format_parser 1.4.0 → 1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cf7fbbf842a1ae6fcde3986b360877223ac699a87950848b508da15f8a8280ad
-  data.tar.gz: 29882db7afe75a1d3b6554f18dbc837cefb1dbe9e8927adafe959ac8d37ade84
+  metadata.gz: 6402f116eddca928e4807f76d4631f052a841c360137833310900b9604107997
+  data.tar.gz: 62e2a34f739d912f850e1e732c3e9cc154eadcaff5c76cc0f56fc163298e9192
 SHA512:
-  metadata.gz: 0cf33f73ac298f565020e9819c9c7d2e2af340490b869b97a008b4466ac2b0825fed70d5d9e255ef1192520cef92fdeeff0c7ade18d5e38910d6dc2fd0de89f3
-  data.tar.gz: c20cdc92df0d29d1e0c4b9f8c05644e17216f239a8d90e9c7af38f5566b4abaaf6f6289d5cc69d6a25b0ed644236403820b5c3402080f0b7ba40ca112b671d3a
+  metadata.gz: 9385682da9e3a86f67e25cf3491c90f8993a4073a9378f33d20e470f5917dea9afe913c29c16f17412e5f46fb226b8016c51a18327eee74b5f624e304d227c83
+  data.tar.gz: 2aa680436faa13496921e6134b3b3c341bd0e0b21c1a2a8656e3102165bb6f5bdec941790797861720f840283a171dc9501ae572f4048c8fbe76393badb8bdea

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 1.4.1
+* Skip Exif chunks that are malformed during `WEBP` parsing.
+
 ## 1.4.0
 * Add support for `WEBP` lossy, lossless and extended file formats.
 

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '1.4.0'
+  VERSION = '1.4.1'
 end

data/lib/parsers/webp_parser.rb

@@ -129,7 +129,7 @@ class FormatParser::WebpParser
       # Try to read the next chunk header, and break the loop if we've reached EOF.
       begin
         fourcc, chunk_size = safe_read(@buf, 8).unpack('A4V')
-      rescue InvalidRead
+      rescue FormatParser::IOUtils::InvalidRead
         break
       end
 
@@ -138,11 +138,18 @@ class FormatParser::WebpParser
 
       case fourcc
       when 'EXIF'
-        exif = exif_from_tiff_io(StringIO.new(safe_read(@buf, chunk_size)))
-        # We use ||= here as one Exif chunk at most should be present, even though it is possible for there to be more.
-        intrinsics[:exif] ||= exif
-        image.height_px, image.width_px = image.width_px, image.height_px if exif&.rotated?
-        image.orientation = exif&.orientation_sym
+        chunk_pos = @buf.pos
+        begin
+          exif = exif_from_tiff_io(StringIO.new(safe_read(@buf, chunk_size)))
+          # We use ||= here as one Exif chunk at most should be present, even though it is possible for there to be more.
+          intrinsics[:exif] ||= exif
+          image.height_px, image.width_px = image.width_px, image.height_px if exif&.rotated?
+          image.orientation = exif&.orientation_sym
+        rescue EXIFR::MalformedTIFF
+          # Exif data was malformed and could not be parsed. Need to ensure that buffer is pointing at the next chunk.
+          @buf.seek(chunk_pos + chunk_size)
+          next
+        end
       when 'XMP'
         # We use ||= here as one XMP chunk at most should be present, even though it is possible for there to be more.
         intrinsics[:xmp] ||= safe_read(@buf, chunk_size)

data/spec/parsers/webp_parser_spec.rb

@@ -118,4 +118,19 @@ describe FormatParser::WebpParser do
     expect(result.orientation).to be_nil
     expect(result.width_px).to eq(211)
   end
+
+  it 'successfully skips malformed Exif chunks' do
+    result = subject.call(File.open(fixtures_dir + 'WEBP/extended-malformed-exif.webp', 'rb'))
+    expect(result).not_to be_nil
+    expect(result.content_type).to eq('image/webp')
+    expect(result.format).to eq(:webp)
+    expect(result.has_multiple_frames).to eq(false)
+    expect(result.has_transparency).to eq(false)
+    expect(result.height_px).to eq(181)
+    expect(result.intrinsics).not_to be_nil
+    expect(result.intrinsics[:exif]).to be_nil
+    expect(result.intrinsics[:xmp]).not_to be_nil
+    expect(result.orientation).to be_nil
+    expect(result.width_px).to eq(65)
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.4.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-07-07 00:00:00.000000000 Z
+date: 2022-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks