format_parser 0.11.0 → 0.12.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ab01944664740856d704875f0a74d1b0540379c8e351176e38d3b5bf119e813f
-  data.tar.gz: b0736ffd074eb3fb49586d52799dd687c72f0a09b6e2d4109b1cbd26a8eac293
+  metadata.gz: 5f66a8afff2b85b57587c1cc7914dda25005b024284104bf3b0324b653a3ceff
+  data.tar.gz: 7e31d48b97e0dedfe5965b6ae524f1a14bbdc751ac50df11666aee3d4a18e5af
 SHA512:
-  metadata.gz: 570e9fcef6a08ad4e800c84d8452d985900f8442d9071477e6cd465b533677f7c39b6ae51c8f94d0ab0e90305ce790c395c3ce54ecda46800921b3311adc23b8
-  data.tar.gz: 0662cc268f0fc1fc61ac97896811e505f1ae251a2a15fe9027de2414107adb1414b6ce4f3a1111be1215e8e48323330ce8b08b98e521bf7d9ec4a26c8d29f01d
+  metadata.gz: 850a9f04a7006a52016d087c479a5b22048396c55ed51766a8d8c50f4ec66385ad565c3a006687428c762d16fd3aae5aa4f1d250ed1926bde07c0a61387f77d4
+  data.tar.gz: 6afa6ca1706cac48d9ea915bcd0c7ea4900d517eef195880cd0124621c0a7af4a1759ab999ede643dcce8a1066f126f59f030dcc963272c95b130bd397150975

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+## 0.12.0
+* Relay upstream status from `RemoteIO` in the `status_code` attribute (returns an `Integer`)
+
 ## 0.11.0
 * Add `Image#display_width_px` and `Image#display_height_px` for EXIF/aspect corrected display dimensions, and provide
   those values from a few parsers already. Also make full EXIF data available for JPEG/TIFF in `intrinsics[:exif]`

data/README.md

@@ -35,7 +35,7 @@ and [dimensions,](https://github.com/sstephenson/dimensions) borrowing from them
 
 ## Basic usage
 
-Pass an IO object that responds to `read` and `seek` to `FormatParser` and the first confirmed match will be returned.
+Pass an IO object that responds to `read` and `seek` to `FormatParser.parse` and the first confirmed match will be returned.
 
 ```ruby
 match = FormatParser.parse(File.open("myimage.jpg", "rb"))
@@ -46,6 +46,14 @@ match.display_height_px     #=> 240
 match.orientation   #=> :top_left
 ```
 
+You can also use `parse_http` passing a URL or `parse_file_at` passing a path:
+
+```ruby
+match = FormatParser.parse_http('https://upload.wikimedia.org/wikipedia/commons/b/b4/Mardin_1350660_1350692_33_images.jpg')
+match.nature        #=> :image
+match.format        #=> :jpg
+```
+
 If you would rather receive all potential results from the gem, call the gem as follows:
 
 ```ruby

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.11.0'
+  VERSION = '0.12.0'
 end

data/lib/parsers/jpeg_parser.rb

@@ -17,6 +17,7 @@ class FormatParser::JPEGParser
     @buf = FormatParser::IOConstraint.new(io)
     @width             = nil
     @height            = nil
+    @exif_data         = nil
     scan
   end
 
@@ -119,6 +120,7 @@ class FormatParser::JPEGParser
     # the second time around. What we care about, rather, is the EXIF data only. So we will
     # pry it out of the APP1 frame and parse it as the TIFF segment - which is what EXIFR
     # does under the hood.
+    marker_length_at = @buf.pos
     app1_frame_content_length = read_short - 2
 
     # If there is certainly not enough data in this APP1 to begin with, bail out.
@@ -132,10 +134,7 @@ class FormatParser::JPEGParser
 
     # If we could not find the magic Exif\0 string at the start of the marker,
     # seek to the start of the next marker and return
-    unless maybe_exif_magic_str == EXIF_MAGIC_STRING
-      safe_skip(@buf, app1_frame_content_length - EXIF_MAGIC_STRING.bytesize)
-      return
-    end
+    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)
@@ -146,6 +145,10 @@ class FormatParser::JPEGParser
   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
+  ensure
+    # 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)
   end
 
   def read_frame

data/lib/remote_io.rb

@@ -4,14 +4,23 @@
 # tweaks using `Faraday.default_connection = ...` these will
 # take effect for these RemoteIO objects as well
 class FormatParser::RemoteIO
+  class UpstreamError < StandardError
+    # @return Integer
+    attr_reader :status_code
+    def initialize(status_code, message)
+      @status_code = status_code
+      super(message)
+    end
+  end
+
   # Represents a failure that might be retried
   # (like a 5xx response or a timeout)
-  class IntermittentFailure < StandardError
+  class IntermittentFailure < UpstreamError
   end
 
   # Represents a failure that should not be retried
   # (like a 4xx response or a DNS resolution error)
-  class InvalidRequest < StandardError
+  class InvalidRequest < UpstreamError
   end
 
   # @param uri[URI, String] the remote URL to obtain
@@ -76,7 +85,7 @@ class FormatParser::RemoteIO
       # Figure out of the server supports content ranges, if it doesn't we have no
       # business working with that server
       range_header = response.headers['Content-Range']
-      raise InvalidRequest, "No range support at #{@uri}" unless range_header
+      raise InvalidRequest.new(response.status, "No range support at #{@uri}") unless range_header
 
       # "Content-Range: bytes 0-0/307404381" is how the response header is structured
       size = range_header[/\/(\d+)$/, 1].to_i
@@ -95,10 +104,10 @@ class FormatParser::RemoteIO
       return
     when 500..599
       FormatParser::Measurometer.increment_counter('format_parser.RemoteIO.upstream50x_errors', 1)
-      raise IntermittentFailure, "Server at #{@uri} replied with a #{response.status} and we might want to retry"
+      raise IntermittentFailure.new(response.status, "Server at #{@uri} replied with a #{response.status} and we might want to retry")
     else
       FormatParser::Measurometer.increment_counter('format_parser.RemoteIO.invalid_request_errors', 1)
-      raise InvalidRequest, "Server at #{@uri} replied with a #{response.status} and refused our request"
+      raise InvalidRequest.new(response.status, "Server at #{@uri} replied with a #{response.status} and refused our request")
     end
   end
 end

data/spec/remote_io_spec.rb

@@ -35,6 +35,27 @@ describe FormatParser::RemoteIO do
     expect { rio.read(100) }.to raise_error(/replied with a 403 and refused/)
   end
 
+  it 'returns nil on a 416 response' do
+    rio = described_class.new('https://images.invalid/img.jpg')
+
+    fake_resp = double(headers: {}, status: 416, body: 'You stepped off the ledge of the range')
+    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+
+    rio.seek(100)
+    expect(rio.read(100)).to be_nil
+  end
+
+  it 'sets the status_code of the exception on a 4xx response from upstream' do
+    rio = described_class.new('https://images.invalid/img.jpg')
+
+    fake_resp = double(headers: {}, status: 403, body: 'Please log in')
+    expect(Faraday).to receive(:get).with('https://images.invalid/img.jpg', nil, range: 'bytes=100-199').and_return(fake_resp)
+
+    rio.seek(100)
+    # rubocop: disable Lint/AmbiguousBlockAssociation
+    expect { rio.read(100) }.to raise_error { |e| expect(e.status_code).to eq(403) }
+  end
+
   it 'returns a nil when the range cannot be satisfied and the response is 416' do
     rio = described_class.new('https://images.invalid/img.jpg')
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.11.0
+  version: 0.12.0
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-04-30 00:00:00.000000000 Z
+date: 2018-05-03 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks