combine_pdf 0.2.5 → 0.2.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 61c4d75ddd1975e567b4b96359f852a4eb13fdf7
-  data.tar.gz: 304f0b46cf41a96eddc46c728a20caf9ff77912c
+  metadata.gz: 63c084e190f8c5f47aaa3db6cd32064a7e7dcfb2
+  data.tar.gz: dbd7e1efe7b372abae318839eb80658913664b29
 SHA512:
-  metadata.gz: 256814f346635778e23265a652ce800e3c951e21e647943f752b2d231ddc68c90cc6ffeb7cfacaadd34b42faff97233637752cbd68329ff064728d673c989fdf
-  data.tar.gz: 29c90166699f5baf305398a1382e2f0db4ceb00e35391955cb5f6a30012a445fd48f3ce5e2d5154851ad1b9ae8d580f286de71ffe8b881e580b051faa1e1ec13
+  metadata.gz: a374e9be84a6397294a09b1fc76ae0a346ee9bce8abf1d8750742417494ecacf2b49ed843c060c13716046121d5c1ca3b570bf7fc18c828a99ce5cb857a043fc
+  data.tar.gz: bf343d5749131896f4fe1dc2882bd62eb0696eb20c9021048e0b1d8f15837b580a0b50a4db083e752a3e73aa5bcbc88909f78c5d46b7f5ddb1e38cb264919e17

data/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 ***
 
+Change log v.0.2.6
+
+**fixed**: Hasan Iskandar fixed issue #30 - Output file cannot be saved from Adobe Reader with "Save As optimizes for Fast Web View" preference enabled. Thank you Hasan.
+
+**update**: More parsing error detection; Updated the endstream EOL marker indentifier for safer indentification.
+
+***
+
 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.

data/lib/combine_pdf/parser.rb

@@ -65,10 +65,13 @@ module CombinePDF
 			@scanner.pos = 0
 			if @scanner.scan /\%PDF\-[\d\-\.]+/
 				@version = @scanner.matched.scan(/[\d\.]+/)[0].to_f
+				@scanner.skip_until /[\n\r]+/
+				# @scanner.skip /[^\d]*/
 			end
-
 			@parsed = _parse_
 
+			raise "Unknown PDF parsing error - maleformed PDF file?" unless (@parsed.select {|i| !i.is_a?(Hash)}).empty?
+
 			if @root_object == {}
 				xref_streams = @parsed.select {|obj| obj.is_a?(Hash) && obj[:Type] == :XRef}
 				xref_streams.each do |xref_dictionary|
@@ -175,8 +178,8 @@ module CombinePDF
 					raise "Parsing Error: PDF file error - a stream object wasn't properly colsed using 'endstream'!" unless str
 					# need to remove end of stream
 					if out.last.is_a? Hash
-						out.last[:raw_stream_content] = str[0...-10] #cuts only one EON char (\n or \r)
-						# out.last[:raw_stream_content] = str.gsub(/[\n\r]?[\n\r]?endstream/, "")
+						# out.last[:raw_stream_content] = str[0...-10] #cuts only one EON char (\n or \r)
+						out.last[:raw_stream_content] = str.gsub(/[\n\r]?[\n\r]endstream\z/, "")
 					else
 						warn "Stream not attached to dictionary!"
 						out << str[0...-10].force_encoding(Encoding::ASCII_8BIT)
@@ -323,7 +326,7 @@ module CombinePDF
 					if @scanner.matched[-1] == 'r'
 						if @scanner.skip_until(/<</)
 							data = _parse_
-							@root_object = {}
+							@root_object ||= {}
 							@root_object[data.shift] = data.shift while data[0]						
 						end
 						##########

data/lib/combine_pdf/pdf_protected.rb

@@ -110,6 +110,8 @@ module CombinePDF
 		def rebuild_catalog_and_objects
 			catalog = rebuild_catalog
 			@objects = []
+			@objects << @info
+			add_referenced @info
 			@objects << catalog
 			add_referenced catalog
 			catalog

data/lib/combine_pdf/pdf_public.rb

@@ -163,8 +163,10 @@ module CombinePDF
 		def to_pdf options = {}
 			#reset version if not specified
 			@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"
+			#set info for merged file
+			@info[:ModDate] = @info[:CreationDate] = Time.now.strftime "D:%Y%m%d%H%M%S%:::z'00"
+			@info[:Subject] = options[:subject] if options[:subject]
+			@info[:Producer] = options[:producer] if options[:producer]
 			#rebuild_catalog
 			catalog = rebuild_catalog_and_objects
 			# add ID and generation numbers to objects
@@ -193,13 +195,7 @@ module CombinePDF
 			out << out.pop + "trailer"
 			out << "<<\n/Root #{false || "#{catalog[:indirect_reference_id]} #{catalog[:indirect_generation_number]} R"}"
 			out << "/Size #{indirect_object_count.to_s}"
-			if @info.is_a?(Hash)
-				PRIVATE_HASH_KEYS.each {|key| @info.delete key} # make sure the dictionary is rendered inline, without stream
-				@info[:CreationDate] = @info[:ModDate] = Time.now.strftime "D:%Y%m%d%H%M%S%:::z'00"
-				@info[:Subject] = options[:subject] if options[:subject]
-				@info[:Producer] = options[:producer] if options[:producer]
-				out << "/Info #{object_to_pdf @info}"
-			end
+			out << "/Info #{@info[:indirect_reference_id]} #{@info[:indirect_generation_number]} R"
 			out << ">>\nstartxref\n#{xref_location.to_s}\n%%EOF"
 			# when finished, remove the numbering system and keep only pointers
 			remove_old_ids

data/lib/combine_pdf/version.rb

@@ -1,4 +1,4 @@
 module CombinePDF
-  VERSION = "0.2.5"
+  VERSION = "0.2.6"
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.5
+  version: 0.2.6
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-09-08 00:00:00.000000000 Z
+date: 2015-10-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -102,10 +102,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5
+rubygems_version: 2.4.5.1
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.
 test_files:
 - test/console
-has_rdoc: