hexapdf 0.15.6 → 0.16.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: bcffb10babdbf723a478ea40721d9515222adf8d12ba9bd799f7b95fa66bc408
-  data.tar.gz: d5929900ab1b010a39964edc366ea223ef8a2ee9bcd1e9a5873874b4d5a8ecc5
+  metadata.gz: 5b2303787fd50c2407bb99336c3315643c4a9401a84a508462715d18a378788c
+  data.tar.gz: 675bb953973762670c598f93ed15fcaa4387f962c0cbdc9d27060bd06de4f5ae
 SHA512:
-  metadata.gz: d12bbd49204c28675d399477ce0249140bf6ead3fe9332541128802f0edc3ebb2b187752b464b9acd3b71ca4ce6cb5cba33caf19282bd5a15020cec3c6e20297
-  data.tar.gz: 8df3586c8069db615bf317f22b28069f4bfd1395d31c285bb5c4a63b1b46ec60b088082a5d461adafd590718df6307734361e1e61fe3210009d158fc95c558be
+  metadata.gz: 81715891b39fc35606baae317fc44a4be4d7710b2a1488f682425620771c2b563ecdfa8ba8ff0028a5226904d511c79b9507c1fed7170fdfd2c7a29aa4706127
+  data.tar.gz: f24fb2cdd07da0c2afde7511c40880e66fd65d87d2fd6035524202fbf8f1040d1e64576b3b080f6aa0d006d5938fc61c399c062d8687b33b3f3a5e9966b3917d

data/CHANGELOG.md

@@ -1,3 +1,35 @@
+## 0.16.0 - 2021-09-28
+
+## Added
+
+* Support for RGB color values of the form "RGB" in addition to "RRGGBB" and for
+  CSS color module level 3 color names
+* Conversion module for Integer fields to fix certain invalid PDF files
+
+
+## 0.15.9 - 2021-09-04
+
+### Fixed
+
+* Handling of files that contain stream length values that are indirect objects
+  not referring to a number
+
+
+## 0.15.8 - 2021-08-16
+
+### Fixed
+
+* Regression when using `-v` with the hexapdf command line tool
+
+
+## 0.15.7 - 2021-07-17
+
+### Fixed
+
+* Infinite loop while parsing PDF array due to missing closing bracket
+* Handling of invalid files with missing or corrupted trailer dictionary
+
+
 ## 0.15.6 - 2021-07-16
 
 ### Fixed

data/lib/hexapdf/cli/command.rb

@@ -119,7 +119,7 @@ module HexaPDF
       # Writes the document to the given file or does nothing if +out_file+ is +nil+.
       def write_document(doc, out_file, incremental: false)
         if out_file
-          doc.validate(auto_correct: true) do |object, msg, correctable|
+          doc.validate(auto_correct: true) do |msg, correctable, object|
             if command_parser.strict && !correctable
               raise "Validation error for object (#{object.oid},#{object.gen}): #{msg}"
             elsif command_parser.verbosity_info?

data/lib/hexapdf/configuration.rb

@@ -245,7 +245,7 @@ module HexaPDF
   #    Defines a mapping from font names and variants to font files.
   #
   #    The value needs to be a hash of the form:
-  #      {"font_name": {variant: file_name, variant2: file_name2, ...}, ...}
+  #      {"font_name" => {variant: file_name, variant2: file_name2, ...}, ...}
   #
   #    Once a font is registered in this way, the font name together with a variant name can be used
   #    with the HexaPDF::Document::Fonts#add method to load the font.

data/lib/hexapdf/content/canvas.rb

@@ -675,6 +675,10 @@ module HexaPDF
       # * Three numeric arguments specify an RGB color (see Content::ColorSpace::DeviceRGB::Color).
       # * A string in the format "RRGGBB" where "RR" is the hexadecimal number for the red, "GG"
       #   for the green and "BB" for the blue color value also specifies an RGB color.
+      # * As does a string in the format "RGB" where "RR", "GG" and "BB" would be used as the
+      #   hexadecimal numbers for the red, green and blue color values of an RGB color.
+      # * Any other string is treated as a CSS Color Module Level 3 color name, see
+      #   https://www.w3.org/TR/css-color-3/#svg-color.
       # * Four numeric arguments specify a CMYK color (see Content::ColorSpace::DeviceCMYK::Color).
       # * A color object is used directly (normally used for color spaces other than DeviceRGB,
       #   DeviceCMYK and DeviceGray).
@@ -1852,7 +1856,7 @@ module HexaPDF
       # on the possible color specifications.
       def color_from_specification(spec)
         if spec.length == 1 && spec[0].kind_of?(String)
-          resources.color_space(:DeviceRGB).color(*spec[0].scan(/../).map!(&:hex))
+          ColorSpace.device_color_from_specification(spec)
         elsif spec.length == 1 && spec[0].respond_to?(:color_space)
           spec[0]
         else

data/lib/hexapdf/content/color_space.rb

@@ -96,6 +96,157 @@ module HexaPDF
     # See: PDF1.7 s8.6
     module ColorSpace
 
