combine_pdf 0.2.14 → 0.2.15

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cb521b662f0f6d91fa36351abcc5fdd03d5786f0
-  data.tar.gz: abf5724947da93d41dfdb428edfcff5dc7e5b215
+  metadata.gz: c3048c37a61edc6d2146a875b7858a67c45cdfee
+  data.tar.gz: 1c34bcc2d900f23c56bd67ea9e83ed7cc5d8ac85
 SHA512:
-  metadata.gz: 9cbb46dd904c73963ff711300a268173ecd935e7bdb2620fb0803b2b23608193c50ff4614774f55c6fba46ba4e8c2b5644296f4865b3c13eb8c8a145a7a92ead
-  data.tar.gz: 87ed4ff4bb904645be3662837ad11abd62b684a7a97eaa416f516b0034cb404a6a2019c07a6e652d4325e7c849e2e1895bab1013a5056e15cd29a3b692a2fe5e
+  metadata.gz: 6cccfd304beb820569452b222725da35df09711ff9c63c96a5b8a73f306f9756d83f86536bb0214789ede6fd380dd8f77615eadec36de7f909b268af0f030b65
+  data.tar.gz: cb6331c3bc3cb57a51034018ee07549fb67d69f05692121a92b48584b6d70c9a581678b804b318d8e87dd2a6f48c9d4eb06ad071dff61213244d941fede3e9d8

data/CHANGELOG.md

@@ -2,9 +2,15 @@
 
 ***
 
+Change log v.0.2.15
+
+**Fix**: Fix for issue #22 where specific PDF files with nested references could cause page stamping to fail, raising an exception. Credit to @tomascharad for finding the issue.
+
+***
+
 Change log v.0.2.14
 
-**Fix**: Fix for issue #39, where certain comments could have caused the object after the comments to be ignored, resulting in parsing errors.
+**Fix**: Fix for issue #39, where certain comments could have caused the object after the comments to be ignored, resulting in parsing errors. Credit to @lgn21st for identifying the issue.
 
 ***
 
@@ -50,7 +56,7 @@ Change log v.0.2.8
 
      Now there is no longer any need for the guesswork. The process is automated for you.
 
-     The moment CombinePDF recognizes a resource name conflice between two pages (such as both pages using one font name to reference two different fonts), CombinePDF will intrusively rename the incoming page's resources. 
+     The moment CombinePDF recognizes a resource name conflice between two pages (such as both pages using one font name to reference two different fonts), CombinePDF will intrusively rename the incoming page's resources.
 
      It is true that the intrusive resource renaming is somewhat risky and might require the inflation of some comperssed page data (resulting in bigger file sizes), but this is the only way to attempt and prevent PDF data curruption.
 
@@ -170,7 +176,7 @@ Change log v.0.1.19
 
 Change log v.0.1.18
 
-**fix**: Thank to Stefan, who reported issue #15 , we discovered that in some cases PDF files presented the wrong PDF standard version, causing an error while attempting to parse their data. The issue has been fixed by allowing the parser to search for PDF Object Streams even when the PDF file claims a PDF version below 1.5. 
+**fix**: Thank to Stefan, who reported issue #15 , we discovered that in some cases PDF files presented the wrong PDF standard version, causing an error while attempting to parse their data. The issue has been fixed by allowing the parser to search for PDF Object Streams even when the PDF file claims a PDF version below 1.5.
 
 ***
 
@@ -259,4 +265,4 @@ Change log v.0.1.6
 
 **known issues**: encrypted PDF files can sometimes silently fail (producing empty pages) - this is because on an attempted decrypt. more work should be done to support encrypted PDF files. please feel fee to help.
 
-I use this version on production, where I have control over the PDF files I use. It is beter then system calls to pdftk (which can cause all threads in ruby to hold, effectively causing my web app to hang).
+I use this version on production, where I have control over the PDF files I use. It is beter then system calls to pdftk (which can cause all threads in ruby to hold, effectively causing my web app to hang).

data/lib/combine_pdf/page_methods.rb

@@ -52,7 +52,7 @@ module CombinePDF
 			inject_page obj, false
 		end
 		def inject_page obj, top = true
-			
+
 			raise TypeError, "couldn't inject data, expecting a PDF page (Hash type)" unless obj.is_a?(Page_Methods)
 
 			obj = obj.copy( should_secure?(obj) ) #obj.copy(secure_injection)
@@ -115,7 +115,7 @@ module CombinePDF
 
 		# get page size
 		def page_size
-			cropbox || mediabox			
+			cropbox || mediabox
 		end
 
 		# accessor (getter) for the :Resources element of the page
@@ -223,7 +223,7 @@ module CombinePDF
 				radius = options[:box_radius]
 				half_radius = (radius.to_f / 2).round 4
 				## set starting point
-				box_stream << "#{options[:x] + radius} #{options[:y]} m\n" 
+				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
 				if options[:box_radius] != 0 # make first corner, if not straight.
@@ -326,7 +326,7 @@ module CombinePDF
 				# format text object(s)
 					# text_stream << "#{options[:font_color].join(' ')} rg\n" # sets the color state
 				encode_text(text, fonts).each do |encoded|
-					text_stream << "BT\n" # the Begine Text marker			
+					text_stream << "BT\n" # the Begine Text marker
 					text_stream << format_name_to_pdf(set_font encoded[0]) # Set font name
 					text_stream << " #{font_size.round 3} Tf\n" # set font size and add font operator
 					text_stream << "#{x.round 4} #{y.round 4} Td\n" # set location for text object
@@ -571,7 +571,7 @@ module CombinePDF
 					box_color = (options[:alternate_color] && ( (row_number.odd? && options[:headers]) || row_number.even? ) ) ? options[:alternate_color] : options[:main_color]
 					textbox text, {x: x, y: (top - (height*row_number)), width: column_widths[i], height: height, box_color: box_color, text_align: options[:row_align]}.merge(options)
 					x += column_widths[i]
-				end			
+				end
 				row_number += 1
 			end
 			self
@@ -615,7 +615,12 @@ module CombinePDF
 		#initializes the content stream in case it was not initialized before
 		def init_contents
 			self[:Contents] = self[:Contents][:referenced_object][:indirect_without_dictionary] if self[:Contents].is_a?(Hash) && self[:Contents][:referenced_object] && self[:Contents][:referenced_object].is_a?(Hash) && self[:Contents][:referenced_object][:indirect_without_dictionary]
+			self[:Contents] = [self[:Contents]] unless self[:Contents].is_a?(Array)
 			self[:Contents].delete({ is_reference_only: true , referenced_object: {indirect_reference_id: 0, raw_stream_content: ''} })
+			# un-nest any referenced arrays
+			self[:Contents].map! {|s| actual_value(s).is_a?(Array) ? actual_value(s) : s}
+			self[:Contents].flatten!
+			self[:Contents].compact!
 			# wrap content streams
 			insert_content 'q', 0
 			insert_content 'Q'
@@ -642,8 +647,11 @@ module CombinePDF
 
 		def prep_content_array
 			return self if self[:Contents].is_a?(Array)
-			self[:Contents] = self[:Contents][:referenced_object] if self[:Contents].is_a?(Hash) && self[:Contents][:referenced_object] && self[:Contents][:referenced_object].is_a?(Array)
-			self[:Contents] = [ self[:Contents] ].compact
+			init_contents
+			# self[:Contents] = self[:Contents][:referenced_object] if self[:Contents].is_a?(Hash) && self[:Contents][:referenced_object] && self[:Contents][:referenced_object].is_a?(Array)
+			# self[:Contents] = self[:Contents][:indirect_without_dictionary] if self[:Contents].is_a?(Hash) && self[:Contents][:indirect_without_dictionary] && self[:Contents][:indirect_without_dictionary].is_a?(Array)
+			# self[:Contents] = [self[:Contents]] unless self[:Contents].is_a?(Array)
+			# self[:Contents].compact!
 			self
 		end
 
@@ -729,7 +737,7 @@ module CombinePDF
 						#add to array
 						if out.last.nil? || out.last[0] != fonts[i]
 							out.last[1] << ">" unless out.last.nil?
-							out << [fonts[i], "<" , 0, 0] 
+							out << [fonts[i], "<" , 0, 0]
 						end
 						out.last[1] << ( fonts_array[i].cmap.nil? ? ( c.unpack("H*")[0] ) : (fonts_array[i].cmap[c]) )
 						if fonts_array[i].metrics[c]
@@ -791,7 +799,7 @@ module CombinePDF
 			# travel every dictionary to pick up names (keys), change them and add them to the dictionary
 			res = self.resources
 			res.each do |k,v|
-				if v.is_a?(Hash)
+				if actual_value(v).is_a?(Hash)
 					# if k == :XObject
 					# 	self[:Resources][k] = v.dup
 					# 	next
@@ -799,7 +807,7 @@ module CombinePDF
 					new_dictionary = {}
 					new_name = "Combine" + SecureRandom.hex(7) + "PDF"
 					i = 1
-					actual_object(v).each do |old_key, value|
+					actual_value(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
@@ -814,10 +822,10 @@ module CombinePDF
 			# we will need to make sure we have access to the stream injected
 			# we will user PDFFilter.inflate_object
 			self[:Contents].each do |c|
-				stream = actual_object(c)
+				stream = actual_value(c)
 				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! 
+					stream[:raw_stream_content].gsub! object_to_pdf(old_key), object_to_pdf(new_key)  ##### PRAY(!) that the parsed datawill be correctly reproduced!
 				end
 				# # # the following code isn't needed now that we wrap both the existing and incoming content streams.
 				# # patch back to PDF defaults, for OCRed PDF files.
@@ -831,15 +839,15 @@ module CombinePDF
 			# travel every dictionary to pick up names (keys), change them and add them to the dictionary
 			res = self.resources
 			foreign_res = page.resources
-			res.each {|k,v| v.keys.each {|name| return true if foreign_res[k] && (foreign_res[k][:referenced_object] || foreign_res[k])[name] && (foreign_res[k][:referenced_object] || foreign_res[k])[name] != (v[:referenced_object] || v)[name]} if v.is_a?(Hash) }
+			res.each do |k,v|
+				if actual_value(v).is_a?(Hash) && actual_value(foreign_res[k]).is_a?(Hash)
+					v.keys.each do |name| return true if actual_value(foreign_res[k]) && actual_value(foreign_res[k])[name] && actual_value(foreign_res[k])[name] != actual_value(v[k])[name]
+					end # else # Do nothing, this is taken care of elseware
+				end
+			end
 			false
 		end
 
 	end
-	
-end
-
-
-
-
 
+end

data/lib/combine_pdf/renderer.rb

@@ -53,7 +53,7 @@ module CombinePDF
 				("(" + ([].tap {|out| object.bytes.each {|byte| STRING_REPLACEMENT_HASH[ byte.chr ] ? (STRING_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)). 
+				# 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
@@ -83,7 +83,7 @@ module CombinePDF
 			# 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)
@@ -135,6 +135,12 @@ module CombinePDF
 			obj.is_a?(Hash) ? (obj[:referenced_object] || obj) : obj
 		end
 
+		def actual_value obj
+			return obj unless obj.is_a?(Hash)
+			obj = obj[:referenced_object] || obj
+			obj[:indirect_without_dictionary] || obj
+		end
+
 		# Ruby normally assigns pointes.
 		# noramlly:
 		#   a = [1,2,3] # => [1,2,3]

data/lib/combine_pdf/version.rb

@@ -1,4 +1,3 @@
 module CombinePDF
-  VERSION = "0.2.14"
+  VERSION = "0.2.15"
 end
-

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.14
+  version: 0.2.15
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-12-23 00:00:00.000000000 Z
+date: 2016-02-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -101,7 +101,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5.1
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.