMPRESSION
 ```
+
 It defaults to `Zlib::DEFAULT_COMPRESSION`. Possible values are `Zlib::BEST_COMPRESSION`, `Zlib::DEFAULT_COMPRESSION` and `Zlib::NO_COMPRESSION`
 
+### Zip64 Support
+
+By default, Zip64 support is disabled for writing. To enable it do this:
+
+```ruby
+Zip.write_zip64_support = true
+```
+
+_NOTE_: If you will enable Zip64 writing then you will need zip extractor with Zip64 support to extract archive.
+
+### Block Form
+
 You can set multiple settings at the same time by using a block:
 
 ```ruby
@@ -267,14 +321,6 @@ You can set multiple settings at the same time by using a block:
   end
 ```
 
-By default, Zip64 support is disabled for writing. To enable it do this:
-
-```ruby
-Zip.write_zip64_support = true
-```
-
-_NOTE_: If you will enable Zip64 writing then you will need zip extractor with Zip64 support to extract archive.
-
 ## Developing
 
 To run the test you need to do this:

data/Rakefile

@@ -1,5 +1,6 @@
 require 'bundler/gem_tasks'
 require 'rake/testtask'
+require 'rubocop/rake_task'
 
 task default: :test
 
@@ -10,6 +11,8 @@ Rake::TestTask.new(:test) do |test|
   test.verbose = true
 end
 
+RuboCop::RakeTask.new
+
 # Rake::TestTask.new(:zip64_full_test) do |test|
 #  test.libs << File.join(File.dirname(__FILE__), 'lib')
 #  test.libs << File.join(File.dirname(__FILE__), 'test')

data/lib/zip.rb

@@ -1,10 +1,11 @@
+require 'English'
 require 'delegate'
 require 'singleton'
 require 'tempfile'
-require 'tmpdir'
 require 'fileutils'
 require 'stringio'
 require 'zlib'
+require 'zip/constants'
 require 'zip/dos_time'
 require 'zip/ioextras'
 require 'rbconfig'
@@ -22,6 +23,7 @@ require 'zip/null_compressor'
 require 'zip/null_input_stream'
 require 'zip/pass_thru_compressor'
 require 'zip/pass_thru_decompressor'
+require 'zip/crypto/decrypted_io'
 require 'zip/crypto/encryption'
 require 'zip/crypto/null_encryption'
 require 'zip/crypto/traditional_encryption'
@@ -29,12 +31,20 @@ require 'zip/inflater'
 require 'zip/deflater'
 require 'zip/streamable_stream'
 require 'zip/streamable_directory'
-require 'zip/constants'
 require 'zip/errors'
 
 module Zip
   extend self
-  attr_accessor :unicode_names, :on_exists_proc, :continue_on_exists_proc, :sort_entries, :default_compression, :write_zip64_support, :warn_invalid_date, :case_insensitive_match
+  attr_accessor :unicode_names,
+                :on_exists_proc,
+                :continue_on_exists_proc,
+                :sort_entries,
+                :default_compression,
+                :write_zip64_support,
+                :warn_invalid_date,
+                :case_insensitive_match,
+                :force_entry_names_encoding,
+                :validate_entry_sizes
 
   def reset!
     @_ran_once = false
@@ -46,6 +56,7 @@ module Zip
     @write_zip64_support = false
     @warn_invalid_date = true
     @case_insensitive_match = false
+    @validate_entry_sizes = true
   end
 
   def setup

data/lib/zip/central_directory.rb

@@ -65,7 +65,7 @@ module Zip
         @entry_set ? @entry_set.size : 0, # number of entries on this disk
         @entry_set ? @entry_set.size : 0, # number of entries total
         cdir_size, # size of central directory
-        offset, # offset of start of central directory in its disk
+        offset # offset of start of central directory in its disk
       ]
       io << tmp.pack('VQ<vvVVQ<Q<Q<Q<')
     end
@@ -96,7 +96,7 @@ module Zip
       @size_in_bytes                                = Entry.read_zip_64_long(buf)
       @cdir_offset                                  = Entry.read_zip_64_long(buf)
       @zip_64_extensible                            = buf.slice!(0, buf.bytesize)
-      raise Error, 'Zip consistency problem while reading eocd structure' unless buf.size == 0
+      raise Error, 'Zip consistency problem while reading eocd structure' unless buf.empty?
     end
 
     def read_e_o_c_d(buf) #:nodoc:
@@ -113,7 +113,7 @@ module Zip
                                                       else
                                                         buf.read(comment_length)
                                                       end
-      raise Error, 'Zip consistency problem while reading eocd structure' unless buf.size == 0
+      raise Error, 'Zip consistency problem while reading eocd structure' unless buf.empty?
     end
 
     def read_central_directory_entries(io) #:nodoc:
@@ -130,7 +130,7 @@ module Zip
 
     def read_from_stream(io) #:nodoc:
       buf = start_buf(io)
-      if self.zip64_file?(buf)
+      if zip64_file?(buf)
         read_64_e_o_c_d(buf)
       else
         read_e_o_c_d(buf)
@@ -141,6 +141,7 @@ module Zip
     def get_e_o_c_d(buf) #:nodoc:
       sig_index = buf.rindex([END_OF_CDS].pack('V'))
       raise Error, 'Zip end of central directory signature not found' unless sig_index
+
       buf = buf.slice!((sig_index + 4)..(buf.bytesize))
 
       def buf.read(count)
@@ -166,8 +167,10 @@ module Zip
     def get_64_e_o_c_d(buf) #:nodoc:
       zip_64_start = buf.rindex([ZIP64_END_OF_CDS].pack('V'))
       raise Error, 'Zip64 end of central directory signature not found' unless zip_64_start
+
       zip_64_locator = buf.rindex([ZIP64_EOCD_LOCATOR].pack('V'))
       raise Error, 'Zip64 end of central directory signature locator not found' unless zip_64_locator
+
       buf = buf.slice!((zip_64_start + 4)..zip_64_locator)
 
       def buf.read(count)
@@ -178,8 +181,8 @@ module Zip
     end
 
