combine_pdf 0.2.11 → 0.2.12

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 4ae077f6437bdf78fe092fef2b738da12e6fb9bc
-  data.tar.gz: eca7b7e5c9c4f0f5b5c77d6d6904aed94e0c348a
+  metadata.gz: f66dc648f9871931fd703730cb5f876d41f17f95
+  data.tar.gz: f0e29ec0a4fdc4950c5f85f48ec5ea7eb556c03d
 SHA512:
-  metadata.gz: 2b7bec4b0cdeb0a3764d0ee0d7a8d8576c8a01c29fb2dfcbfb8d06d64bfe633dfe0aa9da9801e630a59754d621a3b00383df9be3d8a4ec9247c3c47b55a4623f
-  data.tar.gz: 82d77ada70dcf80ca0a4354dd6c9254f56c4ebaa637d0e875a1cb2621829a62c6cdcbe11a8afb421e40da0f6b0b0cc26938c6e7a8294cd8832e2ee2658bc285c
+  metadata.gz: fefebcb9e77a306f4099e91f05fc60efa2596b33afc2ff484562d82cda06494d86e11349c00e6724ad5978b4795cf999236fa273d933df25a93e9975f91e9e65
+  data.tar.gz: 8f2e46ba6d0b3f136d80a38b95d85b6271b433216fa59faea82bf668835a356b65399d87a35fda7e095e3d03d210768fb2b659df3546ddafb4df734fbc8517a7

data/CHANGELOG.md

@@ -2,12 +2,16 @@
 
 ***
 
+Change log v.0.2.12
+
+**Compatability**: fixed issue #36 reported by @vitstradal (thank you for reporting!) regarding PDF files composed by PaperPort. PaperPort (at least version 12) has an issue where PDF data will be placed within a PDF comment. PDF comments start with a "%" sign and end with an EOL marker ("\r" or "\n"). PaperPort ommitted the EOL marker, placing critical data within the comment. A work-around was found by parsing the comment's data and attempting to salvage the misplaced data. This workaround assumes that comments would not contain PDF parsable data at the very end of the comment's line... which is an unsafe assumption. hence, **please let me know if you find _any_ PDF files that worked before the workaround was introduced**.
+
+***
+
 Change log v.0.2.11
 
 **Fix**: fix for issue #35 , which was caused by the broken fix for issue #34. Credit to Davek Rupinski for pointing out the issue.
 
-**Fix**: fixed an issue with data and (file) sending, introduced when extending the `send_data` method to allow for big file uploads.
-
 ***
 
 Change log v.0.2.10

data/lib/combine_pdf/parser.rb

@@ -67,10 +67,15 @@ 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]*/
+				loop do
+					break unless @scanner.scan(/[^\d\r\n]+/)
+					break if @scanner.check(/([\d]+[\s]+[\d]+[\s]+obj[\n\r\s]+\<\<)|([\n\r]+)/)
+					break if @scanner.eos?
+					@scanner.pos += 1
+				end
 			end
 			@parsed = _parse_
+			# puts @parsed
 
 			raise "Unknown PDF parsing error - maleformed PDF file?" unless (@parsed.select {|i| !i.is_a?(Hash)}).empty?
 
@@ -151,7 +156,20 @@ module CombinePDF
 		def _parse_
 			out = []
 			str = ''
+			fresh = true
 			while @scanner.rest? do
+				# last ||= 0
+				# out.last.tap do |o|
+				# 	if o.is_a?(Hash)
+				# 		puts "[#{@scanner.pos}] Parser has a Dictionary (#{o.class.name}) with data:"
+				# 		o.each do |k, v|
+				# 			puts "    #{k}: is #{v.class.name} with data: #{v.to_s[0..4]}#{"..." if v.to_s.length > 5}"
+				# 		end
+				# 	else
+				# 		puts "[#{@scanner.pos}] Parser has #{o.class.name} with data: #{o.to_s[0..4]}#{"..." if o.to_s.length > 5}"
+				# 	end
+				# 	puts "next is #{@scanner.peek 8}"
+				# end unless (last == out.count) || (-1 == (last = out.count))
 				case
 				##########################################
 				## parse an Array
@@ -174,7 +192,8 @@ module CombinePDF
 				##########################################
 				## parse a Stream
 				##########################################
-				when @scanner.scan(/stream[\r]?[\n]/)
+				when @scanner.scan(/stream[\r\n]/)
+					@scanner.pos += 1 if @scanner.peek(1) == "\n".freeze && @scanner.matched[-1] != "\n".freeze
 					# the following was dicarded because some PDF files didn't have an EOL marker as required
 					# str = @scanner.scan_until(/(\r\n|\r|\n)endstream/)
 					# instead, a non-strict RegExp is used:
@@ -199,6 +218,8 @@ module CombinePDF
 					else
 						out << {indirect_without_dictionary: out.pop, indirect_generation_number: out.pop, indirect_reference_id: out.pop}
 					end
+					fresh = true
+					# puts "!!!!!!!!! Error with :indirect_reference_id\n\nObject #{out.last}  :indirect_reference_id = #{out.last[:indirect_reference_id]}" unless out.last[:indirect_reference_id].is_a?(Fixnum)
 				##########################################
 				## parse a Hex String
 				##########################################
@@ -293,7 +314,13 @@ module CombinePDF
 				##########################################
 				when str = @scanner.scan(/\%/)
 					#is a comment, skip until new line
-					@scanner.skip_until /[\n\r]+/
+					loop do
+						break unless @scanner.scan(/[^\d\r\n]+/)
+						break if @scanner.check(/([\d]+ [\d]+ obj)?[\n\r]+/)
+						break if @scanner.eos?
+						@scanner.pos += 1
+					end
+					# puts "AFTER COMMENT: #{@scanner.peek 8}"
 				##########################################
 				## Parse a Name
 				##########################################
@@ -333,7 +360,7 @@ module CombinePDF
 					##########
 					## get root object to check for encryption
 					@scanner.scan_until(/(trailer)|(\%EOF)/)
-
+					fresh = true
 					if @scanner.matched[-1] == 'r'
 						if @scanner.skip_until(/<</)
 							data = _parse_
@@ -350,10 +377,10 @@ module CombinePDF
 					nil
 				when @scanner.scan(/obj[\s]*/)
 					# Fix wkhtmltopdf PDF authoring issue - missing 'endobj' keywords
-					unless out[-4].nil? || out[-4].is_a?(Hash)
+					unless fresh || (out[-4].nil? || out[-4].is_a?(Hash))
 						keep = []
-						keep << out.pop
-						keep << out.pop
+						keep << out.pop # .tap {|i| puts "#{i} is an ID"} 
+						keep << out.pop # .tap {|i| puts "#{i} is a REF"} 
 
 						if out.last.is_a? Hash
 							out << out.pop.merge({indirect_generation_number: out.pop, indirect_reference_id: out.pop})
@@ -365,9 +392,11 @@ module CombinePDF
 						out << keep.pop
 						out << keep.pop
 					end
+					fresh = false
 				else
 					# always advance 
-					# warn "Advnacing for unknown reason..."
+					# warn "Advnacing for unknown reason... #{@scanner.peek(4)}" unless @scanner.peek(1) =~ /[\s\n]/
+					warn "Warning: parser advnacing for unknown reason. Potential data-loss."
 					@scanner.pos = @scanner.pos + 1
 				end
 			end

data/lib/combine_pdf/version.rb

@@ -1,4 +1,4 @@
 module CombinePDF
-  VERSION = "0.2.11"
+  VERSION = "0.2.12"
 end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.11
+  version: 0.2.12
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-11-06 00:00:00.000000000 Z
+date: 2015-11-19 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4