format_parser 0.21.0 → 0.21.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ad2245de4a2119c7572c3962ad14abbf16395b2bec4064b218ee9f99d1e7c24b
-  data.tar.gz: b982bcc7f6626b66684db532317b0c0d35cd062aa89766ea1a230f93e7d996d6
+  metadata.gz: 916f22d0efd27a6e32065b50c51a4a482664c344669aa1f9586769ccf2be7b06
+  data.tar.gz: 3fd1b2ba7285ca69bb8d4c14c9f83e4001b55fee7e85332d97cbdbd36620597f
 SHA512:
-  metadata.gz: 2df2a3763e12e2bb0c70a8f5ec3319fcf6a3210a73461dc8abb5ec2af706028403eca48cf8c589bd40122dff0cfdabce383a79b1253237e219a5c89936ec0a5e
-  data.tar.gz: 0ca6084649313b2c7ad32204b4c8b745f13dbf6cf2c347cb7c80ca7976b964f00feabd9666c0372e9a6c10e4ed250500ed4e202cdb687372cbd369378b7a0faa
+  metadata.gz: df680824b240f15df52fbc6c14d44f9b5fb99a93fb69cf191db6027a9871115f5e3e5bbaec48751853683b01b8e87b4266b0bbfb23700901910f2ce0f8da1137
+  data.tar.gz: d944a5db3fb2e1d06435b10bfc6aa0651312b45393180b08cf7a7f0b6237a0804b90a216cdeaf770e50de1af5bf31234f987e6fabc0e72bcb682e59a87cf2e7a

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.21.1
+* MPEG: Ensure parsing does not inadvertently return an Integer instead of Result|nil
+* MPEG: Scan further into the MPEG file than previously (scan 32 1KB chunks)
+* MPEG: Ensure the parser does not raise an exception when there is no data to read for scanning beyound the initial header
+
 ## 0.21.0
 * Adds support for MPEG video files
 

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.21.0'
+  VERSION = '0.21.1'
 end

data/lib/parsers/mpeg_parser.rb

@@ -26,9 +26,8 @@ class FormatParser::MPEGParser
 
   PACK_HEADER_START_CODE = [0x00, 0x00, 0x01, 0xBA].pack('C*')
   SEQUENCE_HEADER_START_CODE = [0xB3].pack('C*')
-  SEEK_FOR_SEQUENCE_HEADER_TIMES_LIMIT = 4
-  SEEK_FOR_SEQUENCE_HEADER_START_CODE_TIMES_LIMIT = 4
-  BYTES_TO_READ_PER_TIME = 1024
+  MAX_BLOCK_READS = 32
+  BYTES_TO_READ_PER_READ = 1024
 
   def self.likely_match?(filename)
     filename =~ /\.(mpg|mpeg)$/i
@@ -37,18 +36,19 @@ class FormatParser::MPEGParser
   def self.call(io)
     return unless matches_mpeg_header?(io)
 
-    # We are looping though the stream because there can be several sequence headers and some of them are not usefull.
-    # If we detect that the header is not usefull, then we look for the next one for SEEK_FOR_SEQUENCE_HEADER_TIMES_LIMIT
+    # We are looping though the stream because there can be several sequence headers and some of them are not useful.
+    # If we detect that the header is not useful, then we look for the next one for SEEK_FOR_SEQUENCE_HEADER_TIMES_LIMIT
     # If we reach the EOF, then the mpg is likely to be corrupted and we return nil
-    SEEK_FOR_SEQUENCE_HEADER_TIMES_LIMIT.times do
-      return if fetch_next_sequence_header_code_position(io).nil?
+    MAX_BLOCK_READS.times do
+      next unless pos = find_next_header_code_pos(io)
+      io.seek(pos + 1)
       horizontal_size, vertical_size = parse_image_size(io)
       ratio_code, rate_code = parse_rate_information(io)
-
       if valid_aspect_ratio_code?(ratio_code) && valid_frame_rate_code?(rate_code)
         return file_info(horizontal_size, vertical_size, ratio_code, rate_code)
       end
     end
+    nil # otherwise the return value of Integer#times will be returned
   rescue FormatParser::IOUtils::InvalidRead
     nil
   end
@@ -90,15 +90,11 @@ class FormatParser::MPEGParser
   # Returns the position of the next sequence package content in the stream
   # This method will read BYTES_TO_READ_PER_TIME in each loop for a maximum amount of SEEK_FOR_SEQUENCE_HEADER_START_CODE_TIMES_LIMIT times
   # If the package is not found, then it returns nil.
-  def self.fetch_next_sequence_header_code_position(io)
-    SEEK_FOR_SEQUENCE_HEADER_START_CODE_TIMES_LIMIT.times do
-      bytes_stream_read = io.read(BYTES_TO_READ_PER_TIME)
-      header_relative_index = bytes_stream_read.index(SEQUENCE_HEADER_START_CODE)
-      next if header_relative_index.nil?
-      new_io_pos = io.pos - BYTES_TO_READ_PER_TIME + header_relative_index + 1
-      io.seek(new_io_pos)
-      return new_io_pos
-    end
+  def self.find_next_header_code_pos(io)
+    pos_before_read = io.pos
+    bin_str = io.read(BYTES_TO_READ_PER_READ) # bin_str might be nil if we are at EOF
+    header_relative_index = bin_str && bin_str.index(SEQUENCE_HEADER_START_CODE)
+    return pos_before_read + header_relative_index if header_relative_index
   end
 
   # If the first 4 bytes of the stream are equal to 00 00 01 BA, the pack start code for the Pack Header, then it's an MPEG file.

data/spec/parsers/mpeg_parser_spec.rb

@@ -12,6 +12,27 @@ describe FormatParser::MPEGParser do
     expect(parse_result.intrinsics[:frame_rate]).to eq('30')
   end
 
+  it 'returns a nil if it is necessary to iterate over a very large number of bytes and the requisite sequences are not detected' do
+    bytes_buffer = StringIO.new
+    bytes_buffer.write([0x00, 0x00, 0x01, 0xBA].pack('C*')) # MPEG header
+    zero_bytes = [0x00].pack('C') * (1024 * 1024 * 5)
+    bytes_buffer.write(zero_bytes)
+
+    bytes_buffer.rewind
+
+    parse_result = described_class.call(bytes_buffer)
+    expect(parse_result).to be_nil
+  end
+
+  it 'returns a nil if the IO only contains the MPEG header bytes at the start and nothing else' do
+    bytes_buffer = StringIO.new
+    bytes_buffer.write([0x00, 0x00, 0x01, 0xBA].pack('C*')) # MPEG header
+    bytes_buffer.rewind
+
+    parse_result = described_class.call(bytes_buffer)
+    expect(parse_result).to be_nil
+  end
+
   it 'parses a file with mpeg extension' do
     parse_result = described_class.call(File.open(__dir__ + '/../fixtures/MPG/video2.mpeg', 'rb'))
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.21.0
+  version: 0.21.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-03-27 00:00:00.000000000 Z
+date: 2020-04-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks