combine_pdf 1.0.16 → 1.0.22

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d071703a8903bc5a11d7beb5a0bcb284a8bced5763705de3a7dd9ae6be35b64d
-  data.tar.gz: 898069ad7ec79ad4fadea5383a721f28c5dfc3632fc20aaa40624954bfe70170
+  metadata.gz: 96825d0aa74bd673883c4d7dbf3884459ff27c2a3d7bd0c60875e0499c7b9aeb
+  data.tar.gz: 985c39883f343bb5182344ccc31353103fbac89494000362973f08cdd379d2ac
 SHA512:
-  metadata.gz: d52868ff7a021801207ff17a1e87aca8fa1bd82e6fd0dacf91d39d57695b07b87238898238fa90755bfaaec65cb4df384b6db97f3f4e3bf70da7d3d808e55daa
-  data.tar.gz: f68133d14d5eb5f0428097b4421976da49471eed61f4ac0e574c4718b588458f6971fd107ccc397be004997f3c31ac6bfc122675992412fd521a7910d6f2abd9
+  metadata.gz: 8575b612e1eb31775833faba8f310d84680d6ce27512d6a9c182e7598a743956da34e0321f0280d032e3e46b861dd2abdd88b297e65a652ec8e3e416ed9fb0a0
+  data.tar.gz: 2026d924120f1798681842fee7a2eb0de78be6ac493dcbd4ffbb934c1c0135161ccbf29283fb0eec42b4ebab66f84b7fa3ac354a970fad9bc0ad302f64da7c7a

data/CHANGELOG.md

@@ -2,6 +2,36 @@
 
 ***
 
+#### Change log v.1.0.22
+
+**Fix**: fix `fonts` dereferencing issue (#203), credit to @MarcWeber (Marc Weber) for identifying the issue.
+
+**Fix**: fix `metrix` dependency, credit to @casperisfine (Jean byroot Boussier) for PR #195.
+
+#### Change log v.1.0.21
+
+**Fix**: possible fix for issue #184, where nested PDF files within an object stream could break the parser. Credit to Greg Sparrow (@hazelsparrow) for exposng the issue.
+
+#### Change log v.1.0.20
+
+**Fix**: merges PR #180, `TypeError: can't dup NilClass`. Credit to Adam Trepanier (@adam-e-trepanier) for the merge.
+
+#### Change log v.1.0.19
+
+**Fix**: fixes font height and width detection issue. Issue #179. Credit to @5anchezzz for opening the issue.
+
+**Fix**: fixes an indentation warning. Issue #173. Credit to @rubyFeedback for exposing this issue.
+
+#### 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
+
+NB: yanked from RubyGems.org.
+
+**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

@@ -1,8 +1,10 @@
 # CombinePDF - the ruby way for merging PDF files
 [![Gem Version](https://badge.fury.io/rb/combine_pdf.svg)](http://badge.fury.io/rb/combine_pdf)
 [![GitHub](https://img.shields.io/badge/GitHub-Open%20Source-blue.svg)](https://github.com/boazsegev/combine_pdf)
+[![Documentation](http://inch-ci.org/github/boazsegev/combine_pdf.svg?branch=master)](https://www.rubydoc.info/github/boazsegev/combine_pdf)
 [![Maintainers Wanted](https://img.shields.io/badge/maintainers-wanted-red.svg)](https://github.com/pickhardt/maintainers-wanted)
 
+
 CombinePDF is a nifty model, written in pure Ruby, to parse PDF files and combine (merge) them with other PDF files, watermark them or stamp them (all using the PDF file format and pure Ruby code).
 
 ## Install
@@ -41,6 +43,8 @@ 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.
@@ -112,7 +116,42 @@ pdf.number_pages
 pdf.save "file_with_numbering.pdf"
 ```
 
-Numbering can be done with many different options, with different formating, with or without a box object, and even with opacity values - see documentation.
+Numbering can be done with many different options, with different formating, with or without a box object, and even with opacity values - [see documentation](https://www.rubydoc.info/github/boazsegev/combine_pdf/CombinePDF/PDF#number_pages-instance_method).
+
+For example, should you prefer to place the page number on the bottom right side of all PDF pages, do:
+
+```ruby
+pdf.number_pages(location: [:bottom_right])
+```
+
+As another example, the dashes around the number are removed and a box is placed around it. The numbering is semi-transparent and the first 3 pages are numbered using letters (a,b,c) rather than numbers:
+
+
+```ruby
+# number first 3 pages as "a", "b", "c"
+pdf.number_pages(number_format: " %s ",
+                 location: [:top, :bottom, :top_left, :top_right, :bottom_left, :bottom_right],
+                 start_at: "a",
+                 page_range: (0..2),
+                 box_color: [0.8,0.8,0.8],
+                 border_color: [0.4, 0.4, 0.4],
+                 border_width: 1,
+                 box_radius: 6,
+                 opacity: 0.75)
+# number the rest of the pages as 4, 5, ... etc'
+pdf.number_pages(number_format: " %s ",
+                 location: [:top, :bottom, :top_left, :top_right, :bottom_left, :bottom_right],
+                 start_at: 4,
+                 page_range: (3..-1),
+                 box_color: [0.8,0.8,0.8],
+                 border_color: [0.4, 0.4, 0.4],
+                 border_width: 1,
+                 box_radius: 6,
+                 opacity: 0.75)
+```
+
+    pdf.number_pages(number_format: " %s ", location: :bottom_right, font_size: 44)
+
 
 ## Loading and Parsing PDF data
 

data/combine_pdf.gemspec

@@ -19,8 +19,9 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_runtime_dependency 'ruby-rc4', '>= 0.1.5'
+  spec.add_runtime_dependency 'matrix'
 
   # 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/api.rb

@@ -24,11 +24,11 @@ module CombinePDF
     raise TypeError, "couldn't create PDF object, expecting type String" unless string.is_a?(String) || string.is_a?(Pathname)
     begin
       (begin
-     File.file? string
-   rescue
-     false
-   end) ? load(string) : parse(string)
-   rescue => _e
+        File.file? string
+      rescue
+        false
+      end) ? load(string) : parse(string)
+    rescue => _e
       raise 'General PDF error - Use CombinePDF.load or CombinePDF.parse for a non-general error message (the requested file was not found OR the string received is not a valid PDF stream OR the file was found but not valid).'
     end
   end

data/lib/combine_pdf/fonts.rb

@@ -138,12 +138,21 @@ module CombinePDF
       text.each_char do |c|
         metrics_array << (merged_metrics[c] || { wx: 0, boundingbox: [0, 0, 0, 0] })
       end
-      height = metrics_array.map { |m| m ? m[:boundingbox][3] : 0 } .max
-      height -= (metrics_array.map { |m| m ? m[:boundingbox][1] : 0 }).min
+      metrics_array_mapped_top = [].dup
+      metrics_array_mapped_bottom = [].dup
       width = 0.0
       metrics_array.each do |m|
-        width += (m[:wx] || m[:wy])
+        if (m && m[:boundingbox])
+          metrics_array_mapped_top << m[:boundingbox][3]
+          metrics_array_mapped_bottom << m[:boundingbox][1]
+        else
+          metrics_array_mapped_top << 0
+          metrics_array_mapped_bottom << 0
+        end
+        width += (m[:wx] || m[:wy] || 0) if m
       end
+      height = metrics_array_mapped_top.max
+      height -=metrics_array_mapped_bottom.min
       return [height.to_f / 1000 * size, width.to_f / 1000 * size] if metrics_array[0][:wy]
       [width.to_f / 1000 * size, height.to_f / 1000 * size]
     end

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
         ##########################################
@@ -348,29 +351,42 @@ 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
         ##########################################
         elsif @scanner.scan(/stream[ \t]*[\r\n]/)
           @scanner.pos += 1 if @scanner.peek(1) == "\n".freeze && @scanner.matched[-1] != "\n".freeze
+          # advance by the publshed stream length (if any)
+          old_pos = @scanner.pos
+          if(out.last.is_a?(Hash) && out.last[:Length].is_a?(Integer) && out.last[:Length] > 2)
+            @scanner.pos += out.last[:Length] - 2
+          end
+
           # the following was dicarded because some PDF files didn't have an EOL marker as required
           # str = @scanner.scan_until(/(\r\n|\r|\n)endstream/)
           # instead, a non-strict RegExp is used:
-          str = @scanner.scan_until(/endstream/)
+          
 
           # raise error if the stream doesn't end.
-          unless str
+          unless @scanner.skip_until(/endstream/)
             raise ParsingError, "Parsing Error: PDF file error - a stream object wasn't properly closed using 'endstream'!"
           end
+          length = @scanner.pos - (old_pos + 9)
+          length = 0 if(length < 0)
+          length -= 1 if(@scanner.string[old_pos + length - 1] == "\n") 
+          length -= 1 if(@scanner.string[old_pos + length - 1] == "\r") 
+          str = (length > 0) ? @scanner.string.slice(old_pos, length) : ''
+
+          # 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)
-            out.last[:raw_stream_content] = unify_string str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
+            out.last[:raw_stream_content] = unify_string str.force_encoding(Encoding::ASCII_8BIT)
           else
             warn 'Stream not attached to dictionary!'
-            out << str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
+            out << str.force_encoding(Encoding::ASCII_8BIT)
           end
         ##########################################
         ## parse an Object after finished
@@ -528,6 +544,14 @@ 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 +580,18 @@ 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] = []
+              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/pdf_public.rb

@@ -257,12 +257,16 @@ module CombinePDF
     def fonts(limit_to_type0 = false)
       fonts_array = []
       pages.each do |pg|
-        if pg[:Resources][:Font]
-          pg[:Resources][:Font].values.each do |f|
-            f = f[:referenced_object] if f[:referenced_object]
-            if (limit_to_type0 || f[:Subtype] == :Type0) && f[:Type] == :Font && !fonts_array.include?(f)
-              fonts_array << f
-            end
+        r = pg[:Resources]
+        next if !r
+        r = r[:referenced_object] if r[:referenced_object]
+        r = r[:Font]
+        next if !r        
+        r = r[:referenced_object] if r[:referenced_object]
+        r.values.each do |f|
+          f = f[:referenced_object] if f[:referenced_object]
+          if (limit_to_type0 || f[:Subtype] == :Type0) && f[:Type] == :Font && !fonts_array.include?(f)
+            fonts_array << f
           end
         end
       end

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.16'.freeze
+  VERSION = '1.0.22'.freeze
 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'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.16
+  version: 1.0.22
 platform: ruby
 authors:
 - Boaz Segev
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2019-02-22 00:00:00.000000000 Z
+date: 2021-11-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -24,20 +24,34 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 0.1.5
+- !ruby/object:Gem::Dependency
+  name: matrix
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !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
@@ -89,7 +103,7 @@ homepage: https://github.com/boazsegev/combine_pdf
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -104,8 +118,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.0.1
-signing_key: 
+rubygems_version: 3.2.3
+signing_key:
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.
 test_files: