combine_pdf 0.2.17 → 0.2.20

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 28a01d7ee2e0bd120239415e5691dc391a22c1e2
-  data.tar.gz: a7719887e8d6b96dfde01100ff3139a8fdcd0376
+  metadata.gz: 7cc0e0274387687766335c52fd25e98da231ded0
+  data.tar.gz: 809c6a2af4d5eb56857845560205ad222d2cfc88
 SHA512:
-  metadata.gz: ccdc753817129e63d0d118e955d386d27102b72a4cad9f67681dbaf9a5cf3d271a273f06fd4aa1837dcc0bb5738d12aa6a12125bdb4747b71b2702e40ebfd1b6
-  data.tar.gz: 130f7f1b54e1847d1701ddc5311695e25e85f8cea3d2cd3ef4a253ffbc69565f897add7b1b50f0ccfe18d15f06a44791e154d640c513ae9fecfe49e6cd91c1a6
+  metadata.gz: 072bec00cf0b1837017145b528c9e3b290f3dcb958385d1e7efd9d8b879c78724b775e568cbdc5bee93ca72c2f955ff0dd343e290530db9e689123f1e2b260a4
+  data.tar.gz: 21a123a20265221396df344ade4587b80ecba769b770ec5015e1960f2f899abbf3fac2d7df4c9fed59a2bbc7fa4a7bc8d8aa439559e4ff96562f983929f43151

data/CHANGELOG.md

@@ -2,6 +2,24 @@
 
 ***
 
+Change log v.0.2.20
+
+**Fix**: fix for issue #56, discovered by @LeptonHeavy, regarding errors caused by the new PDF form support feature.
+
+***
+
+Change log v.0.2.19 (yanked)
+
+**Partial fix**: unconfirmed fix for issue #56, discovered by @LeptonHeavy, regarding errors caused by the new PDF form support feature.
+
+***
+
+Change log v.0.2.18 (yanked)
+
+**Feature**: added minor (read: initial and incomplete) PDF forms support, in an attempt to preserve form data when combining PDF files.
+
+***
+
 Change log v.0.2.17
 
 **Feature**: added the `page#crop` method to easily crop a PDF file in accordance with the GWG industry association recommendations (updating the `MediaBox` property rather then the `CropBox`). Credit to @wingleungchoi for this feature.

data/README.md

@@ -4,7 +4,7 @@
 
 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
+## Install
 
 Install with ruby gems:
 
@@ -12,6 +12,18 @@ Install with ruby gems:
 gem install combine_pdf
 ```
 
+## Known Limitations
+
+CombinePDF is written natively in Ruby and should (presumably) work on all Ruby platforms that follow Ruby 2.0 compatibility.
+
+However, PDF files are quite complex creatures and no guaranty is provided.
+
+For example, PDF Forms are known to have issues and form data might be lost when attempting to combine PDFs with filled form data (also, forms are global objects, not page specific, so one should combine the whole of the PDF for any data to have any chance of being preserved).
+
+The same applies to PDF links and the table of contents, which all have global attributes and could be corrupted or lost when combining PDF data.
+
+If this library causes loss of data or burns down your house, I'm not to blame - as pointed to by the MIT license. That being said, I'm using the library happily after testing against different solutions.
+
 ## Combine/Merge PDF files or Pages
 
 To combine PDF files (or data):

data/lib/combine_pdf/parser.rb

@@ -36,7 +36,7 @@ module CombinePDF
 		# 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, :names_object
+		attr_reader :info_object, :root_object, :names_object, :forms_object
 
 		# when creating a parser, it is important to set the data (String) we wish to parse.
 		#
@@ -54,6 +54,7 @@ module CombinePDF
 			@root_object = {}
 			@info_object = {}
 			@names_object = {}
+			@forms_object = {}
 			@strings_dictionary = {} # all strings are one string
 			@version = nil
 			@scanner = nil
@@ -470,6 +471,7 @@ module CombinePDF
 					when :Pages
 						catalog_pages(catalogs[:Kids], inheritance_hash.dup ) unless catalogs[:Kids].nil?
 					when :Catalog
+						@forms_object.update( (catalogs[:AcroForm][:referenced_object] || catalogs[:AcroForm]), &self.class.method(:hash_update_proc_for_new) ) if catalogs[:AcroForm]
 						@names_object.update( (catalogs[:Names][:referenced_object] || catalogs[:Names]), &self.class.method(:hash_update_proc_for_new) ) if catalogs[:Names]
 						catalog_pages(catalogs[:Pages], inheritance_hash.dup ) unless catalogs[:Pages].nil?
 					end

data/lib/combine_pdf/pdf_protected.rb

@@ -27,7 +27,7 @@ module CombinePDF
 		# this is used for internal operations, such as injectng data using the << operator.
 		def add_referenced(object, dup_pages = true)
 			# add references but not root
-			case 
+			case
 			when object.is_a?(Array)
 				object.each {|it| add_referenced(it, dup_pages)}
 				return true
@@ -58,8 +58,8 @@ module CombinePDF
 
 				end
 				object.each do |k, v|
-					add_referenced(v, dup_pages) unless k == :Parent 
-				end 
+					add_referenced(v, dup_pages) unless k == :Parent
+				end
 			else
 				return false
 			end
@@ -88,9 +88,18 @@ module CombinePDF
 			# rebuild/rename the names dictionary
 			rebuild_names
 			# build new Catalog object
-			catalog_object = {Type: :Catalog, Pages: {referenced_object: pages_object, is_reference_only: true}, Names: {referenced_object: @names, is_reference_only: true} }
+			catalog_object = {Type: :Catalog, Pages: {referenced_object: pages_object, is_reference_only: true}, Names: {referenced_object: @names, is_reference_only: true}}
 			catalog_object[:ViewerPreferences] = @viewer_preferences unless @viewer_preferences.empty?
 
+			# rebuild/rename the forms dictionary
+			if @forms_data.nil? || @forms_data.empty?
+				@forms_data = nil
+			else
+				@forms_data = {referenced_object: actual_value(@forms_data), is_reference_only: true}
+				catalog_object[:AcroForm] = @forms_data
+			end
+
+
 			# point old Pages pointers to new Pages object
 			## first point known pages objects - enough?
 			pages.each {|p| p[:Parent] = { referenced_object: pages_object, is_reference_only: true} }
@@ -110,6 +119,9 @@ module CombinePDF
 		def names_object
 			@names
 		end
+		def forms_data
+			@forms_data
+		end
 
 		# @private
 		# this is an alternative to the rebuild_catalog catalog method
@@ -213,4 +225,3 @@ module CombinePDF
 
 	end
 end
-

data/lib/combine_pdf/pdf_public.rb

@@ -104,6 +104,7 @@ module CombinePDF
 			@version = parser.version if parser.version.is_a? Float
 			@info = parser.info_object || {}
 			@names = parser.names_object || {}
+			@forms_data = parser.forms_object || {}
 
 			# general globals
 			@set_start_id = 1
@@ -146,9 +147,13 @@ module CombinePDF
 		def author=(new_author = nil)
 			@info[:Author] = new_author
 		end
+		# Clears any existing form data.
+		def clear_forms_data
+			@forms_data.nil? || @forms_data.clear
+		end
 
 		# Save the PDF to file.
-		# 
+		#
 		# file_name:: is a string or path object for the output.
 		#
 		# **Notice!** if the file exists, it **WILL** be overwritten.
@@ -294,7 +299,13 @@ module CombinePDF
 			if data.is_a? PDF
 		 		@version = [@version, data.version].max
 				pages_to_add = data.pages
-				@names.update data.names_object, &self.class.method(:hash_merge_new_no_page)
+				actual_value(@names).update actual_value(data.names_object), &self.class.method(:hash_merge_new_no_page)
+				if actual_value(@forms_data)
+					actual_value(@forms_data).update actual_value(data.forms_data), &self.class.method(:hash_merge_new_no_page) if data.forms_data
+				else
+					@forms_data = data.forms_data
+				end
+				warn "Form data might be lost when combining PDF forms (possible conflicts)." unless data.forms_data.nil? || data.forms_data.empty?
 			elsif data.is_a?(Array) && (data.select {|o| !(o.is_a?(Hash) && o[:Type] == :Page) } ).empty?
 				pages_to_add = data
 			elsif data.is_a?(Hash) && data[:Type] == :Page
@@ -403,7 +414,7 @@ module CombinePDF
 					right_position = page_width - from_side - box_width
 					top_position = page_height - from_height
 					bottom_position = from_height + box_height
-					
+
 					if opt[:location].include? :top
 						 page.textbox text, {x: center_position, y: top_position }.merge(add_opt)
 					end
@@ -444,7 +455,7 @@ module CombinePDF
 				options[:location] ||= [:center]
 				number_pages({number_format: stamp}.merge(options))
 			when Page_Methods
-				# stamp = stamp.copy(true) 
+				# stamp = stamp.copy(true)
 				if options[:underlay]
 					(options[:page_range] ? pages[options[:page_range]] : pages).each {|p| p >> stamp}
 				else
@@ -458,4 +469,3 @@ module CombinePDF
 	end
 
 end
-

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = "0.2.17"
+  VERSION = "0.2.20"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.17
+  version: 0.2.20
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-10 00:00:00.000000000 Z
+date: 2016-04-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4