combine_pdf 1.0.25 → 1.0.27

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 54586af58c21708b23e6c368b9a0841b4363ebd8113103d9d37deb045032485f
-  data.tar.gz: 121335c835d1902872e6b53de3b8bfc798dce9c83c0fdfaa0927c47e2771d0cc
+  metadata.gz: 2ccb4f95b5400a214f06d343f8b0a5b1a7a38b94ce400f2bbe80cefccd902005
+  data.tar.gz: a923391ccc4a37ccf77b89a5113e723d1065e09f0404f0e9c5104034d679363e
 SHA512:
-  metadata.gz: a52629b113303a5df9000ac65d33fa5d7843ee74d8977ee7005ae43a476e63917fb462265915b25f8b5b7c6e902cf9a0f4d36f504dbc47651015c058b322c96b
-  data.tar.gz: 6fb00ab0f0ad9e482a850402e83183e9c1fbc0603093d069930a42ba51d704a4cad5cfb8086a27123cbe06f8b735dade401dc014b843b542cb8b1f84d0a680e0
+  metadata.gz: cc63f8c2c83a90a23579a517314248924207b578fc713c520c0ac4596c214cc2c7df50a173638e0659f58e62ae19ae0958b72eb29b6ed29f27d6ea65b9cdf88f
+  data.tar.gz: 840b62aa7abda71f22c4b83b697046a666043b73d063f5f60046cb76ed9d6f97086d4e7dc9645ece7ef97184d6e38523d90376ba9d55f9138e0b68519ce8b55e

data/.github/workflows/main.yml

@@ -9,7 +9,11 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        ruby: ["2.7", "3.0", "3.1", "3.2"]
+        ruby: ["2.7", "3.0", "3.1", "3.2", "3.3"]
+        rubyopt: [""]
+        include:
+          - ruby: "3.3"
+            rubyopt: "--enable-frozen-string-literal --debug-frozen-string-literal"
 
     steps:
       - name: Checkout code
@@ -25,4 +29,4 @@ jobs:
         run: bundle lock
 
       - name: Run tests
-        run: bundle exec rake test
+        run: bundle exec rake test RUBYOPT="${{ matrix.rubyopt }}"

data/CHANGELOG.md

@@ -1,8 +1,12 @@
 # Change Log
 
+#### Change log v.1.0.26 (2023-12-22)
+
+**Performance**: possible performance bump. Credit to @denislavski (Denislav Naydenov) for opening PR #235.
+
 #### Change log v.1.0.25 (2023-12-19)
 
-**Fix**: possible improve memory usage. Credit to @denislavski (Denislav Naydenov) for opening PR #223 and suggesting this change.
+**Fix**: possible improve memory usage. Credit to @denislavski (Denislav Naydenov) for opening PR #233 and suggesting this change.
 
 #### Change log v.1.0.24 (2023-10-19)
 

data/README.md

@@ -7,23 +7,23 @@
 
 CombinePDF is a nifty model, written in pure Ruby, to parse PDF files and combine (merge) them with other PDF files, watermark them or stamp them (all using the PDF file format and pure Ruby code).
 
-## Install
+## Unmaintained - Help Wanted(!)
 
-Install with ruby gems:
+I decided to stop maintaining this gem and hope someone could take over the PR reviews and maintenance of this gem (or simply open a successful fork).
 
-```ruby
-gem install combine_pdf
-```
+I wrote this gem because I needed to solve an issue with bates-numbering existing PDF documents.
 
-## Help Wanted
+However, since 2014 I have been maintaining the gem for free and for no reason at all, except that I enjoyed sharing it with the community.
 
-I need help maintaining the CombinePDF Ruby gem.
+I love this gem, but I cannot keep maintaining it as I have my own projects to focus own and I need both the time and (more importantly) the mindspace.
 
-I wrote this gem because I needed to solve an issue with bates-numbering existing PDF documents. However, during the last three years or so I have been maintaining the project for no reason at all, except that I enjoyed sharing it with the community.
+## Install
 
-I love this gem, but I feel it's time I took a step back from maintaining it and concentrate on my music and other things I want to develop.
+Install with ruby gems:
 
-Please hit me up if you would like to join in and eventually take over.
+```ruby
+gem install combine_pdf
+```
 
 ## Known Limitations
 

data/lib/combine_pdf/api.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 
 module CombinePDF
   module_function

data/lib/combine_pdf/basic_writer.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code

data/lib/combine_pdf/decrypt.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code
@@ -137,7 +138,7 @@ module CombinePDF
       object_key = @key.dup
       object_key << [encrypted_id].pack('i')[0..2]
       object_key << [encrypted_generation].pack('i')[0..1]
-      object_key << 'sAlT'.force_encoding(Encoding::ASCII_8BIT)
+      object_key << 'sAlT'.b
       key_length = object_key.length < 16 ? object_key.length : 16
 
       begin

data/lib/combine_pdf/exceptions.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module CombinePDF
   class EncryptionError < StandardError
   end

data/lib/combine_pdf/filter.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code

data/lib/combine_pdf/fonts.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code

data/lib/combine_pdf/page_methods.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code
@@ -214,7 +215,7 @@ module CombinePDF
       options[:text_padding] = 0 if options[:text_padding].to_f >= 1
 
       # create box stream
-      box_stream = ''
+      box_stream = +''
       # set graphic state for box
       if options[:box_color] || (options[:border_width].to_i > 0 && options[:border_color])
         # compute x and y position for text
@@ -290,7 +291,7 @@ module CombinePDF
       # reset x,y by text alignment - x,y are calculated from the bottom left
       # each unit (1) is 1/72 Inch
       # create text stream
-      text_stream = ''
+      text_stream = +''
       if !text.to_s.empty? && options[:font_size] != 0 && (options[:font_color] || options[:stroke_color])
         # compute x and y position for text
         x = options[:x] + (options[:width] * options[:text_padding])
@@ -679,7 +680,7 @@ module CombinePDF
       insert_content 'Q'
 
       # Prep content
-      @contents = ''
+      @contents = +''
       insert_content @contents
       @contents
     end
@@ -788,7 +789,7 @@ module CombinePDF
           # add to array
           if out.last.nil? || out.last[0] != fonts[i]
             out.last[1] << '>' unless out.last.nil?
-            out << [fonts[i], '<', 0, 0]
+            out << [fonts[i], (+'<'), 0, 0]
           end
           out.last[1] << (fonts_array[i].cmap.nil? ? (c.unpack('H*')[0]) : fonts_array[i].cmap[c])
           if fonts_array[i].metrics[c]

data/lib/combine_pdf/parser.rb

@@ -262,7 +262,7 @@ module CombinePDF
         ##########################################
         elsif @scanner.scan(/\(/)
           # warn "Found a literal string"
-          str = ''.force_encoding(Encoding::ASCII_8BIT)
+          str = ''.b
           count = 1
           while count > 0 && @scanner.rest?
             scn = @scanner.scan_until(/[\(\)]/)
@@ -369,7 +369,7 @@ module CombinePDF
           # 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:
-          
+
 
           # raise error if the stream doesn't end.
           unless @scanner.skip_until(/endstream/)
@@ -379,7 +379,7 @@ module CombinePDF
           length = 0 if(length < 0)
           length -= 1 if(@scanner.string[old_pos + length - 1] == "\n") 
           length -= 1 if(@scanner.string[old_pos + length - 1] == "\r") 
-          str = (length > 0) ? @scanner.string.slice(old_pos, length) : ''
+          str = (length > 0) ? @scanner.string.slice(old_pos, length) : +''
 
           # warn "CombinePDF parser: detected Stream #{str.length} bytes long #{str[0..3]}...#{str[-4..-1]}"
 
@@ -632,17 +632,17 @@ module CombinePDF
     #
     def serialize_objects_and_references
       obj_dir = {}
-      objid_cache = {}
+      objid_cache = {}.compare_by_identity
       # create a dictionary for referenced objects (no value resolution at this point)
       # at the same time, delete duplicates and old versions when objects have multiple versions
       @parsed.uniq!
       @parsed.length.times do |i|
         o = @parsed[i]
-        objid_cache[o.object_id] = i
+        objid_cache[o] = i
         tmp_key = [o[:indirect_reference_id], o[:indirect_generation_number]]
         if tmp_found = obj_dir[tmp_key]
           tmp_found.clear
-          @parsed[objid_cache[tmp_found.object_id]] = nil
+          @parsed[objid_cache[tmp_found]] = nil
         end
         obj_dir[tmp_key] = o
       end
@@ -765,9 +765,9 @@ module CombinePDF
     # end
 
     # # run block of code on evey PDF object (PDF objects are class Hash)
-    # def each_object(object, limit_references = true, already_visited = {}, &block)
+    # def each_object(object, limit_references = true, already_visited = {}.compare_by_identity, &block)
     # 	unless limit_references
-    # 		already_visited[object.object_id] = true
+    # 		already_visited[object] = true
     # 	end
     # 	case
     # 	when object.is_a?(Array)
@@ -776,7 +776,7 @@ module CombinePDF
     # 		yield(object)
     # 		unless limit_references && object[:is_reference_only]
     # 			object.each do |k,v|
-    # 				each_object(v, limit_references, already_visited, &block) unless already_visited[v.object_id]
+    # 				each_object(v, limit_references, already_visited, &block) unless already_visited[v]
     # 			end
     # 		end
     # 	end

data/lib/combine_pdf/pdf_protected.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 ########################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code
@@ -21,19 +22,19 @@ module CombinePDF
     # this is used for internal operations, such as injectng data using the << operator.
     def add_referenced()
       # an existing object map
-      resolved = {}.dup
-      existing = {}.dup
-      should_resolve = [].dup
+      resolved = {}.compare_by_identity
+      existing = {}
+      should_resolve = []
       #set all existing objects as resolved and register their children for future resolution
-      @objects.each { |obj| existing[obj] = obj ; resolved[obj.object_id] = obj; should_resolve << obj.values}
+      @objects.each { |obj| existing[obj] = obj ; resolved[obj] = obj; should_resolve << obj.values}
       # loop until should_resolve is empty
       while should_resolve.any?
         obj = should_resolve.pop
-        next if resolved[obj.object_id] # the object exists
+        next if resolved[obj] # the object exists
         if obj.is_a?(Hash)
           referenced = obj[:referenced_object]
           if referenced && referenced.any?
-            tmp = resolved[referenced.object_id]
+            tmp = resolved[referenced]
             if !tmp && referenced[:raw_stream_content]
               tmp = existing[referenced[:raw_stream_content]]
               # Avoid endless recursion by limiting it to a number of layers (default == 2)
@@ -42,18 +43,18 @@ module CombinePDF
             if tmp
               obj[:referenced_object] = tmp
             else
-              resolved[obj.object_id] = referenced
+              resolved[obj] = referenced
               #        existing[referenced] = referenced
               existing[referenced[:raw_stream_content]] = referenced
               should_resolve << referenced
               @objects << referenced
             end
           else
-            resolved[obj.object_id] = obj
-            obj.keys.each { |k| should_resolve << obj[k] unless !obj[k].is_a?(Enumerable) || resolved[obj[k].object_id] }
+            resolved[obj] = obj
+            obj.keys.each { |k| should_resolve << obj[k] unless !obj[k].is_a?(Enumerable) || resolved[obj[k]] }
           end
         elsif obj.is_a?(Array)
-          resolved[obj.object_id] = obj
+          resolved[obj] = obj
           should_resolve.concat obj
         end
       end
@@ -78,14 +79,14 @@ module CombinePDF
       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[:referenced_object] || page; page = page.dup if uniqueness[page.object_id]; uniqueness[page.object_id] = page }
+      uniqueness = {}.compare_by_identity
+      page_list.each { |page| page = page[:referenced_object] || page; page = page.dup if uniqueness[page]; uniqueness[page] = page }
       page_list.clear
       page_list = uniqueness.values
       uniqueness.clear
 
       # build new Pages object
-      page_object_kids = [].dup
+      page_object_kids = []
       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 }) }
@@ -186,17 +187,18 @@ module CombinePDF
     POSSIBLE_NAME_TREES = [:Dests, :AP, :Pages, :IDS, :Templates, :URLS, :JavaScript, :EmbeddedFiles, :AlternatePresentations, :Renditions].to_set.freeze
 
     def rebuild_names(name_tree = nil, base = 'CombinePDF_0000000')
+      base = +base
       if name_tree
         return nil unless name_tree.is_a?(Hash)
         name_tree = name_tree[:referenced_object] || name_tree
         dic = []
         # map a names tree and return a valid name tree. Do not recourse.
         should_resolve = [name_tree[:Kids], name_tree[:Names]]
-        resolved = [].to_set
+        resolved = Set.new.compare_by_identity
         while should_resolve.any?
           pos = should_resolve.pop
           if pos.is_a? Array
-            next if resolved.include?(pos.object_id)
+            next if resolved.include?(pos)
             if pos[0].is_a? String
               (pos.length / 2).times do |i|
                 dic << (pos[i * 2].clear << base.next!)
@@ -209,16 +211,16 @@ module CombinePDF
             end
           elsif pos.is_a? Hash
             pos = pos[:referenced_object] || pos
-            next if resolved.include?(pos.object_id)
+            next if resolved.include?(pos)
             should_resolve << pos[:Kids] if pos[:Kids]
             should_resolve << pos[:Names] if pos[:Names]
           end
-          resolved << pos.object_id
+          resolved << pos
         end
         return { referenced_object: { Names: dic }, is_reference_only: true }
       end
       @names ||= @names[:referenced_object]
-      new_names = { Type: :Names }.dup
+      new_names = { Type: :Names }
       POSSIBLE_NAME_TREES.each do |ntree|
         if @names[ntree]
           new_names[ntree] = rebuild_names(@names[ntree], base)
@@ -373,7 +375,7 @@ module CombinePDF
     private
 
     def equal_layers obj1, obj2, layer = CombinePDF.eq_depth_limit
-      return true if obj1.object_id == obj2.object_id
+      return true if obj1.equal?(obj2)
       if obj1.is_a? Hash
         return false unless obj2.is_a? Hash
         return false unless obj1.length == obj2.length

data/lib/combine_pdf/pdf_public.rb

@@ -1,5 +1,6 @@
 # -*- encoding : utf-8 -*-
-########################################################
+## frozen_string_literal: true
+#######################################################
 ## Thoughts from reading the ISO 32000-1:2008
 ## this file is part of the CombinePDF library and the code
 ## is subject to the same license.
@@ -93,7 +94,7 @@ module CombinePDF
       @version = 0
       @viewer_preferences = {}
       @info = {}
-      parser ||= PDFParser.new('')
+      parser ||= PDFParser.new(+'')
       raise TypeError, "initialization error, expecting CombinePDF::PDFParser or nil, but got #{parser.class.name}" unless parser.is_a? PDFParser
       @objects = parser.parse
 
@@ -207,7 +208,7 @@ module CombinePDF
       # xref_location = 0
       # out.each { |line| xref_location += line.bytesize + 1}
       out << "xref\n0 #{indirect_object_count}\n0000000000 65535 f "
-      xref.each { |offset| out << ("%010d 00000 n " % offset) }
+      xref.each { |offset| out << ("%010d 00000 n ".freeze % offset) }
       out << 'trailer'.freeze
       out << "<<\n/Root #{false || "#{catalog[:indirect_reference_id]} #{catalog[:indirect_generation_number]} R"}"
       out << "/Size #{indirect_object_count}"
@@ -216,7 +217,7 @@ 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)).force_encoding(Encoding::ASCII_8BIT)
+      out.join("\n".b).force_encoding(Encoding::ASCII_8BIT)
     end
 
     # this method returns all the pages cataloged in the catalog.

data/lib/combine_pdf/renderer.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 module CombinePDF
   ################################################################
   ## These are common functions, used within the different classes
@@ -123,12 +124,12 @@ module CombinePDF
       # if the object is not a simple object, it is a dictionary
       # A dictionary shall be written as a sequence of key-value pairs enclosed in double angle brackets (<<...>>)
       # (using LESS-THAN SIGNs (3Ch) and GREATER-THAN SIGNs (3Eh)).
-      out << "<<\n".force_encoding(Encoding::ASCII_8BIT)
+      out << "<<\n".b
       object.each do |key, value|
         out << "#{object_to_pdf key} #{object_to_pdf value}\n".force_encoding(Encoding::ASCII_8BIT) unless PDF::PRIVATE_HASH_KEYS.include? key
       end
       object.delete :Length
-      out << '>>'.force_encoding(Encoding::ASCII_8BIT)
+      out << '>>'.b
       out << "\nstream\n#{object[:raw_stream_content]}\nendstream".force_encoding(Encoding::ASCII_8BIT) if object[:raw_stream_content]
       out << "\nendobj\n" if object[:indirect_reference_id]
       out.join.force_encoding(Encoding::ASCII_8BIT)

data/lib/combine_pdf/version.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module CombinePDF
-  VERSION = '1.0.25'.freeze
+  VERSION = '1.0.27'
 end

data/lib/combine_pdf.rb

@@ -1,4 +1,5 @@
 # -*- encoding : utf-8 -*-
+# frozen_string_literal: true
 
 require 'zlib'
 require 'securerandom'

data/test/combine_pdf/renderer_test.rb

@@ -12,7 +12,7 @@ class CombinePDFRendererTest < Minitest::Test
 
   def test_numeric_array_to_pdf
     input = [1.234567, 0.000054, 5, -0.000099]
-    expected = "[1.234567 0.000054 5 -0.000099]".force_encoding('BINARY')
+    expected = "[1.234567 0.000054 5 -0.000099]".b
     actual = TestRenderer.new.test_object(input)
 
     assert_equal(expected, actual)

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: combine_pdf
 version: !ruby/object:Gem::Version
-  version: 1.0.25
+  version: 1.0.27
 platform: ruby
 authors:
 - Boaz Segev
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-12-19 00:00:00.000000000 Z
+date: 2024-11-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ruby-rc4