combine_pdf 1.0.13 → 1.0.18

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 3ca8e3d75a2b167718e3f749076bd5bbbd1701b0218a811fd9fed4dda23c194a
-  data.tar.gz: 71bae00e5caeba7b1f70d2fc3492a669b5c05fcde8d56a9b58b7bbda2010cec9
+  metadata.gz: 95f44419c731c5b1e7625589d159c608ab6948004e347db9ee2380611e10dd6f
+  data.tar.gz: d2ee8cf53e111cdf4051886262ad2a4fa216eca36aaaf1b45b7782379f793642
 SHA512:
-  metadata.gz: 4c680801b7c0c925e1c6a66459b51de48ff3942c1cf24d5b31dbad55a2fb88f434ac4f67404c81ee422e672c92fc852ba4708835904c1d041cc5537abc13ba87
-  data.tar.gz: b2cb8a1eecf10d2503193f09802dc25655cd79b8bf41d422c1c45152fb0cf98e2092788bc19e77d139ec5918fa42782a5f97a2e1e9a7f9703de5be5b4479d2ca
+  metadata.gz: 7cac17e8c080e0eba10f19efa90c5eb6252f12811218ff5ad8f330ec8977abec677628d6cfaf70d9abc5e2b754e711e9024315cad0de2f32286f1d7dbeabec87
+  data.tar.gz: 7e60b19afafa071a6d21ce73da4be142501c0becc4aede5e579706789d0c276903a8193661d0ffa16d0c4c906d0fa6136124011d1de3a8c968a3c1334804d476

data/CHANGELOG.md

@@ -2,6 +2,26 @@
 
 ***
 
+#### 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).
+
+#### Change log v.1.0.15
+
+**Fix**: An attempt to fix JRuby compatibility concerns (issue #127).
+
+#### Change log v.1.0.14
+
+**Fix**: Fixed an issue related to PDF XRef table data, where a malformed EOL marker would cause the parser to fail. Credit to @dangerous (David Rainsford) for exposing this issue in a comment to issue #140.
+
 #### Change log v.1.0.13
 
 **Fix**: Fixed an issue related to PDF object streams (version 1.6) where a numerical object at the beginning of the stream might be mis-parsed as an object reference number rather than an object. Credit to @Defoncesko for reporting issue #141.

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

@@ -20,7 +20,7 @@ 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 "bundler", ">= 1.7"
+  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/api.rb

@@ -140,7 +140,7 @@ module CombinePDF
   # this function enables plug-ins to expend the font functionality of CombinePDF.
   #
   # font_name:: a Symbol with the name of the font. if the fonts exists in the library, it will be overwritten!
-  # font_metrics:: a Hash of font metrics, of the format char => {wx: char_width, boundingbox: [left_x, buttom_y, right_x, top_y]} where char == character itself (i.e. " " for space). The Hash should contain a special value :missing for the metrics of missing characters. an optional :wy might be supported in the future, for up to down fonts.
+  # font_metrics:: a Hash of font metrics, of the format char => {wx: char_width, boundingbox: [left_x, bottom_y, right_x, top_y]} where char == character itself (i.e. " " for space). The Hash should contain a special value :missing for the metrics of missing characters. an optional :wy might be supported in the future, for up to down fonts.
   # font_pdf_object:: a Hash in the internal format recognized by CombinePDF, that represents the font object.
   # font_cmap:: a CMap dictionary Hash) which maps unicode characters to the hex CID for the font (i.e. {"a" => "61", "z" => "7a" }).
   def register_font(font_name, font_metrics, font_pdf_object, font_cmap = nil)

data/lib/combine_pdf/fonts.rb

@@ -100,7 +100,7 @@ module CombinePDF
 
     # adds a correctly formatted font object to the font library.
     # font_name:: a Symbol with the name of the font. if the fonts name exists, the font will be overwritten!
-    # font_metrics:: a Hash of ont metrics, of the format char => {wx: char_width, boundingbox: [left_x, buttom_y, right_x, top_y]} where i == character code (i.e. 32 for space). The Hash should contain a special value :missing for the metrics of missing characters. an optional :wy will be supported in the future, for up to down fonts.
+    # font_metrics:: a Hash of ont metrics, of the format char => {wx: char_width, boundingbox: [left_x, bottom_y, right_x, top_y]} where i == character code (i.e. 32 for space). The Hash should contain a special value :missing for the metrics of missing characters. an optional :wy will be supported in the future, for up to down fonts.
     # font_pdf_object:: a Hash in the internal format recognized by CombinePDF, that represents the font object.
     # font_cmap:: a CMap dictionary Hash) which maps unicode characters to the hex CID for the font (i.e. {"a" => "61", "z" => "7a" }).
     def register_font(font_name, font_metrics, font_pdf_object, font_cmap = nil)

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
@@ -147,15 +147,15 @@ 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.
-    # y:: the BUTTOM position of the box.
+    # y:: the BOTTOM position of the box.
     # width:: the width/length of the box. negative values will be computed from edge of page. defaults to 0 (end of page).
     # height:: the height of the box. negative values will be computed from edge of page. defaults to 0 (end of page).
     # text_align:: symbol for horizontal text alignment, can be ":center" (default), ":right", ":left"
-    # text_valign:: symbol for vertical text alignment, can be ":center" (default), ":top", ":buttom"
+    # text_valign:: symbol for vertical text alignment, can be ":center" (default), ":top", ":bottom"
     # text_padding:: a Float between 0 and 1, setting the padding for the text. defaults to 0.05 (5%).
     # font:: a registered font name or an Array of names. defaults to ":Helvetica". The 14 standard fonts names are:
     # - :"Times-Roman"
@@ -244,8 +244,8 @@ module CombinePDF
         half_radius = (radius.to_f / 2).round 4
         ## set starting point
         box_stream << "#{options[:x] + radius} #{options[:y]} m\n"
-        ## buttom and right corner - first line and first corner
-        box_stream << "#{options[:x] + options[:width] - radius} #{options[:y]} l\n" # buttom
+        ## bottom and right corner - first line and first corner
+        box_stream << "#{options[:x] + options[:width] - radius} #{options[:y]} l\n" # bottom
         if options[:box_radius] != 0 # make first corner, if not straight.
           box_stream << "#{options[:x] + options[:width] - half_radius} #{options[:y]} "
           box_stream << "#{options[:x] + options[:width]} #{options[:y] + half_radius} "
@@ -265,7 +265,7 @@ module CombinePDF
           box_stream << "#{options[:x]} #{options[:y] + options[:height] - half_radius} "
           box_stream << "#{options[:x]} #{options[:y] + options[:height] - radius} c\n"
         end
-        ## left and buttom-left corner
+        ## left and bottom-left corner
         box_stream << "#{options[:x]} #{options[:y] + radius} l\n"
         if options[:box_radius] != 0
           box_stream << "#{options[:x]} #{options[:y] + half_radius} "
@@ -287,7 +287,7 @@ module CombinePDF
       end
       contents << box_stream
 
-      # reset x,y by text alignment - x,y are calculated from the buttom left
+      # reset x,y by text alignment - x,y are calculated from the bottom left
       # each unit (1) is 1/72 Inch
       # create text stream
       text_stream = ''

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)
@@ -418,7 +424,7 @@ module CombinePDF
         ##########################################
         elsif @scanner.scan(/xref/)
           # skip list indetifier lines or list lines ([\d] [\d][\r\n]) ot ([\d] [\d] [nf][\r\n])
-          while @scanner.scan(/[\s]*[\d]+[ \t]+[\d]+[ \t\r]*\n[\r]?/) || @scanner.scan(/[ \t]*[\d]+[ \t]+[\d]+[ \t]+[nf][\s]*/)
+          while @scanner.scan(/[\s]*[\d]+[ \t]+[\d]+[ \t]*[\n\r]+/) || @scanner.scan(/[ \t]*[\d]+[ \t]+[\d]+[ \t]+[nf][\s]*/)
             nil
           end
         ##########################################
@@ -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

@@ -232,15 +232,42 @@ module CombinePDF
     # @private
     # this method reviews a Hash and updates it by merging Hash data,
     # preffering the new over the old.
-    def self.hash_merge_new_no_page(_key, old_data, new_data)
-      return old_data unless new_data
-      return new_data unless old_data
-      if old_data.is_a?(Hash) && new_data.is_a?(Hash)
-        return old_data if (old_data[:Type] == :Page)
-        old_data.merge(new_data, &(@hash_merge_new_no_page_proc ||= method(:hash_merge_new_no_page)))
+    # def self.hash_merge_new_no_page(_key = nil, old_data = nil, new_data = nil)
+    #   return old_data unless new_data
+    #   return new_data unless old_data
+    #   if old_data.is_a?(Hash) && new_data.is_a?(Hash)
+    #     return old_data if (old_data[:Type] == :Page)
+    #     old_data.merge(new_data, &(@hash_merge_new_no_page_proc ||= method(:hash_merge_new_no_page)))
+    #   elsif old_data.is_a? Array
+    #     return old_data + new_data if new_data.is_a?(Array)
+    #     return old_data.dup << new_data
+    #   elsif new_data.is_a? Array
+    #     new_data + [old_data]
+    #   else
+    #     new_data
+    #   end
+    # end
+
+    # @private
+    # JRuby Alternative this method reviews a Hash and updates it by merging Hash data,
+    # preffering the new over the old.
+    HASH_MERGE_NEW_NO_PAGE = Proc.new do |_key = nil, old_data = nil, new_data = nil|
+      if !new_data
+        old_data
+      elsif !old_data
+        new_data
+      elsif old_data.is_a?(Hash) && new_data.is_a?(Hash)
+        if (old_data[:Type] == :Page)
+          old_data
+        else
+          old_data.merge(new_data, &HASH_MERGE_NEW_NO_PAGE)
+        end
       elsif old_data.is_a? Array
-        return old_data + new_data if new_data.is_a?(Array)
-        return old_data.dup << new_data
+        if new_data.is_a?(Array)
+          old_data + new_data
+        else
+          old_data.dup << new_data
+        end
       elsif new_data.is_a? Array
         new_data + [old_data]
       else
@@ -346,16 +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/pdf_public.rb

@@ -306,10 +306,10 @@ module CombinePDF
       if data.is_a? PDF
         @version = [@version, data.version].max
         pages_to_add = data.pages
-        actual_value(@names ||= {}.dup).update data.names, &self.class.method(:hash_merge_new_no_page)
+        actual_value(@names ||= {}.dup).update data.names, &HASH_MERGE_NEW_NO_PAGE
         merge_outlines((@outlines ||= {}.dup), actual_value(data.outlines), location) unless actual_value(data.outlines).empty?
         if actual_value(@forms_data)
-          actual_value(@forms_data).update actual_value(data.forms_data), &self.class.method(:hash_merge_new_no_page) if data.forms_data
+          actual_value(@forms_data).update actual_value(data.forms_data), &HASH_MERGE_NEW_NO_PAGE if data.forms_data
         else
           @forms_data = data.forms_data
         end
@@ -358,9 +358,9 @@ module CombinePDF
     #
     # options:: a Hash of options setting the behavior and format of the page numbers:
     # - :number_format a string representing the format for page number. defaults to ' - %s - ' (allows for letter numbering as well, such as "a", "b"...).
-    # - :location an Array containing the location for the page numbers, can be :top, :buttom, :top_left, :top_right, :bottom_left, :bottom_right or :center (:center == full page). defaults to [:top, :buttom].
+    # - :location an Array containing the location for the page numbers, can be :top, :bottom, :top_left, :top_right, :bottom_left, :bottom_right or :center (:center == full page). defaults to [:top, :bottom].
     # - :start_at an Integer that sets the number for first page number. also accepts a letter ("a") for letter numbering. defaults to 1.
-    # - :margin_from_height a number (PDF points) for the top and buttom margins. defaults to 45.
+    # - :margin_from_height a number (PDF points) for the top and bottom margins. defaults to 45.
     # - :margin_from_side a number (PDF points) for the left and right margins. defaults to 15.
     # - :page_range a range of pages to be numbered (i.e. (2..-1) ) defaults to all the pages (nil). Remember to set the :start_at to the correct value.
     # the options Hash can also take all the options for {Page_Methods#textbox}.

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.13'.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: 1.0.13
+  version: 1.0.18
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-07-11 00:00:00.000000000 Z
+date: 2020-07-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -24,34 +24,20 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.1.5
-- !ruby/object:Gem::Dependency
-  name: bundler
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.7'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.7'
 - !ruby/object:Gem::Dependency
   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
@@ -118,8 +104,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6
+rubygems_version: 3.1.2
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.