rubyzip 1.2.3 → 2.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5bed33b4d4b864f1ad4d1a3483022c13b8079a607b2e4afc5b3828b9267f04c8
-  data.tar.gz: 0acb47d50691a266b1abc45e9b9c2abe5ac2310f38706ef5905bf53723e1f26d
+  metadata.gz: cba65b486ec6325e6623957990539a225398a2b9b665b5814a5c06ba70ea1744
+  data.tar.gz: 37dc716e5d98048e1b0c72165c16deb6a6bfef02556890f783cdc62ff5021f4e
 SHA512:
-  metadata.gz: 64da2a44d5a0b167ad81023554552f7cf101a6e5eb380ef356abaeb3c97d40e6dc6a5013b3fbfa615823833106bb31c8766e38b81d378b685a4eb680f5cc4ab5
-  data.tar.gz: 7f8157731ecfbb4497e97dcaff38bb6f259c5b18f070e04d5706170a999c7e0d41a32487fbf0e297836f60669f6d0a3e0cbbead7f5c2a06b56f651285786163e
+  metadata.gz: 45de19fa6e2c549c07830243686d622adb937509a942eeb1412a05ea6d1f4a1bde5d60429446ff64f607f3a55400a38c9ccd2d30380825fb4b6e55618702d802
+  data.tar.gz: 8d22f9bc464d950e9ede9cfc1da1056ba664ede954b93ae12d0af68e1d859600d8cd63ba5768553f3d810a693d38ce912c0c2d0f3b3d130da973c8bd833fb3bc

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:
 
 ```
@@ -59,7 +61,8 @@ 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 'zip'
@@ -83,7 +86,7 @@ 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 |zipfile|
       write_entries entries, '', zipfile
@@ -97,7 +100,6 @@ class ZipFileGenerator
     entries.each do |e|
       zipfile_path = path == '' ? e : File.join(path, e)
       disk_file_path = File.join(@input_dir, zipfile_path)
-      puts "Deflating #{disk_file_path}"
 
       if File.directory? disk_file_path
         recursively_deflate_directory(disk_file_path, zipfile, zipfile_path)
@@ -109,14 +111,12 @@ class ZipFileGenerator
 
   def recursively_deflate_directory(disk_file_path, zipfile, zipfile_path)
     zipfile.mkdir zipfile_path
-    subdir = Dir.entries(disk_file_path) - %w(. ..)
+    subdir = Dir.entries(disk_file_path) - %w[. ..]
     write_entries subdir, zipfile_path, zipfile
   end
 
   def put_into_archive(disk_file_path, zipfile, zipfile_path)
-    zipfile.get_output_stream(zipfile_path) do |f|
-      f.write(File.open(disk_file_path, 'rb').read)
-    end
+    zipfile.add(zipfile_path, disk_file_path)
   end
 end
 ```
@@ -152,12 +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
@@ -165,6 +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
 ```
@@ -177,7 +181,6 @@ 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 `::Zip::InputStream` finds such entry in the zip archive it will raise an exception.
 
 ### Password Protection (Experimental)
@@ -220,7 +223,9 @@ 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
@@ -234,32 +239,76 @@ 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`
 
-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:
+### Zip64 Support
+
+By default, Zip64 support is disabled for writing. To enable it do this:
 
 ```ruby
-Zip.force_entry_names_encoding = 'UTF-8'
+Zip.write_zip64_support = true
 ```
 
-Allowed encoding names are the same as accepted by `String#force_encoding`
+_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:
 
@@ -272,14 +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/lib/zip.rb

@@ -1,10 +1,10 @@
 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 +22,7 @@ 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'
@@ -29,7 +30,6 @@ require 'zip/inflater'
 require 'zip/deflater'
 require 'zip/streamable_stream'
 require 'zip/streamable_directory'
-require 'zip/constants'
 require 'zip/errors'
 
 module Zip
@@ -42,7 +42,8 @@ module Zip
                 :write_zip64_support,
                 :warn_invalid_date,
                 :case_insensitive_match,
-                :force_entry_names_encoding
+                :force_entry_names_encoding,
+                :validate_entry_sizes
 
   def reset!
     @_ran_once = false
@@ -54,6 +55,7 @@ module Zip
     @write_zip64_support = false
     @warn_invalid_date = true
     @case_insensitive_match = false
+    @validate_entry_sizes = true
   end
 
   def setup

data/lib/zip/constants.rb

@@ -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

data/lib/zip/crypto/decrypted_io.rb

@@ -0,0 +1,39 @@
+module Zip
+  class DecryptedIo #:nodoc:all
+    CHUNK_SIZE = 32_768
+
+    def initialize(io, decrypter)
+      @io = io
+      @decrypter = decrypter
+    end
+
+    def read(length = nil, outbuf = '')
+      return ((length.nil? || length.zero?) ? "" : nil) if eof
+
+      while length.nil? || (buffer.bytesize < length)
+        break if input_finished?
+        buffer << produce_input
+      end
+
+      outbuf.replace(buffer.slice!(0...(length || output_buffer.bytesize)))
+    end
+
+    private
+
+    def eof
+      buffer.empty? && input_finished?
+    end
+
+    def buffer
+      @buffer ||= ''.dup
+    end
+
+    def input_finished?
+      @io.eof
+    end
+
+    def produce_input
+      @decrypter.decrypt(@io.read(CHUNK_SIZE))
+    end
+  end
+end

data/lib/zip/decompressor.rb

@@ -1,9 +1,27 @@
 module Zip
   class Decompressor #:nodoc:all
     CHUNK_SIZE = 32_768
-    def initialize(input_stream)
+
+    def self.decompressor_classes
+      @decompressor_classes ||= {}
+    end
+
+    def self.register(compression_method, decompressor_class)
+      decompressor_classes[compression_method] = decompressor_class
+    end
+
+    def self.find_by_compression_method(compression_method)
+      decompressor_classes[compression_method]
+    end
+
+    attr_reader :input_stream
+    attr_reader :decompressed_size
+
+    def initialize(input_stream, decompressed_size = nil)
       super()
+
       @input_stream = input_stream
+      @decompressed_size = decompressed_size
     end
   end
 end

data/lib/zip/dos_time.rb

@@ -29,6 +29,11 @@ module Zip
       to_i / 2 == other.to_i / 2
     end
 
+    # Create a DOSTime instance from a vanilla Time instance.
+    def self.from_time(time)
+      local(time.year, time.month, time.day, time.hour, time.min, time.sec)
+    end
+
     def self.parse_binary_dos_format(binaryDosDate, binaryDosTime)
       second = 2 * (0b11111 & binaryDosTime)
       minute = (0b11111100000 & binaryDosTime) >> 5

data/lib/zip/entry.rb

@@ -34,7 +34,7 @@ module Zip
       end
       @follow_symlinks = false
 
-      @restore_times       = true
+      @restore_times       = false
       @restore_permissions = false
       @restore_ownership   = false
       # BUG: need an extra field to support uid/gid's
@@ -72,6 +72,14 @@ module Zip
       @extra = ::Zip::ExtraField.new(@extra.to_s) unless @extra.is_a?(::Zip::ExtraField)
     end
 
+    def encrypted?
+      gp_flags & 1 == 1
+    end
+
+    def incomplete?
+      gp_flags & 8 == 8
+    end
+
     def time
       if @extra['UniversalTime']
         @extra['UniversalTime'].mtime
@@ -163,7 +171,7 @@ module Zip
     # is passed.
     def extract(dest_path = nil, &block)
       if dest_path.nil? && !name_safe?
-        puts "WARNING: skipped #{@name} as unsafe"
+        warn "WARNING: skipped '#{@name}' as unsafe."
         return self
       end
 
@@ -406,16 +414,20 @@ module Zip
       @unix_uid   = stat.uid
       @unix_gid   = stat.gid
       @unix_perms = stat.mode & 0o7777
+      @time = ::Zip::DOSTime.from_time(stat.mtime)
     end
 
-    def set_unix_permissions_on_path(dest_path)
-      # BUG: does not update timestamps into account
+    def set_unix_attributes_on_path(dest_path)
       # ignore setuid/setgid bits by default.  honor if @restore_ownership
       unix_perms_mask = 0o1777
       unix_perms_mask = 0o7777 if @restore_ownership
       ::FileUtils.chmod(@unix_perms & unix_perms_mask, dest_path) if @restore_permissions && @unix_perms
       ::FileUtils.chown(@unix_uid, @unix_gid, dest_path) if @restore_ownership && @unix_uid && @unix_gid && ::Process.egid == 0
-      # File::utimes()
+
+      # Restore the timestamp on a file. This will either have come from the
+      # original source file that was copied into the archive, or from the
+      # creation date of the archive if there was no original source file.
+      ::FileUtils.touch(dest_path, mtime: time) if @restore_times
     end
 
     def set_extra_attributes_on_path(dest_path) # :nodoc:
@@ -423,7 +435,7 @@ module Zip
 
       case @fstype
       when ::Zip::FSTYPE_UNIX
-        set_unix_permissions_on_path(dest_path)
+        set_unix_attributes_on_path(dest_path)
       end
     end
 
@@ -591,7 +603,7 @@ module Zip
     def set_time(binary_dos_date, binary_dos_time)
       @time = ::Zip::DOSTime.parse_binary_dos_format(binary_dos_date, binary_dos_time)
     rescue ArgumentError
-      warn 'Invalid date/time in zip entry' if ::Zip.warn_invalid_date
+      warn 'WARNING: invalid date/time in zip entry.' if ::Zip.warn_invalid_date
     end
 
     def create_file(dest_path, _continue_on_exists_proc = proc { Zip.continue_on_exists_proc })
@@ -601,14 +613,26 @@ module Zip
       end
       ::File.open(dest_path, 'wb') do |os|
         get_input_stream do |is|
-          set_extra_attributes_on_path(dest_path)
-
+          bytes_written = 0
+          warned = false
           buf = ''.dup
           while (buf = is.sysread(::Zip::Decompressor::CHUNK_SIZE, buf))
             os << buf
+            bytes_written += buf.bytesize
+            if bytes_written > size && !warned
+              message = "entry '#{name}' should be #{size}B, but is larger when inflated."
+              if ::Zip.validate_entry_sizes
+                raise ::Zip::EntrySizeError, message
+              else
+                warn "WARNING: #{message}"
+                warned = true
+              end
+            end
           end
         end
       end
+
+      set_extra_attributes_on_path(dest_path)
     end
 
     def create_directory(dest_path)
@@ -630,7 +654,7 @@ module Zip
     def create_symlink(dest_path)
       # TODO: Symlinks pose security challenges. Symlink support temporarily
       # removed in view of https://github.com/rubyzip/rubyzip/issues/369 .
-      puts "WARNING: skipped symlink #{dest_path}"
+      warn "WARNING: skipped symlink '#{dest_path}'."
     end
 
     # apply missing data from the zip64 extra information field, if present