combine_pdf 0.2.37 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cac27b28f3653156374b1ea4a429676625ba0c9f
-  data.tar.gz: 8ce9f60a9bdcbd763a72461703c51845dbab0f2c
+  metadata.gz: 3663c5f5602eeed30aba5405fc0503ab9a865432
+  data.tar.gz: f6e07e2fbb180065146c32a440f29348fb2a2808
 SHA512:
-  metadata.gz: 78aa47281a6f9fa5723a99ed9ce666479999348b69a19778e02eb2144e1c507d4a62ac23a07e4b46079193d14fecf77cbb9dac06591ac2354e92046ba0ba5d20
-  data.tar.gz: 2b92948efba5ab031a46865416b13b1aecb892a1763c0d45190598313e6e0139907ece00c129349060ff030c7b38531d1d848f9696168d5fec499a4c65121db8
+  metadata.gz: 835236c99911009df5112cc92c3a042e6fe2dcd634e9b189f9977aef9f9f42ae33ac9865e94d08e8d26b6ff0328d7bf84ccc0dc858897c2c0ceae10c3c80c944
+  data.tar.gz: f11df3aa2c055a17be86c83766ea85f536afc5dcf0b299cd0e5be48344724909619ea54c8b52b7a9997907ec9d5c585d21f9ba81eeb17a74a77234aba2a79994

data/CHANGELOG.md

@@ -2,7 +2,19 @@
 
 ***
 
-#### Change log v.0.2.37 (Release Candidate)
+#### Change log v.1.0.0
+
+**Fix**: Fixed a possible issue with string corruption... it might have only existed in the development version, I'm not sure, but it's fixed anyway.
+
+**Fix** (degrade): Fixed an issue related to deeply nested objects causing unreasonable slowdowns. The issue was resolved by degrading the PDF optimization process to review object with `stream` data instead of reviewing every object. This means more duplicate objects might be observed when similar PDF files are merged.
+
+**Fix**: Fixed an issue related to form data where font information was lost during the PDF optimization process.
+
+**Fix**: Fixed issue #108 by adding support for PDFs that have spaces and missing zeros in their hex encoded strings. Credit to @emmanuelmillionaer.
+
+***
+
+#### Change log v.0.2.37
 
 **Fix**: Fixed `Page_Methods#textbox` default `:x`,`:y` to allow for non-zero/cropped page origin. Credit to @donnguyen for exposing the issue.
 

data/lib/combine_pdf.rb

@@ -138,7 +138,7 @@ end
 # arrays are Array
 # strings are String
 # names are Symbols (String.to_sym)
-# numbers are Fixnum or Float
+# numbers are Integer or Float (Numeric)
 # boolean are TrueClass or FalseClass
 
 ## test performance with:

data/lib/combine_pdf/parser.rb

@@ -107,7 +107,7 @@ module CombinePDF
           @scanner = StringScanner.new o[:raw_stream_content]
           stream_data = _parse_
           id_array = []
-          while stream_data[0].is_a? (Integer)
+          while stream_data[0].is_a? (Numeric)
             id_array << stream_data.shift
             stream_data.shift
           end
@@ -180,57 +180,34 @@ module CombinePDF
         if @scanner.scan(/\[/)
           out << _parse_
         ##########################################
-        ## parse a Dictionary
-        ##########################################
-        elsif @scanner.scan(/<</)
-          data = _parse_
-          obj = {}
-          obj[data.shift] = data.shift while data[0]
-          out << obj
-        ##########################################
-        ## return content of array or dictionary
-        ##########################################
-        elsif @scanner.scan(/\]/) || @scanner.scan(/>>/)
-          return out
-        ##########################################
-        ## parse a Stream
+        ## Parse a Name
         ##########################################
-        elsif @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:
-          str = @scanner.scan_until(/endstream/)
-          # raise error if the stream doesn't end.
-          raise "Parsing Error: PDF file error - a stream object wasn't properly closed 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] = unify_string str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
-          else
-            warn 'Stream not attached to dictionary!'
-            out << str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
-          end
+        # old, probably working version: when str = @scanner.scan(/\/[\#\w\d\.\+\-\\\?\,]+/)
+        # I don't know how to write the /[\x21-\x7e___subtract_certain_hex_values_here____]+/
+        # all allowed regular caracters between ! and ~ : /[\x21-\x24\x26\x27\x2a-\x2e\x30-\x3b\x3d\x3f-\x5a\x5c\x5e-\x7a\x7c\x7e]+
+        # all characters that aren't white space or special: /[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]+
+        elsif str = @scanner.scan(/\/[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]*/)
+          out << (str[1..-1].gsub(/\#[0-9a-fA-F]{2}/) { |a| a[1..2].hex.chr }).to_sym
         ##########################################
-        ## parse an Object after finished
+        ## Parse a Number
         ##########################################
-        elsif str = @scanner.scan(/endobj/)
-          # what to do when this is an object?
-          if out.last.is_a? Hash
-            out << out.pop.merge(indirect_generation_number: out.pop, indirect_reference_id: out.pop)
-          else
-            out << { indirect_without_dictionary: out.pop, indirect_generation_number: out.pop, indirect_reference_id: out.pop }
-          end
-          fresh = true
-          # fix wkhtmltopdf use of PDF 1.1 Dest using symbols instead of strings
-          out.last[:Dest] = unify_string(out.last[:Dest].to_s) if out.last[:Dest] && out.last[:Dest].is_a?(Symbol)
-        # 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?(Integer)
+        elsif str = @scanner.scan(/[\+\-\.\d]+/)
+          str =~ /\./ ? (out << str.to_f) : (out << str.to_i)
         ##########################################
         ## parse a Hex String
         ##########################################
-        elsif str = @scanner.scan(/<[0-9a-fA-F]*>/)
+        elsif str = @scanner.scan(/\<[0-9a-fA-F]*\>/)
           # warn "Found a hex string"
-          out << unify_string([str[1..-2]].pack('H*').force_encoding(Encoding::ASCII_8BIT))
+          str = str.slice(1..-2).force_encoding(Encoding::ASCII_8BIT)
+          # str = "0#{str}" if str.length.odd?
+          out << unify_string([str].pack('H*').force_encoding(Encoding::ASCII_8BIT))
+        ##########################################
+        ## parse a space delimited Hex String
+        ##########################################
+        elsif str = @scanner.scan(/\<[0-9a-fA-F\s]*\>/)
+          # warn "Found a space seperated hex string"
+          str = str.force_encoding(Encoding::ASCII_8BIT).split(/\s/).map! {|b| b.length.odd? ? "0#{b}" : b}
+          out << unify_string(str.pack('H*' * str.length).force_encoding(Encoding::ASCII_8BIT))
         ##########################################
         ## parse a Literal String
         ##########################################
@@ -315,6 +292,52 @@ module CombinePDF
           end
           out << unify_string(str.pack('C*').force_encoding(Encoding::ASCII_8BIT))
         ##########################################
+        ## parse a Dictionary
+        ##########################################
+        elsif @scanner.scan(/<</)
+          data = _parse_
+          obj = {}
+          obj[data.shift] = data.shift while data[0]
+          out << obj
+        ##########################################
+        ## return content of array or dictionary
+        ##########################################
+        elsif @scanner.scan(/\]/) || @scanner.scan(/>>/)
+          return out
+        ##########################################
+        ## parse a Stream
+        ##########################################
+        elsif @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:
+          str = @scanner.scan_until(/endstream/)
+          # raise error if the stream doesn't end.
+          raise "Parsing Error: PDF file error - a stream object wasn't properly closed 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] = unify_string str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
+          else
+            warn 'Stream not attached to dictionary!'
+            out << str.sub(/(\r\n|\n|\r)?endstream\z/, '').force_encoding(Encoding::ASCII_8BIT)
+          end
+        ##########################################
+        ## parse an Object after finished
+        ##########################################
+        elsif str = @scanner.scan(/endobj/)
+          # what to do when this is an object?
+          if out.last.is_a? Hash
+            out << out.pop.merge(indirect_generation_number: out.pop, indirect_reference_id: out.pop)
+          else
+            out << { indirect_without_dictionary: out.pop, indirect_generation_number: out.pop, indirect_reference_id: out.pop }
+          end
+          fresh = true
+          # fix wkhtmltopdf use of PDF 1.1 Dest using symbols instead of strings
+          out.last[:Dest] = unify_string(out.last[:Dest].to_s) if out.last[:Dest] && out.last[:Dest].is_a?(Symbol)
+        # 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?(Numeric)
+        ##########################################
         ## Parse a comment
         ##########################################
         elsif str = @scanner.scan(/\%/)
@@ -326,20 +349,6 @@ module CombinePDF
           end
         # puts "AFTER COMMENT: #{@scanner.peek 8}"
         ##########################################
-        ## Parse a Name
-        ##########################################
-        # old, probably working version: when str = @scanner.scan(/\/[\#\w\d\.\+\-\\\?\,]+/)
-        # I don't know how to write the /[\x21-\x7e___subtract_certain_hex_values_here____]+/
-        # all allowed regular caracters between ! and ~ : /[\x21-\x24\x26\x27\x2a-\x2e\x30-\x3b\x3d\x3f-\x5a\x5c\x5e-\x7a\x7c\x7e]+
-        # all characters that aren't white space or special: /[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]+
-        elsif str = @scanner.scan(/\/[^\x00\x09\x0a\x0c\x0d\x20\x28\x29\x3c\x3e\x5b\x5d\x7b\x7d\x2f\x25]*/)
-          out << (str[1..-1].gsub(/\#[0-9a-fA-F]{2}/) { |a| a[1..2].hex.chr }).to_sym
-        ##########################################
-        ## Parse a Number
-        ##########################################
-        elsif str = @scanner.scan(/[\+\-\.\d]+/)
-          str =~ /\./ ? (out << str.to_f) : (out << str.to_i)
-        ##########################################
         ## Parse an Object Reference
         ##########################################
         elsif @scanner.scan(/R/)
@@ -562,7 +571,7 @@ module CombinePDF
                   o = nil
                 else
                   o[:referenced_object] = obj_dir[[o[:indirect_reference_id], o[:indirect_generation_number]]]
-                  warn "Couldn't connect reference for #{o}" if o[:referenced_object].nil?
+                  warn "Couldn't connect reference for #{o}" if o[:referenced_object].nil? && (o[:indirect_reference_id] + o[:indirect_generation_number] != 0)
                   o.delete :indirect_reference_id
                   o.delete :indirect_generation_number
                   o = (o[:referenced_object] && o[:referenced_object][:indirect_without_dictionary]) || o

data/lib/combine_pdf/pdf_protected.rb

@@ -33,12 +33,14 @@ module CombinePDF
         if obj.is_a?(Hash)
           referenced = obj[:referenced_object]
           if referenced && referenced.any?
-            tmp = resolved[referenced.object_id] || existing[referenced]
+            #         tmp = resolved[referenced.object_id] || existing[referenced]
+            tmp = resolved[referenced.object_id] || (referenced[:raw_stream_content] && existing[referenced[:raw_stream_content]])
             if tmp
               obj[:referenced_object] = tmp
             else
               resolved[obj.object_id] = referenced
-              existing[referenced] = referenced
+              #        existing[referenced] = referenced
+              existing[referenced[:raw_stream_content]] = referenced
               should_resolve << referenced
               @objects << referenced
             end
@@ -150,7 +152,8 @@ module CombinePDF
       catalog = rebuild_catalog
       page_objects = catalog[:Pages][:referenced_object][:Kids].map { |e| @objects << e[:referenced_object]; e[:referenced_object] }
       # adds every referenced object to the @objects (root), addition is performed as pointers rather then copies
-      add_referenced([page_objects, @forms_data, @names, @outlines, @info])
+      # add_referenced([page_objects, @forms_data, @names, @outlines, @info])
+      add_referenced(@objects.dup)
       catalog
     end
 
@@ -163,7 +166,7 @@ module CombinePDF
     def renumber_object_ids(start = nil)
       @set_start_id = start || @set_start_id
       start = @set_start_id
-      history = {}
+      # history = {}
       @objects.each do |obj|
         obj[:indirect_reference_id] = start
         start += 1
@@ -191,7 +194,7 @@ module CombinePDF
             if pos[0].is_a? String
               (pos.length / 2).times do |i|
                 dic << (pos[i * 2].clear << base.next!)
-                pos[(i * 2) + 1][0] = {is_reference_only: true, referenced_object: pages[pos[(i * 2) + 1][0]]} if(pos[(i * 2) + 1].is_a?(Array) && pos[(i * 2) + 1][0].is_a?(Integer))
+                pos[(i * 2) + 1][0] = {is_reference_only: true, referenced_object: pages[pos[(i * 2) + 1][0]]} if(pos[(i * 2) + 1].is_a?(Array) && pos[(i * 2) + 1][0].is_a?(Numeric))
                 dic << (pos[(i * 2) + 1].is_a?(Array) ? { is_reference_only: true, referenced_object: { indirect_without_dictionary: pos[(i * 2) + 1] } } : pos[(i * 2) + 1])
                 # dic << pos[(i * 2) + 1]
               end
@@ -225,12 +228,13 @@ module CombinePDF
     # preffering the new over the old.
     def self.hash_merge_new_no_page(_key, old_data, new_data)
       return old_data unless new_data
+      return new_data unless old_data
       if old_data.is_a?(Hash) && new_data.is_a?(Hash)
         return old_data if (old_data[:Type] == :Page)
         old_data.merge(new_data, &(@hash_merge_new_no_page_proc ||= method(:hash_merge_new_no_page)))
       elsif old_data.is_a? Array
-        new_data = [new_data] unless new_data.is_a? Array
-        old_data + new_data
+        return old_data + new_data if new_data.is_a?(Array)
+        return old_data.dup << new_data
       elsif new_data.is_a? Array
         new_data + [old_data]
       else

data/lib/combine_pdf/pdf_public.rb

@@ -100,7 +100,7 @@ module CombinePDF
       @names = parser.names_object || {}
       @forms_data = parser.forms_object || {}
       @outlines = parser.outlines_object || {}
-      # rebuild the catalo, to fix wkhtmltopdf's use of static page numbers
+      # rebuild the catalog, to fix wkhtmltopdf's use of static page numbers
       rebuild_catalog
 
       # general globals

data/lib/combine_pdf/renderer.rb

@@ -20,7 +20,7 @@ module CombinePDF
         return format_name_to_pdf object
       elsif object.is_a?(Array)
         return format_array_to_pdf object
-      elsif object.is_a?(Integer) || object.is_a?(Float) || object.is_a?(TrueClass) || object.is_a?(FalseClass)
+      elsif object.is_a?(Numeric) || object.is_a?(TrueClass) || object.is_a?(FalseClass)
         return object.to_s
       elsif object.is_a?(Hash)
         return format_hash_to_pdf object

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '0.2.37'.freeze
+  VERSION = '1.0.0'.freeze
 end

data/test/automated

@@ -14,6 +14,7 @@ require 'bundler/setup'
 
 pdf = CombinePDF.load "./Ruby/test\ pdfs/filled_form.pdf"
 pdf.save '01_check_radio_buttuns.pdf'
+pdf = CombinePDF.load "./Ruby/test\ pdfs/filled_form.pdf"
 pdf << CombinePDF.load("./Ruby/test\ pdfs/empty_form.pdf")
 pdf << CombinePDF.load("./Ruby/test\ pdfs/filled_form.pdf")
 pdf.save '02_check_form_unification_middle_is_empty.pdf'
@@ -51,7 +52,16 @@ pdf.save '06_check_links_to_second_copy.pdf'
 lists = %w(./Ruby/test\ pdfs/outlines/self_merge_err.pdf ./Ruby/test\ pdfs/outlines/big_toc.pdf ./Ruby/test\ pdfs/outlines/bigger_toc.pdf ./Ruby/test\ pdfs/outlines/named_dest_no_toc.pdf ./Ruby/test\ pdfs/outlines/named_dest_no_toc2.pdf ./Ruby/test\ pdfs/outlines/named_dest.pdf ./Ruby/test\ pdfs/outlines/named_dest2.pdf)
 
 i = 0
-lists.each { |n| CombinePDF.load(n).save("07_#{(i += 1)}_#{n.split('/')[-1]}"); (CombinePDF.load(n) << CombinePDF.load(n)).save("07_#{i}x2_#{n.split('/')[-1]}") }
+lists.each do |n|
+  # puts "loading #{n}"
+  pdf = CombinePDF.load(n)
+  # puts "saving 07_#{(i += 1)}_#{n.split('/')[-1]}"
+  pdf.save("07_#{(i += 1)}_#{n.split('/')[-1]}")
+  # puts "loading #{n}X2"
+  pdf = CombinePDF.load(n) << CombinePDF.load(n)
+  # puts "saving 07_#{i}x2_#{n.split('/')[-1]}"
+  pdf.save("07_#{i}x2_#{n.split('/')[-1]}")
+end
 pdf = CombinePDF.new
 lists.each { |n| pdf << CombinePDF.load(n) }
 pdf.save('07_named destinations.pdf')

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.37
+  version: 1.0.0
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-05-10 00:00:00.000000000 Z
+date: 2017-05-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -104,7 +104,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.6.11
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.