-
Notifications
You must be signed in to change notification settings - Fork 1
/
term_builder.rb
406 lines (344 loc) · 12.9 KB
/
term_builder.rb
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
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
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
# frozen_string_literal: true
# (c) Copyright 2020 Ribose Inc.
#
require "pp"
module IEV
module Termbase
class TermBuilder
include CLI::UI
using DataConversions
NOTE_REGEX_1 = /Note[\s ]*\d+[\s ]to entry:\s+|Note[\s ]*\d+?[\s ]à l['’]article:[\s ]*|<NOTE\/?>?[\s ]*\d?[\s ]+.*?–\s+|NOTE[\s ]+-[\s ]+/i
NOTE_REGEX_2 = /\nNOTE\s+/
def initialize(data)
@data = data
end
def build
build_term_object
end
def self.build_from(data)
new(data).build
end
attr_reader :data
def find_value_for(key)
data.fetch(key.to_sym, nil)&.sanitize
end
def flesh_date(incomplete_date)
return incomplete_date if incomplete_date.nil? || incomplete_date.empty?
# FIXME: this is a terrible assumption but the IEV export only provides
# year and month
year, month = incomplete_date.split('-')
DateTime.parse("#{year}-#{month}-01").to_s
end
def build_term_object
row_term_id = find_value_for("IEVREF")
row_lang = find_value_for("LANGUAGE").to_three_char_code
set_ui_tag "#{row_term_id} (#{row_lang})"
progress "Processing term #{row_term_id} (#{row_lang})..."
IEV::Termbase::Term.new(
id: row_term_id,
entry_status: extract_entry_status,
classification: find_value_for("SYNONYM1STATUS"),
date_accepted: flesh_date(find_value_for("PUBLICATIONDATE")),
date_amended: flesh_date(find_value_for("PUBLICATIONDATE")),
review_date: flesh_date(find_value_for("PUBLICATIONDATE")),
review_decision_date: flesh_date(find_value_for("PUBLICATIONDATE")),
review_decision_event: "published",
# Beautification
#
terms: extract_terms,
notes: definition_values[:notes].map do |note|
mathml_to_asciimath(note)
end,
examples: definition_values[:examples].map do |example|
mathml_to_asciimath(example)
end,
definition: extract_definition_value,
authoritative_source: extract_authoritative_source,
language_code: row_lang,
superseded_concepts: extract_superseded_concepts,
# @todo: Unsorted Attributes
#
# We need to revisit this attributes and also update
# the correct mapping with the existing attributes.
#
abbrev: nil,
alt: nil,
country_code: nil,
review_indicator: nil,
authoritative_source_similarity: nil,
lineage_source: nil,
review_status: nil,
review_type: nil,
review_decision_notes: nil,
)
end
def definition_values
@definition_values ||= split_definition
end
def replace_newlines(input)
input.gsub('\n', "\n\n").gsub(/<[pbr]+>/, "\n\n").gsub(/\s*\n[\n\s]+/, "\n\n").strip
end
def split_definition
definition = parse_anchor_tag(find_value_for("DEFINITION"))
definitions = { notes: [], examples: [], definition: nil }
return definitions unless definition
definition = replace_newlines(definition)
# Remove mathml <annotation> tag
# puts "DDDD"*10
# # puts definition
# puts "DDDD"*10
# definition = parse_anchor_tag(definition)
# #.to_s.gsub(/<annotation.*?>.*?<\/annotation>/,"").gsub(/<\/?semantics>/,"")
# puts definition
# puts "EEEE"*10
example_block = definition.match(/[\r\n](EXAMPLE|EXEMPLE) (.*?)\r?$/).to_s
if example_block && !example_block.strip.empty?
# We only take the latter captured part
definitions[:examples] = [Regexp.last_match(2).strip]
definition = definition.gsub("#{Regexp.last_match(1)} #{Regexp.last_match(2)}", "")
end
note_split = definition.split(NOTE_REGEX_1).map do |note|
note.split(NOTE_REGEX_2)
end.flatten
definitions[:definition] = note_split.first
definitions[:notes] = note_split[1..-1].map(&:strip) if note_split.size > 1
definitions
end
def extract_terms
[
extract_primary_designation,
*extract_synonymous_designations,
extract_international_symbol_designation,
].compact
end
def extract_primary_designation
raw_term = find_value_for("TERM")
raw_term = "NA" if raw_term == "....."
term = mathml_to_asciimath(parse_anchor_tag(raw_term))
IEV::Termbase::NestedTermBuilder.build(
type: "expression",
term: term,
data: find_value_for("TERMATTRIBUTE"),
status: "Preferred",
)
end
def extract_synonymous_designations
retval = (1..3).map do |num|
designations = find_value_for("SYNONYM#{num}") || ""
# Some synonyms have more than one entry
designations.split(/<[pbr]+>/).map do |raw_term|
term = mathml_to_asciimath(parse_anchor_tag(raw_term))
IEV::Termbase::NestedTermBuilder.build(
type: "expression",
term: term,
data: find_value_for("SYNONYM#{num}ATTRIBUTE"),
status: find_value_for("SYNONYM#{num}STATUS"),
)
end
end
retval.flatten.compact
end
def extract_international_symbol_designation
term = mathml_to_asciimath(parse_anchor_tag(find_value_for("SYMBOLE")))
IEV::Termbase::NestedTermBuilder.build(
type: "symbol",
international: true,
term: term,
)
end
def text_to_asciimath(text)
html_entities_to_asciimath(text.decode_html)
end
def html_to_asciimath(input)
return input if input.nil? || input.empty?
to_asciimath = Nokogiri::HTML.fragment(input, "UTF-8")
to_asciimath.css('i').each do |math_element|
# puts "HTML MATH!! #{math_element.to_xml}"
# puts "HTML MATH!! #{math_element.text}"
decoded = text_to_asciimath(math_element.text)
case decoded.length
when 1..12
# puts "(#{math_element.text} to => #{decoded})"
math_element.replace "stem:[#{decoded}]"
when 0
math_element.remove
else
math_element.replace "_#{decoded}_"
end
end
to_asciimath.css('sub').each do |math_element|
case math_element.text.length
when 0
math_element.remove
else
math_element.replace "~#{text_to_asciimath(math_element.text)}~"
end
end
to_asciimath.css('sup').each do |math_element|
case math_element.text.length
when 0
math_element.remove
else
math_element.replace "^#{text_to_asciimath(math_element.text)}^"
end
end
to_asciimath.css('ol').each do |element|
element.css('li').each do |li|
li.replace ". #{li.text}"
end
end
to_asciimath.css('ul').each do |element|
element.css('li').each do |li|
li.replace "* #{li.text}"
end
end
# Replace sans-serif font with monospace
to_asciimath.css('font[style*="sans-serif"]').each do |x|
x.replace "`#{x.text}`"
end
html_entities_to_stem(
to_asciimath.children.to_s.gsub(/\]stem:\[/, '').gsub(/<\/?[uo]l>/, '')
)
end
def html_entities_to_asciimath(x)
x.gsub("α", "alpha").
gsub("β", "beta").
gsub("γ", "gamma").
gsub("Γ", "Gamma").
gsub("δ", "delta").
gsub("Δ", "Delta").
gsub("ε", "epsilon").
gsub("ϵ", "varepsilon").
gsub("ζ", "zeta").
gsub("η", "eta").
gsub("θ", "theta").
gsub("Θ", "Theta").
gsub("ϑ", "vartheta").
gsub("ι", "iota").
gsub("κ", "kappa").
gsub("λ", "lambda").
gsub("Λ", "Lambda").
gsub("μ", "mu").
gsub("ν", "nu").
gsub("ξ", "xi").
gsub("Ξ", "Xi").
gsub("π", "pi").
gsub("Π", "Pi").
gsub("ρ", "rho").
gsub("β", "beta").
gsub("σ", "sigma").
gsub("Σ", "Sigma").
gsub("τ", "tau").
gsub("υ", "upsilon").
gsub("φ", "phi").
gsub("Φ", "Phi").
gsub("ϕ", "varphi").
gsub("χ", "chi").
gsub("ψ", "psi").
gsub("Ψ", "Psi").
gsub("ω", "omega")
end
def html_entities_to_stem(x)
x.gsub("α", "stem:[alpha]").
gsub("β", "stem:[beta]").
gsub("γ", "stem:[gamma]").
gsub("Γ", "stem:[Gamma]").
gsub("δ", "stem:[delta]").
gsub("Δ", "stem:[Delta]").
gsub("ε", "stem:[epsilon]").
gsub("ϵ", "stem:[varepsilon]").
gsub("ζ", "stem:[zeta]").
gsub("η", "stem:[eta]").
gsub("θ", "stem:[theta]").
gsub("Θ", "stem:[Theta]").
gsub("ϑ", "stem:[vartheta]").
gsub("ι", "stem:[iota]").
gsub("κ", "stem:[kappa]").
gsub("λ", "stem:[lambda]").
gsub("Λ", "stem:[Lambda]").
gsub("μ", "stem:[mu]").
gsub("ν", "stem:[nu]").
gsub("ξ", "stem:[xi]").
gsub("Ξ", "stem:[Xi]").
gsub("π", "stem:[pi]").
gsub("Π", "stem:[Pi]").
gsub("ρ", "stem:[rho]").
gsub("β", "stem:[beta]").
gsub("σ", "stem:[sigma]").
gsub("Σ", "stem:[Sigma]").
gsub("τ", "stem:[tau]").
gsub("υ", "stem:[upsilon]").
gsub("φ", "stem:[phi]").
gsub("Φ", "stem:[Phi]").
gsub("ϕ", "stem:[varphi]").
gsub("χ", "stem:[chi]").
gsub("ψ", "stem:[psi]").
gsub("Ψ", "stem:[Psi]").
gsub("ω", "stem:[omega]")
end
def mathml_to_asciimath(input)
return input if input.nil? || input.empty? || !input.include?("<")
unless input.match?(/<math>/)
return html_to_asciimath(input)
end
# puts "GOING TO MATHML MATH"
# puts input
to_asciimath = Nokogiri::HTML.fragment(input, "UTF-8")
# to_asciimath.remove_namespaces!
to_asciimath.css('math').each do |math_element|
asciimath = MathML2AsciiMath.m2a(text_to_asciimath(math_element.to_xml)).strip
# puts"ASCIIMATH!! #{asciimath}"
if asciimath.empty?
math_element.remove
else
math_element.replace "stem:[#{asciimath}]"
end
end
html_to_asciimath(
to_asciimath.children.to_s
)
end
def extract_definition_value
if definition_values[:definition]
mathml_to_asciimath(definition_values[:definition].strip)
end
end
def extract_entry_status
case find_value_for("STATUS").downcase
when "standard" then "valid"
else nil
end
end
def extract_authoritative_source
source_val = find_value_for("SOURCE")
return nil if source_val.nil?
SourceParser.new(source_val).parsed_sources
end
def extract_superseded_concepts
replaces_val = find_value_for("REPLACES")
return nil if replaces_val.nil?
SupersessionParser.new(replaces_val).supersessions
end
SIMG_PATH_REGEX = "<simg .*\\/\\$file\\/([\\d\\-\\w\.]+)>"
FIGURE_ONE_REGEX = "<p><b>\\s*Figure\\s+(\\d)\\s+[–-]\\s+(.+)\\s*<\\/b>(<\\/p>)?"
FIGURE_TWO_REGEX = "#{FIGURE_ONE_REGEX}\\s*#{FIGURE_ONE_REGEX}"
def parse_anchor_tag(text)
if text
part_number = find_value_for("IEVREF").slice(0,3)
# Convert IEV term references
# Convert href links
# Need to take care of this pattern: `inverse de la <a href="IEV103-06-01">période<a>`
text.
gsub(/<a href="?(IEV)\s*(\d\d\d-\d\d-\d\d)"?>(.*?)<\/?a>/, '{{\3, \1:\2}}').
gsub(/<a href="?\s*(\d\d\d-\d\d-\d\d)"?>(.*?)<\/?a>/, '{{\3, IEV:\2}}').
gsub(/<a href="(.*?)">(.*?)<\/a>/, '\1[\2]').
gsub(Regexp.new([SIMG_PATH_REGEX, "\\s*", FIGURE_TWO_REGEX].join('')), "image::/assets/images/parts/#{part_number}/\\1[Figure \\2 - \\3; \\6]").
gsub(Regexp.new([SIMG_PATH_REGEX, "\\s*", FIGURE_ONE_REGEX].join('')), "image::/assets/images/parts/#{part_number}/\\1[Figure \\2 - \\3]").
gsub(/<img\s+(.+?)\s*>/, "image::/assets/images/parts/#{part_number}/\\1[]").
gsub(/<br>/, "\n").
gsub(/<b>(.*?)<\/b>/, "*\\1*")
end
end
end
end
end