combine_pdf 1.0.16 → 1.0.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d071703a8903bc5a11d7beb5a0bcb284a8bced5763705de3a7dd9ae6be35b64d
-  data.tar.gz: 898069ad7ec79ad4fadea5383a721f28c5dfc3632fc20aaa40624954bfe70170
+  metadata.gz: 95f44419c731c5b1e7625589d159c608ab6948004e347db9ee2380611e10dd6f
+  data.tar.gz: d2ee8cf53e111cdf4051886262ad2a4fa216eca36aaaf1b45b7782379f793642
 SHA512:
-  metadata.gz: d52868ff7a021801207ff17a1e87aca8fa1bd82e6fd0dacf91d39d57695b07b87238898238fa90755bfaaec65cb4df384b6db97f3f4e3bf70da7d3d808e55daa
-  data.tar.gz: f68133d14d5eb5f0428097b4421976da49471eed61f4ac0e574c4718b588458f6971fd107ccc397be004997f3c31ac6bfc122675992412fd521a7910d6f2abd9
+  metadata.gz: 7cac17e8c080e0eba10f19efa90c5eb6252f12811218ff5ad8f330ec8977abec677628d6cfaf70d9abc5e2b754e711e9024315cad0de2f32286f1d7dbeabec87
+  data.tar.gz: 7e60b19afafa071a6d21ce73da4be142501c0becc4aede5e579706789d0c276903a8193661d0ffa16d0c4c906d0fa6136124011d1de3a8c968a3c1334804d476

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ***
 
+#### Change log v.1.0.18
+
+**Fix**: fixed issue with the 1.0.17 release where `ProcSet` PDF Arrays should have been expected but where ignored and a PDF Object was assumed instead (issue #171) - credit to @chuchiperriman (Jesús Barbero Rodríguez).
+
+#### Change log v.1.0.17
+
+**Fix**: fixed issue where nested structure equality tests might provide false positives, resulting in lost data (issue #166) - credit to @cschilbe (Conrad Schilbe).
+
 #### Change log v.1.0.16
 
 **Fix**: some documentation typos were fixed (PR #147) - credit to @djhopper01 (Derek Hopper).

data/README.md

@@ -41,6 +41,8 @@ Quick rundown:
 
 * Sometimes the CombinePDF will raise an exception even if the PDF could be parsed (i.e., when PDF optional content exists)... I find it better to err on the side of caution, although for optional content PDFs an exception is avoidable using `CombinePDF.load(pdf_file, allow_optional_content: true)`.
 
+* The CombinePDF gem runs recursive code to both parse and format the PDF files. Hence, PDF files that have heavily nested objects, as well as those that where combined in a way that results in cyclic nesting, might explode the stack - resulting in an exception or program failure.
+
 CombinePDF is written natively in Ruby and should (presumably) work on all Ruby platforms that follow Ruby 2.0 compatibility.
 
 However, PDF files are quite complex creatures and no guaranty is provided.

data/combine_pdf.gemspec

@@ -21,6 +21,6 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'ruby-rc4', '>= 0.1.5'
 
   # spec.add_development_dependency "bundler", ">= 1.7"
-  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rake", ">= 12.3.3"
   spec.add_development_dependency "minitest"
 end

data/lib/combine_pdf.rb

@@ -5,6 +5,7 @@ require 'securerandom'
 require 'strscan'
 require 'matrix'
 require 'set'
+require 'digest'
 
 # require the RC4 Gem
 require 'rc4'

data/lib/combine_pdf/page_methods.rb

@@ -94,7 +94,7 @@ module CombinePDF
       # end
 
       # set ProcSet to recommended value
-      resources[:ProcSet] = [:PDF, :Text, :ImageB, :ImageC, :ImageI] # this was recommended by the ISO. 32000-1:2008
+      resources[:ProcSet] ||= [:PDF, :Text, :ImageB, :ImageC, :ImageI] # this was recommended by the ISO. 32000-1:2008
 
       if top # if this is a stamp (overlay)
         insert_content CONTENT_CONTAINER_START, 0
@@ -147,7 +147,7 @@ module CombinePDF
 
     # This method adds a simple text box to the Page represented by the PDFWriter class.
     # This function takes two values:
-    # text:: the text to potin the box.
+    # text:: the text to write in the box.
     # properties:: a Hash of box properties.
     # the symbols and values in the properties Hash could be any or all of the following:
     # x:: the left position of the box.

data/lib/combine_pdf/parser.rb

@@ -233,16 +233,18 @@ module CombinePDF
         # all characters that aren't white space or special: /[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]+
         elsif str = @scanner.scan(/\/[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]*/)
           out << (str[1..-1].gsub(/\#[0-9a-fA-F]{2}/) { |a| a[1..2].hex.chr }).to_sym
+          # warn "CombinePDF detected name: #{out.last.to_s}"
         ##########################################
         ## Parse a Number
         ##########################################
         elsif str = @scanner.scan(/[\+\-\.\d]+/)
           str =~ /\./ ? (out << str.to_f) : (out << str.to_i)
+          # warn "CombinePDF detected number: #{out.last.to_s}"
         ##########################################
         ## parse a Hex String
         ##########################################
         elsif str = @scanner.scan(/\<[0-9a-fA-F]*\>/)
-          # warn "Found a hex string"
+          # warn "Found a hex string #{str}"
           str = str.slice(1..-2).force_encoding(Encoding::ASCII_8BIT)
           # str = "0#{str}" if str.length.odd?
           out << unify_string([str].pack('H*').force_encoding(Encoding::ASCII_8BIT))
@@ -336,6 +338,7 @@ module CombinePDF
             end
           end
           out << unify_string(str.pack('C*').force_encoding(Encoding::ASCII_8BIT))
+          # warn "Found Literal String: #{out.last}"
         ##########################################
         ## parse a Dictionary
         ##########################################
@@ -348,6 +351,7 @@ module CombinePDF
         ## return content of array or dictionary
         ##########################################
         elsif @scanner.scan(/\]/) || @scanner.scan(/>>/)
+          # warn "Dictionary / Array ended with #{@scanner.peek(5)}"
           return out
         ##########################################
         ## parse a Stream
@@ -364,6 +368,8 @@ module CombinePDF
             raise ParsingError, "Parsing Error: PDF file error - a stream object wasn't properly closed using 'endstream'!"
           end
 
+          # warn "CombinePDF parser: detected Stream #{str.length} bytes long #{str[0..3]}...#{str[-4..-1]}"
+
           # need to remove end of stream
           if out.last.is_a? Hash
             # out.last[:raw_stream_content] = str[0...-10] #cuts only one EON char (\n or \r)
@@ -528,6 +534,14 @@ module CombinePDF
               inheritance_hash[:Resources] ||= { referenced_object: {}, is_reference_only: true }.dup
               (inheritance_hash[:Resources][:referenced_object] || inheritance_hash[:Resources]).update((catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &HASH_UPDATE_PROC_FOR_OLD)
             end
+            if catalogs[:ProcSet].is_a?(Array)
+              if(inheritance_hash[:ProcSet])
+                inheritance_hash[:ProcSet][:referenced_object].concat(catalogs[:ProcSet])
+                inheritance_hash[:ProcSet][:referenced_object].uniq!
+              else
+                inheritance_hash[:ProcSet] ||= { referenced_object: catalogs[:ProcSet], is_reference_only: true }.dup
+              end
+            end
             if catalogs[:ColorSpace]
               inheritance_hash[:ColorSpace] ||= { referenced_object: {}, is_reference_only: true }.dup
               (inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]).update((catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &HASH_UPDATE_PROC_FOR_OLD)
@@ -556,6 +570,18 @@ module CombinePDF
               catalogs[:ColorSpace] = { referenced_object: catalogs[:ColorSpace], is_reference_only: true } unless catalogs[:ColorSpace][:referenced_object]
               catalogs[:ColorSpace][:referenced_object].update((inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]), &HASH_UPDATE_PROC_FOR_OLD)
             end
+            if inheritance_hash[:ProcSet]
+              if(catalogs[:ProcSet])
+                if catalogs[:ProcSet].is_a?(Array)
+                  catalogs[:ProcSet] = { referenced_object: catalogs[:ProcSet], is_reference_only: true }
+                end
+                catalogs[:ProcSet][:referenced_object].concat(inheritance_hash[:ProcSet][:referenced_object])
+                catalogs[:ProcSet][:referenced_object].uniq!
+              else
+                catalogs[:ProcSet] = { is_reference_only: true }.dup
+                catalogs[:ProcSet][:referenced_object] = catalogs[:ProcSet][:referenced_object].dup
+              end
+            end
             # (catalogs[:ColorSpace] ||= {}).update(inheritance_hash[:ColorSpace], &HASH_UPDATE_PROC_FOR_OLD) if inheritance_hash[:ColorSpace]
             # catalogs[:Order] ||= inheritance_hash[:Order] if inheritance_hash[:Order]
             # catalogs[:AS] ||= inheritance_hash[:AS] if inheritance_hash[:AS]

data/lib/combine_pdf/pdf_protected.rb

@@ -373,16 +373,19 @@ module CombinePDF
     private
 
     def equal_layers obj1, obj2, layer = CombinePDF.eq_depth_limit
-      return true   if(layer == 0)
       return true if obj1.object_id == obj2.object_id
       if obj1.is_a? Hash
         return false unless obj2.is_a? Hash
+        return false unless obj1.length == obj2.length
         keys = obj1.keys;
-        return false if (keys - obj2.keys).any?
+        keys2 = obj2.keys;
+        return false if (keys - keys2).any? || (keys2 - keys).any?
+        return (warn("CombinePDF nesting limit reached") || true) if(layer == 0)
         keys.each {|k| return false unless equal_layers( obj1[k], obj2[k], layer-1) }
       elsif obj1.is_a? Array
         return false unless obj2.is_a? Array
-        (obj1-obj2).any?
+        return false unless obj1.length == obj2.length
+        (obj1-obj2).any? || (obj2-obj1).any?
       else
         obj1 == obj2
       end

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.16'.freeze
+  VERSION = '1.0.18'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.16
+  version: 1.0.18
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-02-22 00:00:00.000000000 Z
+date: 2020-07-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -28,16 +28,16 @@ dependencies:
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 12.3.3
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "~>"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '10.0'
+        version: 12.3.3
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
@@ -104,7 +104,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.1
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.