combine_pdf 0.2.4 → 0.2.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bfa5b9792e629049a4ebf6a379b1e834f6f76eb7
-  data.tar.gz: 0ea35cdbccc1fa1480370cccfa8e11351f6973d5
+  metadata.gz: 61c4d75ddd1975e567b4b96359f852a4eb13fdf7
+  data.tar.gz: 304f0b46cf41a96eddc46c728a20caf9ff77912c
 SHA512:
-  metadata.gz: a5baf7554a0757a4666e22464ef0d6f515153a8ea7c6b1058edb92090f4f683808996b259539b5e2553ced8e74c1c6a78ef4bf947442ee131bb5be31c43d34f0
-  data.tar.gz: 171cf6606fa1a4d91b9652f4d166bfa198ed6acd049631f0f50137362cbcf10a7c5d15b6191434a9bb9bc52b7eab9a00cafe07fb2edeb656bfba2f06eb71eb92
+  metadata.gz: 256814f346635778e23265a652ce800e3c951e21e647943f752b2d231ddc68c90cc6ffeb7cfacaadd34b42faff97233637752cbd68329ff064728d673c989fdf
+  data.tar.gz: 29c90166699f5baf305398a1382e2f0db4ceb00e35391955cb5f6a30012a445fd48f3ce5e2d5154851ad1b9ae8d580f286de71ffe8b881e580b051faa1e1ec13

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ***
 
+Change log v.0.2.5
+
+**feature**: circumvents an issue with 'wkhtmltopdf', where sometimes the `endobj` keyword would be missing, causing malformed PDF data. The parser will now attempt to auto-fix any `endobj` missing keywords.
+
+**semi-fix**: make sure decryption is attempetd using actual values (vs. references). The code was updated for a similar result as should have been achived before.
+
+***
+
 Change log v.0.2.4
 
 **fixed**: Fixed the default page sizes which weren't as described in the documentation and now default to US Letter. The documentation was also fixed. No major version bump is declered since the defaults were faulty and weren't as described (fixed a bug, not changed the API).

data/README.md

@@ -1,4 +1,6 @@
 # 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)
+
 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
@@ -72,7 +74,7 @@ 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.
 
-## Loading PDF data
+## Loading and Rendering PDF data
 
 Loading PDF data can be done from file system or directly from the memory.
 
@@ -82,19 +84,35 @@ Loading data from a file is easy:
 pdf = CombinePDF.load("file.pdf")
 ```
 
-you can also parse PDF files from memory:
+You can also parse PDF files from memory. Loading from the memory is especially effective for importing PDF data recieved through the internet or from a different authoring library such as Prawn:
 
 ```ruby
-pdf_data = IO.read 'file.pdf' # for this demo, load a file to memory
+pdf_data = prawn_pdf_document.render # Import PDF data from Prawn
 pdf = CombinePDF.parse(pdf_data)
 ```
 
-Loading from the memory is especially effective for importing PDF data recieved through the internet or from a different authoring library such as Prawn.
+Similarly, you can output a string of PDF data using `.to_pdf`. For example, to let a user download the PDF from a [Rails](http://rubyonrails.org) or [Plezi](https://github.com/boazsegev/plezi) app:
+
+```ruby
+# in a controller action
+send_data combined_file.to_pdf, filename: "combined.pdf", type: "application/pdf"
+```
+
+Or in [Sinatra](http://www.sinatrarb.com):
+
+```ruby
+# in your path's block
+status 200
+body combined_file.to_pdf
+headers 'content-type' => "application/pdf"
+```
+
+If you prefer to save the PDF data to a file, you can always use the `save` method as we did in our earlier examples.
 
 Demo
 ====
 
-You can see a Demo for a ["Bates stumping web-app"](http://combine-pdf-demo.herokuapp.com/bates) and read through it's [code](http://combine-pdf-demo.herokuapp.com/code) . Good luck :)
+You can see a Demo for a ["Bates stumping web-app"](http://combine-pdf-demo.herokuapp.com/bates) and read through it's [code](https://github.com/boazsegev/combine_pdf_demo/blob/c9914588e4116dcfdaa37f85727f442b064e2b04/pdf_controller.rb) . Good luck :)
 
 Decryption & Filters
 ====================

data/lib/combine_pdf/decrypt.rb

@@ -17,6 +17,7 @@ module CombinePDF
 
 	# This is an internal class. you don't need it.
 	class PDFDecrypt
+		include CombinePDF::Renderer
 
 		# @!visibility private
 		
@@ -25,9 +26,9 @@ module CombinePDF
 		# root_dictionary:: the root PDF dictionary, containing the Encrypt dictionary.
 		def initialize objects=[], root_dictionary = {}
 			@objects = objects
-			@encryption_dictionary = root_dictionary[:Encrypt]
+			@encryption_dictionary = actual_object(root_dictionary[:Encrypt])
 			raise "Cannot decrypt an encrypted file without an encryption dictionary!" unless @encryption_dictionary
-			@root_dictionary = root_dictionary
+			@root_dictionary = actual_object(root_dictionary)
 			@padding_key = [ 0x28, 0xBF, 0x4E, 0x5E, 0x4E, 0x75, 0x8A, 0x41,
 							0x64, 0x00, 0x4E, 0x56, 0xFF, 0xFA, 0x01, 0x08,
 							0x2E, 0x2E, 0x00, 0xB6, 0xD0, 0x68, 0x3E, 0x80,
@@ -41,7 +42,7 @@ module CombinePDF
 		def decrypt
 			raise_encrypted_error @encryption_dictionary unless @encryption_dictionary[:Filter] == :Standard
 			@key = set_general_key
-			case @encryption_dictionary[:V]
+			case actual_object(@encryption_dictionary[:V])
 			when 1,2
 				# raise_encrypted_error
 				_perform_decrypt_proc_ @objects, self.method(:decrypt_RC4)
@@ -49,10 +50,10 @@ module CombinePDF
 				# raise unsupported error for now
 				raise_encrypted_error
 				# make sure CF is a Hash (as required by the PDF standard for this type of encryption).
-				raise_encrypted_error unless @encryption_dictionary[:CF].is_a?(Hash)
+				raise_encrypted_error unless actual_object(@encryption_dictionary[:CF]).is_a?(Hash)
 
 				# do nothing if there is no data to decrypt except embeded files...?
-				return true unless (@encryption_dictionary[:CF].values.select { |v| !v[:AuthEvent] || v[:AuthEvent] == :DocOpen } ).empty?
+				return true unless (actual_object(@encryption_dictionary[:CF]).values.select { |v| !v[:AuthEvent] || v[:AuthEvent] == :DocOpen } ).empty?
 
 				# attempt to decrypt all strings?
 				# attempt to decrypy all streams
@@ -63,6 +64,8 @@ module CombinePDF
 			end
 			#rebuild stream lengths?
 			@objects
+		rescue => e
+			raise_encrypted_error
 		end
 
 		protected
@@ -71,17 +74,17 @@ module CombinePDF
 			# 1) make sure the initial key is 32 byte long (if no password, uses padding).
 			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
+			key << actual_object(@encryption_dictionary[:O]).to_s
 			# 3) Convert the integer value of the P entry to a 32-bit unsigned binary number
 			# and pass these bytes low-order byte first
-			key << [@encryption_dictionary[:P]].pack('i')
+			key << [actual_object(@encryption_dictionary[:P])].pack('i')
 			# 4) Pass the first element of the file’s file identifier array
 			# (the value of the ID entry in the document’s trailer dictionary
-			key << @root_dictionary[:ID][0]
+			key << actual_object(@root_dictionary[:ID])[0]
 			# # 4(a) (Security handlers of revision 4 or greater)
 			# # if document metadata is not being encrypted, add 4 bytes with the value 0xFFFFFFFF.
-			if @encryption_dictionary[:R] >= 4
-				unless @encryption_dictionary[:EncryptMetadata] == false #default is true and nil != false
+			if actual_object(@encryption_dictionary[:R]) >= 4
+				unless actual_object(@encryption_dictionary)[:EncryptMetadata] == false #default is true and nil != false
 					key << "\x00\x00\x00\x00"
 				else
 					key << "\xFF\xFF\xFF\xFF"
@@ -94,17 +97,17 @@ module CombinePDF
 			# pass the first n bytes of the output as input into a new MD5 hash,
 			# where n is the number of bytes of the encryption key as defined by the value of
 			# the encryption dictionary’s Length entry.
-			if @encryption_dictionary[:R] >= 3
+			if actual_object(@encryption_dictionary[:R]) >= 3
 				50.times do|i|
-					key = Digest::MD5.digest(key[0...@encryption_dictionary[:Length]])
+					key = Digest::MD5.digest(key[0...actual_object(@encryption_dictionary[:Length])])
 				end
 			end
 			# 6) Set the encryption key to the first n bytes of the output from the final MD5 hash,
 			# where n shall always be 5 for security handlers of revision 2 but,
 			# for security handlers of revision 3 or greater,
 			# shall depend on the value of the encryption dictionary’s Length entry.
-			if @encryption_dictionary[:R] >= 3
-				@key = key[0..(@encryption_dictionary[:Length]/8)]
+			if actual_object(@encryption_dictionary[:R]) >= 3
+				@key = key[0..(actual_object(@encryption_dictionary[:Length])/8)]
 			else
 				@key = key[0..4]
 			end
@@ -150,14 +153,11 @@ module CombinePDF
 			when object.is_a?(Array)
 				object.map! { |item| _perform_decrypt_proc_(item, decrypt_proc, encrypted_id, encrypted_generation, encrypted_filter) }
 			when object.is_a?(Hash)
-				encrypted_id ||= object[:indirect_reference_id]
-				encrypted_generation ||=  object[:indirect_generation_number]
-				encrypted_filter ||= object[:Filter]
+				encrypted_id ||= actual_object(object[:indirect_reference_id])
+				encrypted_generation ||=  actual_object(object[:indirect_generation_number])
+				encrypted_filter ||= actual_object(object[:Filter])
 				if object[:raw_stream_content]
-					stream_length = object[:Length]
-					if stream_length.is_a?(Hash) && stream_length[:is_reference_only]
-						stream_length = get_refernced_object(stream_length)[:indirect_without_dictionary]
-					end
+					stream_length = actual_object(object[:Length])
 					actual_length = object[:raw_stream_content].length
 					warn "Stream registeded length was #{object[:Length].to_s} and the actual length was #{actual_length}." if actual_length < stream_length
 					length = [ stream_length, actual_length].min

data/lib/combine_pdf/parser.rb

@@ -331,10 +331,26 @@ module CombinePDF
 						@scanner.skip_until(/\%\%EOF/)
 					end
 					
-				when @scanner.scan(/[\s]+/) , @scanner.scan(/obj[\s]*/)
-					# do nothing
-					# warn "White Space, do nothing"
+				when @scanner.scan(/[\s]+/)
+					# Generally, do nothing
 					nil
+				when @scanner.scan(/obj[\s]*/)
+					# Fix wkhtmltopdf PDF authoring issue - missing 'endobj' keywords
+					unless out[-4].nil? || out[-4].is_a?(Hash)
+						keep = []
+						keep << out.pop
+						keep << out.pop
+
+						if out.last.is_a? Hash
+							out << out.pop.merge({indirect_generation_number: out.pop, indirect_reference_id: out.pop})
+						else
+							out << {indirect_without_dictionary: out.pop, indirect_generation_number: out.pop, indirect_reference_id: out.pop}
+						end
+						warn "'endobj' keyword was missing for Object ID: #{out.last[:indirect_reference_id]}, trying to auto-fix issue, but might fail."
+
+						out << keep.pop
+						out << keep.pop
+					end
 				else
 					# always advance 
 					# warn "Advnacing for unknown reason..."
@@ -454,6 +470,11 @@ 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
 
 		# @private

data/lib/combine_pdf/version.rb

@@ -1,4 +1,4 @@
 module CombinePDF
-  VERSION = "0.2.4"
+  VERSION = "0.2.5"
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.4
+  version: 0.2.5
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-08-09 00:00:00.000000000 Z
+date: 2015-09-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -102,9 +102,10 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.7
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.
 test_files:
 - test/console
+has_rdoc: