combine_pdf 0.2.30 → 0.2.31

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f81f9412da41045468ecaa6e10104fc9062eee8d
-  data.tar.gz: 23410127dcabe19c6b9ddee352752f9b7bd0abb6
+  metadata.gz: 63b0c324e1bf003b0c0fc963eb2071b6c4672c18
+  data.tar.gz: 34c200edda06074773888c098b9d4f9a6479d752
 SHA512:
-  metadata.gz: 03fdcce50faf9045930e435cbdf4d31e4ed96419f6e594796df89ab7c6e0891568467d5c1b632338c5e33fe17f3e68fe14c1c7c6c199e6d6d8a33ec47e438a46
-  data.tar.gz: 24442ecac5ee2ed427de851eb5de4081ab8bb4a8625cdcaa2c9d4a84da86c79feaf3b02928ebee22462b2963a94ea9683fde5a47a3e6a35400d9ace2f3b13489
+  metadata.gz: ebf1cd2a7c1077f71d6f41037f0ad341c06e6bbb305bfa030833956feb0bb80576e2eaa5fd7324000ff95834f8c125cafc40a782ac97c16c7e3c7e7c02166794
+  data.tar.gz: a4cc257441939fbc0dd59dffe2d3faf11ade63b89fa2637bee8b54df7ea9e31a2ec5612d366ec9208856d750deac8fe10f1ddcaab6f9bf21996e6aa52c775e90

data/CHANGELOG.md

@@ -2,9 +2,21 @@
 
 ***
 
+Change log v.0.2.31
+
+**Broke**: Broke the fix for issue #65 so that Radio buttons data might be lost... working on a fix.
+
+**Fix**: Fixed issue #82 (reintroduction of issue #19 due to core engine rewrite) related to a workaround for an issue with AcrobatReader. Credit to @gyuchang for testing and helping with the fix.
+
+**Merge**: Merged pull request #80, fixing an issue with byte decoding. Credit to @gyuchang for the PR.
+
+**Performance**: Improved performance for the reference and duplicate object resolution. Credit to @gyuchang for pointing some optimization options.
+
+***
+
 Change log v.0.2.30
 
-**Fix**: Fixed an issue where HTTP artifacts before the beginning of a PDF file / string would prevent the PDF from being parsed. This fixes issue #78 reported by @robvitaro.
+**Fix**: Fixed an issue where HTTP artifacts before the beginning of a PDF file / string would prevent the PDF from being parsed. This should fix issue #78 reported by @robvitaro.
 
 ***
 

data/lib/combine_pdf/parser.rb

@@ -200,7 +200,7 @@ module CombinePDF
           # 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 colsed using 'endstream'!" unless str
+          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)

data/lib/combine_pdf/pdf_protected.rb

@@ -19,84 +19,42 @@ module CombinePDF
     # this function adds the references contained in `@objects`.
     #
     # this is used for internal operations, such as injectng data using the << operator.
-    def add_referenced
+    def add_referenced(should_resolve = [])
       # add references but not root
-      should_resolve = @objects.dup
       dup_pages = nil
-      resolved = [].to_set
+      # an existing object map
+      resolved = {}.dup
+      existing = {}.dup
+      @objects.each { |obj| existing[obj] = obj }
+      # loop until should_resolve is empty
       while should_resolve.any?
         obj = should_resolve.pop
+        next if resolved[obj.object_id] # the object exists
         if obj.is_a?(Hash)
-          next if resolved.include? obj.object_id
-          resolved << obj.object_id
-          if obj[:referenced_object]
-            tmp = @objects.find_index(obj[:referenced_object])
+          referenced = obj[:referenced_object]
+          if referenced && referenced.any?
+            tmp = resolved[referenced.object_id] || existing[referenced]
             if tmp
-              tmp = @objects[tmp]
               obj[:referenced_object] = tmp
             else
-              tmp = obj[:referenced_object]
-              should_resolve << tmp
-              @objects << tmp
+              resolved[obj.object_id] = referenced
+              existing[referenced] = referenced
+              should_resolve << referenced
+              @objects << referenced
             end
           else
-            obj.keys.each { |k| should_resolve << obj[k] unless k == :Parent || resolved.include?(obj[k].object_id) || !obj[k].is_a?(Enumerable) }
+            resolved[obj.object_id] = obj
+            obj.keys.each { |k| should_resolve << obj[k] unless !obj[k].is_a?(Enumerable) || resolved[obj[k].object_id] }
           end
         elsif obj.is_a?(Array)
-          next if resolved.include? obj.object_id
-          resolved << obj.object_id
+          resolved[obj.object_id] = obj
           should_resolve.concat obj
         end
       end
       resolved.clear
+      existing.clear
     end
 
-    # # @private
-    # # Some PDF objects contain references to other PDF objects.
-    # #
-    # # this function adds the references contained in "object", but DOESN'T add the object itself.
-    # #
-    # # 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
-    #   if object.is_a?(Array)
-    #     object.each { |it| add_referenced(it, dup_pages) }
-    #     return true
-    #   elsif object.is_a?(Hash)
-    #     # first if statement is actually a workaround for a bug in Acrobat Reader, regarding duplicate pages.
-    #     if dup_pages && object[:is_reference_only] && object[:referenced_object] && object[:referenced_object].is_a?(Hash) && object[:referenced_object][:Type] == :Page
-    #       if @objects.find_index object[:referenced_object]
-    #         @objects << (object[:referenced_object] = object[:referenced_object].dup)
-    #       else
-    #         @objects << object[:referenced_object]
-    #       end
-    #     elsif object[:is_reference_only] && object[:referenced_object]
-    #       found_at = @objects.find_index object[:referenced_object]
-    #       if found_at
-    #         # if the objects are equal, they might still be different objects!
-    #         # so, we need to make sure they are the same object for the pointers to effect id numbering
-    #         # and formatting operations.
-    #         object[:referenced_object] = @objects[found_at]
-    #         # stop this path, there is no need to run over the Hash's keys and values
-    #         return true
-    #       else
-    #         # stop if page propegation is false
-    #         return true if !dup_pages && object[:referenced_object][:Type] == :Page
-    #         # @objects.include? object[:referenced_object] is bound to be false
-    #         # the object wasn't found - add it to the @objects array
-    #         @objects << object[:referenced_object]
-    #       end
-    #
-    #     end
-    #     object.each do |k, v|
-    #         add_referenced(v, dup_pages) unless RECORSIVE_PROTECTION[k]
-    #     end
-    #   else
-    #     return false
-    #   end
-    #   true
-    # end
-
     # @private
     def rebuild_catalog(*with_pages)
       # # build page list v.1 Slow but WORKS
@@ -113,38 +71,62 @@ module CombinePDF
       # add pages to catalog, if requested
       page_list.concat(with_pages) unless with_pages.empty?
 
+      # duplicate any non-unique pages - This is a special case to resolve Adobe Acrobat Reader issues (see issues #19 and #81)
+      uniqueness = {}.dup
+      page_list.each { |page| page = page.dup if uniqueness[page.object_id]; uniqueness[page.object_id] = page }
+      page_list.clear
+      page_list = uniqueness.values
+      uniqueness.clear
+
       # build new Pages object
-      pages_object = { Type: :Pages, Count: page_list.length, Kids: page_list.map { |p| { referenced_object: p, is_reference_only: true } } }
+      page_object_kids = [].dup
+      pages_object = { Type: :Pages, Count: page_list.length, Kids: page_object_kids }
+      pages_object_reference = { referenced_object: pages_object, is_reference_only: true }
+      page_list.each { |pg| pg[:Parent] = pages_object_reference; page_object_kids << ({ referenced_object: pg, is_reference_only: true }) }
 
       # 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 },
-                         Outlines: { referenced_object: @outlines, is_reference_only: true } }
+                         Pages: { referenced_object: pages_object, is_reference_only: true } }
+      # pages_object[:Parent] = { referenced_object: catalog_object, is_reference_only: true } # causes AcrobatReader to fail
       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: (@forms_data[:referenced_object] || @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 } }
       ## or should we, go over structure? (fails)
       # each_object {|obj| obj[:Parent][:referenced_object] = pages_object if obj.is_a?(Hash) && obj[:Parent].is_a?(Hash) && obj[:Parent][:referenced_object] && obj[:Parent][:referenced_object][:Type] == :Pages}
 
-      # remove old catalog and pages objects
-      @objects.reject! { |obj| obj.is_a?(Hash) && (obj[:Type] == :Catalog || obj[:Type] == :Pages) }
+      # # remove old catalog and pages objects
+      # @objects.reject! { |obj| obj.is_a?(Hash) && (obj[:Type] == :Catalog || obj[:Type] == :Pages) }
+      # remove old objects list and trees
+      @objects.clear
 
       # inject new catalog and pages objects
-      @objects << pages_object
+      @objects << @info if @info
       @objects << catalog_object
+      @objects << pages_object
+
+      # rebuild/rename the forms dictionary
+      if @forms_data.nil? || @forms_data.empty?
+        @forms_data = nil
+      else
+        @forms_data = { referenced_object: (@forms_data[:referenced_object] || @forms_data), is_reference_only: true }
+        catalog_object[:AcroForm] = @forms_data
+        @objects << @forms_data[:referenced_object]
+      end
+
+      # add the names dictionary
+      if @names && @names.length > 1
+        @objects << @names
+        catalog_object[:Names] = { referenced_object: @names, is_reference_only: true }
+      end
+      # add the outlines dictionary
+      if @outlines && @outlines.any?
+        @objects << @outlines
+        catalog_object[:Outlines] = { referenced_object: @outlines, is_reference_only: true }
+      end
 
       catalog_object
     end
@@ -166,26 +148,9 @@ module CombinePDF
     # there is no point is calling the method before preparing the output.
     def rebuild_catalog_and_objects
       catalog = rebuild_catalog
-      @objects.clear
-      @objects << @info
-      @objects << catalog
-      # fix Acrobat Reader issue with page reference uniqueness (must be unique or older Acrobat Reader fails)
-      catalog[:Pages][:referenced_object][:Kids].each do |page|
-        tmp = page[:referenced_object]
-        tmp = page[:referenced_object] = tmp.dup if @objects.include? tmp
-        @objects << tmp
-      end
+      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
-      # puts (Benchmark.measure do
-      add_referenced
-      # end)
-      # @objects << @info
-      # add_referenced @info
-      # add_referenced catalog
-      # add_referenced catalog[:Pages]
-      # add_referenced catalog[:Names], false
-      # add_referenced catalog[:Outlines], false
-      # add_referenced catalog[:AcroForm], false
+      add_referenced([page_objects, @forms_data, @names, @outlines, @info])
       catalog
     end
 
@@ -304,9 +269,9 @@ module CombinePDF
         # parent - the outline base node of the resulting merged outline
         # FIXME implement the possibility to insert somewhere in the middle of the outline
         prev = nil
-        pos = first = actual_object(((position != 0) ? old_data : new_data)[:First])
-        last = actual_object(((position != 0) ? new_data : old_data)[:Last])
-        median = { is_reference_only: true, referenced_object: actual_object(((position != 0) ? new_data : old_data)[:First]) }
+        pos = first = actual_object((position.nonzero? ? old_data : new_data)[:First])
+        last = actual_object((position.nonzero? ? new_data : old_data)[:Last])
+        median = { is_reference_only: true, referenced_object: actual_object((position.nonzero? ? new_data : old_data)[:First]) }
         old_data[:First] = { is_reference_only: true, referenced_object: first }
         old_data[:Last] = { is_reference_only: true, referenced_object: last }
         parent = { is_reference_only: true, referenced_object: old_data }

data/lib/combine_pdf/renderer.rb

@@ -21,7 +21,7 @@ module CombinePDF
       elsif object.is_a?(Array)
         return format_array_to_pdf object
       elsif object.is_a?(Fixnum) || object.is_a?(Float) || object.is_a?(TrueClass) || object.is_a?(FalseClass)
-        return object.to_s + ' '
+        return object.to_s
       elsif object.is_a?(Hash)
         return format_hash_to_pdf object
       else
@@ -33,12 +33,12 @@ module CombinePDF
                                 "\x0D" => '\\r',
                                 "\x09" => '\\t',
                                 "\x08" => '\\b',
-                                "\xFF" => '\\f',
+                                "\x0C" => '\\f', # form-feed (\f) == 0x0C
                                 "\x28" => '\\(',
                                 "\x29" => '\\)',
                                 "\x5C" => '\\\\' }.dup
     32.times { |i| STRING_REPLACEMENT_HASH[i.chr] ||= "\\#{i}" }
-    (256 - 128).times { |i| STRING_REPLACEMENT_HASH[(i + 127).chr] ||= "\\#{i + 127}" }
+    (256 - 127).times { |i| STRING_REPLACEMENT_HASH[(i + 127).chr] ||= "\\#{i + 127}" }
 
     def format_string_to_pdf(object)
       # object.force_encoding(Encoding::ASCII_8BIT)

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '0.2.30'.freeze
+  VERSION = '0.2.31'.freeze
 end

data/test/automated

@@ -28,15 +28,16 @@ pdf = CombinePDF.load './Ruby/test pdfs/names_go_haywire_0.pdf'
 pdf << CombinePDF.load('./Ruby/test pdfs/names_go_haywire_1.pdf')
 pdf.save '04_check_view_and_names_reference.pdf'
 
-str = IO.binread './Ruby/test pdfs/outlines/self_merge_err.pdf'
+pdf = CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
+pdf.save '05_x1_scribus_test.pdf'
 pdf = CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
 pdf << CombinePDF.load('./Ruby/test pdfs/outlines/self_merge_err.pdf')
-pdf.save '05_scribus_test.pdf'
+pdf.save '05_x2_scribus_test.pdf'
 # pdf = CombinePDF.load "./Ruby/test pdfs/named_dest.pdf";nil
 # pdf.save '05_check_named_dest_links.pdf' # this will take a while
 # pdf = CombinePDF.load "./Ruby/test pdfs/named_dest.pdf";nil
-# pdf << CombinePDF.load("./Ruby/test pdfs/named_dest.pdf");nil
-# pdf.save '05_1_check_named_dest_links.pdf' # never ends... :-(
+pdf << CombinePDF.load('./Ruby/test pdfs/named_dest.pdf'); nil
+pdf.save '05_1_timeless_check_named_dest_links.pdf' # never ends... :-(
 
 pdf = CombinePDF.load './Ruby/test pdfs/outline_small.pdf'
 pdf << CombinePDF.load('./Ruby/test pdfs/outline_small.pdf')
@@ -55,6 +56,17 @@ CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err2.pdf").save '08_2-unknown
 CombinePDF.load("./Ruby/test\ pdfs/Scribus-unknown_err3.pdf").save '08_3-unknown-err-empty-str.pdf'
 
 CombinePDF.load("/Users/2Be/Ruby/test\ pdfs/nil_object.pdf").save('09_nil_in_parsed_array.pdf')
+
+require 'prawn'
+IO.binwrite '10_prawn.pdf', (Prawn::Document.new { text 'Hello World!' }).render
+page = CombinePDF.parse((Prawn::Document.new { text 'Hello World!' }).render)
+pdf = CombinePDF.new
+pdf << page
+pdf.save '10_parsed_from_prawn.pdf'
+pdf = CombinePDF.new
+pdf << page << page
+pdf.save('10_AcrobatReader_is_unique_page.pdf')
+
 # unify = [
 #   "./Ruby/test\ pdfs/AESv2\ encrypted.pdf",
 #   "./Ruby/test\ pdfs/data-in-comment.pdf",

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 0.2.30
+  version: 0.2.31
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-07-27 00:00:00.000000000 Z
+date: 2016-08-22 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4
@@ -111,4 +111,3 @@ test_files:
 - test/automated
 - test/console
 - test/named_dest
-has_rdoc: