combine_pdf 0.1.10 → 0.1.11

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0cdaac783f68294ad27e5b4debc724f56190fc02
-  data.tar.gz: c31baf6a9e9fc4076b1d28abafde4e383d797b1f
+  metadata.gz: 40bc13d0d602d989d06580fd8d18d4bff8fd825b
+  data.tar.gz: 5c516b4f7f241018ace628f5b30df65074f416d4
 SHA512:
-  metadata.gz: 10ec2ba8ab2885d7f99cab5c7bcd7feaf22408d8e4da66e0ab3fc2f57ab0c5ba52e9325e3c110642b03a2309561d0494bfaab7b37126c949937f55e66a22ef29
-  data.tar.gz: 3650485fcdbafbd255912365bc6ffee8acd86b16cf07e71653388972ed2fb78f27305ca5b8c4f51303e45b3f59f6d468c8dbdaa180e084aff1045bc5e01c8659
+  metadata.gz: d0a892d29ba0e918ea707a1e0206768450966a35643ed4bab825fe5ce1fea24091b9de8e0d033dba70b3cc5f8052c95f3f58238fc06b644c0ac8c63f85008ce4
+  data.tar.gz: bc3d9c23a738c4f282fd00b213fb0352fe4cf9275f1b54c9b9d92c0f63d0a1bacffd1faa2151310f91bbbb01e2e7244f1c5303b423135659f84a5424f33beccf

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ***
 
+Change log v.0.1.11
+
+**fix**: fixed a bug where Page Resources and ColorSpace data wouldn't be inherited correctly from the Catalog and Pages parent objects. This issue could cause pages to render without all their content intact. This issue is now fixed (although more testing should be done for multiple inheritance).
+
+**?fix?** Attempted to fix [the issue reported by srogers](https://github.com/boazsegev/combine_pdf/issues/10), by forcing all String byte collections to return an Array. waiting confirmation for fix (couldn't reproduce the issue just yet, as I can't seem to install Ruby MRI 1.9.3 on my mac).
+
+***
+
 Change log v.0.1.10
 
 **fix**: fixed a typo that prevented access to the CombinePDF::VERSION constant.

data/lib/combine_pdf/combine_pdf_decrypt.rb

@@ -69,7 +69,7 @@ module CombinePDF
 
 		def set_general_key(password = "")
 			# 1) make sure the initial key is 32 byte long (if no password, uses padding).
-			key = (password.bytes[0..32] + @padding_key)[0..31].pack('C*').force_encoding(Encoding::ASCII_8BIT)
+			key = (password.bytes[0..32].to_a + @padding_key)[0..31].to_a.pack('C*').force_encoding(Encoding::ASCII_8BIT)
 			# 2) add the value of the encryption dictionary’s O entry
 			key << @encryption_dictionary[:O].to_s
 			# 3) Convert the integer value of the P entry to a 32-bit unsigned binary number

data/lib/combine_pdf/combine_pdf_filter.rb

@@ -34,6 +34,7 @@ module CombinePDF
 		#
 		# object:: object to decompress.
 		def inflate_object object = nil
+			return false unless object.is_a?(Hash)
 			filter_array = object[:Filter]
 			if filter_array.is_a?(Hash) && filter_array[:is_reference_only]
 				filter_array = filter_array[:referenced_object]

data/lib/combine_pdf/combine_pdf_operations.rb

@@ -348,7 +348,7 @@ module CombinePDF
 			# 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.map do |b|
+			out = object.to_s.bytes.to_a.map do |b|
 				case b
 				when 0..15
 					'#0' + b.to_s(16)

data/lib/combine_pdf/combine_pdf_parser.rb

@@ -237,7 +237,7 @@ module CombinePDF
 								str << 8
 							when 102 #f
 								str << 255
-							when 48..57 #decimal notation for byte?
+							when 48..57 #octal notation for byte?
 								rep = rep.chr
 								rep += str_bytes.shift.chr if str_bytes[0].between?(48,57)
 								rep += str_bytes.shift.chr if str_bytes[0].between?(48,57) && ((rep + str_bytes[0].chr).to_i <= 255)

data/lib/combine_pdf/combine_pdf_pdf.rb

@@ -144,7 +144,7 @@ module CombinePDF
 
 			#collect objects and set xref table locations
 			loc = 0
-			out.each {|line| loc += line.bytes.length + 1}
+			out.each {|line| loc += line.bytesize + 1}
 			@objects.each do |o|
 				indirect_object_count += 1
 				xref << loc
@@ -152,7 +152,7 @@ module CombinePDF
 				loc += out.last.length + 1
 			end
 			xref_location = 0
-			out.each { |line| xref_location += line.bytes.length + 1}
+			out.each { |line| xref_location += line.bytesize + 1}
 			out << "xref\n\r0 #{(indirect_object_count).to_s}\n\r0000000000 65535 f \n\r"
 			xref.each {|offset| out << ( out.pop + ("%010d 00000 n \n\r" % offset) ) }
 			out << out.pop + "trailer"
@@ -197,7 +197,7 @@ module CombinePDF
 		#
 		# catalogs:: a catalog, or an Array of catalog objects. defaults to the existing catalog.
 		# secure_injection:: a boolean (true / false) controling the behavior of the << operator.
-		def pages(catalogs = nil, secure_injection = true)
+		def pages(catalogs = nil, secure_injection = true, inheritance_hash = {})
 			page_list = []
 			if catalogs == nil
 				catalogs = @objects.select {|obj| obj.is_a?(Hash) && obj[:Type] == :Catalog}
@@ -205,16 +205,24 @@ module CombinePDF
 			end
 			case 
 			when catalogs.is_a?(Array)
-				catalogs.each {|c| page_list.push *(pages(c)) unless c.nil?}
+				catalogs.each {|c| page_list.push *( pages(c, secure_injection, inheritance_hash ) ) unless c.nil?}
 			when catalogs.is_a?(Hash)
 				if catalogs[:is_reference_only]
-					catalogs[:referenced_object] = pages(PDFOperations.get_refernced_object @objects, catalogs) unless catalogs[:referenced_object]
+					# not applicable any more... | catalogs[:referenced_object] = PDFOperations.get_refernced_object(@objects, catalogs) # for some reson, the code was: pages(PDFOperations.get_refernced_object(@objects, catalogs), secure_injection, inheritance_hash) unless catalogs[:referenced_object]
 					if catalogs[:referenced_object]
-						page_list.push *( pages(catalogs[:referenced_object]) )
+						page_list.push *( pages(catalogs[:referenced_object], secure_injection, inheritance_hash) )
 					else
 						warn "couldn't follow reference!!! #{catalogs} not found!"
 					end
 				else
+					unless catalogs[:Type] == :Page
+						# set inheritance, when applicable
+						inheritance_hash[:MediaBox] = catalogs[:MediaBox] if catalogs[:MediaBox]
+						inheritance_hash[:CropBox] = catalogs[:CropBox] if catalogs[:CropBox]
+						(inheritance_hash[:Resources] ||= {}).update( (catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &self.class.method(:hash_update_proc_for_new) ) if catalogs[:Resources]
+						(inheritance_hash[:ColorSpace] ||= {}).update( (catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &self.class.method(:hash_update_proc_for_new) ) if catalogs[:ColorSpace]
+					end
+
 					case catalogs[:Type]
 					when :Page
 						holder = self
@@ -233,15 +241,23 @@ module CombinePDF
 								self
 							end
 						end
-						catalogs[:MediaBox] ||= catalogs[:Parent][:referenced_object][:MediaBox] if catalogs[:Parent].is_a?(Hash) && catalogs[:Parent][:referenced_object].is_a?(Hash) && catalogs[:Parent][:referenced_object][:MediaBox]
-						catalogs[:CropBox] ||= catalogs[:Parent][:referenced_object][:CropBox] if catalogs[:CropBox].is_a?(Hash) && catalogs[:CropBox][:referenced_object].is_a?(Hash) && catalogs[:Parent][:referenced_object][:CropBox]
+
+						# inheritance 
+						catalogs[:MediaBox] ||= inheritance_hash[:MediaBox] if inheritance_hash[:MediaBox]
+						catalogs[:CropBox] ||= inheritance_hash[:CropBox] if inheritance_hash[:CropBox]
+						(catalogs[:Resources] ||= {}).update( inheritance_hash[:Resources], &( self.class.method(:hash_update_proc_for_old) ) ) if inheritance_hash[:Resources]
+						(catalogs[:ColorSpace] ||= {}).update( inheritance_hash[:ColorSpace], &( self.class.method(:hash_update_proc_for_old) ) ) if inheritance_hash[:ColorSpace]
+
+
+						# avoide references on MediaBox and CropBox
 						catalogs[:MediaBox] = catalogs[:MediaBox][:referenced_object][:indirect_without_dictionary] if catalogs[:MediaBox].is_a?(Hash) && catalogs[:MediaBox][:referenced_object].is_a?(Hash) && catalogs[:MediaBox][:referenced_object][:indirect_without_dictionary]
 						catalogs[:CropBox] = catalogs[:CropBox][:referenced_object][:indirect_without_dictionary] if catalogs[:CropBox].is_a?(Hash) && catalogs[:CropBox][:referenced_object].is_a?(Hash) && catalogs[:CropBox][:referenced_object][:indirect_without_dictionary]
+
 						page_list << catalogs
 					when :Pages
-						page_list.push *(pages(catalogs[:Kids])) unless catalogs[:Kids].nil?
+						page_list.push *(pages(catalogs[:Kids], secure_injection, inheritance_hash.dup )) unless catalogs[:Kids].nil?
 					when :Catalog
-						page_list.push *(pages(catalogs[:Pages])) unless catalogs[:Pages].nil?
+						page_list.push *(pages(catalogs[:Pages], secure_injection, inheritance_hash.dup )) unless catalogs[:Pages].nil?
 					end
 				end
 			end
@@ -466,6 +482,7 @@ module CombinePDF
 			case 
 			when object.is_a?(Array)
 				object.each {|it| add_referenced(it)}
+				return true
 			when object.is_a?(Hash)
 				if object[:is_reference_only] && object[:referenced_object]
 					found_at = @objects.find_index object[:referenced_object]
@@ -474,20 +491,22 @@ module CombinePDF
 						# so, we need to make sure they are the same object for the pointers to effect id numbering
 						# and formatting operations.
 						object[:referenced_object] = @objects[found_at]
-					else @objects.include? object[:referenced_object]
+						# stop this path, there is no need to run over the Hash's keys and values
+						return true
+					else
+						# @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]
-						object[:referenced_object].each do |k, v|
-							add_referenced(v) unless k == :Parent
-						end						
 					end
 
-				else
-					object.each do |k, v|
-						add_referenced(v) unless k == :Parent 
-					end
 				end
+				object.each do |k, v|
+					add_referenced(v) unless k == :Parent 
+				end
+			else
+				return false
 			end
+			true
 		end
 		# @private
 		# run block of code on evey PDF object (PDF objects are class Hash)
@@ -497,6 +516,27 @@ module CombinePDF
 
 		protected
 
+		# @private
+		# this method reviews a Hash an updates it by merging Hash data,
+		# preffering the old over the new.
+		def self.hash_update_proc_for_old key, old_data, new_data
+			if old_data.is_a? Hash
+				old_data.merge( new_data, &self.method(:hash_update_proc_for_old) )
+			else
+				old_data
+			end
+		end
+		# @private
+		# this method reviews a Hash an updates it by merging Hash data,
+		# preffering the new over the old.
+		def self.hash_update_proc_for_new key, old_data, new_data
+			if old_data.is_a? Hash
+				old_data.merge( new_data, &self.method(:hash_update_proc_for_new) )
+			else
+				new_data
+			end
+		end
+
 		# @private
 		# this function returns all the Page objects - regardless of order and even if not cataloged
 		# could be used for finding "lost" pages... but actually rather useless. 
@@ -531,7 +571,7 @@ module CombinePDF
 			each_object do |obj|
 				if obj[:is_reference_only]
 					obj[:referenced_object] = objects_reference_hash[ [obj[:indirect_reference_id], obj[:indirect_generation_number] ]   ]
-					warn "couldn't connect a reference!!! could be a null or removed (empty) object, Silent error!!!" unless obj[:referenced_object]
+					warn "couldn't connect a reference!!! could be a null or removed (empty) object, Silent error!!!\n Object raising issue: #{obj.to_s}" unless obj[:referenced_object]
 				end
 			end
 

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = "0.1.10"
+  VERSION = "0.1.11"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.1.10
+  version: 0.1.11
 platform: ruby
 authors:
 - Boaz Segev