alchemy-concept-extractor 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. checksums.yaml +7 -0
  2. data/lib/alchemy-concept-extractor.rb +72 -0
  3. metadata +142 -0
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 69f2c86990c3effefcc3824cb20a9a103e55d023
4
+ data.tar.gz: a6703d0c41bf75220ed400cd29e4d90b11e39485
5
+ SHA512:
6
+ metadata.gz: 72c6b270eb46c580dc38e6f3ca33e8856c5fbabd20e1528c40845dfdf4c10cad2abe164c8bb318beeafb610623c5d1421ea44d477d89b297178db13bfeb0ab86
7
+ data.tar.gz: 68abbd8612bbe9bd2e5cac02abb2edf98ca0176960a920ca6573c081980cdab8683088f98acb00e65626240fadb902c256765be302cc13a68ad00d535849e463
@@ -0,0 +1,72 @@
1
+ module AlchemyConceptExtractor
2
+ require 'uri'
3
+ require 'readline'
4
+ require 'rest_client'
5
+ require 'json'
6
+ require 'pp'
7
+ require 'rdf'
8
+
9
+ include RDF
10
+
11
+ require_relative 'models/extractor.rb'
12
+ require_relative 'models/reporter.rb'
13
+ require_relative 'models/refiner.rb'
14
+
15
+ class ConceptExtractor
16
+ attr :api_key
17
+ attr :outfile_location
18
+ attr :datfile_location
19
+ attr :output_format
20
+ attr :rest_client
21
+ attr :refiner
22
+
23
+ def initialize(api_key,
24
+ outfile_location,
25
+ datfile_location = "uris.dat",
26
+ output_format = :ntriples,
27
+ rest_client = RestClient)
28
+
29
+ @api_key = api_key
30
+ @outfile_location = outfile_location
31
+ @datfile_location = datfile_location
32
+ @output_format = output_format
33
+ @rest_client = rest_client
34
+ @refiner = Refiner.new
35
+ end
36
+
37
+ def uris
38
+ uris_file = IO.read(@datfile_location)
39
+ uris = uris_file.split("\n")
40
+
41
+ uris
42
+ end
43
+
44
+ def append_graph_to_file(graph)
45
+ reporter = Reporter.new(graph)
46
+ serialised_rdf = reporter.report(@output_format)
47
+
48
+ File.open outfile_location, 'a' do |file|
49
+ file.puts serialised_rdf
50
+ end
51
+ end
52
+
53
+ def extract
54
+ extractor = Extractor.new(@api_key,@rest_client)
55
+
56
+ File.delete @outfile_location if File.exist? @outfile_location
57
+ uris.each do | uri |
58
+ puts "Disambiguating: #{uri}"
59
+
60
+ concepts = extractor.get_concepts uri
61
+ graph = @refiner.refine(concepts)
62
+ append_graph_to_file(graph)
63
+ end
64
+ end
65
+ end
66
+
67
+ def self.extract(api_key,datfile_location,outfile_location,output_format = :ntriples, rest_client = RestClient)
68
+ concept_extractor = ConceptExtractor.new(api_key,outfile_location,datfile_location,output_format,rest_client)
69
+ concept_extractor.extract
70
+ end
71
+
72
+ end
metadata ADDED
@@ -0,0 +1,142 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: alchemy-concept-extractor
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.1
5
+ platform: ruby
6
+ authors:
7
+ - Philip Lamond
8
+ - Robert Kenny
9
+ autorequire:
10
+ bindir: bin
11
+ cert_chain: []
12
+ date: 2012-09-25 00:00:00.000000000 Z
13
+ dependencies:
14
+ - !ruby/object:Gem::Dependency
15
+ name: rest-client
16
+ requirement: !ruby/object:Gem::Requirement
17
+ requirements:
18
+ - - '>='
19
+ - !ruby/object:Gem::Version
20
+ version: 1.6.7
21
+ type: :runtime
22
+ prerelease: false
23
+ version_requirements: !ruby/object:Gem::Requirement
24
+ requirements:
25
+ - - '>='
26
+ - !ruby/object:Gem::Version
27
