tao_rdfizer 0.9.11 → 0.10.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/tao_rdfizer/tao_rdfizer.rb +55 -23
- metadata +3 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 112cb7c3d78d77ca2df491e26f05eeb52334ed291483bb6bfa586bf707304608
|
4
|
+
data.tar.gz: e4bbdf5b014fed6779dc79f3b786a2d9d066a2a4dd9a8a1e8a87dec466d908ae
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: a291bf21a29a638ec0c3b42b16ff06e7530a8d7245965fb0901f7b4452358d6ecc7876a89c8d8c244a89fb7f47276c9105fb9b301311c09e51b86a5c0e1576dd
|
7
|
+
data.tar.gz: ad6a621f7a38146ee0ca0eccaa1b2c709a315b2d39bd000c801c4249f7fee0ecf22600fef4ff8baeb6160cf155e4fa033034d4aff5fa1d0d8cf4e9b78d16a5c8
|
@@ -19,7 +19,12 @@ class TAO::RDFizer
|
|
19
19
|
@prefix_ttl_erb = ERB.new(ERB_PREFIXES_TTL, nil, '-')
|
20
20
|
end
|
21
21
|
|
22
|
-
def rdfize(annotations_col)
|
22
|
+
def rdfize(annotations_col, with_prefix = true)
|
23
|
+
# check the format
|
24
|
+
annotations_col.each do |annotations|
|
25
|
+
raise "'target' is missing" unless annotations.has_key? :target
|
26
|
+
end
|
27
|
+
|
23
28
|
# namespaces
|
24
29
|
namespaces = {}
|
25
30
|
|
@@ -27,6 +32,7 @@ class TAO::RDFizer
|
|
27
32
|
anns[:namespaces].each {|n| namespaces[n[:prefix]] = n[:uri]} unless anns[:namespaces].nil?
|
28
33
|
|
29
34
|
unless @mode ==:spans
|
35
|
+
raise ArgumentError, "A project name has to be specified." unless anns.has_key?(:project)
|
30
36
|
prefix_for_this = anns[:project].downcase.gsub(/ /, '_')
|
31
37
|
raise ArgumentError, "'#{prefix_for_this}' is a reserved prefix for this project." if namespaces.has_key?(prefix_for_this)
|
32
38
|
project_uri = 'http://pubannotation.org/projects/' + anns[:project]
|
@@ -34,6 +40,7 @@ class TAO::RDFizer
|
|
34
40
|
end
|
35
41
|
|
36
42
|
denotations = []
|
43
|
+
attributes = []
|
37
44
|
relations = []
|
38
45
|
spans = []
|
39
46
|
|
@@ -46,34 +53,57 @@ class TAO::RDFizer
|
|
46
53
|
end
|
47
54
|
|
48
55
|
# denotations and relations
|
49
|
-
_denotations = annotations[:denotations]
|
50
|
-
|
51
|
-
|
52
|
-
_relations = [] if _relations.nil?
|
56
|
+
_denotations = annotations[:denotations] || []
|
57
|
+
_attributes = annotations[:attributes] || []
|
58
|
+
_relations = annotations[:relations] || []
|
53
59
|
if @mode == :spans && annotations.has_key?(:tracks)
|
54
60
|
annotations[:tracks].each do |track|
|
55
61
|
_denotations += track[:denotations]
|
62
|
+
_attributes += track[:attributes]
|
56
63
|
_relations += track[:relations]
|
57
64
|
end
|
58
65
|
end
|
59
66
|
|
60
67
|
begin
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
+
if @mode == :annotations
|
69
|
+
# index attributes
|
70
|
+
attributesh = _attributes.inject({}) do |h, a|
|
71
|
+
if a[:pred].end_with?('_id')
|
72
|
+
subj = a[:subj]
|
73
|
+
h[subj] = [] unless h.has_key? subj
|
74
|
+
h[subj] << a[:obj]
|
75
|
+
end
|
76
|
+
h
|
77
|
+
end
|
78
|
+
|
79
|
+
# denotations preprocessing
|
80
|
+
_denotations.each do |d|
|
81
|
+
span_uri = "<#{text_uri}/spans/#{d[:span][:begin]}-#{d[:span][:end]}>"
|
82
|
+
d[:span_uri] = span_uri
|
83
|
+
d[:obj_uri] = "#{prefix_for_this}:#{text_id}-#{d[:id]}"
|
84
|
+
class_uris = (attributesh[d[:id]] || []).push(d[:obj])
|
85
|
+
d[:class_uris] = class_uris.map{|uri| find_uri(uri, namespaces, prefix_for_this)}
|
86
|
+
rescue ArgumentError => e
|
87
|
+
raise ArgumentError, "[#{sourcedb}-#{sourceid}-#{d[:id]}] " + e.message
|
88
|
+
end
|
68
89
|
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
90
|
+
# relations preprocessing
|
91
|
+
_relations.each do |r|
|
92
|
+
r[:subj_uri] = "#{prefix_for_this}:#{text_id}-#{r[:subj]}"
|
93
|
+
r[:obj_uri] = "#{prefix_for_this}:#{text_id}-#{r[:obj]}"
|
94
|
+
r[:pred_uri] = find_uri(r[:pred], namespaces, prefix_for_this)
|
95
|
+
rescue ArgumentError => e
|
96
|
+
raise ArgumentError, "[#{sourcedb}-#{sourceid}-#{r[:id]}] " + e.message
|
97
|
+
end
|
98
|
+
else
|
99
|
+
# denotations preprocessing
|
100
|
+
_denotations.each do |d|
|
101
|
+
span_uri = "<#{text_uri}/spans/#{d[:span][:begin]}-#{d[:span][:end]}>"
|
102
|
+
d[:span_uri] = span_uri
|
103
|
+
rescue ArgumentError => e
|
104
|
+
raise ArgumentError, "[#{sourcedb}-#{sourceid}-#{d[:id]}] " + e.message
|
105
|
+
end
|
74
106
|
end
|
75
|
-
rescue ArgumentError => e
|
76
|
-
raise ArgumentError, "[#{sourcedb}-#{sourceid}] " + e
|
77
107
|
end
|
78
108
|
|
79
109
|
unless @mode == :annotations
|
@@ -88,7 +118,7 @@ class TAO::RDFizer
|
|
88
118
|
s[:text] = text[s[:begin] ... s[:end]]
|
89
119
|
end
|
90
120
|
|
91
|
-
# index
|
121
|
+
# index spans
|
92
122
|
spanh = _spans.inject({}){|r, s| r[s[:span_uri]] = s; r}
|
93
123
|
|
94
124
|
# add denotation information
|
@@ -142,7 +172,9 @@ class TAO::RDFizer
|
|
142
172
|
spans += _spans unless @mode == :annotations
|
143
173
|
end
|
144
174
|
|
145
|
-
ttl
|
175
|
+
ttl = ''
|
176
|
+
ttl += @prefix_ttl_erb.result(binding) if with_prefix
|
177
|
+
ttl += @tao_ttl_erb.result(binding)
|
146
178
|
end
|
147
179
|
|
148
180
|
private
|
@@ -172,7 +204,7 @@ class TAO::RDFizer
|
|
172
204
|
clabel = if label.match(/^\W+$/)
|
173
205
|
'SYM'
|
174
206
|
else
|
175
|
-
label.sub(/^\W+/, '').sub(
|
207
|
+
label.sub(/^\W+/, '').sub(/[^a-zA-Z0-9_)]+$/, '').gsub(/ +/, '_')
|
176
208
|
end
|
177
209
|
namespaces.has_key?('_base') ? "<#{clabel}>" : "#{prefix_for_this}:#{clabel.gsub('(', '\(').gsub(')', '\)')}"
|
178
210
|
end
|
@@ -181,7 +213,7 @@ class TAO::RDFizer
|
|
181
213
|
ERB_ANNOTATIONS_TTL = <<~HEREDOC
|
182
214
|
<% denotations.each do |d| -%>
|
183
215
|
<%= d[:obj_uri] %> tao:denoted_by <%= d[:span_uri] %> ;
|
184
|
-
|
216
|
+
<%= d[:class_uris].map{|c| "\trdf:type " + c}.join(" ;\n") + " ." %>
|
185
217
|
<% end -%>
|
186
218
|
<%# relations -%>
|
187
219
|
<% relations.each do |r| -%>
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: tao_rdfizer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.10.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Jin-Dong Kim
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2021-05-15 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: It uses TAO (text annotation ontology) for representation of annotations
|
14
14
|
to text.
|
@@ -40,8 +40,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
40
40
|
- !ruby/object:Gem::Version
|
41
41
|
version: '0'
|
42
42
|
requirements: []
|
43
|
-
|
44
|
-
rubygems_version: 2.7.9
|
43
|
+
rubygems_version: 3.0.9
|
45
44
|
signing_key:
|
46
45
|
specification_version: 4
|
47
46
|
summary: A RDF statement generator for annotations in the PubAnnotation JSON format.
|