rdf2json 0.0.2 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 229b623b98cb1edf2917e919f28cedaaa40d4405
-  data.tar.gz: e8b2debf2eceff26846ff3e9e1b549f3c188e1b9
+  metadata.gz: 744a041e168424a1d704f0be0e89e36a52e3f24b
+  data.tar.gz: 0cf661762f47da4666a5f69a05d8f107f35bfdc7
 SHA512:
-  metadata.gz: fa6329cafa516402423d0f2f4eaef39f0021951951cb4ec8db4034b03338b5e9c4967499fb75aa9068c82b32aae95fb73f82777c738cf702dc3255800e918613
-  data.tar.gz: 74b64a2375e9274e24da1c8b3560fcaffb9b0264b4218ed688f14b095ad948642c9ca92f6e87124d09bc0d1873741598e6b95a38646c75fde2b2e696ffe0681c
+  metadata.gz: 2e062d274606bce55c58c3cf31ae4e7e52138e5d682cce733c63003145028a6a79c0efbba90d73a58418fe7985bc1c4f7b5dfaea32cd2116f5ee41bd810057b2
+  data.tar.gz: 85885316a1eb81fbdea361f1beb6aefe2568c4105657e4c5e4cb4cdcb455562bfbc173f2321c5a8f9d4cdffda126a8431db7eb9dae3aaff1727bde40ad6c1315

data/.travis.yml

@@ -1,14 +1,8 @@
 language: ruby
 rvm:
-  - 1.9.2
   - 1.9.3
   - 2.0.0
   - 2.1.1
 
-# - rbx-19mode
-#  - 1.8.7
-#  - jruby-18mode # JRuby in 1.8 mode
-#  - rbx-18mode
-
 # uncomment this line if your project needs to run something other than `rake`:
 # script: bundle exec rspec spec

data/Gemfile

@@ -5,9 +5,13 @@ source "http://rubygems.org"
 gem "rdf", ">= 1.1.3"
 gem "json-ld", ">= 1.1.3"
 
+# Coverage via Coveralls:
+gem 'coveralls', require: false
+
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.
 group :development do
+  gem "minitest", ">= 5.3.4"
   gem "shoulda", ">= 0"
   gem "simplecov", ">= 0"
   gem "jeweler", "~> 1.8.4"

data/README.md

@@ -1,6 +1,7 @@
 # rdf2json
 
 [![Build Status](https://secure.travis-ci.org/joejimbo/rdf2json.png)](http://travis-ci.org/joejimbo/rdf2json)
+[![Coverage Status](https://coveralls.io/repos/joejimbo/rdf2json/badge.png?branch=master)](https://coveralls.io/r/joejimbo/rdf2json?branch=master)
 
 Reads RDF N-Triple/N-Quads that are sorted by subject and
 append a JSON/JSON-LD document per line in a designated
@@ -37,6 +38,7 @@ sort -k 1,1 UNSORTED.EXT > SORTED.EXT
 
 #### Common options
 
+*  `-s`, `--silent`: Do not output summary statistics.
 *  `-h`, `--help`: Show this message.
 
 #### JSON output (`--minimize` option)

data/VERSION

@@ -1 +1 @@
-0.0.2
+0.1.0

data/lib/rdf2json/rdf2json.rb

@@ -13,7 +13,26 @@ module RDF2JSON
 # Command line interface; reads parameters, outputs help, or proceeds with the
 # transformation of RDF N-Triples/N-Quads into JSON/JSON-LD.
 def self.cli
-  options = {}
+  options_or_exit_code = option_parser
+
+  exit options_or_exit_code unless options_or_exit_code.kind_of?(Hash)
+  options = options_or_exit_code
+  
+  begin
+    # Why instantiate a Converter instance here? Well, for implementing parallelization later:
+    Converter.new(options[:input], options[:output], options[:input_format], options[:output_format], options[:namespace], options[:prefix], !options[:silent]).convert
+  rescue Interrupt
+    # The user hit Ctrl-C, which is okay and does not need error reporting.
+    exit 0
+  end
+end
+
+# Command line option parser. Returns either the set options as a hash, or,
+# returns an integer that indicates the shell error return code.
+#
+# +argv+:: optional command line arguments (may be nil; for unit testing)
+def self.option_parser(argv = nil)
+  options = { :silent => false }
 
   parser = OptionParser.new { |opts|
     opts.banner = 'Usage: rdf2json [options] --input filename.nt --output filename.json'
@@ -62,24 +81,31 @@ def self.cli
     opts.separator ''
     opts.separator 'Common options:'
 
+    opts.on_tail('-s', '--silent', 'Do not output summary statistics.') { |silent|
+      options[:silent] = true
+    }
     opts.on_tail('-h', '--help', 'Show this message.') { |help|
       puts opts
-      exit
+      return 0
     }
   }
 
   begin
-    parser.parse!
+    if argv then
+      parser.parse! argv
+    else
+      parser.parse!
+    end
   rescue
     puts parser
-    exit 1
+    return 1
   end
 
   unless options.has_key?(:input) and options.has_key?(:output) then
     puts 'Error: Requires --input and --output parameters.'
     puts ''
     puts parser
-    exit 2
+    return 2
   end
 
   if options.has_key?(:ntriples) and options.has_key?(:nquads) then
@@ -88,18 +114,18 @@ def self.cli
     puts '       setting the input fileformat.'
     puts ''
     puts parser
-    exit 3
+    return 3
   end
 
   extension = File.extname(options[:input])
   if options.has_key?(:ntriples) then
-    input_format = :ntriples
+    options[:input_format] = :ntriples
   elsif options.has_key?(:nquads) then
-    input_format = :nquads
+    options[:input_format] = :nquads
   elsif extension == '.nt' then
-    input_format = :ntriples
+    options[:input_format] = :ntriples
   elsif extension == '.nq' then
-    input_format = :nquads
+    options[:input_format] = :nquads
   else
     puts 'Error: Cannot determine input file format by filename extension.'
     puts '       Recognized fileformat extensions are .nt and .nq for N-Triples'
@@ -108,26 +134,20 @@ def self.cli
     puts '       when one of those options is given.'
     puts ''
     puts parser
-    exit 4
+    return 4
   end
 
-  output_format = :jsonld
-  output_format = :json if options[:minimize]
+  options[:output_format] = :jsonld
+  options[:output_format] = :json if options[:minimize]
 
   unless File.exist?(options[:input]) then
     puts 'Error: Input file (--input parameter) does not seem to exist.'
     puts ''
     puts parser
-    exit 6
+    return 6
   end
 
-  begin
-    # Why instantiate a Converter instance here? Well, for implementing parallelization later:
-    Converter.new(options[:input], options[:output], input_format, output_format, options[:namespace], options[:prefix]).convert
-  rescue Interrupt
-    # The user hit Ctrl-C, which is okay and does not need error reporting.
-    exit 0
-  end
+  return options
 end
 
 # Class that takes an input file (RDF N-Triples/N-Quads) and appends JSON/JSON-LD to
@@ -143,13 +163,15 @@ class Converter
   # +output_format+:: format of the output (:json or jsonld)
   # +namespace+:: a possible namespace for replacing "@id" keys (may be nil)
   # +prefix+:: a possible prefix for shortening keys (may be nil)
-  def initialize(input_filename, output_filename, input_format, output_format, namespace, prefix)
+  # +summary+:: determines whether summary statistics should be printed (may be nil; means no summary)
+  def initialize(input_filename, output_filename, input_format, output_format, namespace = nil, prefix = nil, summary = nil)
     @input_file = File.open(input_filename, 'r')
     @output_file = File.open(output_filename, 'a')
     @input_format = input_format
     @output_format = output_format
     @namespace = namespace
     @prefix = prefix
+    @summary = summary
   end
 
   # Convert the input file by appending the newly formatted data to the output file.
@@ -160,6 +182,7 @@ class Converter
   # of lines appended).
   def convert
     no_of_lines = 0
+    documents = 0
     no_of_statements = 0
     read_errors = 0
     last_subject = nil
@@ -167,14 +190,16 @@ class Converter
 
