format_parser 0.9.3 → 0.9.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA256:
-  metadata.gz: cd4a3b56391cebff09efc933b5fd48188c67f913adeec46c77a832ff067fd870
-  data.tar.gz: 159c14df0b5740f627a99915f05750bf753c89620017733eab067c6e865e972d
+SHA1:
+  metadata.gz: 1ea761c606eb23bb10fd39f158afa2a628930018
+  data.tar.gz: eda078a306d8ded4dbdbdb4570608fe99b80b3e8
 SHA512:
-  metadata.gz: 559b0f5709bd8fc23cb20468eed5c3840a4087a444a581591b530490278532dff8700a54652e7e9cc8ab82b89ac2db910bf8e79620c7de5cf5a172cd7285ade3
-  data.tar.gz: d5baa5e7b5aea3cce2acf2513509b4dac8ad40dceb29a69875a10e4322dd136214ae650e82254416d1d39907a33cb18ed0d40634af0fa974a68ce2b0dc99b7dd
+  metadata.gz: 5596e607f371f5b05503d25fc749964af5dd3b945a3ec5011efcb4262a03c3325ea344a00e103cea13cf76e85bea41f10d4633d7f6f3a67dfeb17a7cbe04f2ea
+  data.tar.gz: d25fff95fbb51bd7b414e3e29104b798a8b5d6f11e1a4711266c16cadd532a436463be6ad0414acdda7904562a196b262738483a05e7cfa73d2138ebb4022200

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 0.9.4
+* Fix a TIFF parsing regression introduced in 0.3.1 that led to all TIFFs being incorrectly parsed
+
 ## 0.9.3
 * Fix a JPEG parsing regression introduced in 0.9.1
 

data/README.md

@@ -136,6 +136,10 @@ Unless specified otherwise in this section the fixture files are MIT licensed an
 ### M4A
 - fixture.m4a was created by one of the project maintainers and is MIT licensed
 
+### TIFF
+- `Shinbutsureijoushuincho.tiff` is obtained from Wikimedia Commons and is Creative Commons licensed
+- `IMG_9266_*.tif` and all it's variations were created by the project maintainers
+
 ### ZIP
 - The .zip fixture files have been created by the project maintainers
 

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.9.3'
+  VERSION = '0.9.4'
 end

data/lib/parsers/jpeg_parser.rb

@@ -118,6 +118,12 @@ class FormatParser::JPEGParser
     # does under the hood.
     app1_frame_content_length = read_short - 2
 
+    # If there is certainly not enough data in this APP1 to begin with, bail out.
+    # For the sake of the argument assume that a usable EXIF marker would contain
+    # at least 2 bytes of data - not exact science, but it can help us
+    # avoid reading _anything_ from the APP1 marker body if it's too small anyway
+    return if app1_frame_content_length < (EXIF_MAGIC_STRING.bytesize + 2)
+
     # Peek whether the contents of the marker starts with Exif\0
     maybe_exif_magic_str = safe_read(@buf, EXIF_MAGIC_STRING.bytesize)
 

data/lib/parsers/tiff_parser.rb

@@ -1,70 +1,37 @@
 class FormatParser::TIFFParser
   include FormatParser::IOUtils
 
-  LITTLE_ENDIAN_TIFF_HEADER_BYTES = [0x49, 0x49, 0x2A, 0x0]
-  BIG_ENDIAN_TIFF_HEADER_BYTES = [0x4D, 0x4D, 0x0, 0x2A]
-  WIDTH_TAG  = 0x100
-  HEIGHT_TAG = 0x101
+  MAGIC_LE = [0x49, 0x49, 0x2A, 0x0].pack('C4')
+  MAGIC_BE = [0x4D, 0x4D, 0x0, 0x2A].pack('C4')
 
   def call(io)
     io = FormatParser::IOConstraint.new(io)
-    magic_bytes = safe_read(io, 4).unpack('C4')
-    endianness = scan_tiff_endianness(magic_bytes)
-    return if !endianness || cr2_check(io)
 
-    w, h = read_tiff_by_endianness(io, endianness)
+    return unless [MAGIC_LE, MAGIC_BE].include?(safe_read(io, 4))
+    io.seek(io.pos + 2) # Skip over the offset of the IFD, EXIFR will re-read it anyway
+    return if cr2?(io)
+
+    # The TIFF scanner in EXIFR is plenty good enough,
+    # so why don't we use it? It does all the right skips
+    # in all the right places.
     scanner = FormatParser::EXIFParser.new(io)
     scanner.scan_image_tiff
+    return unless scanner.exif_data
+
     FormatParser::Image.new(
       format: :tif,
-      width_px: w,
-      height_px: h,
+      width_px: scanner.exif_data.image_width,
+      height_px: scanner.exif_data.image_length,
       # might be nil if EXIF metadata wasn't found
       orientation: scanner.orientation
     )
+  rescue EXIFR::MalformedTIFF
+    nil
   end
 
-  # TIFFs can be either big or little endian, so we check here
-  # and set our unpack method argument to suit.
-  def scan_tiff_endianness(magic_bytes)
-    if magic_bytes == LITTLE_ENDIAN_TIFF_HEADER_BYTES
-      'v'
-    elsif magic_bytes == BIG_ENDIAN_TIFF_HEADER_BYTES
-      'n'
-    end
-  end
-
-  # The TIFF format stores metadata in a flexible set of information fields
-  # called tags, which are stored in a header referred to as the IFD or
-  # Image File Directory. It is not necessarily in the same place in every image,
-  # so we need to do some work to scan through it and find the tags we need.
-  # For more information the TIFF wikipedia page is a reasonable place to start:
-  # https://en.wikipedia.org/wiki/TIFF
-  def scan_ifd(cache, offset, endianness)
-    entry_count = safe_read(cache, 4).unpack(endianness)[0]
-    entry_count.times do |i|
-      cache.seek(offset + 2 + (12 * i))
-      tag = safe_read(cache, 4).unpack(endianness)[0]
-      if tag == WIDTH_TAG
-        @width = safe_read(cache, 4).unpack(endianness.upcase)[0]
-      elsif tag == HEIGHT_TAG
-        @height = safe_read(cache, 4).unpack(endianness.upcase)[0]
-      end
-    end
-  end
-
-  def read_tiff_by_endianness(io, endianness)
-    io.seek(4)
-    offset = safe_read(io, 4).unpack(endianness.upcase)[0]
-    io.seek(offset)
-    scan_ifd(io, offset, endianness)
-    [@width, @height]
-  end
-
-  def cr2_check(io)
+  def cr2?(io)
     io.seek(8)
-    cr2_check_bytes = safe_read(io, 2)
-    cr2_check_bytes == 'CR'
+    safe_read(io, 2) == 'CR'
   end
 
   FormatParser.register_parser self, natures: :image, formats: :tif

data/spec/parsers/tiff_parser_spec.rb

@@ -1,7 +1,7 @@
 require 'spec_helper'
 
 describe FormatParser::TIFFParser do
-  describe 'is able to parse all the examples from FastImage' do
+  describe 'with FastImage TIFF examples' do
     Dir.glob(fixtures_dir + '/TIFF/*.tif').each do |tiff_path|
       it "is able to parse #{File.basename(tiff_path)}" do
         parsed = subject.call(File.open(tiff_path, 'rb'))
@@ -19,6 +19,48 @@ describe FormatParser::TIFFParser do
     end
   end
 
+  it 'extracts dimensions from a very large TIFF economically' do
+    tiff_path = fixtures_dir + '/TIFF/Shinbutsureijoushuincho.tiff'
+
+    io = File.open(tiff_path, 'rb')
+    io_with_stats = FormatParser::ReadLimiter.new(io)
+
+    parsed = subject.call(io_with_stats)
+
+    expect(parsed).not_to be_nil
+    expect(parsed.width_px).to eq(1120)
+    expect(parsed.height_px).to eq(1559)
+
+    expect(io_with_stats.reads).to be_within(4).of(4)
+    expect(io_with_stats.seeks).to be_within(4).of(4)
+    expect(io_with_stats.bytes).to be_within(1024).of(8198)
+  end
+
+  it 'correctly extracts dimensions for one fixture' do
+    tiff_path = fixtures_dir + '/TIFF/IMG_9266_8b_rgb_le_interleaved.tif'
+
+    parsed = subject.call(File.open(tiff_path, 'rb'))
+
+    expect(parsed).not_to be_nil
+    expect(parsed.width_px).to eq(320)
+    expect(parsed.height_px).to eq(240)
+  end
+
+  describe 'correctly extracts dimensions from various TIFF flavors of the same file' do
+    Dir.glob(fixtures_dir + '/TIFF/IMG_9266*.tif').each do |tiff_path|
+      it "is able to parse #{File.basename(tiff_path)}" do
+        parsed = subject.call(File.open(tiff_path, 'rb'))
+
+        expect(parsed).not_to be_nil
+        expect(parsed.nature).to eq(:image)
+        expect(parsed.format).to eq(:tif)
+
+        expect(parsed.width_px).to eq(320)
+        expect(parsed.height_px).to eq(240)
+      end
+    end
+  end
+
   describe 'is able to parse all the TIFF exif examples from FastImage' do
     Dir.glob(fixtures_dir + '/exif-orientation-testimages/tiff-*/*.tif').each do |tiff_path|
       it "is able to parse #{File.basename(tiff_path)}" do
@@ -34,9 +76,9 @@ describe FormatParser::TIFFParser do
     end
   end
 
-  describe 'is able to return nil when parsing CR2 examples' do
+  describe 'bails out on CR2 files, such as' do
     Dir.glob(fixtures_dir + '/CR2/*.CR2').each do |cr2_path|
-      it "is able to return nil when parsing #{File.basename(cr2_path)}" do
+      it "skips #{File.basename(cr2_path)}" do
         parsed = subject.call(File.open(cr2_path, 'rb'))
         expect(parsed).to be_nil
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.9.3
+  version: 0.9.4
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-04-21 00:00:00.000000000 Z
+date: 2018-04-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -247,7 +247,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.7.3
+rubygems_version: 2.5.2
 signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata