rdf 3.1.7 → 3.1.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 7e220d98b1d53ade20bf5999761a948e495597dc74eaccd6830c22adadc77fa4
-  data.tar.gz: 13b643963aeb32f99e2c455490e3cbc661c56153abb6dd38ff192e42ce0ee5f5
+  metadata.gz: d2becf1b8beb0505402d0b4d2a6f7795cca3657bc579ffac31f3b6037d34e550
+  data.tar.gz: 14b57058dab38a7f7a23df435b83ce8e45c56c51ef718a107e1f1fedb6939a63
 SHA512:
-  metadata.gz: 9a845aa06b3cb0af80aa3e2ca0d9f051d4158258d5007032f73b974c4976e0dd9a34b8d1c55eda3fe2b5fd8c5f9ee9528647514f81387f0032e4adcbc8a0f46d
-  data.tar.gz: 388f74852651a13a7a24f10c6dee8767d76d44b7d002d58efc356dfae76629c7fccd0c462a19df874ee64c39516b838661e4b586847718084a41ad72644483fa
+  metadata.gz: 685797b5318d90aeba5755a88cc4aa0acc37b69bcc209d579d52910f0940cdf93d2b453cb3b60a0779cfadda80a2bc050afad2d18b276d973b21e6f1e3f79317
+  data.tar.gz: a13b21146dfa64967464026e99d80bff9f6b472f4ef7d8079ee53a7e80d80f8577b4b7deee9b60643697354e6b42d093b4229d21978f93b5c65b4a2fa050270f

data/README.md

@@ -6,9 +6,9 @@ This is a pure-Ruby library for working with [Resource Description Framework
 * <https://ruby-rdf.github.com/rdf>
 
 [![Gem Version](https://badge.fury.io/rb/rdf.png)](https://badge.fury.io/rb/rdf)
-[![Build Status](https://travis-ci.org/ruby-rdf/rdf.png?branch=master)](https://travis-ci.org/ruby-rdf/rdf)
-[![Coverage Status](https://coveralls.io/repos/ruby-rdf/rdf/badge.svg)](https://coveralls.io/r/ruby-rdf/rdf)
-[![Join the chat at https://gitter.im/ruby-rdf/rdf](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/ruby-rdf/rdf?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
+[![Build Status](https://github.com/ruby-rdf/rdf/workflows/CI/badge.svg?branch=develop)](https://github.com/ruby-rdf/rdf/actions?query=workflow%3ACI)
+[![Coverage Status](https://coveralls.io/repos/ruby-rdf/rdf/badge.svg)](https://coveralls.io/github/ruby-rdf/rdf)
+[![Gitter chat](https://badges.gitter.im/ruby-rdf/rdf.png)](https://gitter.im/ruby-rdf/rdf)
 
 ## Features
 
@@ -39,6 +39,22 @@ resources. Clients may also consider using [RestClient Components][] to enable
 client-side caching of HTTP results using [Rack::Cache][] or other Rack
 middleware.
 
+See {RDF::Util::File} for configuring other mechanisms for retrieving resources.
+
+### Term caching and configuration.
+
+RDF.rb uses a weak-reference cache for storing internalized versions of URIs and Nodes. This is particularly useful for Nodes as two nodes are equivalent only if they're the same node.
+
+By default, each cache can grow to an unlimited size, but this can be configured using {RDF.config}, for general limits, along with URI- or Node-specific limits.
+
+For example, to limit the size of the URI intern cache only:
+
+    RDF.config.uri_cache_size = 10_000
+
+The default for creating new caches without a specific initialization size can be set using:
+
+    RDF.config.cache_size = 100_000
+
 ## Differences between RDF 1.0 and RDF 1.1
 
 This version of RDF.rb is fully compatible with [RDF 1.1][], but it creates some
@@ -246,17 +262,10 @@ By default, the N-Triples reader will reject a document containing a subject res
     end
     # => RDF::ReaderError
 
-Readers support a `rdfstar` option with either `:PG` (Property Graph) or `:SA` (Separate Assertions) modes. In `:PG` mode, statements that are used in the subject or object positions are also implicitly added to the graph:
-
-    graph = RDF::Graph.new do |graph|
-      RDF::NTriples::Reader.new(nt, rdfstar: :PG) {|reader| graph << reader}
-    end
-    graph.count #=> 2
-
-When using the `:SA` mode, only one statement is asserted, although the reified statement is contained within the graph.
+Readers support a boolean valued `rdfstar` option.
 
     graph = RDF::Graph.new do |graph|
-      RDF::NTriples::Reader.new(nt, rdfstar: :SA) {|reader| graph << reader}
+      RDF::NTriples::Reader.new(nt, rdfstar: true) {|reader| graph << reader}
     end
     graph.count #=> 1
 
@@ -478,7 +487,7 @@ see <https://unlicense.org/> or the accompanying {file:UNLICENSE} file.
 [RDF::TriX]:        https://ruby-rdf.github.com/rdf-trix
 [RDF::Turtle]:      https://ruby-rdf.github.com/rdf-turtle
 [RDF::Raptor]:      https://ruby-rdf.github.com/rdf-raptor
-[RDF*]:             https://lists.w3.org/Archives/Public/public-rdf-star/
+[RDF*]:             https://w3c.github.io/rdf-star/rdf-star-cg-spec.html
 [LinkedData]:       https://ruby-rdf.github.com/linkeddata
 [JSON::LD]:         https://ruby-rdf.github.com/json-ld
 [RestClient]:       https://rubygems.org/gems/rest-client

data/VERSION

@@ -1 +1 @@
-3.1.7
+3.1.8

data/lib/rdf.rb

@@ -2,6 +2,7 @@ require 'stringio'
 require 'bigdecimal'
 require 'date'
 require 'time'
+require "ostruct"
 
 require 'rdf/version'
 require 'rdf/extensions'
@@ -79,6 +80,29 @@ module RDF
   # CLI
   autoload :CLI,         'rdf/cli'
 
+  ##
+  # Configuration, used open for configuring constants used within the codebase.
+  #
+  # @example set default cache size to be at most 10,000 entries
+  #
+  #   RDF.config.cache_size = 10_000
+  #
+  # @example set cache size for interned URIs to 5,000 entries
+  #
+  #   RDF.config.uri_cache_size = 5_000
+  #
+  # Defaults:
+  #   * `cache_size`: -1
+  #   * `uri_cache_size`: `cache_size`
+  #   * `node_cache_size`: `cache_size`
+  #
+  # @note cache configurations must be set before initial use, when the caches are allocated.
+  # @see RDF::Util::Cache.new
+  # @return [Object]
+  def self.config
+    @config ||= OpenStruct.new(cache_size: -1, uri_cache_size: nil, node_cache_size: nil)
+  end
+
   ##
   # Alias for `RDF::Resource.new`.
   #

data/lib/rdf/cli.rb

@@ -162,6 +162,7 @@ module RDF
     # * `lambda` code run to execute command.
     # * `filter` Option values that must match for command to be used
     # * `control` Used to indicate how (if) command is displayed
+    # * `repository` Use this repository, if set
     # * `options` an optional array of `RDF::CLI::Option` describing command-specific options.
     # * `option_use`: A hash of option symbol to option usage, used for overriding the default status of an option for this command.
     # @return [Hash{Symbol => Hash{Symbol => Object}}]
@@ -493,6 +494,9 @@ module RDF
             raise ArgumentError, "Incompatible command #{c} used with option #{opt}=#{options[opt]}"
           end
         end
+
+        # The command may specify a repository instance to use
+        options[:repository] ||= COMMANDS[c.to_sym][:repository]
       end
 
       # Hacks for specific options
@@ -501,9 +505,11 @@ module RDF
       options[:format] = options[:format].to_sym if options[:format]
       options[:output_format] = options[:output_format].to_sym if options[:output_format]
 
-      @repository = options[:ordered] ?
-        [].extend(RDF::Enumerable, RDF::Queryable) :
-        RDF::Repository.new
+      # Allow repository to be set via option.
+      @repository = options[:repository] ||
+        (options[:ordered] ?
+          [].extend(RDF::Enumerable, RDF::Queryable) :
+          RDF::Repository.new)
 
       # Parse input files if any command requires it
       if cmds.any? {|c| COMMANDS[c.to_sym][:parse]}
@@ -518,7 +524,10 @@ module RDF
 
       # Run each command in sequence
       cmds.each do |command|
-        COMMANDS[command.to_sym][:lambda].call(args, output: output, **options.merge(messages: messages))
+        COMMANDS[command.to_sym][:lambda].call(args,
+          output: output,
+          messages: messages,
+          **options.merge(repository: repository))
       end
 
       # Normalize messages

data/lib/rdf/model/list.rb

@@ -49,14 +49,23 @@ module RDF
     #     g = RDF::Graph.new << l
     #     g.count # => l.count
     #
+    # @example use a transaction for block initialization
+    #     l = RDF::List(graph: graph, wrap_transaction: true) do |list|
+    #       list << RDF::Literal(1)
+    #       # list.graph.rollback will rollback all list changes within this block.
+    #     end
+    #     list.count #=> 1
+    #
     # @param  [RDF::Resource]         subject (RDF.nil)
     #   Subject should be an {RDF::Node}, not a {RDF::URI}. A list with an IRI head will not validate, but is commonly used to detect if a list is valid.
     # @param  [RDF::Graph]        graph (RDF::Graph.new)
     # @param  [Array<RDF::Term>]  values
     #   Any values which are not terms are coerced to `RDF::Literal`.
+    # @param [Boolean] wrap_transaction (false)
+    #   Wraps the callback in a transaction, and replaces the graph with that transaction for the duraction of the callback. This has the effect of allowing any list changes to be made atomically, or rolled back.
     # @yield  [list]
     # @yieldparam [RDF::List] list
-    def initialize(subject: nil, graph: nil, values: nil, &block)
+    def initialize(subject: nil, graph: nil, values: nil, wrap_transaction: false, &block)
       @subject = subject || RDF.nil
       @graph   = graph   || RDF::Graph.new
       is_empty = @graph.query({subject: subject, predicate: RDF.first}).empty?
@@ -78,9 +87,25 @@ module RDF
       end
 
       if block_given?
-        case block.arity
-          when 1 then block.call(self)
-          else instance_eval(&block)
+        if wrap_transaction
+          old_graph = @graph
+          begin
+            Transaction.begin(@graph, graph_name: @graph.graph_name, mutable: @graph.mutable?) do |trans|
+              @graph = trans
+              case block.arity
+                when 1 then block.call(self)
+                else instance_eval(&block)
+              end
+              trans.execute if trans.mutated?
+            end
+          ensure
+            @graph = old_graph
+          end
+        else
+          case block.arity
+            when 1 then block.call(self)
+            else instance_eval(&block)
+          end
         end
       end
     end

data/lib/rdf/model/node.rb

@@ -13,18 +13,14 @@ module RDF
     include RDF::Resource
 
     ##
-    # Defines the maximum number of interned Node references that can be held
-    # cached in memory at any one time.
+    # Cache size may be set through {RDF.config} using `node_cache_size`.
     #
     # @note caching interned nodes means that two different invocations using the same symbol will result in the same node, which may not be appropriate depending on the graph from which it is used. RDF requires that bnodes with the same label are, in fact, different bnodes, unless they are used within the same document.
-    CACHE_SIZE = -1 # unlimited by default
-
-    ##
     # @return [RDF::Util::Cache]
     # @private
     def self.cache
       require 'rdf/util/cache' unless defined?(::RDF::Util::Cache)
-      @cache ||= RDF::Util::Cache.new(CACHE_SIZE)
+      @cache ||= RDF::Util::Cache.new(RDF.config.node_cache_size)
     end
 
     ##

data/lib/rdf/model/uri.rb

@@ -27,11 +27,6 @@ module RDF
   class URI
     include RDF::Resource
 
-    ##
-    # Defines the maximum number of interned URI references that can be held
-    # cached in memory at any one time.
-    CACHE_SIZE = -1 # unlimited by default
-    
     # IRI components
     UCSCHAR = Regexp.compile(<<-EOS.gsub(/\s+/, ''))
       [\\u00A0-\\uD7FF]|[\\uF900-\\uFDCF]|[\\uFDF0-\\uFFEF]|
@@ -117,11 +112,13 @@ module RDF
     ).freeze
 
     ##
+    # Cache size may be set through {RDF.config} using `uri_cache_size`.
+    #
     # @return [RDF::Util::Cache]
     # @private
     def self.cache
       require 'rdf/util/cache' unless defined?(::RDF::Util::Cache)
-      @cache ||= RDF::Util::Cache.new(CACHE_SIZE)
+      @cache ||= RDF::Util::Cache.new(RDF.config.uri_cache_size)
     end
 
     ##

data/lib/rdf/nquads.rb

@@ -69,9 +69,9 @@ module RDF
 
           begin
             unless blank? || read_comment
-              subject   = read_uriref || read_node || read_rdfstar || fail_subject
+              subject   = read_uriref || read_node || read_embTriple || fail_subject
               predicate = read_uriref(intern: true) || fail_predicate
-              object    = read_uriref || read_node || read_literal || read_rdfstar || fail_object
+              object    = read_uriref || read_node || read_literal || read_embTriple || fail_object
               graph_name    = read_uriref || read_node
               if validate? && !read_eos
                 log_error("Expected end of statement (found: #{current_line.inspect})", lineno: lineno, exception: RDF::ReaderError)

data/lib/rdf/ntriples/reader.rb

@@ -213,7 +213,7 @@ module RDF::NTriples
       begin
         read_statement
       rescue RDF::ReaderError
-        value = read_uriref || read_node || read_literal || read_rdfstar
+        value = read_uriref || read_node || read_literal || read_embTriple
         log_recover
         value
       end
@@ -229,9 +229,9 @@ module RDF::NTriples
 
         begin
           unless blank? || read_comment
-            subject   = read_uriref || read_node || read_rdfstar || fail_subject
+            subject   = read_uriref || read_node || read_embTriple || fail_subject
             predicate = read_uriref(intern: true) || fail_predicate
-            object    = read_uriref || read_node || read_literal || read_rdfstar || fail_object
+            object    = read_uriref || read_node || read_literal || read_embTriple || fail_object
 
             if validate? && !read_eos
               log_error("Expected end of statement (found: #{current_line.inspect})", lineno: lineno, exception: RDF::ReaderError)
@@ -247,11 +247,11 @@ module RDF::NTriples
 
     ##
     # @return [RDF::Statement]
-    def read_rdfstar
+    def read_embTriple
       if @options[:rdfstar] && match(ST_START)
-        subject   = read_uriref || read_node || read_rdfstar || fail_subject
+        subject   = read_uriref || read_node || read_embTriple || fail_subject
         predicate = read_uriref(intern: true) || fail_predicate
-        object    = read_uriref || read_node || read_literal || read_rdfstar || fail_object
+        object    = read_uriref || read_node || read_literal || read_embTriple || fail_object
         if !match(ST_END)
           log_error("Expected end of statement (found: #{current_line.inspect})", lineno: lineno, exception: RDF::ReaderError)
         end

data/lib/rdf/ntriples/writer.rb

@@ -227,7 +227,7 @@ module RDF::NTriples
     # @param  [RDF::Statement] statement
     # @param  [Hash{Symbol => Object}] options ({})
     # @return [String]
-    def format_rdfstar(statement, **options)
+    def format_embTriple(statement, **options)
       "<<%s %s %s>>" % statement.to_a.map { |value| format_term(value, **options) }
     end
     ##

data/lib/rdf/query.rb

@@ -255,7 +255,7 @@ module RDF
     # @see    RDF::Query::Pattern#cost
     # @since  0.3.0
     def optimize!(**options)
-      optional, required = @patterns.partition(&:optional?)
+      optional, required = @patterns.uniq.partition(&:optional?)
       required.sort! do |a, b|
         (a.cost || 0) <=> (b.cost || 0)
       end

data/lib/rdf/reader.rb

@@ -160,10 +160,10 @@ module RDF
         end,
         RDF::CLI::Option.new(
           symbol: :rdfstar,
-          control: :select,
-          datatype: [:PG, :SA],
-          on: ["--rdf-star MODE"],
-          description: "Parse RDF*, either in Property Graph mode (PG) or Separate Assertions mode (SA).") {|arg| arg.to_sym},
+          datatype: TrueClass,
+          control: :checkbox,
+          on: ["--rdfstar"],
+          description: "Parse RDF*."),
         RDF::CLI::Option.new(
           symbol: :validate,
           datatype: TrueClass,
@@ -276,10 +276,8 @@ module RDF
     #   the encoding of the input stream
     # @param [Boolean]  intern       (true)
     #   whether to intern all parsed URIs
-    # @param [:PG, :SA] rdfstar      (nil)
+    # @param [Boolean] rdfstar      (false)
     #   support parsing RDF* statement resources.
-    #   If `:PG`, referenced statements are also emitted.
-    #   If `:SA`, referenced statements are not emitted.
     # @param [Hash]     prefixes     (Hash.new)
     #   the prefix mappings to use (not supported by all readers)
     # @param  [Hash{Symbol => Object}] options
@@ -295,7 +293,7 @@ module RDF
                    encoding:      Encoding::UTF_8,
                    intern:        true,
                    prefixes:      Hash.new,
-                   rdfstar:       nil,
+                   rdfstar:       false,
                    validate:      false,
                    **options,
                    &block)
@@ -401,9 +399,6 @@ module RDF
     # Statements are yielded in the order that they are read from the input
     # stream.
     #
-    # If the `rdfstar` option is `:PG` and triples include
-    # embedded statements, they are also enumerated.
-    #
     # @overload each_statement
     #   @yield  [statement]
     #     each statement
@@ -423,7 +418,6 @@ module RDF
           loop do
             st = read_statement
             block.call(st)
-            each_pg_statement(st, &block) if options[:rdfstar] == :PG
           end
         rescue EOFError
           rewind rescue nil
@@ -441,9 +435,6 @@ module RDF
     # Triples are yielded in the order that they are read from the input
     # stream.
     #
-    # If the `rdfstar` option is `:PG` and triples include
-    # embedded statements, they are also enumerated.
-    #
     # @overload each_triple
     #   @yield  [subject, predicate, object]
     #     each triple
@@ -464,10 +455,6 @@ module RDF
           loop do
             triple = read_triple
             block.call(*triple)
-            if options[:rdfstar] == :PG
-              block.call(*triple[0].to_a) if triple[0].is_a?(Statement)
-              block.call(*triple[2].to_a) if triple[2].is_a?(Statement)
-            end
           end
         rescue EOFError
           rewind rescue nil

data/lib/rdf/util/cache.rb

@@ -17,6 +17,9 @@ module RDF; module Util
   # @see   http://en.wikipedia.org/wiki/Weak_reference
   # @since 0.2.0
   class Cache
+    # The configured cache capacity.
+    attr_reader :capacity
+
     ##
     # @private
     def self.new(*args)
@@ -36,8 +39,8 @@ module RDF; module Util
 
     ##
     # @param  [Integer] capacity
-    def initialize(capacity = -1)
-      @capacity = capacity
+    def initialize(capacity = nil)
+      @capacity = capacity || RDF.config.cache_size
       @cache  ||= {}
       @index  ||= {}
     end
@@ -106,7 +109,7 @@ module RDF; module Util
     class WeakRefCache < Cache
       ##
       # @param  [Integer] capacity
-      def initialize(capacity = -1)
+      def initialize(capacity = nil)
         require 'weakref' unless defined?(::WeakRef)
         super
       end

data/lib/rdf/writer.rb

@@ -516,7 +516,7 @@ module RDF
         when RDF::Literal   then format_literal(term, **options)
         when RDF::URI       then format_uri(term, **options)
         when RDF::Node      then format_node(term, **options)
-        when RDF::Statement then format_rdfstar(term, **options)
+        when RDF::Statement then format_embTriple(term, **options)
         else nil
       end
     end
@@ -574,7 +574,7 @@ module RDF
     # @return [String]
     # @raise  [NotImplementedError] unless implemented in subclass
     # @abstract
-    def format_rdfstar(value, **options)
+    def format_embTriple(value, **options)
       raise NotImplementedError.new("#{self.class}#format_statement") # override in subclasses
     end
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rdf
 version: !ruby/object:Gem::Version
-  version: 3.1.7
+  version: 3.1.8
 platform: ruby
 authors:
 - Arto Bendiken
@@ -10,7 +10,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2020-11-15 00:00:00.000000000 Z
+date: 2020-12-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: link_header
@@ -164,42 +164,42 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.9.20
+        version: '0.9'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.9.20
+        version: '0.9'
 - !ruby/object:Gem::Dependency
   name: faraday
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.17'
+        version: '1.2'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.17'
+        version: '1.2'
 - !ruby/object:Gem::Dependency
   name: faraday_middleware
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.13'
+        version: '1.0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.13'
+        version: '1.0'
 description: RDF.rb is a pure-Ruby library for working with Resource Description Framework
   (RDF) data.
 email: public-rdf-ruby@w3.org
@@ -303,7 +303,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.1.4
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: A Ruby library for working with Resource Description Framework (RDF) data.