combine_pdf 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b732c13238534158bddb82ff89b5c0d14fdccdd2
-  data.tar.gz: 45ef6b52039c289ba1f71cce445c245d42c01bc1
+  metadata.gz: 7d910d296f84bd5493a258317eace2f9cabf7d4b
+  data.tar.gz: 67efe73d182be27f9ad597e48cff83c3147ab37d
 SHA512:
-  metadata.gz: 0ac937aea55ebc4f5be4cb9a2a7c9fadd45cc4e3dd01ff86749486541e1056787e89795fd514f031036e4156d4c7807101e82d0b88c64d00b813966211f97b15
-  data.tar.gz: 1b89918e8c4e79e005dcd1961f8f89fcb89565ed95b57e429a7fb82a1cbabe009665d3396a54db0c6e38ced2b9dc72c720157348404b4a791d374bfae5669353
+  metadata.gz: 8924f5bb53e5f8e00c224f360e343688b9902d1c2e7b59c319e07cc66ce763b08651619be64217d1af4a7e1029344091dcb106ffbc7ac41a3e496c5a0e0f7bbc
+  data.tar.gz: d2162982205d6c89a6ace341d8d2a3e123caff712d7c8dd3e9220ec4ce4dc67dfa2759e4429a07bc2c28d66600be00c5b6221d26c11bb34501d4fdb42092aba5

data/lib/combine_pdf.rb

@@ -5,6 +5,10 @@ require 'zlib'
 require 'securerandom'
 require 'strscan'
 
+#require the RC4 Gem
+require 'rc4'
+
+
 load "combine_pdf/combine_pdf_operations.rb"
 load "combine_pdf/combine_pdf_basic_writer.rb"
 load "combine_pdf/combine_pdf_decrypt.rb"
@@ -13,26 +17,6 @@ load "combine_pdf/combine_pdf_filter.rb"
 load "combine_pdf/combine_pdf_parser.rb"
 load "combine_pdf/combine_pdf_pdf.rb"
 
-# # will be removed one font support and font library is completed.
-# require "combine_pdf/font_metrics/courier-bold_metrics.rb"
-# require "combine_pdf/font_metrics/courier-boldoblique_metrics.rb"
-# require "combine_pdf/font_metrics/courier-oblique_metrics.rb"
-# require "combine_pdf/font_metrics/courier_metrics.rb"
-# require "combine_pdf/font_metrics/helvetica-bold_metrics.rb"
-# require "combine_pdf/font_metrics/helvetica-boldoblique_metrics.rb"
-# require "combine_pdf/font_metrics/helvetica-oblique_metrics.rb"
-# require "combine_pdf/font_metrics/helvetica_metrics.rb"
-# require "combine_pdf/font_metrics/symbol_metrics.rb"
-# require "combine_pdf/font_metrics/times-bold_metrics.rb"
-# require "combine_pdf/font_metrics/times-bolditalic_metrics.rb"
-# require "combine_pdf/font_metrics/times-italic_metrics.rb"
-# require "combine_pdf/font_metrics/times-roman_metrics.rb"
-# require "combine_pdf/font_metrics/zapfdingbats_metrics.rb"
-# require "combine_pdf/font_metrics/metrics_dictionary.rb"
-
-
-
-
 
 # This is a pure ruby library to combine/merge, stmap/overlay and number PDF files - as well as to create tables (ment for indexing combined files).
 #
@@ -314,9 +298,9 @@ end
 # numbers are Fixnum or Float
 # boolean are TrueClass or FalseClass
 
-## You can test performance with:
-## puts Benchmark.measure { pdf = CombinePDF.new(file_name); pdf.save "test.pdf" } # PDFEditor.new_pdf
-## demo: file_name = "/Users/2Be/Ruby/pdfs/encrypted.pdf"; pdf=0; puts Benchmark.measure { pdf = CombinePDF.new(file_name); pdf.save "test.pdf" }
+## test performance with:
+## puts Benchmark.measure { pdf = CombinePDF.new(file); pdf.save "test.pdf" } # PDFEditor.new_pdf
+## demo: file_name = "~/Ruby/pdfs/encrypted.pdf"; pdf=0; puts Benchmark.measure { pdf = CombinePDF.new(file_name); pdf.save "test.pdf" }
 ## at the moment... my code it terribly slow for larger files... :(
 ## The file saving is solved (I hope)... but file loading is an issue.
 ##  pdf.each_object {|obj| puts "Stream length: #{obj[:raw_stream_content].length} was registered as #{obj[:Length].is_a?(Hash)? obj[:Length][:referenced_object][:indirect_without_dictionary] : obj[:Length]}" if obj[:raw_stream_content] }
@@ -324,5 +308,30 @@ end
 ##  puts Benchmark.measure { 1000.times { (CombinePDF::PDFOperations.get_refernced_object pdf.objects, {indirect_reference_id: 100, indirect_generation_number:0}).object_id } }
 ##  puts Benchmark.measure { 1000.times { (pdf.objects.select {|o| o[:indirect_reference_id]== 100 && o[:indirect_generation_number] == 0})[0].object_id } }
 ## puts Benchmark.measure { {}.tap {|out| pdf.objects.each {|o| out[ [o[:indirect_reference_id], o[:indirect_generation_number] ] ] = o }} }
-
+##
+#### local test for CombinePDF
+## file = "/Users/2Be/Ruby/pdfs/encrypted.pdf"
+## puts Benchmark.measure { 1000.times { pdf = CombinePDF.new(file); pdf.save "test.pdf" } }
+### gives : 2.540000   0.140000   2.680000 (  2.696524)
+## puts Benchmark.measure { pdf = CombinePDF.new() ; 1000.times { pdf << CombinePDF.new(file) } ; pdf.save "test.pdf" }
+### gives: 11.770000   0.090000  11.860000 ( 11.879411) #why the difference? NOT the object reference rebuilding...
+### file size: 7Kb success
+###### gives: 7.440000   0.100000   7.540000 (  7.536460) (!!!) with draft file size 8kb
+##
+#### local test by pdftk
+## pdftk_path = '/Users/2Be/Ruby/pdfs/pdftk_lib/bin/pdftk'
+## file_array = []
+## 1000.times { file_array << file }
+## puts Benchmark.measure { system ( pdftk_path + " '" + file_array.join("' '") + "' input_pw '' output 'test.pdf'" ) }
+### gives: 0.000000   0.000000   3.250000 (  3.244724)
+### FAILS with no output, unwilling to decrypt.
+###### gives:  0.000000   0.000000   2.640000 (  2.661801) with draft file size 1.3MB (!!)
+#### local test by pyton
+## pyton_path = '/Users/2Be/Ruby/pdfs/pdftk_lib/join.py'
+## file_array = []
+## 1000.times { file_array << file }
+## puts Benchmark.measure { system ( pyton_path + " -o 'test.pdf' '#{file_array.join "' '"}' " ) }
+### gives 0.000000   0.000000   1.010000 (  1.147135)
+### file merge FAILS with 1,000 empty pages (undecrypted)
+####### gives: 0.000000   0.000000   1.770000 (  1.775513) with draft. file size 4.9MB (!!!)
 

data/lib/combine_pdf/combine_pdf_basic_writer.rb

@@ -133,7 +133,7 @@ module CombinePDF
 				y = options[:y]
 
 				# set graphic state for the box
-				box_stream << "q\nq\nq\n"
+				box_stream << "q\n"
 				box_graphic_state = { ca: options[:opacity], CA: options[:opacity], LW: options[:border_width], LC: 0, LJ: 0,  LD: 0 }
 				if options[:box_radius] != 0 # if the text box has rounded corners
 					box_graphic_state[:LC], box_graphic_state[:LJ] =  2, 1
@@ -191,7 +191,7 @@ module CombinePDF
 				end
 
 				# exit graphic state for the box
-				box_stream << "Q\nQ\nQ\n"
+				box_stream << "Q\n"
 			end
 			contents << box_stream
 
@@ -227,7 +227,7 @@ module CombinePDF
 				end
 
 				# set graphic state for text
-				text_stream << "q\nq\nq\n"
+				text_stream << "q\n"
 				text_graphic_state = graphic_state({ca: options[:opacity], CA: options[:opacity], LW: options[:stroke_width].to_f, LC: 2, LJ: 1,  LD: 0})
 				text_stream << "#{PDFOperations._object_to_pdf text_graphic_state} gs\n"
 				text_stream << "DeviceRGB CS\nDeviceRGB cs\n"
@@ -261,7 +261,7 @@ module CombinePDF
 					y -= encoded[3]/1000*font_size #update text starting point
 				end
 				# exit graphic state for text
-				text_stream << "Q\nQ\nQ\n"
+				text_stream << "Q\n"
 			end
 			contents << text_stream
 

data/lib/combine_pdf/combine_pdf_decrypt.rb

@@ -43,7 +43,6 @@ module CombinePDF
 			@key = set_general_key
 			case @encryption_dictionary[:V]
 			when 1,2
-				warn "trying to decrypt with RC4."
 				# raise_encrypted_error
 				_perform_decrypt_proc_ @objects, self.method(:decrypt_RC4)
 			else
@@ -109,7 +108,7 @@ module CombinePDF
 			# (0..2).each { |e| object_key << (encrypted_id >> e*8 & 0xFF ) }
 			# (0..1).each { |e| object_key << (encrypted_generation >> e*8 & 0xFF ) }
 			key_length = object_key.length < 16 ? object_key.length : 16
-			rc4 = RC4.new( Digest::MD5.digest(object_key)[(0...key_length)] )
+			rc4 = ::RC4.new( Digest::MD5.digest(object_key)[(0...key_length)] )
 			rc4.decrypt(encrypted)
 		end
 		def decrypt_AES(encrypted, encrypted_id, encrypted_generation, encrypted_filter)

data/lib/combine_pdf/combine_pdf_operations.rb

@@ -37,6 +37,7 @@ module CombinePDF
 
 			# 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]
@@ -45,6 +46,7 @@ module CombinePDF
 			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]

data/lib/combine_pdf/combine_pdf_parser.rb

@@ -65,7 +65,6 @@ module CombinePDF
 				@version = @scanner.matched.scan(/[\d\.]+/)[0].to_f
 			end
 
-			warn "Starting to parse PDF data."
 			@parsed = _parse_
 
 			if @root_object == {}
@@ -75,7 +74,6 @@ module CombinePDF
 				end
 			end
 			raise "root is unknown - cannot determine if file is Encrypted" if @root_object == {}
-			warn "Injecting actual values into root object: #{@root_object}."
 			PDFOperations.change_references_to_actual_values @parsed, @root_object
 
 			if @root_object[:Encrypt]
@@ -91,7 +89,6 @@ module CombinePDF
 					warn "PDF 1.5 Object streams found - they are not fully supported! attempting to extract objects."
 					
 					object_streams.each do |o|
-						warn "Attempting #{o.select {|k,v| k != :raw_stream_content}}"
 						## un-encode (using the correct filter) the object streams
 						PDFFilter.inflate_object o 
 						## extract objects from stream to top level arry @parsed
@@ -123,7 +120,6 @@ module CombinePDF
 			else
 				@info_object = {}
 			end
-			warn "setting parsed collection and returning collection."
 			@parsed
 		end
 
@@ -133,7 +129,6 @@ module CombinePDF
 		def _parse_
 			out = []
 			str = ''
-			# warn "Scaning for objects, starting at #{@scanner.pos}: #{@scanner.peek(10)}"
 			while @scanner.rest? do
 				case
 				##########################################
@@ -171,7 +166,6 @@ module CombinePDF
 				## parse an Object after finished
 				##########################################
 				when str = @scanner.scan(/endobj/)
-					# warn "Proccessing Object"
 					#what to do when this is an object?
 					if out.last.is_a? Hash
 						out << out.pop.merge({indirect_generation_number: out.pop, indirect_reference_id: out.pop})

data/lib/combine_pdf/combine_pdf_pdf.rb

@@ -115,12 +115,10 @@ module CombinePDF
 			end
 			# general globals
 			@string_output = :literal
-			@need_to_rebuild_resources = false
 			@set_start_id = 1
 			@info[:Producer] = "Ruby CombinePDF Library by Boaz Segev"
 			@info.delete :CreationDate
 			@info.delete :ModDate
-			warn "finished to initialize PDF object."
 		end
 
 		# Formats the data to PDF formats and returns a binary string that represents the PDF file content.
@@ -133,17 +131,11 @@ module CombinePDF
 			@version = 1.5 if @version.to_f == 0.0
 			#set creation date for merged file
 			@info[:CreationDate] = Time.now.strftime "D:%Y%m%d%H%M%S%:::z'00"
-			#rebuild resources if needed
-			if @need_to_rebuild_resources
-				rebuild_resources
-			end
 			#rebuild_catalog
 			catalog = rebuild_catalog_and_objects
 			# add ID and generation numbers to objects
 			renumber_object_ids
 
-			warn "Formatting PDF output"
-
 			out = []
 			xref = []
 			indirect_object_count = 1 #the first object is the null object
@@ -159,7 +151,6 @@ module CombinePDF
 				out << PDFOperations._object_to_pdf(o)
 				loc += out.last.length + 1
 			end
-			warn "Building XREF"
 			xref_location = 0
 			out.each { |line| xref_location += line.bytes.length + 1}
 			out << "xref\n\r0 #{(indirect_object_count).to_s}\n\r0000000000 65535 f \n\r"
@@ -275,7 +266,7 @@ module CombinePDF
 			fonts_array
 		end
 
-		# add the pages (or file) to the PDF (combine/merge) and return the new pages array.
+		# add the pages (or file) to the PDF (combine/merge) and RETURNS SELF, for nesting.
 		# for example:
 		#
 		#   pdf = CombinePDF.new "first_file.pdf"
@@ -290,17 +281,14 @@ module CombinePDF
 			## and how to handles imported pages?
 			if data.is_a?(PDF)
 		 		@version = [@version, data.version].max
-
-				@need_to_rebuild_resources = true
-
 		 		@objects.push(*data.objects)
 				# rebuild_catalog
-				return rebuild_catalog[:Pages][:referenced_object][:Kids]
+				return self
 			end
 			insert -1, data
 		end
 
-		# add the pages (or file) to the BEGINNING of the PDF (combine/merge) and return the new pages array.
+		# add the pages (or file) to the BEGINNING of the PDF (combine/merge) and RETURNS SELF for nesting operators.
 		# for example:
 		#
 		#   pdf = CombinePDF.new "second_file.pdf"
@@ -311,6 +299,7 @@ module CombinePDF
 		# data:: is PDF page (Hash), and Array of PDF pages or a parsed PDF object to be added.
 		def >> (data)
 			insert 0, data
+			self
 		end
 
 		# add PDF pages (or PDF files) into a specific location.
@@ -519,8 +508,6 @@ module CombinePDF
 		end
 		# @private
 		def serialize_objects_and_references(object = nil)
-			warn "connecting objects with their references (serialize_objects_and_references)."
-
 			# # Version 3.5 injects indirect objects if they arn't dictionaries.
 			# # benchmark 1000.times was 3.568246 sec for pdf = CombinePDF.new "/Users/2Be/Desktop/מוצגים/20121002\ הודעת\ הערעור.pdf" }
 			# # puts Benchmark.measure { 1000.times {pdf.serialize_objects_and_references} }
@@ -653,49 +640,6 @@ module CombinePDF
 			catalog
 		end
 
-		# @private
-		# disabled, don't use. simpley returns true.
-		def rebuild_resources
-
-			warn "Resources re-building disabled as it isn't worth the price in peformance as of yet."
-
-			return true
-
-			warn "Re-Building Resources"
-			@need_to_rebuild_resources = false
-			# what are resources?
-			# anything at the top level of the file exept catalogs, page lists (Pages) and pages...
-			not_resources = [:Catalog, :Pages, :Page]
-			# get old resources list
-			old_resources = @objects.select {|obj| obj.is_a?(Hash) && !not_resources.include?(obj[:Type])}
-			# collect all unique resources while ignoring double values and resetting references
-			# also ignore inner values (canot use PRIVATE_HASH_KEYS because of stream and other issues)
-			ignore_keys = [:indirect_reference_id, :indirect_generation_number, :is_reference_only, :referenced_object]
-			new_resources = []
-			all_references = references
-			old_resources.each do |old_r|
-				add = true
-				new_resources.each do |new_r|
-					# ## v.1.0 - slower
-					# if (old_r.reject {|k,v| ignore_keys.include?(k) }) == (new_r.reject {|k,v| ignore_keys.include?(k)})
-					# 	all_references.each {|ref| ref[:referenced_object] = new_r if ref[:referenced_object].object_id == old_r.object_id }  # fails, but doesn't assume all references are connected: compare_reference_values(old_r, ref) }
-					# 	add = false
-					# end
-					## v.1.1 - faster, doesn't build two hashes (but iterates one)
-					if ( [].tap {|out| old_r.each {|k,v| out << true unless ((!ignore_keys.include?(k)) && new_r[k] == v) } } .empty?)
-						all_references.each {|ref| ref[:referenced_object] = new_r if ref[:referenced_object].object_id == old_r.object_id }  # fails, but doesn't assume all references are connected: compare_reference_values(old_r, ref) }
-						add = false
-					end
-				end
-				new_resources << old_r if add
-			end
-			# remove old resources
-			@objects.reject! {|obj| old_resources.include?(obj)}
-			# insert new resources
-			@objects.push *new_resources
-			# rebuild stream lengths?
-		end
-
 		# @private
 		# the function rerturns true if the reference belongs to the object
 		def compare_reference_values(obj, ref)

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Boaz Segev
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-19 00:00:00.000000000 Z
+date: 2014-09-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -26,8 +26,8 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 0.1.5
 description: A nifty gem, in pure Ruby, to parse PDF files and combine (merge) them
-  with other PDF files, number the pages, watermark them or stamp them (all using
-  the PDF file format).
+  with other PDF files, number the pages, watermark them or stamp them, create tables
+  or basic text objects etc` (all using the PDF file format).
 email: bsegev@gmail.com
 executables: []
 extensions: []