     @input_file.each_line { |line|
       no_of_lines += 1
-      line.chomp!
 
       subject = "#{line.sub(/>.*/, '')}>"
 
+      last_subject = subject unless last_subject
+
       if subject == last_subject then
         subject_block << line
       else
         stats = write_graph(subject_block)
+        documents += stats[:documents]
         no_of_statements += stats[:no_of_statements]
         read_errors += stats[:read_errors]
         subject_block = ''
@@ -184,12 +209,18 @@ class Converter
     }
 
     stats = write_graph(subject_block)
+    documents += stats[:documents]
     no_of_statements += stats[:no_of_statements]
     read_errors += stats[:read_errors]
 
-    puts "Total number of lines read                   : #{no_of_lines}"
-    puts "Statement read errors (N-Quads or N-Triples) : #{read_errors}"
-    puts "JSON/JSON-LD documents output                : #{no_of_statements}"
+    @output_file.close
+
+    if @summary then
+      puts "Total number of lines read                   : #{no_of_lines}"
+      puts "Statement read errors (N-Quads or N-Triples) : #{read_errors}"
+      puts "Statements that are captured in JSON/JSON-LD : #{no_of_statements}"
+      puts "JSON/JSON-LD documents output                : #{documents}"
+    end
   end
 
   # Minimize a JSON-LD hash to JSON.
@@ -224,7 +255,7 @@ class Converter
   #
   # +block+:: one or more lines that share the same subject in RDF N-Triples/N-Quads
   def write_graph(block)
-    return { :read_errors => 0, :no_of_statements => 0 } unless block and not block.empty?
+    return { :read_errors => 0, :no_of_statements => 0, :documents => 0 } unless block and not block.empty?
 
     # Virtuoso output error-handling:
     block.gsub!("\\'", "'")
@@ -243,6 +274,7 @@ class Converter
       end
     }
 
+    documents = 0
     JSON::LD::API::fromRdf(graph) { |document|
       document.each{ |entity|
         # Parsed JSON-LD representation:
@@ -252,10 +284,11 @@ class Converter
         minify(entity) if @output_format == :json
 
         @output_file.puts entity.to_json
+        documents += 1
       }
     }
 
-    return { :read_errors => read_errors, :no_of_statements => no_of_statements }
+    return { :read_errors => read_errors, :no_of_statements => no_of_statements, :documents => documents }
   end
 
 end

data/test/helper.rb

@@ -23,12 +23,25 @@ rescue Bundler::BundlerError => e
   $stderr.puts "Run `bundle install` to install missing gems"
   exit e.status_code
 end
-require 'test/unit'
+require 'minitest'
+require 'minitest/spec'
+require 'minitest/autorun'
 require 'shoulda'
 
 $LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
 $LOAD_PATH.unshift(File.dirname(__FILE__))
-require 'bio-rdf2json'
 
-class Test::Unit::TestCase
+require 'coveralls'
+
+SimpleCov.formatter = Coveralls::SimpleCov::Formatter
+SimpleCov.start do
+  add_filter 'test'
+  add_filter 'gems'
+  add_filter 'rubies'
+  add_group 'Converter', 'lib'
 end
+
+Coveralls.wear!
+
+require 'rdf2json'
+

data/test/test_rdf2json.rb

@@ -0,0 +1,224 @@
+require 'helper'
+
+require 'tempfile'
+
+# Test the RDF N-Triples/N-Quads to JSON/JSON-LD conversion.
+class TestRDF2JSON < Minitest::Test
+
+  # RDF N-Triples test dataset:
+  @@test_ntriples = <<-EOI
+<s1> <http://test/p1> <o1> .
+<s1> <p2> "l1" .
+<s1> <p3> <o3> .
+<s1> <p3> <o4> .
+<s2> <http://test/p1> <o5> .
+<s2> <p4> "l2" .
+EOI
+
+  # RDF N-Triples test dataset:
+  @@test_nquads = <<-EOI
+<s1> <http://test/p1> <o1> <g1> .
+<s1> <p2> "l1" <g1> .
+<s1> <p3> <o3> <g1> .
+<s1> <p3> <o4> <g1> .
+<s2> <http://test/p1> <o5> <g2> .
+<s2> <p4> "l2" <g2> .
+EOI
+
+  # Dummy file path for a fake input file; command line parameter testing.
+  @@dummy_file = '/tmp/non_existing_file_239805167_ALHFASBIWEO.nt'
+
+  # Creates a temporary file that holds either N-Triples or N-Quads.
+  #
+  # +format+:: whether N-Triples or N-Quads should be used (:ntriples, :nquads)
+  def self.create_input(format)
+    input = Tempfile.new('rdf2json-converter-input')
+    if format == :ntriples then
+      input.puts @@test_ntriples
+    elsif format == :nquads then
+      input.puts @@test_nquads
+    else
+      raise "Passed a constant to create_input that is not understood."
+    end
+    input.close
+
+    return input
+  end
+
+  # Reads JSON/JSON-LD documents from a file; one document per line.
+  #
+  # +output+:: handle to the file that contains JSON/JSON-LD documents (one per line)
+  def self.get_json(output)
+    output.rewind
+
+    return output.readlines
+  end
+
+  # Tests whether the reference and output arrays match.
+  #
+  # +reference+:: an array of reference objects
+  # +output+:: an array containing the converter output objects
+  def self.test(reference, output)
+    output.length.must_equal(reference.length)
+    reference.each_index { |index|
+      output[index].must_equal(reference[index])
+    }
+  end
+
+  # Temporarily redirect STDOUT, so that the testing output
+  # does not get cluttered.
+  #
+  # +method+:: name of the class method that should be called on RDF2JSON
+  # +parameters+:: optional parameters for the method call
+  def self.silence(method, parameters = nil)
+    stdout, $stdout = $stdout, StringIO.new
+    result = RDF2JSON.send(method, *parameters)
+    $stdout = stdout
+
+    return result
+  end
+
+  # Command line parameter tests.
+  describe 'Command line parameters' do
+    it 'no input or output specified' do
+      TestRDF2JSON.silence('option_parser').must_equal(2)
+    end
+
+    it 'input file does not exist' do
+      argv = [ [ '--input', @@dummy_file, '--output', '/dev/null' ] ]
+      TestRDF2JSON.silence('option_parser', argv).must_equal(6)
+    end
+
+    it 'input file format cannot be determined by extension' do
+      argv = [ [ '--input', @@dummy_file + '.unknown', '--output', '/dev/null' ] ]
+      TestRDF2JSON.silence('option_parser', argv).must_equal(4)
+    end
+
+    it 'both RDF N-Triples and RDF N-Quads specified as input format' do
+      argv = [ [ '--input', @@dummy_file, '--output', '/dev/null', '--triples', '--quads' ] ]
+      TestRDF2JSON.silence('option_parser', argv).must_equal(3)
+    end
+
+    it 'help requested' do
+      argv = [ [ '--help' ] ]
+      TestRDF2JSON.silence('option_parser', argv).must_equal(0)
+    end
+
+    it 'nonsense parameters provided' do
+      argv = [ [ '--hey', '--hello', '--wassup' ] ]
+      TestRDF2JSON.silence('option_parser', argv).must_equal(1)
+    end
+  end
+
+  # N-Triples to JSON/JSON-LD tests.
+  describe 'N-Triple conversion' do
+    before do
+      @input = TestRDF2JSON.create_input(:ntriples)
+      @output = Tempfile.new('rdf2json-converter-output')
+    end
+
+    after do
+      @input.unlink
+      @output.unlink
+    end
+
+    it 'input: N-Triples; output: JSON-LD' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :ntriples, :jsonld, nil, nil)
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"@id":"s1","http://test/p1":[{"@id":"o1"}],"p2":[{"@value":"l1"}],"p3":[{"@id":"o3"},{"@id":"o4"}]}' + "\n",
+                          '{"@id":"s2","p4":[{"@value":"l2"}]}' + "\n"
+                        ],
+                        json)
+    end
+
+    it 'input: N-Triples; output: JSON (minified JSON-LD)' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :ntriples, :json, nil, nil)
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"@id":"s1","http://test/p1":["o1"],"p2":["l1"],"p3":["o3","o4"]}' + "\n",
+                          '{"@id":"s2","p4":["l2"]}' + "\n"
+                        ],
+                        json)
+    end
+
+    it 'input: N-Triples; output: JSON (minified JSON-LD); namespace: primary_key' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :ntriples, :json, 'primary_key', nil)
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"http://test/p1":["o1"],"p2":["l1"],"p3":["o3","o4"],"primary_key":"s1"}' + "\n",
+                          '{"p4":["l2"],"primary_key":"s2"}' + "\n"
+                        ],
+                        json)
+    end
+
+    it 'input: N-Triples; output: JSON (minified JSON-LD); prefix: http://test/' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :ntriples, :json, nil, 'http://test/')
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"@id":"s1","p2":["l1"],"p3":["o3","o4"],"p1":["o1"]}' + "\n",
+                          '{"@id":"s2","p4":["l2"]}' + "\n"
+                        ],
+                        json)
+    end
+
+    it 'input: N-Triples; output: JSON (minified JSON-LD); namespace: primary_key, prefix: http://test/' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :ntriples, :json, 'primary_key', 'http://test/')
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"p2":["l1"],"p3":["o3","o4"],"primary_key":"s1","p1":["o1"]}' + "\n",
+                          '{"p4":["l2"],"primary_key":"s2"}' + "\n"
+                        ],
+                        json)
+    end
+
+  end
+
+  # N-Quads to JSON/JSON-LD tests; assumes that namespace and prefix handling are not affected
+  # by the change of input format (hence, not tested again).
+  describe 'N-Quads conversion' do
+    before do
+      @input = TestRDF2JSON.create_input(:nquads)
+      @output = Tempfile.new('rdf2json-converter-output')
+    end
+
+    after do
+      @input.unlink
+      @output.unlink
+    end
+
+    it 'input: N-Quads; output: JSON-LD' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :nquads, :jsonld, nil, nil)
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"@id":"s1","http://test/p1":[{"@id":"o1"}],"p2":[{"@value":"l1"}],"p3":[{"@id":"o3"},{"@id":"o4"}]}' + "\n",
+                          '{"@id":"s2","p4":[{"@value":"l2"}]}' + "\n"
+                        ],
+                        json)
+    end
+
+    it 'input: N-Quads; output: JSON (minified JSON-LD)' do
+      converter = RDF2JSON::Converter.new(@input.path, @output.path, :nquads, :json, nil, nil)
+      converter.convert
+      
+      json = TestRDF2JSON.get_json(@output)
+      TestRDF2JSON.test([
+                          '{"@id":"s1","http://test/p1":["o1"],"p2":["l1"],"p3":["o3","o4"]}' + "\n",
+                          '{"@id":"s2","p4":["l2"]}' + "\n"
+                        ],
+                        json)
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rdf2json
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.1.0
 platform: ruby
 authors:
 - Joachim Baran
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-05-28 00:00:00.000000000 Z
+date: 2014-05-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rdf
@@ -38,6 +38,34 @@ dependencies:
     - - '>='
       - !ruby/object:Gem::Version
         version: 1.1.3
+- !ruby/object:Gem::Dependency
+  name: coveralls
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 5.3.4
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 5.3.4
 - !ruby/object:Gem::Dependency
   name: shoulda
   requirement: !ruby/object:Gem::Requirement
@@ -128,7 +156,7 @@ files:
 - lib/rdf2json.rb
 - lib/rdf2json/rdf2json.rb
 - test/helper.rb
-- test/test_bio-rdf2json.rb
+- test/test_rdf2json.rb
 - bin/rdf2json
 homepage: http://github.com/joejimbo/rdf2json
 licenses:

data/test/test_bio-rdf2json.rb

@@ -1,7 +0,0 @@
-require 'helper'
-
-class TestBioRdf2json < Test::Unit::TestCase
-  should "probably rename this file and start testing for real" do
-    flunk "hey buddy, you should probably rename this file and start testing for real"
-  end
-end