     # For iterating over the entries.
-    def each(&proc)
-      @entry_set.each(&proc)
+    def each(&a_proc)
+      @entry_set.each(&a_proc)
     end
 
     # Returns the number of entries in the central directory (and
@@ -191,13 +194,14 @@ module Zip
     def self.read_from_stream(io) #:nodoc:
       cdir = new
       cdir.read_from_stream(io)
-      return cdir
+      cdir
     rescue Error
-      return nil
+      nil
     end
 
     def ==(other) #:nodoc:
       return false unless other.kind_of?(CentralDirectory)
+
       @entry_set.entries.sort == other.entries.sort && comment == other.comment
     end
   end

data/lib/zip/compressor.rb

@@ -1,7 +1,6 @@
 module Zip
   class Compressor #:nodoc:all
-    def finish
-    end
+    def finish; end
   end
 end
 

data/lib/zip/constants.rb

@@ -11,9 +11,9 @@ module Zip
   VERSION_NEEDED_TO_EXTRACT              = 20
   VERSION_NEEDED_TO_EXTRACT_ZIP64        = 45
 
-  FILE_TYPE_FILE    = 010
-  FILE_TYPE_DIR     = 004
-  FILE_TYPE_SYMLINK = 012
+  FILE_TYPE_FILE    = 0o10
+  FILE_TYPE_DIR     = 0o04
+  FILE_TYPE_SYMLINK = 0o12
 
   FSTYPE_FAT      = 0
   FSTYPE_AMIGA    = 1
@@ -60,4 +60,56 @@ module Zip
     FSTYPE_MAC_OSX  => 'Mac OS/X (Darwin)'.freeze,
     FSTYPE_ATHEOS   => 'AtheOS'.freeze
   }.freeze
+
+  COMPRESSION_METHOD_STORE = 0
+  COMPRESSION_METHOD_SHRINK = 1
+  COMPRESSION_METHOD_REDUCE_1 = 2
+  COMPRESSION_METHOD_REDUCE_2 = 3
+  COMPRESSION_METHOD_REDUCE_3 = 4
+  COMPRESSION_METHOD_REDUCE_4 = 5
+  COMPRESSION_METHOD_IMPLODE = 6
+  # RESERVED = 7
+  COMPRESSION_METHOD_DEFLATE = 8
+  COMPRESSION_METHOD_DEFLATE_64 = 9
+  COMPRESSION_METHOD_PKWARE_DCLI = 10
+  # RESERVED = 11
+  COMPRESSION_METHOD_BZIP2 = 12
+  # RESERVED = 13
+  COMPRESSION_METHOD_LZMA = 14
+  # RESERVED = 15
+  COMPRESSION_METHOD_IBM_CMPSC = 16
+  # RESERVED = 17
+  COMPRESSION_METHOD_IBM_TERSE = 18
+  COMPRESSION_METHOD_IBM_LZ77 = 19
+  COMPRESSION_METHOD_JPEG = 96
+  COMPRESSION_METHOD_WAVPACK = 97
+  COMPRESSION_METHOD_PPMD = 98
+  COMPRESSION_METHOD_AES = 99
+
+  COMPRESSION_METHODS = {
+    COMPRESSION_METHOD_STORE       => 'Store (no compression)',
+    COMPRESSION_METHOD_SHRINK      => 'Shrink',
+    COMPRESSION_METHOD_REDUCE_1    => 'Reduce with compression factor 1',
+    COMPRESSION_METHOD_REDUCE_2    => 'Reduce with compression factor 2',
+    COMPRESSION_METHOD_REDUCE_3    => 'Reduce with compression factor 3',
+    COMPRESSION_METHOD_REDUCE_4    => 'Reduce with compression factor 4',
+    COMPRESSION_METHOD_IMPLODE     => 'Implode',
+    # RESERVED = 7
+    COMPRESSION_METHOD_DEFLATE     => 'Deflate',
+    COMPRESSION_METHOD_DEFLATE_64  => 'Deflate64(tm)',
+    COMPRESSION_METHOD_PKWARE_DCLI => 'PKWARE Data Compression Library Imploding (old IBM TERSE)',
+    # RESERVED = 11
+    COMPRESSION_METHOD_BZIP2       => 'BZIP2',
+    # RESERVED = 13
+    COMPRESSION_METHOD_LZMA        => 'LZMA',
+    # RESERVED = 15
+    COMPRESSION_METHOD_IBM_CMPSC   => 'IBM z/OS CMPSC Compression',
+    # RESERVED = 17
+    COMPRESSION_METHOD_IBM_TERSE   => 'IBM TERSE (new)',
+    COMPRESSION_METHOD_IBM_LZ77    => 'IBM LZ77 z Architecture (PFS)',
+    COMPRESSION_METHOD_JPEG        => 'JPEG variant',
+    COMPRESSION_METHOD_WAVPACK     => 'WavPack compressed data',
+    COMPRESSION_METHOD_PPMD        => 'PPMd version I, Rev 1',
+    COMPRESSION_METHOD_AES         => 'AES encryption'
+  }.freeze
 end