Module: CombinePDF::PDFOperations

Defined in:

lib/combine_pdf/operations.rb

Overview

This is an internal class. you don’t need it.

Class Method Summary

• ._each_object(object, limit_references = true, first_call = true, &block) ⇒ Object
• ._format_array_to_pdf(object) ⇒ Object
• ._format_hash_to_pdf(object) ⇒ Object
• ._format_name_to_pdf(object) ⇒ Object
• ._format_string_to_pdf(object) ⇒ Object
• ._object_to_pdf(object) ⇒ Object

  Formats an object into PDF format.

• .change_connected_references_to_actual_values(hash_with_references = {}) ⇒ Object
• .change_references_to_actual_values(objects_array = [], hash_with_references = {}) ⇒ Object
• .connect_references_and_actual_values(objects_array = [], hash_with_references = {}) ⇒ Object
• .copy_and_secure_for_injection(page) ⇒ Object

  copy_and_secure_for_injection(page) - page is a page in the pages array, i.e.

• .create_deep_copy(object) ⇒ Object

  Ruby normally assigns pointes.

• .flatten_resources_dictionaries(resources) ⇒ Object
• .get_referenced(object) ⇒ Object

  returns the PDF Object Hash holding the acutal data (if exists) or the original hash (if it wasn’t a reference).

• .get_refernced_object(objects_array = [], reference_hash = {}) ⇒ Object
• .remove_old_ids(objects) ⇒ Object

  removes id and generation number values, for better comparrison and avoiding object duplication objects

  one or more objects in a PDF file/page.

Class Method Details

._each_object(object, limit_references = true, first_call = true, &block) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 253

def _each_object(object, limit_references = true, first_call = true, &block)
	# #####################
	# ## v.1.2 needs optimazation
	# case
	# when object.is_a?(Array)
	# 	object.each {|obj| _each_object(obj, limit_references, &block)}
	# when object.is_a?(Hash)
	# 	yield(object)
	# 	object.each do |k,v|
	# 		unless (limit_references && k == :referenced_object)
	# 			unless k == :Parent
	# 				_each_object(v, limit_references, &block)
	# 			end
	# 		end
	# 	end
	# end
	#####################
	## v.2.1 needs optimazation
	## version 2.1 is slightly faster then v.1.2
	@already_visited = [] if first_call
	unless limit_references
		@already_visited << object.object_id
	end
	case
	when object.is_a?(Array)
		object.each {|obj| _each_object(obj, limit_references, false, &block)}
	when object.is_a?(Hash)
		yield(object)
		unless limit_references && object[:is_reference_only]
			object.each do |k,v|
				_each_object(v, limit_references, false, &block) unless @already_visited.include? v.object_id
			end
		end					
	end
end

._format_array_to_pdf(object) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 355

def _format_array_to_pdf(object)
	# 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

._format_hash_to_pdf(object) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 362

def _format_hash_to_pdf(object)
	# if the object is only a reference:
	# special conditions apply, and there is only the setting of the reference (if needed) and output
	if object[:is_reference_only]
		#
		if object[:referenced_object] && object[:referenced_object].is_a?(Hash)
			object[:indirect_reference_id] = object[:referenced_object][:indirect_reference_id]
			object[:indirect_generation_number] = object[:referenced_object][:indirect_generation_number]
		end
		object[:indirect_reference_id] ||= 0
		object[:indirect_generation_number] ||= 0
		return "#{object[:indirect_reference_id].to_s} #{object[:indirect_generation_number].to_s} R".force_encoding(Encoding::ASCII_8BIT)
	end

	# if the object is indirect...
	out = []
	if object[:indirect_reference_id]
		object[:indirect_reference_id] ||= 0
		object[:indirect_generation_number] ||= 0
		out << "#{object[:indirect_reference_id].to_s} #{object[:indirect_generation_number].to_s} obj\n".force_encoding(Encoding::ASCII_8BIT)
		if object[:indirect_without_dictionary]
			out << _object_to_pdf(object[:indirect_without_dictionary])
			out << "\nendobj\n"
			return out.join().force_encoding(Encoding::ASCII_8BIT)
		end
	end
	# correct stream length, if the object is a stream.
	object[:Length] = object[:raw_stream_content].bytesize if object[:raw_stream_content]

	# if the object is not a simple object, it is a dictionary
	# A dictionary shall be written as a sequence of key-value pairs enclosed in double angle brackets (<<...>>)
	# (using LESS-THAN SIGNs (3Ch) and GREATER-THAN SIGNs (3Eh)).
	out << "<<\n".force_encoding(Encoding::ASCII_8BIT)
	object.each do |key, value|
		out << "#{_object_to_pdf key} #{_object_to_pdf value}\n".force_encoding(Encoding::ASCII_8BIT) unless PRIVATE_HASH_KEYS.include? key
	end
	out << ">>".force_encoding(Encoding::ASCII_8BIT)
	out << "\nstream\n#{object[:raw_stream_content]}\nendstream".force_encoding(Encoding::ASCII_8BIT) if object[:raw_stream_content]
	out << "\nendobj\n" if object[:indirect_reference_id]
	out.join().force_encoding(Encoding::ASCII_8BIT)
end

._format_name_to_pdf(object) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 333

def _format_name_to_pdf(object)
	# a name object is an atomic symbol uniquely defined by a sequence of ANY characters (8-bit values) except null (character code 0).
	# print name as a simple string. all characters between ~ and ! (except #) can be raw
	# the rest will have a number sign and their HEX equivalant
	# from the standard:
	# When writing a name in a PDF file, a SOLIDUS (2Fh) (/) shall be used to introduce a name. The SOLIDUS is not part of the name but is a prefix indicating that what follows is a sequence of characters representing the name in the PDF file and shall follow these rules:
	# a) A NUMBER SIGN (23h) (#) in a name shall be written by using its 2-digit hexadecimal code (23), preceded by the NUMBER SIGN.
	# 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.to_a.map do |b|
		case b
		when 0..15
			'#0' + b.to_s(16)
		when 15..32, 35, 37, 40, 41, 47, 60, 62, 91, 93, 123, 125, 127..256
			'#' + b.to_s(16)
		else
			b.chr
		end
	end
	"/" + out.join()
end

._format_string_to_pdf(object) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 311

def _format_string_to_pdf(object)
	if @string_output == :literal #if format is set to Literal
		#### can be better...
		replacement_hash = {
			"\x0A" => "\\n",
			"\x0D" => "\\r",
			"\x09" => "\\t",
			"\x08" => "\\b",
			"\xFF" => "\\f",
			"\x28" => "\\(",
			"\x29" => "\\)",
			"\x5C" => "\\\\"
		}
		32.times {|i| replacement_hash[i.chr] ||= "\\#{i}"}
		(256-128).times {|i| replacement_hash[(i + 127).chr] ||= "\\#{i+127}"}
		("(" + ([].tap {|out| object.bytes.each {|byte| replacement_hash[ byte.chr ] ? (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)). 
		("<" + object.unpack('H*')[0] + ">").force_encoding(Encoding::ASCII_8BIT)
	end
end

._object_to_pdf(object) ⇒ Object

Formats an object into PDF format. This is used my the PDF object to format the PDF file and it is used in the secure injection which is still being developed.

# File 'lib/combine_pdf/operations.rb', line 292

def _object_to_pdf object
	case
	when object.nil?
		return "null"
	when object.is_a?(String)
		return _format_string_to_pdf object
	when object.is_a?(Symbol)
		return _format_name_to_pdf object
	when object.is_a?(Array)
		return _format_array_to_pdf object
	when object.is_a?(Fixnum), object.is_a?(Float), object.is_a?(TrueClass), object.is_a?(FalseClass)
		return object.to_s + " "
	when object.is_a?(Hash)
		return _format_hash_to_pdf object
	else
		return ''
	end
end

.change_connected_references_to_actual_values(hash_with_references = {}) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 221

def change_connected_references_to_actual_values(hash_with_references = {})
	if hash_with_references.is_a?(Hash)
		hash_with_references.each do |k,v|
			if v.is_a?(Hash) && v[:is_reference_only]
				if v[:indirect_without_dictionary]
					hash_with_references[k] = v[:indirect_without_dictionary]
				elsif  v[:referenced_object]
					hash_with_references[k] = v[:referenced_object]
				else
					raise "Cannot change references to values, as they are disconnected!"
				end
			end
		end
		hash_with_references.each {|k, v| change_connected_references_to_actual_values(v) if v.is_a?(Hash) || v.is_a?(Array)}
	elsif hash_with_references.is_a?(Array)
		hash_with_references.each {|item| change_connected_references_to_actual_values(item) if item.is_a?(Hash) || item.is_a?(Array)}
	end
	hash_with_references		
end

.change_references_to_actual_values(objects_array = [], hash_with_references = {}) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 210

def change_references_to_actual_values(objects_array = [], hash_with_references = {})
	hash_with_references.each do |k,v|
		if v.is_a?(Hash) && v[:is_reference_only]
			hash_with_references[k] = PDFOperations.get_refernced_object( objects_array, v)
			hash_with_references[k] = hash_with_references[k][:indirect_without_dictionary] if hash_with_references[k].is_a?(Hash) && hash_with_references[k][:indirect_without_dictionary]
			warn "Couldn't connect all values from references - didn't find reference #{hash_with_references}!!!" if hash_with_references[k] == nil
			hash_with_references[k] = v unless hash_with_references[k]
		end
	end
	hash_with_references
end

.connect_references_and_actual_values(objects_array = [], hash_with_references = {}) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 240

def connect_references_and_actual_values(objects_array = [], hash_with_references = {})
	ret = true
	hash_with_references.each do |k,v|
		if v.is_a?(Hash) && v[:is_reference_only]
			ref_obj = PDFOperations.get_refernced_object( objects_array, v)
			hash_with_references[k] = ref_obj[:indirect_without_dictionary] if ref_obj.is_a?(Hash) && ref_obj[:indirect_without_dictionary]
			ret = false
		end
	end
	ret		
end

.copy_and_secure_for_injection(page) ⇒ Object

copy_and_secure_for_injection(page)

• page is a page in the pages array, i.e. pdf.pages

takes a page object and:

makes a deep copy of the page (Ruby defaults to pointers, so this will copy the memory).

then it will rewrite the content stream with renamed resources, so as to avoid name conflicts.

# File 'lib/combine_pdf/operations.rb', line 98

def copy_and_secure_for_injection(page)
	# copy page
	new_page = create_deep_copy page

	# initiate dictionary from old names to new names
	names_dictionary = {}

	# itirate through all keys that are name objects and give them new names (add to dic)
	# this should be done for every dictionary in :Resources
	# this is a few steps stage:

	# 1. get resources object
	resources = new_page[:Resources]
	if resources[:is_reference_only]
		resources = resources[:referenced_object]
		raise "Couldn't tap into resources dictionary, as it is a reference and isn't linked." unless resources
	end

	# 2. establich direct access to dictionaries and remove reference values
	flatten_resources_dictionaries resources

	# 3. travel every dictionary to pick up names (keys), change them and add them to the dictionary
	resources.each do |k,v|
		if v.is_a?(Hash)
			new_dictionary = {}
			new_name = "Combine" + SecureRandom.hex(7) + "PDF"
			i = 1
			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
				i += 1
			end
			resources[k] = new_dictionary
		end
	end

	# now that we have replaced the names in the resources dictionaries,
	# it is time to replace the names inside the stream
	# we will need to make sure we have access to the stream injected
	# we will user PDFFilter.inflate_object
	(new_page[:Contents].is_a?(Array) ? new_page[:Contents] : [new_page[:Contents] ]).each do |c|
		stream = c[:referenced_object]
		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! 
		end
		# patch back to PDF defaults, for OCRed PDF files.
		# stream[:raw_stream_content] = "q\nq\nq\nDeviceRGB CS\nDeviceRGB cs\n0 0 0 rg\n0 0 0 RG\n0 Tr\n%s\nQ\nQ\nQ\n" % stream[:raw_stream_content]
		# the following was removed for Acrobat Reader compatability: DeviceRGB CS\nDeviceRGB cs\n
		stream[:raw_stream_content] = "q\nq\nq\n0 0 0 rg\n0 0 0 RG\n0 Tr\n1 0 0 1 0 0 cm\n%s\nQ\nQ\nQ\n" % stream[:raw_stream_content]
	end

	new_page
end

.create_deep_copy(object) ⇒ Object

Ruby normally assigns pointes. noramlly:

a = [1,2,3] # => [1,2,3]
b = a # => [1,2,3]
a << 4 # => [1,2,3,4]
b # => [1,2,3,4]

This method makes sure that the memory is copied instead of a pointer assigned. this works using recursion, so that arrays and hashes within arrays and hashes are also copied and not pointed to. One needs to be careful of infinit loops using this function.

# File 'lib/combine_pdf/operations.rb', line 184

def create_deep_copy object
	if object.is_a?(Array)
		return object.map { |e|  create_deep_copy e  }
	elsif object.is_a?(Hash)
		return {}.tap {|out|  object.each {|k,v| out[create_deep_copy(k)] = create_deep_copy(v) unless k == :Parent} }
	elsif object.is_a?(String)
		return object.dup
	else
		return object # objects that aren't Strings, Arrays or Hashes (such as Symbols and Fixnums) won't be edited inplace.
	end
end

.flatten_resources_dictionaries(resources) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 153

def flatten_resources_dictionaries(resources)
	resources.each do |k,v|
		if v.is_a?(Hash) && v[:is_reference_only]
			if v[:referenced_object]
				resources[k] = resources[k][:referenced_object].dup
				resources[k].delete(:indirect_reference_id)
				resources[k].delete(:indirect_generation_number)
			elsif v[:indirect_without_dictionary]
				resources[k] = resources[k][:indirect_without_dictionary]
			end
		end
	end
end

.get_referenced(object) ⇒ Object

returns the PDF Object Hash holding the acutal data (if exists) or the original hash (if it wasn’t a reference)

works only AFTER references have been connected.

# File 'lib/combine_pdf/operations.rb', line 170

def get_referenced object
	object[:referenced_object] || object
end

.get_refernced_object(objects_array = [], reference_hash = {}) ⇒ Object

# File 'lib/combine_pdf/operations.rb', line 201

def get_refernced_object(objects_array = [], reference_hash = {})
	objects_array.each do |stored_object|
		return stored_object if ( stored_object.is_a?(Hash) &&
			reference_hash[:indirect_reference_id] == stored_object[:indirect_reference_id] &&
			reference_hash[:indirect_generation_number] == stored_object[:indirect_generation_number] )
	end
	warn "didn't find reference #{reference_hash}"
	nil		
end

.remove_old_ids(objects) ⇒ Object

removes id and generation number values, for better comparrison and avoiding object duplication

objects

one or more objects in a PDF file/page.

# File 'lib/combine_pdf/operations.rb', line 198

def remove_old_ids objects
	_each_object(objects) {|obj| obj.delete(:indirect_reference_id); obj.delete(:indirect_generation_number)}
end