combine_pdf 1.0.7 → 1.0.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 26b12c91a180581e3aab431bac1cb46b0d9cecb1
-  data.tar.gz: f9fe760a66b6a8314106faab6c5b2a45a889e440
+SHA256:
+  metadata.gz: 9e5d5d814a254c4939fa88b782ebe49057b917d81134c3fc94385eb19d814092
+  data.tar.gz: b43a6e98d54ca72f7f13600898bdf1d6bbe0614276d411f8575ed9c1fe54c3d0
 SHA512:
-  metadata.gz: 72f53db4e8cb69b52fa8044bffe42acb21f683fd39afdd7bbf96a924916775fb2ac338c2fb4f5ddd23d0685d0442ec3acc9ee0416581c9f82b576e86beea6c45
-  data.tar.gz: a555bd19c697042ee8e75742b7a6f0e14282abf650443571bef157c39d4d34d4ab70fa3b7ed7acee9aa49dcd045bacced91ea01fd58f7bb31763614debc8083c
+  metadata.gz: 061b5aa579f0dd243eb2602150933a00258d54cf22504ba3d15355ff6593f25f3b429e7b752d3f81172e5d3a3186f03b345e228d447236732bf20edf38336686
+  data.tar.gz: db6820d4af86523dd174f25885e7ab5378bdb176bff40fbb20d58203af264df2c2811a4767b41a2ccf84b3391fa9c3046bfb6efa5ed614c24f0ddf3d52439aa1

data/CHANGELOG.md

@@ -2,6 +2,18 @@
 
 ***
 
+#### Change log v.1.0.8
+
+**Fix**: Fixed an issue with octal representation in escaped string data. The issue would (usually) go unnoticed (altering internal labels in a non-disruptive manner), however the issue did effect `ColorSpace` data in the rare use of `ICCBased` color maps, causing color distortion and transparency loss.
+
+**Fix**: Fixed an issue with non English alphabet in PDF literal strings. This issue went undetected since PDF literal strings aren't used by CombinePDF except for the date stamping...
+
+**Fix**: Improbable, but possibly a fix for issue #127, where the JRuby interpreter would fail to pass the correct arguments to the Hash update Proc. Since I'm trying to author a workaround, I have my doubts... but an attempt is better than nothing.
+
+**Update**: Improved parsing error handling, courtesy of Evgeny Garlukovich (@evgenygarl).
+
+**Update**: Added reader methods for the `names` and `outlines` PDF objects in response to issue #133. Use with care.
+
 #### Change log v.1.0.7
 
 **Fix**: Fix an issue where page property inheritance might break PDF structure if there's a conflict between property types (inheritance using properties by reference vs. nested properties), fixing issue #124. Credit to @erikaxel for exposing the issue.

data/lib/combine_pdf/parser.rb

@@ -6,6 +6,8 @@
 ########################################################
 
 module CombinePDF
+  ParsingError = Class.new(StandardError)
+
   # @!visibility private
   # @private
   #:nodoc: all
@@ -77,7 +79,9 @@ module CombinePDF
       @parsed = _parse_
       # puts @parsed
 
-      raise 'Unknown PDF parsing error - malformed PDF file?' unless (@parsed.select { |i| !i.is_a?(Hash) }).empty?
+      unless (@parsed.select { |i| !i.is_a?(Hash) }).empty?
+        raise ParsingError, 'Unknown PDF parsing error - malformed PDF file?'
+      end
 
       if @root_object == {}.freeze
         xref_streams = @parsed.select { |obj| obj.is_a?(Hash) && obj[:Type] == :XRef }
@@ -86,7 +90,9 @@ module CombinePDF
         end
       end
 
-      raise 'root is unknown - cannot determine if file is Encrypted' if @root_object == {}.freeze
+      if @root_object == {}.freeze
+        raise ParsingError, 'root is unknown - cannot determine if file is Encrypted'
+      end
 
       if @root_object[:Encrypt]
         # change_references_to_actual_values @root_object
@@ -310,10 +316,10 @@ module CombinePDF
               when 102 # f, form-feed
                 str << 12
               when 48..57 # octal notation for byte?
-                rep = rep.chr
-                rep += str_bytes.shift.chr if str_bytes[0].between?(48, 57)
-                rep += str_bytes.shift.chr if str_bytes[0].between?(48, 57) && ((rep + str_bytes[0].chr).to_i <= 255)
-                str << rep.to_i
+                rep -= 48
+                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0].between?(48, 57)
+                rep = (rep << 3) + (str_bytes.shift-48) if str_bytes[0].between?(48, 57) && (((rep << 3) + (str_bytes[0] - 48)) <= 255)
+                str << rep
               when 10 # new line, ignore
                 str_bytes.shift if str_bytes[0] == 13
                 true
@@ -350,8 +356,12 @@ module CombinePDF
           # 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
+          unless str
+            raise ParsingError, "Parsing Error: PDF file error - a stream object wasn't properly closed using 'endstream'!"
+          end
+
           # 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)
@@ -475,7 +485,9 @@ module CombinePDF
         @parsed.delete_if { |obj| obj.nil? || obj[:Type] == :Catalog }
         @parsed << catalogs
 
-        raise "Unknown error - parsed data doesn't contain a cataloged object!" unless catalogs
+        unless catalogs
+          raise ParsingError, "Unknown error - parsed data doesn't contain a cataloged object!"
+        end
       end
       if catalogs.is_a?(Array)
         catalogs.each { |c| catalog_pages(c, inheritance_hash) unless c.nil? }
@@ -488,20 +500,23 @@ module CombinePDF
           end
         else
           unless catalogs[:Type] == :Page
-            raise "Optional Content PDF files aren't supported and their pages cannot be safely extracted." if (catalogs[:AS] || catalogs[:OCProperties]) && !@allow_optional_content
+            if (catalogs[:AS] || catalogs[:OCProperties]) && !@allow_optional_content
+              raise ParsingError, "Optional Content PDF files aren't supported and their pages cannot be safely extracted."
+            end
+
             inheritance_hash[:MediaBox] = catalogs[:MediaBox] if catalogs[:MediaBox]
             inheritance_hash[:CropBox] = catalogs[:CropBox] if catalogs[:CropBox]
             inheritance_hash[:Rotate] = catalogs[:Rotate] if catalogs[:Rotate]
             if catalogs[:Resources]
               inheritance_hash[:Resources] ||= { referenced_object: {}, is_reference_only: true }.dup
-              (inheritance_hash[:Resources][:referenced_object] || inheritance_hash[:Resources]).update((catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &self.class.method(:hash_update_proc_for_old))
+              (inheritance_hash[:Resources][:referenced_object] || inheritance_hash[:Resources]).update((catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &HASH_UPDATE_PROC_FOR_OLD)
             end
             if catalogs[:ColorSpace]
               inheritance_hash[:ColorSpace] ||= { referenced_object: {}, is_reference_only: true }.dup
-              (inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]).update((catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &self.class.method(:hash_update_proc_for_old))
+              (inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]).update((catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &HASH_UPDATE_PROC_FOR_OLD)
             end
-            # (inheritance_hash[:Resources] ||= {}).update((catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &self.class.method(:hash_update_proc_for_new)) if catalogs[:Resources]
-            # (inheritance_hash[:ColorSpace] ||= {}).update((catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &self.class.method(:hash_update_proc_for_new)) if catalogs[:ColorSpace]
+            # (inheritance_hash[:Resources] ||= {}).update((catalogs[:Resources][:referenced_object] || catalogs[:Resources]), &HASH_UPDATE_PROC_FOR_NEW) if catalogs[:Resources]
+            # (inheritance_hash[:ColorSpace] ||= {}).update((catalogs[:ColorSpace][:referenced_object] || catalogs[:ColorSpace]), &HASH_UPDATE_PROC_FOR_NEW) if catalogs[:ColorSpace]
 
             # inheritance_hash[:Order] = catalogs[:Order] if catalogs[:Order]
             # inheritance_hash[:OCProperties] = catalogs[:OCProperties] if catalogs[:OCProperties]
@@ -517,14 +532,14 @@ module CombinePDF
             if inheritance_hash[:Resources]
               catalogs[:Resources] ||= { referenced_object: {}, is_reference_only: true }.dup
               catalogs[:Resources] = { referenced_object: catalogs[:Resources], is_reference_only: true } unless catalogs[:Resources][:referenced_object]
-              catalogs[:Resources][:referenced_object].update((inheritance_hash[:Resources][:referenced_object] || inheritance_hash[:Resources]), &self.class.method(:hash_update_proc_for_old))
+              catalogs[:Resources][:referenced_object].update((inheritance_hash[:Resources][:referenced_object] || inheritance_hash[:Resources]), &HASH_UPDATE_PROC_FOR_OLD)
             end
             if inheritance_hash[:ColorSpace]
               catalogs[:ColorSpace] ||= { referenced_object: {}, is_reference_only: true }.dup
               catalogs[:ColorSpace] = { referenced_object: catalogs[:ColorSpace], is_reference_only: true } unless catalogs[:ColorSpace][:referenced_object]
-              catalogs[:ColorSpace][:referenced_object].update((inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]), &self.class.method(:hash_update_proc_for_old))
+              catalogs[:ColorSpace][:referenced_object].update((inheritance_hash[:ColorSpace][:referenced_object] || inheritance_hash[:ColorSpace]), &HASH_UPDATE_PROC_FOR_OLD)
             end
-            # (catalogs[:ColorSpace] ||= {}).update(inheritance_hash[:ColorSpace], &self.class.method(:hash_update_proc_for_old)) if inheritance_hash[:ColorSpace]
+            # (catalogs[:ColorSpace] ||= {}).update(inheritance_hash[:ColorSpace], &HASH_UPDATE_PROC_FOR_OLD) if inheritance_hash[:ColorSpace]
             # catalogs[:Order] ||= inheritance_hash[:Order] if inheritance_hash[:Order]
             # catalogs[:AS] ||= inheritance_hash[:AS] if inheritance_hash[:AS]
             # catalogs[:OCProperties] ||= inheritance_hash[:OCProperties] if inheritance_hash[:OCProperties]
@@ -538,9 +553,9 @@ 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]
-            @outlines_object.update((catalogs[:Outlines][:referenced_object] || catalogs[:Outlines]), &self.class.method(:hash_update_proc_for_new)) if catalogs[:Outlines]
+            @forms_object.update((catalogs[:AcroForm][:referenced_object] || catalogs[:AcroForm]), &HASH_UPDATE_PROC_FOR_NEW) if catalogs[:AcroForm]
+            @names_object.update((catalogs[:Names][:referenced_object] || catalogs[:Names]), &HASH_UPDATE_PROC_FOR_NEW) if catalogs[:Names]
+            @outlines_object.update((catalogs[:Outlines][:referenced_object] || catalogs[:Outlines]), &HASH_UPDATE_PROC_FOR_NEW) if catalogs[:Outlines]
             if catalogs[:Dests] # convert PDF 1.1 Dests to PDF 1.2+ Dests
               dests_arry = (@names_object[:Dests] ||= {})
               dests_arry = ((dests_arry[:referenced_object] || dests_arry)[:Names] ||= [])
@@ -654,30 +669,45 @@ module CombinePDF
 
     # All Strings are one String
     def unify_string(str)
+      str.force_encoding(Encoding::ASCII_8BIT)
       @strings_dictionary[str] ||= str
     end
 
     # @private
     # this method reviews a Hash and updates it by merging Hash data,
     # preffering the old over the new.
-    def self.hash_update_proc_for_old(_key, old_data, new_data)
+    HASH_UPDATE_PROC_FOR_OLD = Proc.new do |_key, old_data, new_data|
       if old_data.is_a? Hash
-        old_data.merge(new_data, &method(:hash_update_proc_for_old))
+        old_data.merge(new_data, &HASH_UPDATE_PROC_FOR_OLD)
       else
         old_data
       end
     end
+    # def self.hash_update_proc_for_old(_key, old_data, new_data)
+    #   if old_data.is_a? Hash
+    #     old_data.merge(new_data, &method(:hash_update_proc_for_old))
+    #   else
+    #     old_data
+    #   end
+    # end
 
     # @private
     # this method reviews a Hash an updates it by merging Hash data,
     # preffering the new over the old.
-    def self.hash_update_proc_for_new(_key, old_data, new_data)
+    HASH_UPDATE_PROC_FOR_NEW = Proc.new do |_key, old_data, new_data|
       if old_data.is_a? Hash
-        old_data.merge(new_data, &method(:hash_update_proc_for_new))
+        old_data.merge(new_data, &HASH_UPDATE_PROC_FOR_NEW)
       else
         new_data
       end
     end
+    # def self.hash_update_proc_for_new(_key, old_data, new_data)
+    #   if old_data.is_a? Hash
+    #     old_data.merge(new_data, &method(:hash_update_proc_for_new))
+    #   else
+    #     new_data
+    #   end
+    # end
 
     # # run block of code on evey PDF object (PDF objects are class Hash)
     # def each_object(object, limit_references = true, already_visited = {}, &block)

data/lib/combine_pdf/pdf_protected.rb

@@ -137,11 +137,14 @@ module CombinePDF
       catalog_object
     end
 
+    # Deprecation Notice
     def names_object
+      puts "CombinePDF Deprecation Notice: the protected method `names_object` will be deprecated in the upcoming version. Use `names` instead."
       @names
     end
 
     def outlines_object
+      puts "CombinePDF Deprecation Notice: the protected method `outlines_object` will be deprecated in the upcoming version. Use `oulines` instead."
       @outlines
     end
     # def forms_data

data/lib/combine_pdf/pdf_public.rb

@@ -82,6 +82,10 @@ module CombinePDF
     # use, for example:
     #   pdf.viewer_preferences[:HideMenubar] = true
     attr_reader :viewer_preferences
+    # Access the Outlines PDF object Hash (or reference). Use with care.
+    attr_reader :outlines
+    # Access the Names PDF object Hash (or reference). Use with care.
+    attr_reader :names
 
     def initialize(parser = nil)
       # default before setting
@@ -207,7 +211,7 @@ module CombinePDF
       # when finished, remove the numbering system and keep only pointers
       remove_old_ids
       # output the pdf stream
-      out.join("\n").force_encoding(Encoding::ASCII_8BIT)
+      out.join("\n".force_encoding(Encoding::ASCII_8BIT)).force_encoding(Encoding::ASCII_8BIT)
     end
 
     # this method returns all the pages cataloged in the catalog.
@@ -302,8 +306,8 @@ module CombinePDF
       if data.is_a? PDF
         @version = [@version, data.version].max
         pages_to_add = data.pages
-        actual_value(@names ||= {}.dup).update actual_value(data.names_object), &self.class.method(:hash_merge_new_no_page)
-        merge_outlines((@outlines ||= {}.dup), data.outlines_object, location) unless actual_value(data.outlines_object).empty?
+        actual_value(@names ||= {}.dup).update data.names, &self.class.method(:hash_merge_new_no_page)
+        merge_outlines((@outlines ||= {}.dup), actual_value(data.outlines), location) unless actual_value(data.outlines).empty?
         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

data/lib/combine_pdf/renderer.rb

@@ -29,25 +29,30 @@ module CombinePDF
       end
     end
 
-    STRING_REPLACEMENT_HASH = { "\x0A" => '\\n',
-                                "\x0D" => '\\r',
-                                "\x09" => '\\t',
-                                "\x08" => '\\b',
-                                "\x0C" => '\\f', # form-feed (\f) == 0x0C
-                                "\x28" => '\\(',
-                                "\x29" => '\\)',
-                                "\x5C" => '\\\\' }.dup
-    32.times { |i| STRING_REPLACEMENT_HASH[i.chr] ||= "\\#{i}" }
-    (256 - 127).times { |i| STRING_REPLACEMENT_HASH[(i + 127).chr] ||= "\\#{i + 127}" }
+    STRING_REPLACEMENT_ARRAY = []
+    256.times {|i| STRING_REPLACEMENT_ARRAY[i] = [i]}
+    8.times { |i| STRING_REPLACEMENT_ARRAY[i] =  "\\00#{i.to_s(8)}".bytes.to_a }
+    24.times { |i| STRING_REPLACEMENT_ARRAY[i + 7] =  "\\0#{i.to_s(8)}".bytes.to_a }
+    (256 - 127).times { |i| STRING_REPLACEMENT_ARRAY[(i + 127)] ||= "\\#{(i + 127).to_s(8)}".bytes.to_a }
+    STRING_REPLACEMENT_ARRAY[0x0A] = '\\n'.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x0D] = '\\r'.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x09] = '\\t'.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x08] = '\\b'.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x0C] = '\\f'.bytes.to_a # form-feed (\f) == 0x0C
+    STRING_REPLACEMENT_ARRAY[0x28] = '\\('.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x29] = '\\)'.bytes.to_a
+    STRING_REPLACEMENT_ARRAY[0x5C] = '\\\\'.bytes.to_a
 
     def format_string_to_pdf(object)
+      obj_bytes = object.bytes.to_a
       # object.force_encoding(Encoding::ASCII_8BIT)
-      if !object.match(/[^D\:\d\+\-Z\']/) # if format is set to Literal and string isn't a date
-        ('(' + ([].tap { |out| object.bytes.to_a.each { |byte| STRING_REPLACEMENT_HASH[byte.chr] ? (STRING_REPLACEMENT_HASH[byte.chr].bytes.each { |b| out << b }) : out << byte } }).pack('C*') + ')').force_encoding(Encoding::ASCII_8BIT)
-      else
+      if object.length == 0 || obj_bytes.min <= 31 || obj_bytes.max >= 127 # || (obj_bytes[0] != 68  object.match(/[^D\:\d\+\-Z\']/))
         # A hexadecimal string shall be written as a sequence of hexadecimal digits (0–9 and either A–F or a–f)
         # encoded as ASCII characters and enclosed within angle brackets (using LESS-THAN SIGN (3Ch) and GREATER- THAN SIGN (3Eh)).
         "<#{object.unpack('H*')[0]}>".force_encoding(Encoding::ASCII_8BIT)
+      else
+        # a good fit for a Literal String or the string is a date (MUST be literal)
+        ('(' + ([].tap { |out| obj_bytes.each { |byte| out.concat(STRING_REPLACEMENT_ARRAY[byte]) } } ).pack('C*') + ')').force_encoding(Encoding::ASCII_8BIT)
       end
     end
 

data/lib/combine_pdf/version.rb

@@ -1,3 +1,3 @@
 module CombinePDF
-  VERSION = '1.0.7'.freeze
+  VERSION = '1.0.8'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.7
+  version: 1.0.8
 platform: ruby
 authors:
 - Boaz Segev
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-02 00:00:00.000000000 Z
+date: 2018-02-02 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: 2.6.11
+rubygems_version: 2.7.3
 signing_key: 
 specification_version: 4
 summary: Combine, stamp and watermark PDF files in pure Ruby.