zip_tricks 5.2.0 → 5.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b686d9ddb071cdb677559d12879dfa88a77ac63ce6eabad99ce2d8e674c80c28
-  data.tar.gz: fc8d6382de69962cf2cb7585b9a7476e7694abaca77cf969f2cf9b905076d59c
+  metadata.gz: 96ce140b83c0f42fa013278de28cf3c2668fcec1bf1150951c6e6a6a00291125
+  data.tar.gz: f5f3fbca524376d336c04dd3f2e728bc7315187f70cefcaf97958a247b19e95d
 SHA512:
-  metadata.gz: 2949e24de0a8bc731ed0ae4d5fc30534e97ad1102f11c07a353ab211c2948bc1957c35527b4cb00eeb5751713d17a7653adbf65ea188b4fa9d0b0f0567926afe
-  data.tar.gz: 54972bf28272c68ce9bcada1f872840de04f7ae9a9e0276abeceb828373639f3ae9a999e788401937454d0354d86b87e462d4b60554e2478e7d8a7e6ac9c1348
+  metadata.gz: 9c794589191612f8ceba1fbef03e801a9610a7d29b5593a7d4ceecd27466706de10aa44ceb152771a13fc3aba42b38a8989104704284c4bfd18b14eb3d5828af
+  data.tar.gz: 65e8f07cd490e0a40a6770064eb76d85d9b43177f5fed7b5c46afa68d9347ae67f4c22e140924a9ae476932856e8ed9cd732d217ee5d7cc643971dac8b92729e

data/.rubocop.yml

@@ -11,3 +11,5 @@ Style/GlobalVars:
       - qa/*.rb
       - spec/spec_helper.rb
       - spec/support/zip_inspection.rb
+Layout/IndentHeredoc:
+  Enabled: false

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+## 5.3
+
+* Raise in `Streamer#close` when the IO offset of the Streamer does not match the size of the written entries. This is a situation which
+  can occur if one adds the local headers, writes the bodies of the files to the socket/output directly, and forgets to adjust the internal
+  Streamer offset. The unadjusted offset would then produce incorrect values in both the local headers which come after the missing
+  offset adjustment _and_ in the central directory headers. Some ZIP unarchivers are able to recover from this (ones that read
+  files "straight-ahead" but others aren't - if the ZIP unarchiver uses central directory entries it would be using incorrect offsets.
+  Instead of producing an invalid ZIP, raise an exception which explains what happened and how it can be resolved.
+
 ## 5.2
 
 * Remove `Streamer#add_compressed_entry` and `SizeEstimator#add_compressed_entry`

data/lib/zip_tricks/file_reader.rb

@@ -82,7 +82,9 @@ class ZipTricks::FileReader
 
   private_constant :StoredReader, :InflatingReader
 
-  # Represents a file within the ZIP archive being read
+  # Represents a file within the ZIP archive being read. This is different from
+  # the Entry object used in Streamer for ZIP writing, since during writing more
+  # data can be kept in memory for immediate use.
   class ZipEntry
     # @return [Fixnum] bit-packed version signature of the program that made the archive
     attr_accessor :made_by

data/lib/zip_tricks/streamer.rb

@@ -91,6 +91,7 @@ class ZipTricks::Streamer
   InvalidOutput = Class.new(ArgumentError)
   Overflow = Class.new(StandardError)
   UnknownMode = Class.new(StandardError)
+  OffsetOutOfSync = Class.new(StandardError)
 
   private_constant :DeflatedWriter, :StoredWriter, :STORED, :DEFLATED
 
@@ -149,7 +150,6 @@ class ZipTricks::Streamer
     @dedupe_filenames = auto_rename_duplicate_filenames
     @out = ZipTricks::WriteAndTell.new(stream)
     @files = []
-    @local_header_offsets = []
     @path_set = ZipTricks::PathSet.new
     @writer = writer
   end
@@ -360,14 +360,16 @@ class ZipTricks::Streamer
   #
   # @return [Integer] the offset the output IO is at after closing the archive
   def close
+    # Make sure offsets are in order
+    verify_offsets!
+
     # Record the central directory offset, so that it can be written into the EOCD record
     cdir_starts_at = @out.tell
 
     # Write out the central directory entries, one for each file
-    @files.each_with_index do |entry, i|
-      header_loc = @local_header_offsets.fetch(i)
+    @files.each do |entry|
       @writer.write_central_directory_file_header(io: @out,
-                                                  local_file_header_location: header_loc,
+                                                  local_file_header_location: entry.local_header_offset,
                                                   gp_flags: entry.gp_flags,
                                                   storage_mode: entry.storage_mode,
                                                   compressed_size: entry.compressed_size,
@@ -420,15 +422,40 @@ class ZipTricks::Streamer
     last_entry.compressed_size = compressed_size
     last_entry.uncompressed_size = uncompressed_size
 
+    offset_before_data_descriptor = @out.tell
     @writer.write_data_descriptor(io: @out,
                                   crc32: last_entry.crc32,
                                   compressed_size: last_entry.compressed_size,
                                   uncompressed_size: last_entry.uncompressed_size)
+    last_entry.bytes_used_for_data_descriptor = @out.tell - offset_before_data_descriptor
+
     @out.tell
   end
 
   private
 
+  def verify_offsets!
+    # We need to check whether the offsets noted for the entries actually make sense
+    computed_offset = @files.map(&:total_bytes_used).inject(0, &:+)
+    actual_offset = @out.tell
+    if computed_offset != actual_offset
+      message = <<-EMS
+The offset of the Streamer output IO is out of sync with the expected value. All entries written so far,
+including their compressed bodies, local headers and data descriptors, add up to a certain offset,
+but this offset does not match the actual offset of the IO.
+
+Entries add up to #{computed_offset} bytes and the IO is at #{actual_offset} bytes.
+
+This can happen if you write local headers for an entry, write the "body" of the entry directly to the IO
+object which is your destination, but do not adjust the offset known to the Streamer object. To adjust
+the offfset you need to call `Streamer#simulate_write(body_size)` after outputting the entry. Otherwise
+the local header offsets of the entries you write are going to be incorrect and some ZIP applications
+are going to have problems opening your archive.
+EMS
+      raise OffsetOutOfSync, message
+    end
+  end
+
   def add_file_and_write_local_header(
       filename:,
       modification_time:,
@@ -461,16 +488,18 @@ class ZipTricks::Streamer
       uncompressed_size = 0
     end
 
+    local_header_starts_at = @out.tell
+
     e = Entry.new(filename,
                   crc32,
                   compressed_size,
                   uncompressed_size,
                   storage_mode,
                   modification_time,
-                  use_data_descriptor)
-
-    @files << e
-    @local_header_offsets << @out.tell
+                  use_data_descriptor,
+                  _local_file_header_offset = local_header_starts_at,
+                  _bytes_used_for_local_header = 0,
+                  _bytes_used_for_data_descriptor = 0)
 
     @writer.write_local_file_header(io: @out,
                                     gp_flags: e.gp_flags,
@@ -480,6 +509,9 @@ class ZipTricks::Streamer
                                     mtime: e.mtime,
                                     filename: e.filename,
                                     storage_mode: e.storage_mode)
+    e.bytes_used_for_local_header = @out.tell - e.local_header_offset
+
+    @files << e
   end
 
   def remove_backslash(filename)

data/lib/zip_tricks/streamer/entry.rb

@@ -4,7 +4,7 @@
 # Normally you will not have to use this class directly
 class ZipTricks::Streamer::Entry < Struct.new(:filename, :crc32, :compressed_size,
                                               :uncompressed_size, :storage_mode, :mtime,
-                                              :use_data_descriptor)
+                                              :use_data_descriptor, :local_header_offset, :bytes_used_for_local_header, :bytes_used_for_data_descriptor)
   def initialize(*)
     super
     filename.force_encoding(Encoding::UTF_8)
@@ -15,6 +15,10 @@ class ZipTricks::Streamer::Entry < Struct.new(:filename, :crc32, :compressed_siz
                            end)
   end
 
+  def total_bytes_used
+    bytes_used_for_local_header + compressed_size + bytes_used_for_data_descriptor
+  end
+
   # Set the general purpose flags for the entry. We care about is the EFS
   # bit (bit 11) which should be set if the filename is UTF8. If it is, we need to set the
   # bit so that the unarchiving application knows that the filename in the archive is UTF-8

data/lib/zip_tricks/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module ZipTricks
-  VERSION = '5.2.0'
+  VERSION = '5.3.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: zip_tricks
 version: !ruby/object:Gem::Version
-  version: 5.2.0
+  version: 5.3.0
 platform: ruby
 authors:
 - Julik Tarkhanov