combine_pdf 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 169d63fc09f86f09a633e199582c65212fbcd158
-  data.tar.gz: 6f5d94234603827a33100c77e4b66ac41492c60c
+  metadata.gz: 91a403f449ba29c772a9e6d12e114e0271129ecb
+  data.tar.gz: 9b94530e869fe1a5936706305c2407eeeb9f35a7
 SHA512:
-  metadata.gz: ffb49820460e29f7d6d857fe6f66af7a9b0f97edae28a2ab1caa814eb5e84d521f91b76e091b2b33fe36f716684253a30fc51cc777e8696c5ee09ed21ebae0ae
-  data.tar.gz: fb6e175436280fd64499684151f29c7cf9254ca21be6a0052e42f80c6d29ede70ed982afbf7aef07fd31cbcf88c460f9eb1a84bea3f363a74ac78d3bb5bc44e2
+  metadata.gz: ce4a31ce78d6ff246f51ced6567b73fb5b5905cfbcf43fa2d980996d16e66570e1777a350cec53527d5772eae07be8dfc768f7b68811505428e4788cb55e195f
+  data.tar.gz: 9fc48d3e72643e48b179ceb01d755fc928585b5d911f53bc83fa96f41c87353c46a517966c9c094ff0e116dcb95010d7aced07cb3aafe1a12ea8d0c1b21da2bd

data/lib/combine_pdf.rb

@@ -37,9 +37,12 @@ require "combine_pdf/font_metrics/metrics_dictionary.rb"
 # == Combine / Merge
 # To combine PDF files (or data):
 #   pdf = CombinePDF.new
-#   pdf << CombinePDF.new "file1.pdf" # one way to combine, very fast.
+#   pdf << CombinePDF.new("file1.pdf") # one way to combine, very fast.
 #   CombinePDF.new("file2.pdf").pages.each {|page| pdf << page} # different way to combine, slower.
 #   pdf.save "combined.pdf"
+#
+# Or, you can do it all in one line:
+#   ( CombinePDF.new("file1.pdf") << CombinePDF.new("file2.pdf") << CombinePDF.new("file3.pdf") ).save "combined.pdf"
 # == Stamp / Watermark
 # <b>has issues with specific PDF files - please see the issues</b>: https://github.com/boazsegev/combine_pdf/issues/2 
 # To combine PDF files (or data), first create the stamp from a PDF file:
@@ -50,6 +53,10 @@ require "combine_pdf/font_metrics/metrics_dictionary.rb"
 #   pdf.pages.each {|page| page << stamp_page}
 # Notice the << operator is on a page and not a PDF object. The << operator acts differently on PDF objects and on Pages.
 #
+# The << operator defaults to secure injection by renaming references to avoid conflics. For overlaying pages using compressed data that might not be editable (due to limited filter support), you can use:
+#   pdf.pages(nil, false).each {|page| page << stamp_page}
+#
+#
 # Notice that page objects are Hash class objects and the << operator was added to the Page instances without altering the class.
 #
 # == Decryption & Filters

data/lib/combine_pdf/combine_pdf_basic_writer.rb

@@ -15,7 +15,7 @@ module CombinePDF
 	# 
 	# <b>This doesn't work yet!</b>
 	#
-	# and alsom, for even when it will work, UNICODE SUPPORT IS MISSING!
+	# and also, even when it will work, UNICODE SUPPORT IS MISSING!
 	#
 	# in the future I wish to make a simple PDF page writer, that has only one functions - the text box.
 	# Once the simple writer is ready (creates a text box in a self contained Page element),
@@ -26,7 +26,9 @@ module CombinePDF
 	#
 	# Writing on this Page is done using the text_box function.
 	#
-	# the rest of the functions are for internal use.
+	# Setting the page dimentions can be either at the new or using the media_box method.
+	#
+	# the rest of the methods are for internal use.
 	#
 	# Once the Page is completed (the last text box was added),
 	# we can insert the page to a CombinePDF object.
@@ -53,16 +55,6 @@ module CombinePDF
 			self[:Contents] = { is_reference_only: true , referenced_object: {indirect_reference_id: 0, raw_stream_content: ""} }
 			self[:MediaBox] = media_box
 		end
-
-		# accessor (getter) for the :Resources element of the page
-		def resources
-			self[:Resources]
-		end
-		# accessor (getter) for the stream in the :Contents element of the page
-		# after getting the string object, you can operate on it but not replace it (use << or other String methods).
-		def contents
-			self[:Contents][:referenced_object][:raw_stream_content]
-		end
 		# accessor (getter) for the :MediaBox element of the page
 		def media_box
 			self[:MediaBox]
@@ -72,73 +64,6 @@ module CombinePDF
 		def media_box=(dimentions = [0.0, 0.0, 612.0, 792.0])
 			self[:MediaBox] = dimentions
 		end
-		# creates a font object and adds the font to the resources dictionary
-		# returns the name of the font for the content stream.
-		# font_name:: a Symbol of one of the 14 Type 1 fonts, known as the standard 14 fonts:
-		# - :"Times-Roman"
-		# - :"Times-Bold"
-		# - :"Times-Italic"
-		# - :"Times-BoldItalic"
-		# - :Helvetica
-		# - :"Helvetica-Bold"
-		# - :"Helvetica-BoldOblique"
-		# - :"Helvetica- Oblique"
-		# - :Courier
-		# - :"Courier-Bold"
-		# - :"Courier-Oblique"
-		# - :"Courier-BoldOblique"
-		# - :Symbol
-		# - :ZapfDingbats
-		def font(font_name = :Helvetica)
-			# refuse any other fonts that arn't basic standard fonts
-			allow_fonts = [ :"Times-Roman",
-					:"Times-Bold",
-					:"Times-Italic",
-					:"Times-BoldItalic",
-					:Helvetica,
-					:"Helvetica-Bold",
-					:"Helvetica-BoldOblique",
-					:"Helvetica-Oblique",
-					:Courier,
-					:"Courier-Bold",
-					:"Courier-Oblique",
-					:"Courier-BoldOblique",
-					:Symbol,
-					:ZapfDingbats ]
-			raise "add_font(font_name) accepts only one of the 14 standards fonts - wrong font_name!" unless allow_fonts.include? font_name
-			# if the font exists, return it's name
-			resources[:Font] ||= {}
-			resources[:Font].each do |k,v|
-				if v.is_a?(Hash) && v[:Type] == :Font && v[:BaseFont] == font_name
-					return k
-				end
-			end
-			# create font object
-			font_object = { Type: :Font, Subtype: :Type1, BaseFont: font_name}
-			# set a secure name for the font
-			name = (SecureRandom.urlsafe_base64(9)).to_sym
-			# add object to reasource
-			resources[:Font][name] = font_object
-			#return name
-			name
-		end
-		def graphic_state(graphic_state_dictionary = {})
-			# if the graphic state exists, return it's name
-			resources[:ExtGState] ||= {}
-			resources[:ExtGState].each do |k,v|
-				if v.is_a?(Hash) && v == graphic_state_dictionary
-					return k
-				end
-			end
-			# set graphic state type
-			graphic_state_dictionary[:Type] = :ExtGState
-			# set a secure name for the graphic state
-			name = (SecureRandom.urlsafe_base64(9)).to_sym
-			# add object to reasource
-			resources[:ExtGState][name] = graphic_state_dictionary
-			#return name
-			name
-		end
 
 		# <b>INCOMPLETE</b>
 		#
@@ -226,6 +151,84 @@ module CombinePDF
 			self
 		end
 
+		protected
+
+		# accessor (getter) for the :Resources element of the page
+		def resources
+			self[:Resources]
+		end
+		# accessor (getter) for the stream in the :Contents element of the page
+		# after getting the string object, you can operate on it but not replace it (use << or other String methods).
+		def contents
+			self[:Contents][:referenced_object][:raw_stream_content]
+		end
+		# creates a font object and adds the font to the resources dictionary
+		# returns the name of the font for the content stream.
+		# font_name:: a Symbol of one of the 14 Type 1 fonts, known as the standard 14 fonts:
+		# - :"Times-Roman"
+		# - :"Times-Bold"
+		# - :"Times-Italic"
+		# - :"Times-BoldItalic"
+		# - :Helvetica
+		# - :"Helvetica-Bold"
+		# - :"Helvetica-BoldOblique"
+		# - :"Helvetica- Oblique"
+		# - :Courier
+		# - :"Courier-Bold"
+		# - :"Courier-Oblique"
+		# - :"Courier-BoldOblique"
+		# - :Symbol
+		# - :ZapfDingbats
+		def font(font_name = :Helvetica)
+			# refuse any other fonts that arn't basic standard fonts
+			allow_fonts = [ :"Times-Roman",
+					:"Times-Bold",
+					:"Times-Italic",
+					:"Times-BoldItalic",
+					:Helvetica,
+					:"Helvetica-Bold",
+					:"Helvetica-BoldOblique",
+					:"Helvetica-Oblique",
+					:Courier,
+					:"Courier-Bold",
+					:"Courier-Oblique",
+					:"Courier-BoldOblique",
+					:Symbol,
+					:ZapfDingbats ]
+			raise "add_font(font_name) accepts only one of the 14 standards fonts - wrong font_name!" unless allow_fonts.include? font_name
+			# if the font exists, return it's name
+			resources[:Font] ||= {}
+			resources[:Font].each do |k,v|
+				if v.is_a?(Hash) && v[:Type] == :Font && v[:BaseFont] == font_name
+					return k
+				end
+			end
+			# create font object
+			font_object = { Type: :Font, Subtype: :Type1, BaseFont: font_name}
+			# set a secure name for the font
+			name = (SecureRandom.urlsafe_base64(9)).to_sym
+			# add object to reasource
+			resources[:Font][name] = font_object
+			#return name
+			name
+		end
+		def graphic_state(graphic_state_dictionary = {})
+			# if the graphic state exists, return it's name
+			resources[:ExtGState] ||= {}
+			resources[:ExtGState].each do |k,v|
+				if v.is_a?(Hash) && v == graphic_state_dictionary
+					return k
+				end
+			end
+			# set graphic state type
+			graphic_state_dictionary[:Type] = :ExtGState
+			# set a secure name for the graphic state
+			name = (SecureRandom.urlsafe_base64(9)).to_sym
+			# add object to reasource
+			resources[:ExtGState][name] = graphic_state_dictionary
+			#return name
+			name
+		end
 	end
 	
 end

data/lib/combine_pdf/combine_pdf_parser.rb

@@ -10,29 +10,26 @@
 
 module CombinePDF
 
-	########################################################
-	## This is the Parser class.
-	## It takes PDF data and parses it, returning an array
-	## of data.
-	## That array can be used to initialize a PDF object.
-	## The Parser class doesn't involve itself with the
-	## file version.
-	########################################################
 
+	#######################################################
 	#@private
 	#:nodoc: all
+	# This is the Parser class.
+	#
+	# It takes PDF data and parses it.
+	#
+	# The information is then used to initialize a PDF object.
+	#######################################################
 	class PDFParser
-		# LITERAL_STRING_REPLACEMENT_HASH = {
-		# 	110 => 10, # "\\n".bytes = [92, 110]  "\n".ord = 10
-		# 	114 => 13, #r
-		# 	116 => 9, #t
-		# 	98 => 8, #b 
-		# 	102 => 255, #f
-		# 	40 => 40, #(
-		# 	41 => 41, #)
-		# 	92 => 92 #\
-		# 	}
-		attr_reader :parsed, :version, :info_object, :root_object
+
+		# the array containing all the parsed data (PDF Objects)
+		attr_reader :parsed
+		# a Float representing the PDF version of the data parsed (if exists).
+		attr_reader :version
+		# 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
 		def initialize (string)
 			raise TypeError, "couldn't parse and data, expecting type String" unless string.is_a? String
 			@string_to_parse = string.force_encoding(Encoding::ASCII_8BIT)
@@ -46,6 +43,7 @@ module CombinePDF
 			@scanner = nil
 		end
 
+		# parse the data in the parser (set in the initialize / new method)
 		def parse
 			return @parsed unless @parsed.empty?
 			@scanner = StringScanner.new @string_to_parse

data/lib/combine_pdf/combine_pdf_pdf.rb

@@ -38,13 +38,13 @@ module CombinePDF
 		# use, for example:
 		#   pdf.info[:Title] = "title"
 		attr_reader :info
-		# sets the string output format (PDF files store strings in to type of formats).
+		# gets/sets the string output format (PDF files store strings in to type of formats).
 		#
 		# Accepts:
 		# - :literal
 		# - :hex
 		attr_accessor :string_output
-		# A Float attrinute, setting and returning the PDF version of the file (1.1-1.7).
+		# set/get the PDF version of the file (1.1-1.7) - shuold be type Float.
 		attr_accessor :version
 		def initialize (*args)
 			# default before setting
@@ -139,8 +139,18 @@ module CombinePDF
 		# This method also adds the << operator to each page instance, so that content can be
 		# injected to the pages, as described above.
 		#
+		# if the secure_injection is false, then the << operator will not alter the any of the information added to the page.
+		# this might cause conflicts in the added content, but is available for situations in which
+		# the content added is compressed using unsupported filters or options.
+		#
+		# the default is for the << operator to attempt a secure copy, by attempting to rename the content references and avoiding conflicts.
+		# because of not all PDF files are created equal (some might have formating errors or differences), it is imposiible to learn if the attempt wa successful.
+		#
 		# (page objects are Hash class objects. the << operator is added to the specific instances without changing the class)
-		def pages(catalogs = nil)
+		#
+		# 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)
 			page_list = []
 			if catalogs == nil
 				catalogs = @objects.select {|obj| obj.is_a?(Hash) && obj[:Type] == :Catalog}
@@ -161,11 +171,20 @@ module CombinePDF
 					case catalogs[:Type]
 					when :Page
 						holder = self
-						catalogs.define_singleton_method("<<".to_sym) do |obj|
-							obj = PDFOperations.copy_and_secure_for_injection obj
-							PDFOperations.inject_to_page self, obj
-							holder.add_referenced self # add new referenced objects
-							self
+						if secure_injection
+							catalogs.define_singleton_method("<<".to_sym) do |obj|
+								obj = PDFOperations.copy_and_secure_for_injection obj
+								PDFOperations.inject_to_page self, obj
+								holder.add_referenced self # add new referenced objects
+								self
+							end
+						else
+							catalogs.define_singleton_method("<<".to_sym) do |obj|
+								obj = PDFOperations.create_deep_copy obj
+								PDFOperations.inject_to_page self, obj
+								holder.add_referenced self # add new referenced objects
+								self
+							end
 						end
 						page_list << catalogs
 					when :Pages
@@ -222,30 +241,62 @@ module CombinePDF
 		end
 
 		# get the title for the pdf
-		# The title is stored in the information dictionary and isn't requited
+		# The title is stored in the information dictionary and isn't required
 		def title
 			return @info[:Title]
 		end
 		# set the title for the pdf
-		# The title is stored in the information dictionary and isn't requited
+		# The title is stored in the information dictionary and isn't required
 		# new_title:: a string that is the new author value.
 		def title=(new_title = nil)
 			@info[:Title] = new_title
 		end
-		# get the author value for the pdf
-		# The author is stored in the information dictionary and isn't requited
+		# get the author value for the pdf.
+		# The author is stored in the information dictionary and isn't required
 		def author
 			return @info[:Author]
 		end
-		# set the author for the pdf
-		# The author is stored in the information dictionary and isn't requited
+		# set the author value for the pdf.
+		# The author is stored in the information dictionary and isn't required
+		#
 		# new_title:: a string that is the new author value.
 		def author=(new_author = nil)
 			@info[:Author] = new_author
 		end
 	end
 	class PDF #:nodoc: all
-
+		# @private
+		# Some PDF objects contain references to other PDF objects.
+		#
+		# 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)
+			# add references but not root
+			case 
+			when object.is_a?(Array)
+				object.each {|it| add_referenced(it)}
+			when object.is_a?(Hash)
+				if object[:is_reference_only] && object[:referenced_object]
+					unless @objects.include? object[:referenced_object]
+						@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
+			end
+		end
+		# @private
+		# run block of code on evey object (Hash)
+		def each_object(&block)
+			PDFOperations._each_object(@objects, &block)
+		end
+		protected
 		# @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. 
@@ -339,31 +390,8 @@ module CombinePDF
 			end
 		end
 
-		# @private
-		def add_referenced(object)
-			# add references but not root
-			case 
-			when object.is_a?(Array)
-				object.each {|it| add_referenced(it)}
-			when object.is_a?(Hash)
-				if object[:is_reference_only] && object[:referenced_object]
-					unless @objects.include? object[:referenced_object]
-						@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
-			end
-		end
 		# @private
 		def rebuild_catalog(*with_pages)
-			##########################
-			## Test-Run - How is that done?
 			warn "Re-Building Catalog"
 
 			# # build page list v.1 Slow but WORKS
@@ -373,7 +401,7 @@ module CombinePDF
 			# page_list = []
 			# PDFOperations._each_object(old_catalogs,false) { |p| page_list << p if p.is_a?(Hash) && p[:Type] == :Page }
 
-			# build page list v.2
+			# build page list v.2 faster, better, and works
 			# Benchmark testing value: 0.215114
 			page_list = pages
 
@@ -458,12 +486,6 @@ module CombinePDF
 			# rebuild stream lengths?
 		end
 
-		# @private
-		# run block of code on evey object (Hash)
-		def each_object(&block)
-			PDFOperations._each_object(@objects, &block)
-		end
-
 		# @private
 		# the function rerturns true if the reference belongs to the object
 		def compare_reference_values(obj, ref)

data/lib/combine_pdf/font_metrics/courier-bold_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		COURIER_BOLD_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/courier-boldoblique_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		COURIER_BOLDOBLIQUE_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/courier-oblique_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		COURIER_OBLIQUE_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/courier_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		COURIER_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/helvetica-bold_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		HELVETICA_BOLD_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/helvetica-boldoblique_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		HELVETICA_BOLDOBLIQUE_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/helvetica-oblique_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		HELVETICA_OBLIQUE_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/helvetica_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		HELVETICA_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/metrics_dictionary.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		METRICS_DICTIONARY = {
 			:"Times-Roman"			=>	TIMES_ROMAN_METRICS,
 			:"Times-Bold"			=>	TIMES_BOLD_METRICS,

data/lib/combine_pdf/font_metrics/symbol_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		SYMBOL_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/times-bold_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		TIMES_BOLD_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/times-bolditalic_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		TIMES_BOLDITALIC_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/times-italic_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		TIMES_ITALIC_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/times-roman_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		TIMES_ROMAN_METRICS = 
 			{"space"=>{:charcode=>32,

data/lib/combine_pdf/font_metrics/zapfdingbats_metrics.rb

@@ -1,5 +1,6 @@
 module CombinePDF
 	class PDFWriter < Hash
+		protected
 		# with thanks to Jan Krutisch, the creator of the afm gem.
 		ZAPFDINGBATS_METRICS = 
 			{"space"=>{:charcode=>32,

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Boaz Segev