+      # Mapping of CSS Color Module Level 3 names to RGB values.
+      CSS_COLOR_NAMES = {
+        "aliceblue" => [240, 248, 255],
+        "antiquewhite" => [250, 235, 215],
+        "aqua" => [0, 255, 255],
+        "aquamarine" => [127, 255, 212],
+        "azure" => [240, 255, 255],
+        "beige" => [245, 245, 220],
+        "bisque" => [255, 228, 196],
+        "black" => [0, 0, 0],
+        "blanchedalmond" => [255, 235, 205],
+        "blue" => [0, 0, 255],
+        "blueviolet" => [138, 43, 226],
+        "brown" => [165, 42, 42],
+        "burlywood" => [222, 184, 135],
+        "cadetblue" => [95, 158, 160],
+        "chartreuse" => [127, 255, 0],
+        "chocolate" => [210, 105, 30],
+        "coral" => [255, 127, 80],
+        "cornflowerblue" => [100, 149, 237],
+        "cornsilk" => [255, 248, 220],
+        "crimson" => [220, 20, 60],
+        "cyan" => [0, 255, 255],
+        "darkblue" => [0, 0, 139],
+        "darkcyan" => [0, 139, 139],
+        "darkgoldenrod" => [184, 134, 11],
+        "darkgray" => [169, 169, 169],
+        "darkgreen" => [0, 100, 0],
+        "darkgrey" => [169, 169, 169],
+        "darkkhaki" => [189, 183, 107],
+        "darkmagenta" => [139, 0, 139],
+        "darkolivegreen" => [85, 107, 47],
+        "darkorange" => [255, 140, 0],
+        "darkorchid" => [153, 50, 204],
+        "darkred" => [139, 0, 0],
+        "darksalmon" => [233, 150, 122],
+        "darkseagreen" => [143, 188, 143],
+        "darkslateblue" => [72, 61, 139],
+        "darkslategray" => [47, 79, 79],
+        "darkslategrey" => [47, 79, 79],
+        "darkturquoise" => [0, 206, 209],
+        "darkviolet" => [148, 0, 211],
+        "deeppink" => [255, 20, 147],
+        "deepskyblue" => [0, 191, 255],
+        "dimgray" => [105, 105, 105],
+        "dimgrey" => [105, 105, 105],
+        "dodgerblue" => [30, 144, 255],
+        "firebrick" => [178, 34, 34],
+        "floralwhite" => [255, 250, 240],
+        "forestgreen" => [34, 139, 34],
+        "fuchsia" => [255, 0, 255],
+        "gainsboro" => [220, 220, 220],
+        "ghostwhite" => [248, 248, 255],
+        "gold" => [255, 215, 0],
+        "goldenrod" => [218, 165, 32],
+        "gray" => [128, 128, 128],
+        "green" => [0, 128, 0],
+        "greenyellow" => [173, 255, 47],
+        "grey" => [128, 128, 128],
+        "honeydew" => [240, 255, 240],
+        "hotpink" => [255, 105, 180],
+        "indianred" => [205, 92, 92],
+        "indigo" => [75, 0, 130],
+        "ivory" => [255, 255, 240],
+        "khaki" => [240, 230, 140],
+        "lavender" => [230, 230, 250],
+        "lavenderblush" => [255, 240, 245],
+        "lawngreen" => [124, 252, 0],
+        "lemonchiffon" => [255, 250, 205],
+        "lightblue" => [173, 216, 230],
+        "lightcoral" => [240, 128, 128],
+        "lightcyan" => [224, 255, 255],
+        "lightgoldenrodyellow" => [250, 250, 210],
+        "lightgray" => [211, 211, 211],
+        "lightgreen" => [144, 238, 144],
+        "lightgrey" => [211, 211, 211],
+        "lightpink" => [255, 182, 193],
+        "lightsalmon" => [255, 160, 122],
+        "lightseagreen" => [32, 178, 170],
+        "lightskyblue" => [135, 206, 250],
+        "lightslategray" => [119, 136, 153],
+        "lightslategrey" => [119, 136, 153],
+        "lightsteelblue" => [176, 196, 222],
+        "lightyellow" => [255, 255, 224],
+        "lime" => [0, 255, 0],
+        "limegreen" => [50, 205, 50],
+        "linen" => [250, 240, 230],
+        "magenta" => [255, 0, 255],
+        "maroon" => [128, 0, 0],
+        "mediumaquamarine" => [102, 205, 170],
+        "mediumblue" => [0, 0, 205],
+        "mediumorchid" => [186, 85, 211],
+        "mediumpurple" => [147, 112, 219],
+        "mediumseagreen" => [60, 179, 113],
+        "mediumslateblue" => [123, 104, 238],
+        "mediumspringgreen" => [0, 250, 154],
+        "mediumturquoise" => [72, 209, 204],
+        "mediumvioletred" => [199, 21, 133],
+        "midnightblue" => [25, 25, 112],
+        "mintcream" => [245, 255, 250],
+        "mistyrose" => [255, 228, 225],
+        "moccasin" => [255, 228, 181],
+        "navajowhite" => [255, 222, 173],
+        "navy" => [0, 0, 128],
+        "oldlace" => [253, 245, 230],
+        "olive" => [128, 128, 0],
+        "olivedrab" => [107, 142, 35],
+        "orange" => [255, 165, 0],
+        "orangered" => [255, 69, 0],
+        "orchid" => [218, 112, 214],
+        "palegoldenrod" => [238, 232, 170],
+        "palegreen" => [152, 251, 152],
+        "paleturquoise" => [175, 238, 238],
+        "palevioletred" => [219, 112, 147],
+        "papayawhip" => [255, 239, 213],
+        "peachpuff" => [255, 218, 185],
+        "peru" => [205, 133, 63],
+        "pink" => [255, 192, 203],
+        "plum" => [221, 160, 221],
+        "powderblue" => [176, 224, 230],
+        "purple" => [128, 0, 128],
+        "red" => [255, 0, 0],
+        "rosybrown" => [188, 143, 143],
+        "royalblue" => [65, 105, 225],
+        "saddlebrown" => [139, 69, 19],
+        "salmon" => [250, 128, 114],
+        "sandybrown" => [244, 164, 96],
+        "seagreen" => [46, 139, 87],
+        "seashell" => [255, 245, 238],
+        "sienna" => [160, 82, 45],
+        "silver" => [192, 192, 192],
+        "skyblue" => [135, 206, 235],
+        "slateblue" => [106, 90, 205],
+        "slategray" => [112, 128, 144],
+        "slategrey" => [112, 128, 144],
+        "snow" => [255, 250, 250],
+        "springgreen" => [0, 255, 127],
+        "steelblue" => [70, 130, 180],
+        "tan" => [210, 180, 140],
+        "teal" => [0, 128, 128],
+        "thistle" => [216, 191, 216],
+        "tomato" => [255, 99, 71],
+        "turquoise" => [64, 224, 208],
+        "violet" => [238, 130, 238],
+        "wheat" => [245, 222, 179],
+        "white" => [255, 255, 255],
+        "whitesmoke" => [245, 245, 245],
+        "yellow" => [255, 255, 0],
+        "yellowgreen" => [154, 205, 50],
+      }.freeze
+
       # :call-seq:
       #   ColorSpace.device_color_from_specification(gray)           => color
       #   ColorSpace.device_color_from_specification(r, g, b)        => color
@@ -111,6 +262,10 @@ module HexaPDF
       # * Three numeric arguments specify an RGB color (see DeviceRGB::Color).
       # * A string in the format "RRGGBB" where "RR" is the hexadecimal number for the red, "GG"
       #   for the green and "BB" for the blue color value also specifies an RGB color.
+      # * As does a string in the format "RGB" where "RR", "GG" and "BB" would be used as the
+      #   hexadecimal numbers for the red, green and blue color values of an RGB color.
+      # * Any other string is treated as a CSS Color Module Level 3 color name, see
+      #   https://www.w3.org/TR/css-color-3/#svg-color.
       # * Four numeric arguments specify a CMYK color (see DeviceCMYK::Color).
       # * An array is treated as if its items were specified separately as arguments.
       #
@@ -118,7 +273,18 @@ module HexaPDF
       # values are first normalized - see DeviceGray#color, DeviceRGB#color and DeviceCMYK#color.
       def self.device_color_from_specification(*spec)
         spec.flatten!
-        spec = spec[0].scan(/../).map!(&:hex) if spec.length == 1 && spec[0].kind_of?(String)
+        first_item = spec[0]
+        if spec.length == 1 && first_item.kind_of?(String)
+          spec = if first_item.match?(/\A\h{6}\z/)
+                   first_item.scan(/../).map!(&:hex)
+                 elsif first_item.match?(/\A\h{3}\z/)
+                   first_item.each_char.map {|x| (x*2).hex}
+                 elsif CSS_COLOR_NAMES.key?(first_item)
+                   CSS_COLOR_NAMES[first_item]
+                 else
+                   raise ArgumentError, "Given string is neither a hex color nor a color name"
+                 end
+        end
         GlobalConfiguration.constantize('color_space.map', for_components(spec)).new.color(*spec)
       end
 

data/lib/hexapdf/dictionary_fields.rb

@@ -349,9 +349,30 @@ module HexaPDF
 
     end
 
+    # Converter module for fields of type Integer.
+    module IntegerConverter
+
+      # This converter is usable if the +type+ is Integer.
+      def self.usable_for?(type)
+        type == Integer
+      end
+
+      # :nodoc:
+      def self.additional_types
+      end
+
+      # Converts a Float value into an Integer if the float is equal to its integer value. Otherwise
+      # returns +nil+
+      def self.convert(data, _type, _document)
+        return unless data.kind_of?(Float) && data == data.to_i
+        data.to_i
+      end
+
+    end
+
     Field.converters.replace([FileSpecificationConverter, DictionaryConverter, ArrayConverter,
                               StringConverter, PDFByteStringConverter, DateConverter,
-                              RectangleConverter])
+                              RectangleConverter, IntegerConverter])
 
   end
 

data/lib/hexapdf/parser.rb

@@ -165,7 +165,7 @@ module HexaPDF
                  else
                    0
                  end
-        @tokenizer.pos = pos + length
+        @tokenizer.pos = pos + length rescue pos
 
         tok = @tokenizer.next_token
         unless tok.kind_of?(Tokenizer::Token) && tok == 'endstream'
@@ -447,6 +447,15 @@ module HexaPDF
 
       if !trailer || trailer.empty?
         _, trailer = load_revision(startxref_offset) rescue nil
+        unless trailer
+          xref.each do |_oid, _gen, xref_entry|
+            obj, * = parse_indirect_object(xref_entry.pos) rescue nil
+            if obj.kind_of?(Hash) && obj[:Type] == :Catalog
+              trailer = {Root: HexaPDF::Reference.new(xref_entry.oid, xref_entry.gen)}
+              break
+            end
+          end
+        end
         unless trailer
           @in_reconstruct_revision = false
           raise_malformed("Could not reconstruct malformed PDF because trailer was not found", pos: 0)

data/lib/hexapdf/tokenizer.rb

@@ -55,6 +55,9 @@ module HexaPDF
 
     # This object is returned when there are no more tokens to read.
     NO_MORE_TOKENS = ::Object.new
+    def NO_MORE_TOKENS.to_s
+      "EOS - no more tokens"
+    end
 
     # Characters defined as whitespace.
     #
@@ -384,7 +387,11 @@ module HexaPDF
       result = []
       while true
         obj = next_object(allow_end_array_token: true)
-        break if obj.equal?(TOKEN_ARRAY_END)
+        if obj.equal?(TOKEN_ARRAY_END)
+          break
+        elsif obj.equal?(NO_MORE_TOKENS)
+          raise HexaPDF::MalformedPDFError.new("Unclosed array found", pos: pos)
+        end
         result << obj
       end
       result
@@ -403,7 +410,8 @@ module HexaPDF
         key = next_token
         break if key.equal?(TOKEN_DICT_END)
         unless key.kind_of?(Symbol)
-          raise HexaPDF::MalformedPDFError.new("Dictionary keys must be PDF name objects", pos: pos)
+          raise HexaPDF::MalformedPDFError.new("Dictionary keys must be PDF name objects, " \
+                                               "found '#{key}'", pos: pos)
         end
 
         val = next_object

data/lib/hexapdf/version.rb

@@ -37,6 +37,6 @@
 module HexaPDF
 
   # The version of HexaPDF.
-  VERSION = '0.15.6'
+  VERSION = '0.16.0'
 
 end

data/test/hexapdf/common_tokenizer_tests.rb

@@ -161,6 +161,21 @@ module CommonTokenizerTests
     assert_raises(HexaPDF::MalformedPDFError) { @tokenizer.next_object }
   end
 
+  it "next_object: fails for an array without closing bracket, encountering EOS" do
+    create_tokenizer("[1 2")
+    exception = assert_raises(HexaPDF::MalformedPDFError) { @tokenizer.next_object }
+    assert_match(/Unclosed array found/, exception.message)
+  end
+
+  it "next_object: fails for a dictionary without closing bracket, encountering EOS" do
+    create_tokenizer("<</Name 5")
+    exception = assert_raises(HexaPDF::MalformedPDFError) { @tokenizer.next_object }
+    assert_match(/must be PDF name objects.*EOS/, exception.message)
+    create_tokenizer("<</Name 5 /Other")
+    exception = assert_raises(HexaPDF::MalformedPDFError) { @tokenizer.next_object }
+    assert_match(/must be PDF name objects.*EOS/, exception.message)
+  end
+
   it "returns the correct position on operations" do
     create_tokenizer("hallo du" << " " * 50000 << "hallo du")
     @tokenizer.next_token

data/test/hexapdf/content/test_color_space.rb

@@ -73,10 +73,18 @@ describe HexaPDF::Content::ColorSpace do
       assert_equal([0.2, 1, 0], @class.device_color_from_specification(51, 255, 0).components)
     end
 
-    it "works for RGB values given as string" do
+    it "works for RGB values given as full hex string" do
       assert_equal([0.2, 1, 0], @class.device_color_from_specification("33FF00").components)
     end
 
+    it "works for RGB values given as half hex string" do
+      assert_equal([0.2, 1, 0], @class.device_color_from_specification("3F0").components)
+    end
+
+    it "works for RGB values given as color names" do
+      assert_equal([0, 0, 1], @class.device_color_from_specification("blue").components)
+    end
+
     it "works for CMYK values" do
       assert_equal([0.51, 0.9, 1, 0.5],
                    @class.device_color_from_specification(51, 90, 100, 50).components)
@@ -85,6 +93,10 @@ describe HexaPDF::Content::ColorSpace do
     it "works when an array is given" do
       assert_equal([0.2], @class.device_color_from_specification([51]).components)
     end
+
+    it "raises an error if an invalid color string is given" do
+      assert_raises(ArgumentError) { @class.device_color_from_specification("unknown") }
+    end
   end
 
   it "returns a device color object for prenormalized color values" do

data/test/hexapdf/test_dictionary_fields.rb

@@ -242,4 +242,19 @@ describe HexaPDF::DictionaryFields do
       doc.verify
     end
   end
+
+  describe "IntegerConverter" do
+    before do
+      @field = self.class::Field.new(Integer)
+    end
+
+    it "no additional field types allowed" do
+      assert_equal([Integer], @field.type)
+    end
+
+    it "allows conversion to an Integer from an equivalent Float value" do
+      refute_same(3, @field.convert(3.1, nil))
+      assert_same(3, @field.convert(3.0, nil))
+    end
+  end
 end

data/test/hexapdf/test_parser.rb

@@ -113,13 +113,21 @@ describe HexaPDF::Parser do
       assert_nil(object)
     end
 
-    it "recovers from an invalid stream length value" do
+    it "recovers from a stream length value that doesn't reflect the correct length" do
       create_parser("1 0 obj<</Length 4>> stream\n12endstream endobj")
       obj, _, _, stream = @parser.parse_indirect_object
       assert_equal(2, obj[:Length])
       assert_equal('12', TestHelper.collector(stream.fiber))
     end
 
+    it "recovers from an invalid stream length value" do
+      create_parser("1 0 obj<</Length 2 0 R>> stream\n12endstream endobj")
+      @document.add([5], oid: 2)
+      obj, _, _, stream = @parser.parse_indirect_object
+      assert_equal(2, obj[:Length])
+      assert_equal('12', TestHelper.collector(stream.fiber))
+    end
+
     it "works even if the keyword endobj is missing or mangled" do
       create_parser("1 0 obj<</Length 4>>5")
       object, * = @parser.parse_indirect_object
@@ -619,7 +627,12 @@ describe HexaPDF::Parser do
       assert_equal({Size: 1}, @parser.reconstructed_revision.trailer.value)
     end
 
-    it "fails if no trailer is found and the trailer specified at the startxref position is not valid" do
+    it "constructs a trailer with a /Root entry if no valid trailer was found" do
+      create_parser("1 0 obj\n<</Type /Catalog/Pages 2 0 R>>\nendobj\nxref trailer <</Size 1/Prev 5\n%%EOF")
+      assert_equal({Root: HexaPDF::Reference.new(1, 0)}, @parser.reconstructed_revision.trailer.value)
+    end
+
+    it "fails if no valid trailer is found and couldn't be constructed" do
       create_parser("1 0 obj\n5\nendobj\nquack trailer <</Size 1>>\nstartxref\n22\n%%EOF")
       assert_raises(HexaPDF::MalformedPDFError) { @parser.reconstructed_revision.trailer }
     end

data/test/hexapdf/test_writer.rb

@@ -40,7 +40,7 @@ describe HexaPDF::Writer do
       219
       %%EOF
       3 0 obj
-      <</Producer(HexaPDF version 0.15.6)>>
+      <</Producer(HexaPDF version 0.16.0)>>
       endobj
       xref
       3 1
@@ -72,7 +72,7 @@ describe HexaPDF::Writer do
       141
       %%EOF
       6 0 obj
-      <</Producer(HexaPDF version 0.15.6)>>
+      <</Producer(HexaPDF version 0.16.0)>>
       endobj
       2 0 obj
       <</Length 10>>stream

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: hexapdf
 version: !ruby/object:Gem::Version
-  version: 0.15.6
+  version: 0.16.0
 platform: ruby
 authors:
 - Thomas Leitner
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2021-07-16 00:00:00.000000000 Z
+date: 2021-09-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: cmdparse