format_parser 0.24.0 → 0.24.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cef6e8b3f4c3914ef022e7ff0e92d38357670315c0804efe8a2967f7f4228f53
-  data.tar.gz: '09a817b4fc688a3695800f4602a5901613b591d7a30ba26b86988720da7e13a9'
+  metadata.gz: c76879d955fbe7598ee7ccdfc663876a29621e1fe4e54721edbba19d8e5f9c81
+  data.tar.gz: 7cd4161abb24e1a195fec86dc6c9ced63cb642832edf4d4d9c33129208fdf8b4
 SHA512:
-  metadata.gz: 979804c2a7381d09e1f4952396321e185a917587d44409b1f7d45be0e05b466601eb7281e3d463785c6c18d79ba48ff3858bcd60c0f6791e2d394c4fa40ed684
-  data.tar.gz: a58cd8cab20fa8b8b7886a36479bd03fb6f5a4afbf9435d09318da502de50f6f257e45b012a56c79b4309dbaaf96feedb6b2b12016979bffa1336c528a591e3b
+  metadata.gz: 6125db42f078e6e7d4fb0a9111ce29d6750a6b5fedcbfd9a7b28f66fca8fbf59e513f2b91cccc7a2409744dd1a49b7e60361bc7af0c8414bde42e9fd535941e9
+  data.tar.gz: f285a67739a9722a77aa9871e0d9b553a463dd22090c3728c8f97898740b303d91c214f2565d679895325e2d45399be311550e4263554d5e056d2ce528108374

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 0.24.1
+* Fix MP3 frames reading to jump correctly to the next bytes
+
 ## 0.24.0
 * The TIFF parser will now return :arw as format for Sony ARW files insted of :tif so that the caller can decide whether it
   wants to deal with RAW processing or not

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.24.0'
+  VERSION = '0.24.1'
 end

data/lib/parsers/mp3_parser.rb

@@ -20,13 +20,14 @@ class FormatParser::MP3Parser
 
   # We limit the number of MPEG frames we scan
   # to obtain our duration estimation
-  MAX_FRAMES_TO_SCAN = 128
+  MAX_FRAMES_TO_SCAN = 500
 
   # Default frame size for mp3
   SAMPLES_PER_FRAME = 1152
 
   # For some edge cases
   ZIP_LOCAL_ENTRY_SIGNATURE = "PK\x03\x04\x14\x00".b
+  PNG_HEADER_BYTES = [137, 80, 78, 71, 13, 10, 26, 10].pack('C*')
 
   # Wraps the Tag object returned by ID3Tag in such
   # a way that a usable JSON representation gets
@@ -60,8 +61,12 @@ class FormatParser::MP3Parser
     # To avoid having that happen, we check for the PKZIP signature -
     # local entry header signature - at the very start of the file.
     # If the file is too small safe_read will fail too and the parser
-    # will terminate here.
-    return if safe_read(io, 6) == ZIP_LOCAL_ENTRY_SIGNATURE
+    # will terminate here. Same with PNGs. In the future
+    # we should implement "confidence" for MP3 as of all our formats
+    # it is by far the most lax.
+    header = safe_read(io, 8)
+    return if header.start_with?(ZIP_LOCAL_ENTRY_SIGNATURE)
+    return if header.start_with?(PNG_HEADER_BYTES)
 
     # Read all the ID3 tags (or at least attempt to)
     io.seek(0)
@@ -131,27 +136,28 @@ class FormatParser::MP3Parser
   # if you have a minute. https://pypi.python.org/pypi/tinytag
   def parse_mpeg_frames(io)
     mpeg_frames = []
+    bytes_to_read = 4
 
     MAX_FRAMES_TO_SCAN.times do |frame_i|
       # Read through until we can latch onto the 11 sync bits. Read in 4-byte
       # increments to save on read() calls
-      data = io.read(4)
+      data = io.read(bytes_to_read)
 
       # If we are at EOF - stop iterating
-      break unless data && data.bytesize == 4
+      break unless data && data.bytesize == bytes_to_read
 
       # Look for the sync pattern. It can be either the last byte being 0xFF,
       # or any of the 2 bytes in sequence being 0xFF and > 0xF0.
       four_bytes = data.unpack('C4')
       seek_jmp = sync_bytes_offset_in_4_byte_seq(four_bytes)
       if seek_jmp > 0
-        io.seek(io.pos + seek_jmp)
+        io.seek(io.pos - bytes_to_read + seek_jmp)
         next
       end
 
       # Once we are past that stage we have latched onto a sync frame header
       sync, conf, bitrate_freq, rest = four_bytes
-      frame_detail = parse_mpeg_frame_header(io.pos - 4, sync, conf, bitrate_freq, rest)
+      frame_detail = parse_mpeg_frame_header(io.pos - bytes_to_read, sync, conf, bitrate_freq, rest)
       mpeg_frames << frame_detail
 
       # There might be a xing header in the first frame that contains
@@ -166,7 +172,7 @@ class FormatParser::MP3Parser
         end
       end
       if frame_detail.frame_length > 1 # jump over current frame body
-        io.seek(io.pos + frame_detail.frame_length - 4)
+        io.seek(io.pos + frame_detail.frame_length - bytes_to_read)
       end
     end
     [nil, mpeg_frames]

data/spec/parsers/mp3_parser_spec.rb

@@ -15,6 +15,12 @@ describe FormatParser::MP3Parser do
     expect(parsed.media_duration_seconds).to be_within(0.1).of(0.836)
   end
 
+  it 'does not misdetect a PNG' do
+    fpath = fixtures_dir + '/PNG/anim.png'
+    parsed = subject.call(File.open(fpath, 'rb'))
+    expect(parsed).to be_nil
+  end
+
   describe 'title/artist/album attributes' do
     let(:parsed) { subject.call(File.open(fpath, 'rb')) }
 
@@ -90,6 +96,14 @@ describe FormatParser::MP3Parser do
     expect(parsed.title).to eq('test')
   end
 
+  it 'reads the mpeg frames correctly' do
+    fpath = fixtures_dir + '/MP3/test_read_frames.mp3'
+
+    parsed = subject.call(File.open(fpath, 'rb'))
+
+    expect(parsed.audio_sample_rate_hz). to eq(48000)
+  end
+
   it 'parses the Cassy MP3' do
     fpath = fixtures_dir + '/MP3/Cassy.mp3'
     parsed = subject.call(File.open(fpath, 'rb'))

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.24.0
+  version: 0.24.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2020-09-15 00:00:00.000000000 Z
+date: 2020-09-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -292,7 +292,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.6
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata