format_parser 0.14.0 → 0.14.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0d9daf0603ac099b75a9ddb85b8061190dc8fe2f3aad46633ff94b1f4a99020e
-  data.tar.gz: d4343aa08f9ec6a6864a5aed3b7ea174f779c3ea0954417e9b31a2c871126f27
+  metadata.gz: 90513000619c11b5a98669f465add204ca68465065681424627adcdf66c634dd
+  data.tar.gz: 1515277ec5edc3bedc7631a7a3e5b56975010e1d7a84b5e166b4eae6977eb90a
 SHA512:
-  metadata.gz: 2d63a7d9802157e35260b91f5a8077008fa4e7c19837cc4a01ff0d3954fa22d29455a13cb914bc892782d986a7d85b9465eb21b8c753d16c0da774ddb0f5c47c
-  data.tar.gz: 651d41396efdeb4e9f74173d284617baa0bf34f3ce6e8a6890a1ceadf2ef4a3556a3dd0b4b282dc84ea9f65c020ecbe1ae942da78eed85bed6d969161dbb0cbb
+  metadata.gz: ec36c70f585ebc72089be82bba55b21b83d53d59a4233f33be4e78cbde5f7b12bdb99587238a00cfdf023a24daafadc8803d43e88bacd994c97cfe47c3aac4f1
+  data.tar.gz: 1e964c45d81b43def5575331f02f0949892ddc06f006c7b83275f72cffafefef25cef6b2b8627db0edb6969a8da1e72fa612f600091630fe0822f842062e75d1

data/CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.14.1
+* Care caching: Clear pages more deliberately instead of relegating them to GC
+* JPEG: Clear the EXIF buffer explicitly
+
 ## 0.14.0
 * PDF: Reduce the PDF parser to the basic binary detection (PDF/not PDF) until we have a better/more robust PDF parser
 * MP3: Fix the byte length of MPEG frames calculation to correctly account for ID3V1 and ID3V2 instead of ID3V1 twice

data/lib/care.rb

@@ -137,6 +137,7 @@ class Care
     #
     # @return void
     def clear
+      @pages.map { |maybe_page_str| maybe_page_str.clear if maybe_page_str.respond_to?(:clear) }
       @pages.clear
     end
 

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.14.0'
+  VERSION = '0.14.1'
 end

data/lib/parsers/jpeg_parser.rb

@@ -134,12 +134,13 @@ class FormatParser::JPEGParser
     # seek to the start of the next marker and return
     return unless maybe_exif_magic_str == EXIF_MAGIC_STRING
 
-    # ...and only then read the marker contents and parse it as EXIF
-    exif_data = safe_read(@buf, app1_frame_content_length - EXIF_MAGIC_STRING.bytesize)
+    # ...and only then read the marker contents and parse it as EXIF.
+    # Use StringIO.new instead of #write - https://github.com/aws/aws-sdk-ruby/issues/785#issuecomment-95456838
+    exif_buf = StringIO.new(safe_read(@buf, app1_frame_content_length - EXIF_MAGIC_STRING.bytesize))
 
-    Measurometer.add_distribution_value('format_parser.JPEGParser.bytes_sent_to_exif_parser', exif_data.bytesize)
+    Measurometer.add_distribution_value('format_parser.JPEGParser.bytes_sent_to_exif_parser', exif_buf.size)
 
-    @exif_data = exif_from_tiff_io(StringIO.new(exif_data))
+    @exif_data = exif_from_tiff_io(exif_buf)
   rescue EXIFR::MalformedTIFF
     # Not a JPEG or the Exif headers contain invalid data, or
     # an APP1 marker was detected in a file that is not a JPEG
@@ -147,6 +148,9 @@ class FormatParser::JPEGParser
     # Reposition the file pointer to where the next marker will begin,
     # regardless whether we did find usable EXIF or not
     @buf.seek(marker_length_at + 2 + app1_frame_content_length)
+
+    # Make sure to explicitly clear the EXIF buffers since they can be large
+    exif_buf.truncate(0) if exif_buf
   end
 
   def read_frame

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.14.0
+  version: 0.14.1
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-06-18 00:00:00.000000000 Z
+date: 2018-07-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks