combine_pdf 0.2.6 → 0.2.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 63c084e190f8c5f47aaa3db6cd32064a7e7dcfb2
-  data.tar.gz: dbd7e1efe7b372abae318839eb80658913664b29
+  metadata.gz: e1379a60fa97dde419575868f841a676254f61cd
+  data.tar.gz: e55e8f95eaefa828499d393147a13ace92fbd70b
 SHA512:
-  metadata.gz: a374e9be84a6397294a09b1fc76ae0a346ee9bce8abf1d8750742417494ecacf2b49ed843c060c13716046121d5c1ca3b570bf7fc18c828a99ce5cb857a043fc
-  data.tar.gz: bf343d5749131896f4fe1dc2882bd62eb0696eb20c9021048e0b1d8f15837b580a0b50a4db083e752a3e73aa5bcbc88909f78c5d46b7f5ddb1e38cb264919e17
+  metadata.gz: 2cd478b21fe7634e7abb4552fa1b0770465c7e097b00c7ba842d19e243a529667e8b48fdeb7bae64117e30419e9d7fd7a9aeca39d35f342910df4656f887f6c6
+  data.tar.gz: 72d49c89926cb106d133fb17746ec2374225c2d5e5e72c8a4f1c38779d9f6abc188a82c1aa610ebb15ce8adf6da9419ae6ef175dd3b3fb84e6bc8cb938cd9680

data/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ***
 
+Change log v.0.2.7
+
+**Fix**: Fixed an issue where a malformed PDF String could cause the parser to hang.
+
+**Update**: Inner PDF links (links to pages within the PDF file) will now be preserved when importing a whole PDF (although Outlines, for now, are discarede and their related links will be discarded as well). If the same destination page is inserted more than once (the first version will be preferred).
+
+**Deprecation Warning**: the `Page_Methods#secure_injection`, `Page_Methods#make_unsecure` and `Page_Methods#make_secure` methods are deprecated. Use `Page_Methods#copy(true)` for safeguarding against font/resource conflicts when "stamping" one PDF page over another.
+
+***
+
 Change log v.0.2.6
 
 **fixed**: Hasan Iskandar fixed issue #30 - Output file cannot be saved from Adobe Reader with "Save As optimizes for Fast Web View" preference enabled. Thank you Hasan.

data/lib/combine_pdf.rb

@@ -4,6 +4,7 @@ require 'zlib'
 require 'securerandom'
 require 'strscan'
 require 'matrix'
+require 'set'
 
 #require the RC4 Gem
 require 'rc4'

data/lib/combine_pdf/page_methods.rb

@@ -23,19 +23,23 @@ module CombinePDF
 
 		# accessor (getter) for the secure_injection setting
 		def secure_injection
+			warn "**Deprecation Warning**: the `Page_Methods#secure_injection`, `Page_Methods#make_unsecure` and `Page_Methods#make_secure` methods are deprecated. Use `Page_Methods#copy(true)` for safeguarding against font/resource conflicts when 'stamping' one PDF page over another."
 			@secure_injection
 		end
 		# accessor (setter) for the secure_injection setting
 		def secure_injection= safe
+			warn "**Deprecation Warning**: the `Page_Methods#secure_injection`, `Page_Methods#make_unsecure` and `Page_Methods#make_secure` methods are deprecated. Use `Page_Methods#copy(true)` for safeguarding against font/resource conflicts when 'stamping' one PDF page over another."
 			@secure_injection = safe
 		end
 		# sets secure_injection to `true` and returns self, allowing for chaining methods
 		def make_secure
+			warn "**Deprecation Warning**: the `Page_Methods#secure_injection`, `Page_Methods#make_unsecure` and `Page_Methods#make_secure` methods are deprecated. Use `Page_Methods#copy(true)` for safeguarding against font/resource conflicts when 'stamping' one PDF page over another."
 			@secure_injection = true
 			self
 		end
 		# sets secure_injection to `false` and returns self, allowing for chaining methods
 		def make_unsecure
+			warn "**Deprecation Warning**: the `Page_Methods#secure_injection`, `Page_Methods#make_unsecure` and `Page_Methods#make_secure` methods are deprecated. Use `Page_Methods#copy(true)` for safeguarding against font/resource conflicts when 'stamping' one PDF page over another."
 			@secure_injection = false
 			self
 		end

data/lib/combine_pdf/parser.rb

@@ -36,7 +36,7 @@ module CombinePDF
 		# the info and root objects, as found (if found) in the PDF file.
 		#
 		# they are mainly to used to know if the file is (was) encrypted and to get more details.
-		attr_reader :info_object, :root_object
+		attr_reader :info_object, :root_object, :names_object
 
 		# when creating a parser, it is important to set the data (String) we wish to parse.
 		#
@@ -53,6 +53,8 @@ module CombinePDF
 			@references = []
 			@root_object = {}
 			@info_object = {}
+			@names_object = {}
+			@strings_dictionary = {} # all strings are one string
 			@version = nil
 			@scanner = nil
 		end
@@ -113,6 +115,9 @@ module CombinePDF
 				end
 			end
 
+			# Strings were unified, we can let them go..
+			@strings_dictionary.clear
+
 			
 			# serialize_objects_and_references.catalog_pages
 
@@ -179,10 +184,10 @@ module CombinePDF
 					# 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] = str.gsub(/[\n\r]?[\n\r]endstream\z/, "")
+						out.last[:raw_stream_content] = unify_string str.sub(/[\n\r]?[\n\r]endstream\z/, "").force_encoding(Encoding::ASCII_8BIT)
 					else
 						warn "Stream not attached to dictionary!"
-						out << str[0...-10].force_encoding(Encoding::ASCII_8BIT)
+						out << str.sub(/[\n\r]?[\n\r]endstream\z/, "").force_encoding(Encoding::ASCII_8BIT)
 					end
 				##########################################
 				## parse an Object after finished
@@ -199,7 +204,7 @@ module CombinePDF
 				##########################################
 				when str = @scanner.scan(/<[0-9a-fA-F]+>/)
 					# warn "Found a hex string"
-					out << [str[1..-2]].pack('H*')
+					out << unify_string([str[1..-2]].pack('H*').force_encoding(Encoding::ASCII_8BIT))
 				##########################################
 				## parse a Literal String
 				##########################################
@@ -208,14 +213,20 @@ module CombinePDF
 					str = ''.force_encoding(Encoding::ASCII_8BIT)
 					count = 1
 					while count > 0 && @scanner.rest? do
-						str += @scanner.scan_until(/[\(\)]/).to_s
+						scn = @scanner.scan_until(/[\(\)]/)
+						unless scn
+							warn "Unknown error parsing string at #{@scanner.pos} for string: #{str}!"
+							count = 0 # error
+							next
+						end
+
+						str += scn.to_s
 						seperator_count = 0
 						seperator_count += 1 while str[-2-seperator_count] == "\\"
 
 						case str[-1]
 						when '('
-							## The following solution fails when (string ends with this sign: \\)
-
+							## The following solution might fail when (string ends with this sign: \\)
 							count += 1 unless seperator_count.odd?
 						when ')'
 							count -= 1 unless seperator_count.odd?
@@ -276,7 +287,7 @@ module CombinePDF
 							str << str_bytes.shift
 						end
 					end
-					out << str.pack('C*').force_encoding(Encoding::ASCII_8BIT)
+					out << unify_string(str.pack('C*').force_encoding(Encoding::ASCII_8BIT))
 				##########################################
 				## Parse a comment
 				##########################################
@@ -368,7 +379,7 @@ module CombinePDF
 
 
 		# resets cataloging and pages
-		def catalog_pages(catalogs = nil, secure_injection = false, inheritance_hash = {})
+		def catalog_pages(catalogs = nil, inheritance_hash = {})
 			unless catalogs
 
 				if root_object[:Root]
@@ -383,11 +394,11 @@ module CombinePDF
 			end
 			case 
 			when catalogs.is_a?(Array)
-				catalogs.each {|c| catalog_pages(c, secure_injection, inheritance_hash ) unless c.nil?}
+				catalogs.each {|c| catalog_pages(c, inheritance_hash ) unless c.nil?}
 			when catalogs.is_a?(Hash)
 				if catalogs[:is_reference_only]
 					if catalogs[:referenced_object]
-						catalog_pages(catalogs[:referenced_object], secure_injection, inheritance_hash)
+						catalog_pages(catalogs[:referenced_object], inheritance_hash)
 					else
 						warn "couldn't follow reference!!! #{catalogs} not found!"
 					end
@@ -424,11 +435,11 @@ module CombinePDF
 						catalogs[:Rotate] = catalogs[:Rotate][:referenced_object][:indirect_without_dictionary] if catalogs[:Rotate].is_a?(Hash) && catalogs[:Rotate][:referenced_object].is_a?(Hash) && catalogs[:Rotate][:referenced_object][:indirect_without_dictionary]
 
 						catalogs.instance_eval {extend Page_Methods}
-						catalogs.secure_injection = secure_injection
 					when :Pages
-						catalog_pages(catalogs[:Kids], secure_injection, inheritance_hash.dup ) unless catalogs[:Kids].nil?
+						catalog_pages(catalogs[:Kids], inheritance_hash.dup ) unless catalogs[:Kids].nil?
 					when :Catalog
-						catalog_pages(catalogs[:Pages], secure_injection, inheritance_hash.dup ) unless catalogs[:Pages].nil?
+						@names_object.update( (catalogs[:Names][:referenced_object] || catalogs[:Names]), &self.class.method(:hash_update_proc_for_new) ) if catalogs[:Names]
+						catalog_pages(catalogs[:Pages], inheritance_hash.dup ) unless catalogs[:Pages].nil?
 					end
 				end
 			end
@@ -473,11 +484,11 @@ module CombinePDF
 				obj.delete(:indirect_reference_id); obj.delete(:indirect_generation_number)
 			end
 			self
-		# rescue => e
-		# 	puts (@parsed.select {|o| !o.is_a?(Hash)})
-		# 	puts (@parsed)
-		# 	puts (@references)
-		# 	raise e
+		end
+
+		# All Strings are one String
+		def unify_string str
+			@strings_dictionary[str] ||= str
 		end
 
 		# @private

data/lib/combine_pdf/pdf_protected.rb

@@ -25,15 +25,15 @@ module CombinePDF
 		# this function adds the references contained in "object", but DOESN'T add the object itself.
 		#
 		# this is used for internal operations, such as injectng data using the << operator.
-		def add_referenced(object)
+		def add_referenced(object, dup_pages = true)
 			# add references but not root
 			case 
 			when object.is_a?(Array)
-				object.each {|it| add_referenced(it)}
+				object.each {|it| add_referenced(it, dup_pages)}
 				return true
 			when object.is_a?(Hash)
 				# first if statement is actually a workaround for a bug in Acrobat Reader, regarding duplicate pages.
-				if object[:is_reference_only] && object[:referenced_object] && object[:referenced_object].is_a?(Hash) && object[:referenced_object][:Type] == :Page
+				if dup_pages && object[:is_reference_only] && object[:referenced_object] && object[:referenced_object].is_a?(Hash) && object[:referenced_object][:Type] == :Page
 					if @objects.find_index object[:referenced_object]
 						@objects << (object[:referenced_object] = object[:referenced_object].dup)
 					else
@@ -49,6 +49,8 @@ module CombinePDF
 						# stop this path, there is no need to run over the Hash's keys and values
 						return true
 					else
+						# stop if page propegation is false
+						return true if !dup_pages && object[:referenced_object][:Type] == :Page
 						# @objects.include? object[:referenced_object] is bound to be false
 						# the object wasn't found - add it to the @objects array
 						@objects << object[:referenced_object]
@@ -56,8 +58,8 @@ module CombinePDF
 
 				end
 				object.each do |k, v|
-					add_referenced(v) unless k == :Parent 
-				end
+					add_referenced(v, dup_pages) unless k == :Parent 
+				end 
 			else
 				return false
 			end
@@ -83,8 +85,10 @@ module CombinePDF
 			# build new Pages object
 			pages_object = {Type: :Pages, Count: page_list.length, Kids: page_list.map {|p| {referenced_object: p, is_reference_only: true} } }
 
+			# rebuild/rename the names dictionary
+			rebuild_names
 			# build new Catalog object
-			catalog_object = {Type: :Catalog, Pages: {referenced_object: pages_object, is_reference_only: true} }
+			catalog_object = {Type: :Catalog, Pages: {referenced_object: pages_object, is_reference_only: true}, Names: {referenced_object: @names, is_reference_only: true} }
 			catalog_object[:ViewerPreferences] = @viewer_preferences unless @viewer_preferences.empty?
 
 			# point old Pages pointers to new Pages object
@@ -103,17 +107,22 @@ module CombinePDF
 			catalog_object
 		end
 
+		def names_object
+			@names
+		end
+
 		# @private
 		# this is an alternative to the rebuild_catalog catalog method
 		# this method is used by the to_pdf method, for streamlining the PDF output.
 		# there is no point is calling the method before preparing the output.
 		def rebuild_catalog_and_objects
 			catalog = rebuild_catalog
-			@objects = []
+			@objects.clear
 			@objects << @info
 			add_referenced @info
 			@objects << catalog
-			add_referenced catalog
+			add_referenced catalog[:Pages]
+			add_referenced catalog[:Names], false
 			catalog
 		end
 
@@ -138,6 +147,70 @@ module CombinePDF
 			@objects.each {|obj| obj.delete(:indirect_reference_id); obj.delete(:indirect_generation_number)}
 		end
 
+		def rebuild_names name_tree = nil, base = "CombinePDF_0000000"
+			if name_tree
+				dic = []
+				case name_tree
+				when Array
+					if name_tree[0].is_a? String
+						(name_tree.length/2).times do |i|
+							dic << (name_tree[i*2].clear << base.next!)
+							dic << name_tree[(i*2) + 1]
+						end
+					else
+						name_tree.each {|kid| dic.concat rebuild_names(kid, base) }
+					end
+				when Hash
+					if name_tree[:Kids]
+						dic.concat rebuild_names(name_tree[:Kids], base)
+					elsif name_tree[:Names]
+						dic.concat rebuild_names(name_tree[:Names], base)
+					elsif name_tree[:referenced_object]
+						dic.concat rebuild_names(name_tree[:referenced_object], base)
+					end
+				end
+				return dic
+			end
+			@names.keys.each do |k|
+				@names[k] = {referenced_object: { Names: rebuild_names(@names[k], base) } , is_reference_only: true} unless k == :Type
+			end
+		end
+
+		# @private
+		# this method reviews a Hash an updates it by merging Hash data,
+		# preffering the new over the old.
+		def self.hash_merge_new_no_page key, old_data, new_data
+			if old_data.is_a? Hash
+				return old_data if old_data[:Type] == :Page
+				old_data.merge( new_data, &( @hash_merge_new_no_page_proc ||= self.method(:hash_merge_new_no_page) ) )
+			elsif old_data.is_a? Array
+				old_data + new_data
+			else
+				new_data
+			end
+		end
+
+
+		private
+
+		def renaming_dictionary object = nil, dictionary = {}
+			object ||= @names
+			case object
+			when Array
+				object.length.times {|i| object[i].is_a?(String) ? (dictionary[object[i]] = (dictionary.last || "Random_0001").next) : renaming_dictionary(object[i], dictionary) }
+			when Hash
+				object.values.each {|v| renaming_dictionary v, dictionary }
+			end
+		end
+
+		def rename_object object, dictionary
+			case object
+			when Array
+				object.length.times {|i| }
+			when Hash
+			end
+		end
+
 	end
 end
 

data/lib/combine_pdf/pdf_public.rb

@@ -103,6 +103,7 @@ module CombinePDF
 			# set data from parser
 			@version = parser.version if parser.version.is_a? Float
 			@info = parser.info_object || {}
+			@names = parser.names_object || {}
 
 			# general globals
 			@set_start_id = 1
@@ -293,6 +294,7 @@ module CombinePDF
 			if data.is_a? PDF
 		 		@version = [@version, data.version].max
 				pages_to_add = data.pages
+				@names.update data.names_object, &self.class.method(:hash_merge_new_no_page)
 			elsif data.is_a?(Array) && (data.select {|o| !(o.is_a?(Hash) && o[:Type] == :Page) } ).empty?
 				pages_to_add = data
 			elsif data.is_a?(Hash) && data[:Type] == :Page

data/lib/combine_pdf/version.rb

@@ -1,4 +1,4 @@
 module CombinePDF
-  VERSION = "0.2.6"
+  VERSION = "0.2.7"
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.6
+  version: 0.2.7
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-10-08 00:00:00.000000000 Z
+date: 2015-10-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -74,7 +74,6 @@ files:
 - lib/combine_pdf/decrypt.rb
 - lib/combine_pdf/filter.rb
 - lib/combine_pdf/fonts.rb
-- lib/combine_pdf/operations.rb
 - lib/combine_pdf/page_methods.rb
 - lib/combine_pdf/parser.rb
 - lib/combine_pdf/pdf_protected.rb
@@ -108,3 +107,4 @@ specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.
 test_files:
 - test/console
+has_rdoc: 

data/lib/combine_pdf/operations.rb

@@ -1,416 +0,0 @@
-module CombinePDF
-
-	################################################################
-	## These are common functions, used within the different classes
-	## These functions aren't open to the public.
-	################################################################
-
-
-
-	# holds a simple content stream that starts a PDF graphic state container - used for wrapping malformed PDF content streams.
-	CONTENT_CONTAINER_START = { is_reference_only: true , referenced_object: {indirect_reference_id: 0, raw_stream_content: 'q'} }
-	# holds a simple content stream that ends a PDF graphic state container - used for wrapping malformed PDF content streams.
-	CONTENT_CONTAINER_MIDDLE = { is_reference_only: true , referenced_object: {indirect_reference_id: 0, raw_stream_content: "Q\nq"} }
-	# holds a simple content stream that ends a PDF graphic state container - used for wrapping malformed PDF content streams.
-	CONTENT_CONTAINER_END = { is_reference_only: true , referenced_object: {indirect_reference_id: 0, raw_stream_content: 'Q'} }
-
-	# @private
-	# @!visibility private
-	#:nodoc: all
-
-	protected
-
-	# @!visibility private
-
-	# This is an internal class. you don't need it.
-	module PDFOperations
-
-		module_function
-
-		# @!visibility private
-
-		def inject_to_page page = {Type: :Page, MediaBox: [0,0,612.0,792.0], Resources: {}, Contents: []}, stream = nil, top = true
-			# make sure both the page reciving the new data and the injected page are of the correct data type.
-			return false unless page.is_a?(Hash) && stream.is_a?(Hash)
-
-			# following the reference chain and assigning a pointer to the correct Resouces object.
-			# (assignments of Strings, Arrays and Hashes are pointers in Ruby, unless the .dup method is called)
-			page[:Resources] ||= {}
-			original_resources = page[:Resources]
-			if original_resources[:is_reference_only]
-				original_resources = original_resources[:referenced_object]
-				raise "Couldn't tap into resources dictionary, as it is a reference and isn't linked." unless original_resources
-			end
-			original_contents = page[:Contents]
-			original_contents = [original_contents] unless original_contents.is_a? Array
-
-			stream[:Resources] ||= {}
-			stream_resources = stream[:Resources]
-			if stream_resources[:is_reference_only]
-				stream_resources = stream_resources[:referenced_object]
-				raise "Couldn't tap into resources dictionary, as it is a reference and isn't linked." unless stream_resources
-			end
-			stream_contents = stream[:Contents]
-			stream_contents = [stream_contents] unless stream_contents.is_a? Array
-
-			# collect keys as objects - this is to make sure that
-			# we are working on the actual resource data, rather then references
-			flatten_resources_dictionaries stream_resources
-			flatten_resources_dictionaries original_resources
-
-			# injecting each of the values in the injected Page
-			stream_resources.each do |key, new_val|
-				unless PRIVATE_HASH_KEYS.include? key # keep CombinePDF structual data intact.
-					if original_resources[key].nil?
-						original_resources[key] = new_val
-					elsif original_resources[key].is_a?(Hash) && new_val.is_a?(Hash)
-						new_val.update original_resources[key] # make sure the old values are respected
-						original_resources[key].update new_val # transfer old and new values to the injected page
-					end #Do nothing if array - ot is the PROC array, which is an issue
-				end
-			end
-			original_resources[:ProcSet] = [:PDF, :Text, :ImageB, :ImageC, :ImageI] # this was recommended by the ISO. 32000-1:2008
-
-			if top # if this is a stamp (overlay)
-				page[:Contents] = original_contents
-				page[:Contents].unshift create_deep_copy(CONTENT_CONTAINER_START)
-				page[:Contents].push create_deep_copy(CONTENT_CONTAINER_MIDDLE)
-				page[:Contents].push *stream_contents
-				page[:Contents].push create_deep_copy(CONTENT_CONTAINER_END)
-			else #if this was a watermark (underlay? would be lost if the page was scanned, as white might not be transparent)
-				page[:Contents] = stream_contents
-				page[:Contents].unshift create_deep_copy(CONTENT_CONTAINER_START)
-				page[:Contents].push create_deep_copy(CONTENT_CONTAINER_MIDDLE)
-				page[:Contents].push *original_contents
-				page[:Contents].push create_deep_copy(CONTENT_CONTAINER_END)
-			end
-
-			page
-		end
-		# copy_and_secure_for_injection(page)
-		# - page is a page in the pages array, i.e.
-		#   pdf.pages[0]
-		# takes a page object and:
-		#
-		# makes a deep copy of the page (Ruby defaults to pointers, so this will copy the memory).
-		#
-		# then it will rewrite the content stream with renamed resources, so as to avoid name conflicts.
-		def copy_and_secure_for_injection(page)
-			# copy page
-			new_page = create_deep_copy page
-
-			# initiate dictionary from old names to new names
-			names_dictionary = {}
-
-			# itirate through all keys that are name objects and give them new names (add to dic)
-			# this should be done for every dictionary in :Resources
-			# this is a few steps stage:
-
-			# 1. get resources object
-			resources = new_page[:Resources]
-			if resources[:is_reference_only]
-				resources = resources[:referenced_object]
-				raise "Couldn't tap into resources dictionary, as it is a reference and isn't linked." unless resources
-			end
-
-			# 2. establich direct access to dictionaries and remove reference values
-			flatten_resources_dictionaries resources
-
-			# 3. travel every dictionary to pick up names (keys), change them and add them to the dictionary
-			resources.each do |k,v|
-				if v.is_a?(Hash)
-					new_dictionary = {}
-					new_name = "Combine" + SecureRandom.hex(7) + "PDF"
-					i = 1
-					v.each do |old_key, value|
-						new_key = (new_name + i.to_s).to_sym
-						names_dictionary[old_key] = new_key
-						new_dictionary[new_key] = value
-						i += 1
-					end
-					resources[k] = new_dictionary
-				end
-			end
-
-			# now that we have replaced the names in the resources dictionaries,
-			# it is time to replace the names inside the stream
-			# we will need to make sure we have access to the stream injected
-			# we will user PDFFilter.inflate_object
-			(new_page[:Contents].is_a?(Array) ? new_page[:Contents] : [new_page[:Contents] ]).each do |c|
-				stream = c[:referenced_object]
-				PDFFilter.inflate_object stream
-				names_dictionary.each do |old_key, new_key|
-					stream[:raw_stream_content].gsub! _object_to_pdf(old_key), _object_to_pdf(new_key)  ##### PRAY(!) that the parsed datawill be correctly reproduced! 
-				end
-				# patch back to PDF defaults, for OCRed PDF files.
-				# stream[:raw_stream_content] = "q\nq\nq\nDeviceRGB CS\nDeviceRGB cs\n0 0 0 rg\n0 0 0 RG\n0 Tr\n%s\nQ\nQ\nQ\n" % stream[:raw_stream_content]
-				# the following was removed for Acrobat Reader compatability: DeviceRGB CS\nDeviceRGB cs\n
-				stream[:raw_stream_content] = "q\nq\nq\n0 0 0 rg\n0 0 0 RG\n0 Tr\n1 0 0 1 0 0 cm\n%s\nQ\nQ\nQ\n" % stream[:raw_stream_content]
-			end
-
-			new_page
-		end
-		def flatten_resources_dictionaries(resources)
-			resources.each do |k,v|
-				if v.is_a?(Hash) && v[:is_reference_only]
-					if v[:referenced_object]
-						resources[k] = resources[k][:referenced_object].dup
-						resources[k].delete(:indirect_reference_id)
-						resources[k].delete(:indirect_generation_number)
-					elsif v[:indirect_without_dictionary]
-						resources[k] = resources[k][:indirect_without_dictionary]
-					end
-				end
-			end
-		end
-
-		# returns the PDF Object Hash holding the acutal data (if exists) or the original hash (if it wasn't a reference)
-		#
-		# works only AFTER references have been connected.
-		def get_referenced object
-			object[:referenced_object] || object
-		end
-
-
-		# Ruby normally assigns pointes.
-		# noramlly:
-		#   a = [1,2,3] # => [1,2,3]
-		#   b = a # => [1,2,3]
-		#   a << 4 # => [1,2,3,4]
-		#   b # => [1,2,3,4]
-		# This method makes sure that the memory is copied instead of a pointer assigned.
-		# this works using recursion, so that arrays and hashes within arrays and hashes are also copied and not pointed to.
-		# One needs to be careful of infinit loops using this function.
-		def create_deep_copy object
-			if object.is_a?(Array)
-				return object.map { |e|  create_deep_copy e  }
-			elsif object.is_a?(Hash)
-				return {}.tap {|out|  object.each {|k,v| out[create_deep_copy(k)] = create_deep_copy(v) unless k == :Parent} }
-			elsif object.is_a?(String)
-				return object.dup
-			else
-				return object # objects that aren't Strings, Arrays or Hashes (such as Symbols and Fixnums) won't be edited inplace.
-			end
-		end
-		# removes id and generation number values, for better comparrison
-		# and avoiding object duplication
-		# objects:: one or more objects in a PDF file/page.
-		def remove_old_ids objects
-			_each_object(objects) {|obj| obj.delete(:indirect_reference_id); obj.delete(:indirect_generation_number)}
-		end
-		def get_refernced_object(objects_array = [], reference_hash = {})
-			objects_array.each do |stored_object|
-				return stored_object if ( stored_object.is_a?(Hash) &&
-					reference_hash[:indirect_reference_id] == stored_object[:indirect_reference_id] &&
-					reference_hash[:indirect_generation_number] == stored_object[:indirect_generation_number] )
-			end
-			warn "didn't find reference #{reference_hash}"
-			nil		
-		end
-		def change_references_to_actual_values(objects_array = [], hash_with_references = {})
-			hash_with_references.each do |k,v|
-				if v.is_a?(Hash) && v[:is_reference_only]
-					hash_with_references[k] = PDFOperations.get_refernced_object( objects_array, v)
-					hash_with_references[k] = hash_with_references[k][:indirect_without_dictionary] if hash_with_references[k].is_a?(Hash) && hash_with_references[k][:indirect_without_dictionary]
-					warn "Couldn't connect all values from references - didn't find reference #{hash_with_references}!!!" if hash_with_references[k] == nil
-					hash_with_references[k] = v unless hash_with_references[k]
-				end
-			end
-			hash_with_references
-		end
-		def change_connected_references_to_actual_values(hash_with_references = {})
-			if hash_with_references.is_a?(Hash)
-				hash_with_references.each do |k,v|
-					if v.is_a?(Hash) && v[:is_reference_only]
-						if v[:indirect_without_dictionary]
-							hash_with_references[k] = v[:indirect_without_dictionary]
-						elsif  v[:referenced_object]
-							hash_with_references[k] = v[:referenced_object]
-						else
-							raise "Cannot change references to values, as they are disconnected!"
-						end
-					end
-				end
-				hash_with_references.each {|k, v| change_connected_references_to_actual_values(v) if v.is_a?(Hash) || v.is_a?(Array)}
-			elsif hash_with_references.is_a?(Array)
-				hash_with_references.each {|item| change_connected_references_to_actual_values(item) if item.is_a?(Hash) || item.is_a?(Array)}
-			end
-			hash_with_references		
-		end
-		def connect_references_and_actual_values(objects_array = [], hash_with_references = {})
-			ret = true
-			hash_with_references.each do |k,v|
-				if v.is_a?(Hash) && v[:is_reference_only]
-					ref_obj = PDFOperations.get_refernced_object( objects_array, v)
-					hash_with_references[k] = ref_obj[:indirect_without_dictionary] if ref_obj.is_a?(Hash) && ref_obj[:indirect_without_dictionary]
-					ret = false
-				end
-			end
-			ret		
-		end
-
-
-		def _each_object(object, limit_references = true, first_call = true, &block)
-			# #####################
-			# ## v.1.2 needs optimazation
-			# case
-			# when object.is_a?(Array)
-			# 	object.each {|obj| _each_object(obj, limit_references, &block)}
-			# when object.is_a?(Hash)
-			# 	yield(object)
-			# 	object.each do |k,v|
-			# 		unless (limit_references && k == :referenced_object)
-			# 			unless k == :Parent
-			# 				_each_object(v, limit_references, &block)
-			# 			end
-			# 		end
-			# 	end
-			# end
-			#####################
-			## v.2.1 needs optimazation
-			## version 2.1 is slightly faster then v.1.2
-			@already_visited = [] if first_call
-			unless limit_references
-				@already_visited << object.object_id
-			end
-			case
-			when object.is_a?(Array)
-				object.each {|obj| _each_object(obj, limit_references, false, &block)}
-			when object.is_a?(Hash)
-				yield(object)
-				unless limit_references && object[:is_reference_only]
-					object.each do |k,v|
-						_each_object(v, limit_references, false, &block) unless @already_visited.include? v.object_id
-					end
-				end					
-			end
-		end
-
-
-
-		# Formats an object into PDF format. This is used my the PDF object to format the PDF file and it is used in the secure injection which is still being developed.
-		def _object_to_pdf object
-			case
-			when object.nil?
-				return "null"
-			when object.is_a?(String)
-				return _format_string_to_pdf object
-			when object.is_a?(Symbol)
-				return _format_name_to_pdf object
-			when object.is_a?(Array)
-				return _format_array_to_pdf object
-			when object.is_a?(Fixnum), object.is_a?(Float), object.is_a?(TrueClass), object.is_a?(FalseClass)
-				return object.to_s + " "
-			when object.is_a?(Hash)
-				return _format_hash_to_pdf object
-			else
-				return ''
-			end
-		end
-
-		def _format_string_to_pdf(object)
-			if @string_output == :literal #if format is set to Literal
-				#### can be better...
-				replacement_hash = {
-					"\x0A" => "\\n",
-					"\x0D" => "\\r",
-					"\x09" => "\\t",
-					"\x08" => "\\b",
-					"\xFF" => "\\f",
-					"\x28" => "\\(",
-					"\x29" => "\\)",
-					"\x5C" => "\\\\"
-				}
-				32.times {|i| replacement_hash[i.chr] ||= "\\#{i}"}
-				(256-128).times {|i| replacement_hash[(i + 127).chr] ||= "\\#{i+127}"}
-				("(" + ([].tap {|out| object.bytes.each {|byte| replacement_hash[ byte.chr ] ? (replacement_hash[ byte.chr ].bytes.each {|b| out << b}) : out << byte } }).pack('C*') + ")").force_encoding(Encoding::ASCII_8BIT)
-			else
-				# A hexadecimal string shall be written as a sequence of hexadecimal digits (0–9 and either A–F or a–f)
-				# encoded as ASCII characters and enclosed within angle brackets (using LESS-THAN SIGN (3Ch) and GREATER- THAN SIGN (3Eh)). 
-				("<" + object.unpack('H*')[0] + ">").force_encoding(Encoding::ASCII_8BIT)
-			end
-		end
-		def _format_name_to_pdf(object)
-			# a name object is an atomic symbol uniquely defined by a sequence of ANY characters (8-bit values) except null (character code 0).
-			# print name as a simple string. all characters between ~ and ! (except #) can be raw
-			# the rest will have a number sign and their HEX equivalant
-			# from the standard:
-			# When writing a name in a PDF file, a SOLIDUS (2Fh) (/) shall be used to introduce a name. The SOLIDUS is not part of the name but is a prefix indicating that what follows is a sequence of characters representing the name in the PDF file and shall follow these rules:
-			# a) A NUMBER SIGN (23h) (#) in a name shall be written by using its 2-digit hexadecimal code (23), preceded by the NUMBER SIGN.
-			# b) Any character in a name that is a regular character (other than NUMBER SIGN) shall be written as itself or by using its 2-digit hexadecimal code, preceded by the NUMBER SIGN.
-			# c) Any character that is not a regular character shall be written using its 2-digit hexadecimal code, preceded by the NUMBER SIGN only.
-			# [0x00, 0x09, 0x0a, 0x0c, 0x0d, 0x20, 0x28, 0x29, 0x3c, 0x3e, 0x5b, 0x5d, 0x7b, 0x7d, 0x2f, 0x25]
-			out = object.to_s.bytes.to_a.map do |b|
-				case b
-				when 0..15
-					'#0' + b.to_s(16)
-				when 15..32, 35, 37, 40, 41, 47, 60, 62, 91, 93, 123, 125, 127..256
-					'#' + b.to_s(16)
-				else
-					b.chr
-				end
-			end
-			"/" + out.join()
-		end
-		def _format_array_to_pdf(object)
-			# An array shall be written as a sequence of objects enclosed in SQUARE BRACKETS (using LEFT SQUARE BRACKET (5Bh) and RIGHT SQUARE BRACKET (5Dh)).
-			# EXAMPLE [549 3.14 false (Ralph) /SomeName]
-			("[" + (object.collect {|item| _object_to_pdf(item)}).join(' ') + "]").force_encoding(Encoding::ASCII_8BIT)
-			
-		end
-
-		def _format_hash_to_pdf(object)
-			# if the object is only a reference:
-			# special conditions apply, and there is only the setting of the reference (if needed) and output
-			if object[:is_reference_only]
-				#
-				if object[:referenced_object] && object[:referenced_object].is_a?(Hash)
-					object[:indirect_reference_id] = object[:referenced_object][:indirect_reference_id]
-					object[:indirect_generation_number] = object[:referenced_object][:indirect_generation_number]
-				end
-				object[:indirect_reference_id] ||= 0
-				object[:indirect_generation_number] ||= 0
-				return "#{object[:indirect_reference_id].to_s} #{object[:indirect_generation_number].to_s} R".force_encoding(Encoding::ASCII_8BIT)
-			end
-
-			# if the object is indirect...
-			out = []
-			if object[:indirect_reference_id]
-				object[:indirect_reference_id] ||= 0
-				object[:indirect_generation_number] ||= 0
-				out << "#{object[:indirect_reference_id].to_s} #{object[:indirect_generation_number].to_s} obj\n".force_encoding(Encoding::ASCII_8BIT)
-				if object[:indirect_without_dictionary]
-					out << _object_to_pdf(object[:indirect_without_dictionary])
-					out << "\nendobj\n"
-					return out.join().force_encoding(Encoding::ASCII_8BIT)
-				end
-			end
-			# correct stream length, if the object is a stream.
-			object[:Length] = object[:raw_stream_content].bytesize if object[:raw_stream_content]
-
-			# if the object is not a simple object, it is a dictionary
-			# A dictionary shall be written as a sequence of key-value pairs enclosed in double angle brackets (<<...>>)
-			# (using LESS-THAN SIGNs (3Ch) and GREATER-THAN SIGNs (3Eh)).
-			out << "<<\n".force_encoding(Encoding::ASCII_8BIT)
-			object.each do |key, value|
-				out << "#{_object_to_pdf key} #{_object_to_pdf value}\n".force_encoding(Encoding::ASCII_8BIT) unless PRIVATE_HASH_KEYS.include? key
-			end
-			out << ">>".force_encoding(Encoding::ASCII_8BIT)
-			out << "\nstream\n#{object[:raw_stream_content]}\nendstream".force_encoding(Encoding::ASCII_8BIT) if object[:raw_stream_content]
-			out << "\nendobj\n" if object[:indirect_reference_id]
-			out.join().force_encoding(Encoding::ASCII_8BIT)
-		end
-	end
-end
-
-#########################################################
-# this file is part of the CombinePDF library and the code
-# is subject to the same license (MIT).
-#########################################################
-# PDF object types cross reference:
-# Indirect objects, references, dictionaries and streams are Hash
-# arrays are Array
-# strings are String
-# names are Symbols (String.to_sym)
-# numbers are Fixnum or Float
-# boolean are TrueClass or FalseClass