rdf-normalize 0.6.1 → 0.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7b8d7e930eb7f452fef42bd6f66b29dfcd3f526f7c9dafebbfe214ed5dfa4007
-  data.tar.gz: c4c60292f9868d39d50545dca77c8d5afd85885b0a1fc690b0ce84d2ee00ddd7
+  metadata.gz: 150cdddab40f368e1d1e68ebc65efe3990032729e8d9a591ef8436d61e81d057
+  data.tar.gz: 4510812f3e52b0159ec2025421d116d5c98d37840f3f87e25affb8392a5aa8b0
 SHA512:
-  metadata.gz: 05dd3390670479211a348c4fbd91e0c369355f374d72d2834697641ab64b3cce438b4df8ee63f6db50af1d68e036fa747762474448e6d326d5bfa758ca120b3d
-  data.tar.gz: 6189376e59d897e1e6d4b440b6ed75f0e7de970d6cbacb6b21e7e75976e7da0b6e6899085e2972eabf307556d9b17eb5277509fde3096e3ab428a0e84758d9c8
+  metadata.gz: ff3fd846a595da0df711bd83673498d259260a19f42f59a9d5f10e55a70670de7c0fba4b301d63ea725e2484179fd6b91b462ea943df9afe8c3d937660d06327
+  data.tar.gz: c66aa1ec1740e1d0c894d5ed9104b61819d055fc83aa2c6674fa1c34d2c9e62c395a78bb6aeec2b46c68c063fc6e79d55250e8d590a0f97c0624888488c4d60c

data/README.md

@@ -22,7 +22,7 @@ Algorithms implemented:
 Install with `gem install rdf-normalize`
 
 * 100% free and unencumbered [public domain](https://unlicense.org/) software.
-* Compatible with  Ruby >= 2.6.
+* Compatible with  Ruby >= 3.0.
 
 ## Usage
 
@@ -37,7 +37,14 @@ Full documentation available on [GitHub][Normalize doc]
     require 'rdf/normalize'
     require 'rdf/turtle'
     g = RDF::Graph.load("etc/doap.ttl")
-    puts g.dump(:normalize)
+    puts g.dump(:normalize) # Can also use :canonicalize
+
+### Normalizing an abstract Graph/Dataset
+    require 'rdf/normalize'
+    require 'rdf/turtle'
+    g = RDF::Graph.load("etc/doap.ttl")
+    g_canon = g.canonicalize # graph with URIs, literals, and blank nodes canonicalized.
+    puts g_canon.dump(:nquads) # Normalized, but not sorted
 
 ### Principle Classes
 * {RDF::Normalize}
@@ -46,11 +53,13 @@ Full documentation available on [GitHub][Normalize doc]
   * {RDF::Normalize::Writer}
   * {RDF::Normalize::URGNA2012}
   * {RDF::Normalize::RDFC10}
+* {RDF::Canonicalize} – extends {RDF::Normalize}
+  * {RDF::Canonicalize::Format}
 
 ## Dependencies
 
-* [Ruby](https://ruby-lang.org/) (>= 2.6)
-* [RDF.rb](https://rubygems.org/gems/rdf) (~> 3.2)
+* [Ruby](https://ruby-lang.org/) (>= 3.0)
+* [RDF.rb](https://rubygems.org/gems/rdf) (~> 3.3)
 
 ## Installation
 

data/VERSION

@@ -1 +1 @@
-0.6.1
+0.7.0

data/lib/rdf/normalize/format.rb

@@ -2,7 +2,18 @@ require 'rdf/nquads'
 
 module RDF::Normalize
   class Format < RDF::Format
-    content_type     'application/normalized+n-quads', alias: 'application/x-normalized+n-quads'
+    content_type     'application/canonical+n-quads', alias: 'application/x-canonical+n-quads'
+    content_encoding 'utf-8'
+
+    # It reads like normal N-Quads
+    reader { RDF::NQuads::Reader}
+    writer { RDF::Normalize::Writer }
+  end
+end
+
+module RDF::Canonicalize
+  class Format < RDF::Format
+    content_type     'application/canonical+n-quads', alias: 'application/x-canonical+n-quads'
     content_encoding 'utf-8'
 
     # It reads like normal N-Quads

data/lib/rdf/normalize/rdfc10.rb

@@ -17,10 +17,16 @@ module RDF::Normalize
     # @option options [Integer] :max_calls (40)
     #   Maximum number of calls allowed for recursive blank node labeling,
     #   as a multiple of the total number of blank nodes in the dataset.
+    # @options options [:MD5, :SHA1, :SHA2, :SHA256, :SHA384, :SHA512] :hash_algorithm (:SHA256)
+    #   See [Digest Algorithms](https://github.com/ruby/digest#digest-algorithms)
     # @return [RDF::Enumerable]
     # raise [RuntimeError] if the maximum number of levels of recursion is exceeded.
     def initialize(enumerable, **options)
       @dataset, @options = enumerable, options
+      @options[:hash_algorithm] ||= :SHA256
+      unless %i{MD5 SHA1 SHA2 SHA256 SHA384 SHA512}.include?(@options[:hash_algorithm])
+        raise UnknownHashAlgorithm, "UnknownHashAlgorithm: #{@options[:hash_algorithm].inspect}. Use one of MD5, SHA1, SHA2, SHA256, SHA384, or SHA512"
+      end
     end
 
     # Yields each normalized statement
@@ -158,6 +164,7 @@ module RDF::Normalize
       include RDF::Util::Logger
 
       attr_accessor :bnode_to_statements
+      attr_accessor :hash_algorithm
       attr_accessor :hash_to_bnodes
       attr_accessor :canonical_issuer
       attr_accessor :max_calls
@@ -165,6 +172,7 @@ module RDF::Normalize
 
       def initialize(**options)
         @options = options
+        @hash_algorithm = Digest.const_get(options.fetch(:hash_algorithm, :SHA256))
         @bnode_to_statements, @hash_to_bnodes, @canonical_issuer = {}, {}, IdentifierIssuer.new("c14n")
         @max_calls, @total_calls = nil, 0
       end
@@ -233,7 +241,7 @@ module RDF::Normalize
       # @param [RDF::Node] node
       # @param [IdentifierIssuer] issuer
       # @return [Array<String,IdentifierIssuer>] the Hash and issuer
-      # @raise [RuntimeError] If total number of calls has exceeded `max_calls` times the number of blank nodes in the dataset.
+      # @raise [MaxCallsExceeded] If total number of calls has exceeded `max_calls` times the number of blank nodes in the dataset.
       def hash_n_degree_quads(node, issuer)
         log_debug("hndq:")
         log_debug("  log point", "Hash N-Degree Quads function (4.9.3).")
@@ -241,7 +249,7 @@ module RDF::Normalize
         log_debug("  issuer") {issuer.inspect}
 
         if max_calls && total_calls >= max_calls
-          raise "Exceeded maximum number of calls (#{total_calls}) allowed to hash_n_degree_quads"
+          raise MaxCallsExceeded, "Exceeded maximum number of calls (#{total_calls}) allowed to hash_n_degree_quads"
         end
         @total_calls += 1
 
@@ -367,7 +375,7 @@ module RDF::Normalize
       protected
 
       def hexdigest(val)
-        Digest::SHA256.hexdigest(val)
+        hash_algorithm.hexdigest(val)
       end
 
       # Group adjacent bnodes by hash

data/lib/rdf/normalize.rb

@@ -3,7 +3,7 @@ require 'digest'
 
 module RDF
   ##
-  # **`RDF::Normalize`** is an RDF Graph normalization plugin for RDF.rb.
+  # **`RDF::Normalize`** is an RDF Graph canonicalization plugin for RDF.rb.
   #
   # @example Requiring the `RDF::Normalize` module
   #   require 'rdf/normalize'
@@ -18,7 +18,7 @@ module RDF
   # @example Returning normalized N-Quads
   #
   #   g = RDF::Graph.load("etc/doap.ttl")
-  #   g.dump(:normalize)
+  #   g.dump(:normalize) # or :canonicalize
   #
   # @example Writing a repository as normalized N-Quads
   #
@@ -66,5 +66,30 @@ module RDF
     end
     module_function :new
 
+    class MaxCallsExceeded < RuntimeError; end
+    class UnknownHashAlgorithm < RuntimeError; end
+  end
+
+  module Canonicalize
+    # RDF::Canonicalize extends RDF::Normalize.
+    include Normalize
+  end
+
+  # Change RDF::Enumerable#canonicalize
+  module Enumerable
+    ##
+    # Returns the resulting Enumerable result from RDF::Normalize.
+    # This also canonicalizes URIs and Literals.
+    #
+    # @return [RDF::Enumerable]
+    remove_method :canonicalize if method_defined? :canonicalize
+    def canonicalize
+      # Ensure that statements are queryable, countable and enumerable
+      this = self
+      enum = Enumerator.new do |yielder|
+        this.send(:each_statement) {|y| yielder << y.canonicalize}
+      end
+      RDF::Normalize.new(enum)
+    end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rdf-normalize
 version: !ruby/object:Gem::Version
-  version: 0.6.1
+  version: 0.7.0
 platform: ruby
 authors:
 - Gregg Kellogg
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-07-17 00:00:00.000000000 Z
+date: 2023-09-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdf
@@ -16,70 +16,70 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
 - !ruby/object:Gem::Dependency
   name: rdf-spec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.10'
+        version: '3.12'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.10'
+        version: '3.12'
 - !ruby/object:Gem::Dependency
   name: json-ld
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
 - !ruby/object:Gem::Dependency
   name: rdf-trig
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '3.2'
+        version: '3.3'
 - !ruby/object:Gem::Dependency
   name: yard
   requirement: !ruby/object:Gem::Requirement
@@ -129,14 +129,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.6'
+      version: '3.0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.13
+rubygems_version: 3.4.19
 signing_key:
 specification_version: 4
 summary: RDF Graph normalizer for Ruby.