+ version: 1.6.7
28
+ - !ruby/object:Gem::Dependency
29
+ name: json
30
+ requirement: !ruby/object:Gem::Requirement
31
+ requirements:
32
+ - - '>='
33
+ - !ruby/object:Gem::Version
34
+ version: 1.7.5
35
+ type: :runtime
36
+ prerelease: false
37
+ version_requirements: !ruby/object:Gem::Requirement
38
+ requirements:
39
+ - - '>='
40
+ - !ruby/object:Gem::Version
41
+ version: 1.7.5
42
+ - !ruby/object:Gem::Dependency
43
+ name: rdf
44
+ requirement: !ruby/object:Gem::Requirement
45
+ requirements:
46
+ - - '>='
47
+ - !ruby/object:Gem::Version
48
+ version: 0.3.8
49
+ type: :runtime
50
+ prerelease: false
51
+ version_requirements: !ruby/object:Gem::Requirement
52
+ requirements:
53
+ - - '>='
54
+ - !ruby/object:Gem::Version
55
+ version: 0.3.8
56
+ - !ruby/object:Gem::Dependency
57
+ name: rdf-rdfxml
58
+ requirement: !ruby/object:Gem::Requirement
59
+ requirements:
60
+ - - '>='
61
+ - !ruby/object:Gem::Version
62
+ version: 0.3.8
63
+ type: :runtime
64
+ prerelease: false
65
+ version_requirements: !ruby/object:Gem::Requirement
66
+ requirements:
67
+ - - '>='
68
+ - !ruby/object:Gem::Version
69
+ version: 0.3.8
70
+ - !ruby/object:Gem::Dependency
71
+ name: rdf-trig
72
+ requirement: !ruby/object:Gem::Requirement
73
+ requirements:
74
+ - - '>='
75
+ - !ruby/object:Gem::Version
76
+ version: 0.1.3
77
+ type: :runtime
78
+ prerelease: false
79
+ version_requirements: !ruby/object:Gem::Requirement
80
+ requirements:
81
+ - - '>='
82
+ - !ruby/object:Gem::Version
83
+ version: 0.1.3
84
+ - !ruby/object:Gem::Dependency
85
+ name: rdf-turtle
86
+ requirement: !ruby/object:Gem::Requirement
87
+ requirements:
88
+ - - '>='
89
+ - !ruby/object:Gem::Version
90
+ version: 0.1.2
91
+ type: :runtime
92
+ prerelease: false
93
+ version_requirements: !ruby/object:Gem::Requirement
94
+ requirements:
95
+ - - '>='
96
+ - !ruby/object:Gem::Version
97
+ version: 0.1.2
98
+ - !ruby/object:Gem::Dependency
99
+ name: rdf-xsd
100
+ requirement: !ruby/object:Gem::Requirement
101
+ requirements:
102
+ - - '>='
103
+ - !ruby/object:Gem::Version
104
+ version: 0.3.8
105
+ type: :runtime
106
+ prerelease: false
107
+ version_requirements: !ruby/object:Gem::Requirement
108
+ requirements:
109
+ - - '>='
110
+ - !ruby/object:Gem::Version
111
+ version: 0.3.8
112
+ description: Extracts concepts for a given URI from the Alchemy API (http://www.alchemyapi.com/)
113
+ email: philip.lamond@bbc.co.uk
114
+ executables: []
115
+ extensions: []
116
+ extra_rdoc_files: []
117
+ files:
118
+ - lib/alchemy-concept-extractor.rb
119
+ homepage: https://github.com/BBC-Knowlearn/alchemy-concept-extractor.git
120
+ licenses: []
121
+ metadata: {}
122
+ post_install_message:
123
+ rdoc_options: []
124
+ require_paths:
125
+ - lib
126
+ required_ruby_version: !ruby/object:Gem::Requirement
127
+ requirements:
128
+ - - '>='
129
+ - !ruby/object:Gem::Version
130
+ version: '0'
131
+ required_rubygems_version: !ruby/object:Gem::Requirement
132
+ requirements:
133
+ - - '>='
134
+ - !ruby/object:Gem::Version
135
+ version: '0'
136
+ requirements: []
137
+ rubyforge_project:
138
+ rubygems_version: 2.0.3
139
+ signing_key:
140
+ specification_version: 4
141
+ summary: Alchemy API Concept Extractor
142
+ test_files: []