Class: Iev::TermBuilder
Constant Summary
Constants included
from Utilities
Utilities::FIGURE_ONE_REGEX, Utilities::FIGURE_TWO_REGEX, Utilities::IEV_CODE_RE, Utilities::IEV_CODE_TEXT_RE, Utilities::IMAGE_PATH_PREFIX, Utilities::SIMG_PATH_REGEX
Instance Attribute Summary collapse
Class Method Summary
collapse
Instance Method Summary
collapse
Methods included from Utilities
#parse_anchor_tag, #replace_newlines
Methods included from Cli::Ui
debug, error, info, progress, set_ui_tag, warn
Constructor Details
Returns a new instance of TermBuilder.
13
14
15
|
# File 'lib/iev/term_builder.rb', line 13
def initialize(data)
@data = data
end
|
Instance Attribute Details
#data ⇒ Object
Returns the value of attribute data.
25
26
27
|
# File 'lib/iev/term_builder.rb', line 25
def data
@data
end
|
Class Method Details
.build_from(data) ⇒ Object
21
22
23
|
# File 'lib/iev/term_builder.rb', line 21
def self.build_from(data)
new(data).build
end
|
Instance Method Details
#build ⇒ Object
17
18
19
|
# File 'lib/iev/term_builder.rb', line 17
def build
build_term_object
end
|
#build_concept_data ⇒ Object
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
|
# File 'lib/iev/term_builder.rb', line 59
def build_concept_data
cd = Glossarist::ConceptData.new
cd.id = term_id
cd.language_code = term_language
pub_date = flesh_date(find_value_for("PUBLICATIONDATE"))
if pub_date
cd.dates = [
Glossarist::ConceptDate.new(type: "accepted", date: pub_date),
Glossarist::ConceptDate.new(type: "amended", date: pub_date),
]
cd.review_date = pub_date
cd.review_decision_date = pub_date
end
cd.review_decision_event = "published"
definition =
cd.definition = [definition] if definition
cd.examples =
cd.notes =
cd.terms =
domain = extract_domain
cd.domain = domain if domain
sources =
cd.sources = sources if sources&.any?
related =
cd.related = related if related&.any?
cd
end
|
#build_term_object ⇒ Object
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
# File 'lib/iev/term_builder.rb', line 42
def build_term_object
set_ui_tag "#{term_id} (#{term_language})"
progress "Processing term #{term_id} (#{term_language})..."
split_definition
concept_data = build_concept_data
concept = Glossarist::LocalizedConcept.new
concept.data = concept_data
concept.id = term_id
concept.entry_status =
concept.classification =
concept
end
|
265
266
267
268
269
270
271
272
273
274
275
|
# File 'lib/iev/term_builder.rb', line 265
def
source_val = find_value_for("SOURCE")
return nil if source_val.nil?
sources = SourceParser.new(source_val, term_domain)
.parsed_sources
.compact
sources.each { |src| src.type = "authoritative" }
sources.empty? ? nil : sources
end
|
250
251
252
253
254
255
256
257
258
259
260
261
262
263
|
# File 'lib/iev/term_builder.rb', line 250
def
classification_val = find_value_for("SYNONYM1STATUS")
case classification_val
when nil, ""
nil
when "认可的", "допустимый", "admitido"
"admitted"
when "首选的", "suositettava", "suositeltava", "рекомендуемый", "preferente"
"preferred"
else
classification_val.downcase
end
end
|
223
224
225
226
227
228
|
# File 'lib/iev/term_builder.rb', line 223
def
return unless @definition
content = convert_content(@definition)
Glossarist::DetailedDefinition.new(content: content)
end
|
#extract_domain ⇒ Object
Derives the domain (subject area section) from the IEVREF identifier.
Returns the section or area title text as a localized string. Per the concept model, ConceptData#domain is a LocalizedString (the domain name), not a URI. Structural membership is expressed via ManagedConceptData#domains[] with ConceptReference objects.
111
112
113
114
115
116
117
118
119
120
121
122
123
|
# File 'lib/iev/term_builder.rb', line 111
def extract_domain
return nil unless term_id
code = IevCode.new(term_id)
section = Iev.find_section(code.section_code) if code.section_code
return section.title if section
area = Iev.find_subject_area(code.area_code)
area&.title
rescue StandardError => e
warn "IEV: extract_domain failed for #{term_id}: #{e.message}"
nil
end
|
244
245
246
247
248
|
# File 'lib/iev/term_builder.rb', line 244
def
case find_value_for("STATUS").downcase
when "standard" then "valid"
end
end
|
230
231
232
233
234
235
|
# File 'lib/iev/term_builder.rb', line 230
def
@examples.map do |str|
content = convert_content((str))
Glossarist::DetailedDefinition.new(content: content)
end
end
|
218
219
220
221
|
# File 'lib/iev/term_builder.rb', line 218
def
raw_term = find_value_for("SYMBOLE")
raw_term && build_symbol_designation(raw_term)
end
|
237
238
239
240
241
242
|
# File 'lib/iev/term_builder.rb', line 237
def
@notes.map do |str|
content = convert_content((str))
Glossarist::DetailedDefinition.new(content: content)
end
end
|
190
191
192
193
194
195
196
197
198
199
|
# File 'lib/iev/term_builder.rb', line 190
def
raw_term = find_value_for("TERM")
raw_term = "NA" if raw_term == "....."
build_expression_designation(
raw_term,
attribute_data: find_value_for("TERMATTRIBUTE"),
status: "preferred",
)
end
|
277
278
279
280
281
282
|
# File 'lib/iev/term_builder.rb', line 277
def
replaces_val = find_value_for("REPLACES")
return nil if replaces_val.nil?
SupersessionParser.new(replaces_val).supersessions
end
|
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
|
# File 'lib/iev/term_builder.rb', line 201
def
retval = (1..3).map do |num|
designations = find_value_for("SYNONYM#{num}") || ""
designations.split(/<[pbr]+>/).map do |raw_term|
build_expression_designation(
raw_term,
attribute_data: find_value_for("SYNONYM#{num}ATTRIBUTE"),
status: find_value_for("SYNONYM#{num}STATUS")&.downcase,
)
end
end
retval.flatten.compact
end
|
182
183
184
185
186
187
188
|
# File 'lib/iev/term_builder.rb', line 182
def
[
,
*,
,
].compact
end
|
#find_value_for(key) ⇒ Object
27
28
29
|
# File 'lib/iev/term_builder.rb', line 27
def find_value_for(key)
data.fetch(key.to_sym, nil)&.sanitize
end
|
#flesh_date(incomplete_date) ⇒ Object
31
32
33
34
35
36
37
38
39
40
|
# File 'lib/iev/term_builder.rb', line 31
def flesh_date(incomplete_date)
return incomplete_date if incomplete_date.nil? || incomplete_date.empty?
year, month, day = incomplete_date.split("-")
month ||= "01"
day ||= "01"
DateTime.parse("#{year}-#{month}-#{day}").to_s
end
|
#split_definition ⇒ Object
Splits unified definition (from the spreadsheet) into separate definition, examples, and notes strings (for YAMLs).
Sets @definition, @examples and @notes variables.
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
# File 'lib/iev/term_builder.rb', line 129
def split_definition
slicer_rx = %r{
\s*
(?:<p>\s*)?
(
(?<example>
# English example
\bEXAMPLE\b |
^\bExamples\s+are\b: |
^\bExamples\b: |
^\bExample\b: |
# French examples
\bEXEMPLE\b |
^\bExemples\b:
)
|
(?<note>
Note\s*\d+\sto\sentry: |
Note \d+\sto\sentry: |
Note\s*\d+\sto\sthe\sentry: |
Note\sto\sentry\s*\d+: |
Note\s*\d+?\sà\sl'article: |
<NOTE/?>?\s*\d?\s+[–-]\s* |
NOTE(?:\s+-)?\s* |
Note\s+\d+\s[–-]\s* |
Note \d+\s
)
)
\s*
}x
@examples = []
@notes = []
definition_arr = []
next_part_arr = definition_arr
remaining_str = find_value_for("DEFINITION")
while (md = remaining_str&.match(slicer_rx))
next_part = md.pre_match
next_part.sub!(/^\[:Ex(a|e)mple\]/, 'Ex\1mple')
next_part_arr.push(next_part)
next_part_arr = md[:example] ? @examples : @notes
remaining_str = md.post_match
remaining_str.sub!(/^Ex(a|e)mple/, '[:Ex\1mple]') if md[:note]
end
remaining_str&.sub!(/^\[:Ex(a|e)mple\]/, 'Ex\1mple')
next_part_arr.push(remaining_str)
@definition = definition_arr.first
@definition = nil if @definition&.empty?
end
|
#term_domain ⇒ Object
97
98
99
|
# File 'lib/iev/term_builder.rb', line 97
def term_domain
@term_domain ||= term_id.slice(0, 3)
end
|
#term_id ⇒ Object
93
94
95
|
# File 'lib/iev/term_builder.rb', line 93
def term_id
@term_id ||= find_value_for("IEVREF")
end
|
#term_language ⇒ Object
101
102
103
|
# File 'lib/iev/term_builder.rb', line 101
def term_language
@term_language ||= find_value_for("LANGUAGE").to_three_char_code
end
|