relaton-iec 0.1.0
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.
- checksums.yaml +7 -0
- data/.gitignore +13 -0
- data/.rspec +3 -0
- data/.rubocop.yml +10 -0
- data/.travis.yml +16 -0
- data/Gemfile +6 -0
- data/Gemfile.lock +92 -0
- data/LICENSE.txt +21 -0
- data/README.adoc +52 -0
- data/Rakefile +6 -0
- data/appveyor.yml +30 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/relaton/processor.rb +23 -0
- data/lib/relaton_iec.rb +10 -0
- data/lib/relaton_iec/hit.rb +51 -0
- data/lib/relaton_iec/hit_collection.rb +67 -0
- data/lib/relaton_iec/iec_bibliography.rb +156 -0
- data/lib/relaton_iec/scrapper.rb +413 -0
- data/lib/relaton_iec/statuses.yml +132 -0
- data/lib/relaton_iec/version.rb +3 -0
- data/relaton_iec.gemspec +38 -0
- metadata +235 -0
@@ -0,0 +1,156 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# require 'isobib/iso_bibliographic_item'
|
4
|
+
require "relaton_iec/scrapper"
|
5
|
+
require "relaton_iec/hit_collection"
|
6
|
+
require "date"
|
7
|
+
|
8
|
+
module RelatonIec
|
9
|
+
# Class methods for search ISO standards.
|
10
|
+
class IecBibliography
|
11
|
+
class << self
|
12
|
+
# @param text [String]
|
13
|
+
# @return [RelatonIec::HitCollection]
|
14
|
+
def search(text, year = nil)
|
15
|
+
HitCollection.new text, year
|
16
|
+
rescue SocketError, OpenURI::HTTPError
|
17
|
+
warn "Could not access http://www.iec.ch"
|
18
|
+
[]
|
19
|
+
end
|
20
|
+
|
21
|
+
# @param text [String]
|
22
|
+
# @return [Array<IsoBibliographicItem>]
|
23
|
+
# def search_and_fetch(text, year = nil)
|
24
|
+
# Scrapper.get(text, year)
|
25
|
+
# end
|
26
|
+
|
27
|
+
# @param code [String] the ISO standard Code to look up (e..g "ISO 9000")
|
28
|
+
# @param year [String] the year the standard was published (optional)
|
29
|
+
# @param opts [Hash] options; restricted to :all_parts if all-parts reference is required
|
30
|
+
# @return [String] Relaton XML serialisation of reference
|
31
|
+
def get(code, year = nil, opts = {})
|
32
|
+
if year.nil?
|
33
|
+
/^(?<code1>[^:]+):(?<year1>[^:]+)$/ =~ code
|
34
|
+
unless code1.nil?
|
35
|
+
code = code1
|
36
|
+
year = year1
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
return iev if code.casecmp("IEV").zero?
|
41
|
+
|
42
|
+
code += "-1" if opts[:all_parts]
|
43
|
+
ret = iecbib_get1(code, year, opts)
|
44
|
+
return nil if ret.nil?
|
45
|
+
|
46
|
+
ret.to_most_recent_reference unless year || opts[:keep_year]
|
47
|
+
ret.to_all_parts if opts[:all_parts]
|
48
|
+
ret
|
49
|
+
end
|
50
|
+
|
51
|
+
private
|
52
|
+
|
53
|
+
def fetch_ref_err(code, year, missed_years)
|
54
|
+
id = year ? "#{code}:#{year}" : code
|
55
|
+
warn "WARNING: no match found online for #{id}. "\
|
56
|
+
"The code must be exactly like it is on the standards website."
|
57
|
+
warn "(There was no match for #{year}, though there were matches "\
|
58
|
+
"found for #{missed_years.join(', ')}.)" unless missed_years.empty?
|
59
|
+
if /\d-\d/ =~ code
|
60
|
+
warn "The provided document part may not exist, or the document "\
|
61
|
+
"may no longer be published in parts."
|
62
|
+
else
|
63
|
+
warn "If you wanted to cite all document parts for the reference, "\
|
64
|
+
"use \"#{code} (all parts)\".\nIf the document is not a standard, "\
|
65
|
+
"use its document type abbreviation (TS, TR, PAS, Guide)."
|
66
|
+
end
|
67
|
+
nil
|
68
|
+
end
|
69
|
+
|
70
|
+
def fetch_pages(s, n)
|
71
|
+
workers = RelatonBib::WorkersPool.new n
|
72
|
+
workers.worker { |w| { i: w[:i], hit: w[:hit].fetch } }
|
73
|
+
s.each_with_index { |hit, i| workers << { i: i, hit: hit } }
|
74
|
+
workers.end
|
75
|
+
workers.result.sort { |x, y| x[:i] <=> y[:i] }.map { |x| x[:hit] }
|
76
|
+
end
|
77
|
+
|
78
|
+
def isobib_search_filter(code)
|
79
|
+
docidrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+}
|
80
|
+
corrigrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+:[0-9]+/}
|
81
|
+
warn "fetching #{code}..."
|
82
|
+
result = search(code)
|
83
|
+
result.select do |i|
|
84
|
+
i.hit[:code] &&
|
85
|
+
i.hit[:code].match(docidrx).to_s == code &&
|
86
|
+
corrigrx !~ i.hit[:code]
|
87
|
+
end
|
88
|
+
end
|
89
|
+
|
90
|
+
def iev(code = "IEC 60050")
|
91
|
+
RelatonIsoBib::XMLParser.from_xml(<<~"END")
|
92
|
+
<bibitem>
|
93
|
+
<fetched>#{Date.today}</fetched>
|
94
|
+
<title format="text/plain" language="en" script="Latn">International Electrotechnical Vocabulary</title>
|
95
|
+
<link type="src">http://www.electropedia.org</link>
|
96
|
+
<docidentifier>#{code}:2011</docidentifier>
|
97
|
+
<date type="published"><on>2011</on></date>
|
98
|
+
<contributor>
|
99
|
+
<role type="publisher"/>
|
100
|
+
<organization>
|
101
|
+
<name>International Electrotechnical Commission</name>
|
102
|
+
<abbreviation>IEC</abbreviation>
|
103
|
+
<uri>www.iec.ch</uri>
|
104
|
+
</organization>
|
105
|
+
</contributor>
|
106
|
+
<language>en</language> <language>fr</language>
|
107
|
+
<script>Latn</script>
|
108
|
+
<status> <stage>60</stage> </status>
|
109
|
+
<copyright>
|
110
|
+
<from>2018</from>
|
111
|
+
<owner>
|
112
|
+
<organization>
|
113
|
+
<name>International Electrotechnical Commission</name>
|
114
|
+
<abbreviation>IEC</abbreviation>
|
115
|
+
<uri>www.iec.ch</uri>
|
116
|
+
</organization>
|
117
|
+
</owner>
|
118
|
+
</copyright>
|
119
|
+
</bibitem>
|
120
|
+
END
|
121
|
+
end
|
122
|
+
|
123
|
+
# Sort through the results from Isobib, fetching them three at a time,
|
124
|
+
# and return the first result that matches the code,
|
125
|
+
# matches the year (if provided), and which # has a title (amendments do not).
|
126
|
+
# Only expects the first page of results to be populated.
|
127
|
+
# Does not match corrigenda etc (e.g. ISO 3166-1:2006/Cor 1:2007)
|
128
|
+
# If no match, returns any years which caused mismatch, for error reporting
|
129
|
+
def isobib_results_filter(result, year)
|
130
|
+
missed_years = []
|
131
|
+
result.each_slice(3) do |s| # ISO website only allows 3 connections
|
132
|
+
fetch_pages(s, 3).each_with_index do |r, _i|
|
133
|
+
return { ret: r } if !year
|
134
|
+
|
135
|
+
r.dates.select { |d| d.type == "published" }.each do |d|
|
136
|
+
return { ret: r } if year.to_i == d.on.year
|
137
|
+
|
138
|
+
missed_years << d.on.year
|
139
|
+
end
|
140
|
+
end
|
141
|
+
end
|
142
|
+
{ years: missed_years }
|
143
|
+
end
|
144
|
+
|
145
|
+
def iecbib_get1(code, year, _opts)
|
146
|
+
return iev if code.casecmp("IEV").zero?
|
147
|
+
|
148
|
+
result = isobib_search_filter(code) || return
|
149
|
+
ret = isobib_results_filter(result, year)
|
150
|
+
return ret[:ret] if ret[:ret]
|
151
|
+
|
152
|
+
fetch_ref_err(code, year, ret[:years])
|
153
|
+
end
|
154
|
+
end
|
155
|
+
end
|
156
|
+
end
|
@@ -0,0 +1,413 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "relaton_iso_bib"
|
4
|
+
require "relaton_iec/hit"
|
5
|
+
require "nokogiri"
|
6
|
+
require "net/http"
|
7
|
+
|
8
|
+
# Capybara.request_driver :poltergeist do |app|
|
9
|
+
# Capybara::Poltergeist::Driver.new app, js_errors: false
|
10
|
+
# end
|
11
|
+
# Capybara.default_driver = :poltergeist
|
12
|
+
|
13
|
+
module RelatonIec
|
14
|
+
# Scrapper.
|
15
|
+
# rubocop:disable Metrics/ModuleLength
|
16
|
+
module Scrapper
|
17
|
+
DOMAIN = "https://webstore.iec.ch"
|
18
|
+
|
19
|
+
TYPES = {
|
20
|
+
"ISO" => "international-standard",
|
21
|
+
"TS" => "technicalSpecification",
|
22
|
+
"TR" => "technicalReport",
|
23
|
+
"PAS" => "publiclyAvailableSpecification",
|
24
|
+
"AWI" => "appruvedWorkItem",
|
25
|
+
"CD" => "committeeDraft",
|
26
|
+
"FDIS" => "finalDraftInternationalStandard",
|
27
|
+
"NP" => "newProposal",
|
28
|
+
"DIS" => "draftInternationalStandard",
|
29
|
+
"WD" => "workingDraft",
|
30
|
+
"R" => "recommendation",
|
31
|
+
"Guide" => "guide",
|
32
|
+
}.freeze
|
33
|
+
|
34
|
+
class << self
|
35
|
+
# @param text [String]
|
36
|
+
# @return [Array<Hash>]
|
37
|
+
# def get(text)
|
38
|
+
# iso_workers = WorkersPool.new 4
|
39
|
+
# iso_workers.worker { |hit| iso_worker(hit, iso_workers) }
|
40
|
+
# algolia_workers = start_algolia_search(text, iso_workers)
|
41
|
+
# iso_docs = iso_workers.result
|
42
|
+
# algolia_workers.end
|
43
|
+
# algolia_workers.result
|
44
|
+
# iso_docs
|
45
|
+
# end
|
46
|
+
|
47
|
+
# Parse page.
|
48
|
+
# @param hit [Hash]
|
49
|
+
# @return [Hash]
|
50
|
+
# rubocop:disable Metrics/AbcSize, Metrics/MethodLength
|
51
|
+
def parse_page(hit_data)
|
52
|
+
doc = get_page hit_data[:url]
|
53
|
+
|
54
|
+
# Fetch edition.
|
55
|
+
edition = doc.at("//th[contains(., 'Edition')]/following-sibling::td/span").text
|
56
|
+
|
57
|
+
status, relations = fetch_status_relations hit_data[:url]
|
58
|
+
|
59
|
+
RelatonIsoBib::IsoBibliographicItem.new(
|
60
|
+
docid: [RelatonBib::DocumentIdentifier.new(id: hit_data[:code], type: "IEC")],
|
61
|
+
structuredidentifier: fetch_structuredidentifier(doc),
|
62
|
+
edition: edition,
|
63
|
+
language: ["en"],
|
64
|
+
script: ["Latn"],
|
65
|
+
titles: fetch_titles(hit_data),
|
66
|
+
type: fetch_type(doc),
|
67
|
+
docstatus: status,
|
68
|
+
ics: fetch_ics(doc),
|
69
|
+
dates: fetch_dates(doc),
|
70
|
+
contributors: fetch_contributors(hit_data[:code]),
|
71
|
+
editorialgroup: fetch_workgroup(doc),
|
72
|
+
abstract: fetch_abstract(doc),
|
73
|
+
copyright: fetch_copyright(hit_data[:code], doc),
|
74
|
+
link: fetch_link(doc, hit_data[:url]),
|
75
|
+
relations: relations,
|
76
|
+
)
|
77
|
+
end
|
78
|
+
# rubocop:enable Metrics/AbcSize, Metrics/MethodLength
|
79
|
+
|
80
|
+
private
|
81
|
+
|
82
|
+
# Start search workers.
|
83
|
+
# @param text[String]
|
84
|
+
# @param iec_workers [Isobib::WorkersPool]
|
85
|
+
# @reaturn [Isobib::WorkersPool]
|
86
|
+
# def start_algolia_search(text, iec_workers)
|
87
|
+
# index = Algolia::Index.new 'all_en'
|
88
|
+
# workers = WorkersPool.new
|
89
|
+
# workers.worker do |page|
|
90
|
+
# algolia_worker(index, text, page, workers, iec_workers)
|
91
|
+
# end
|
92
|
+
|
93
|
+
# # Add first page so search worker will start.
|
94
|
+
# workers << 0
|
95
|
+
# end
|
96
|
+
|
97
|
+
# Fetch ISO documents.
|
98
|
+
# @param hit [Hash]
|
99
|
+
# @param isiso_workers [Isobib::WorkersPool]
|
100
|
+
# def iso_worker(hit, iso_workers)
|
101
|
+
# print "Parse #{iso_workers.size} of #{iso_workers.nb_hits} \r"
|
102
|
+
# parse_page hit
|
103
|
+
# end
|
104
|
+
|
105
|
+
# Fetch hits from algolia search service.
|
106
|
+
# @param index[Algolia::Index]
|
107
|
+
# @param text [String]
|
108
|
+
# @param page [Integer]
|
109
|
+
# @param algolia_workers [Isobib::WorkersPool]
|
110
|
+
# @param isiso_workers [Isobib::WorkersPool]
|
111
|
+
# def algolia_worker(index, text, page, algolia_workers, iso_workers)
|
112
|
+
# res = index.search text, facetFilters: ['category:standard'], page: page
|
113
|
+
# next_page = res['page'] + 1
|
114
|
+
# algolia_workers << next_page if next_page < res['nbPages']
|
115
|
+
# res['hits'].each do |hit|
|
116
|
+
# iso_workers.nb_hits = res['nbHits']
|
117
|
+
# iso_workers << hit
|
118
|
+
# end
|
119
|
+
# iso_workers.end unless next_page < res['nbPages']
|
120
|
+
# end
|
121
|
+
|
122
|
+
# Fetch abstracts.
|
123
|
+
# @param doc [Nokigiri::HTML::Document]
|
124
|
+
# @return [Array<Array>]
|
125
|
+
def fetch_abstract(doc)
|
126
|
+
abstract_content = doc.at('//div[@itemprop="description"]').text
|
127
|
+
[{
|
128
|
+
content: abstract_content,
|
129
|
+
language: "en",
|
130
|
+
script: "Latn",
|
131
|
+
format: "text/plain",
|
132
|
+
}]
|
133
|
+
end
|
134
|
+
|
135
|
+
# Get langs.
|
136
|
+
# @param doc [Nokogiri::HTML::Document]
|
137
|
+
# @return [Array<Hash>]
|
138
|
+
# def langs(doc)
|
139
|
+
# lgs = [{ lang: 'en' }]
|
140
|
+
# doc.css('ul#lang-switcher ul li a').each do |lang_link|
|
141
|
+
# lang_path = lang_link.attr('href')
|
142
|
+
# lang = lang_path.match(%r{^\/(fr)\/})
|
143
|
+
# lgs << { lang: lang[1], path: lang_path } if lang
|
144
|
+
# end
|
145
|
+
# lgs
|
146
|
+
# end
|
147
|
+
|
148
|
+
# rubocop:disable Metrics/AbcSize, Metrics/MethodLength
|
149
|
+
|
150
|
+
# Get page.
|
151
|
+
# @param path [String] page's path
|
152
|
+
# @return [Array<Nokogiri::HTML::Document, String>]
|
153
|
+
def get_page(url)
|
154
|
+
uri = URI url
|
155
|
+
resp = Net::HTTP.get_response(uri) # .encode("UTF-8")
|
156
|
+
if resp.code == "301"
|
157
|
+
path = resp["location"]
|
158
|
+
url = DOMAIN + path
|
159
|
+
uri = URI url
|
160
|
+
resp = Net::HTTP.get_response(uri) # .encode("UTF-8")
|
161
|
+
end
|
162
|
+
# n = 0
|
163
|
+
# while resp.body !~ /<strong/ && n < 10
|
164
|
+
# resp = Net::HTTP.get_response(uri)#.encode("UTF-8")
|
165
|
+
# n += 1
|
166
|
+
# end
|
167
|
+
Nokogiri::HTML(resp.body)
|
168
|
+
end
|
169
|
+
# rubocop:enable Metrics/AbcSize
|
170
|
+
|
171
|
+
# Fetch structuredidentifier.
|
172
|
+
# @param doc [Nokogiri::HTML::Document]
|
173
|
+
# @return [RelatonIsoBib::StructuredIdentifier]
|
174
|
+
def fetch_structuredidentifier(doc)
|
175
|
+
item_ref = doc.at("//span[@itemprop='productID']")
|
176
|
+
unless item_ref
|
177
|
+
return RelatonIsoBib::StructuredIdentifier.new(
|
178
|
+
project_number: "?", part_number: "", prefix: nil, id: "?",
|
179
|
+
)
|
180
|
+
end
|
181
|
+
|
182
|
+
m = item_ref.text.match(
|
183
|
+
/(?<=\s)(?<project>\d+)-?(?<part>(?<=-)\d+|)-?(?<subpart>(?<=-)\d+|)/,
|
184
|
+
)
|
185
|
+
RelatonIsoBib::StructuredIdentifier.new(
|
186
|
+
project_number: m[:project],
|
187
|
+
part_number: m[:part],
|
188
|
+
subpart_number: m[:subpart],
|
189
|
+
prefix: nil,
|
190
|
+
type: "IEC",
|
191
|
+
id: item_ref.text,
|
192
|
+
)
|
193
|
+
end
|
194
|
+
|
195
|
+
# Fetch status.
|
196
|
+
# @param doc [Nokogiri::HTML::Document]
|
197
|
+
# @param status [String]
|
198
|
+
# @return [Hash]
|
199
|
+
def fetch_status(doc)
|
200
|
+
wip = doc.at('//ROW[STATUS[.="PREPARING"]]')
|
201
|
+
if wip
|
202
|
+
statuses = YAML.load_file "lib/relaton_iec/statuses.yml"
|
203
|
+
s = wip.at("STAGE").text
|
204
|
+
stage, substage = statuses[s]["stage"].split "."
|
205
|
+
# status = statuses[s]["status"]
|
206
|
+
else
|
207
|
+
# status = "Published"
|
208
|
+
stage = "60"
|
209
|
+
substage = "60"
|
210
|
+
end
|
211
|
+
RelatonBib::DocumentStatus.new(stage: stage, substage: substage)
|
212
|
+
end
|
213
|
+
# rubocop:enable Metrics/MethodLength
|
214
|
+
|
215
|
+
# Fetch workgroup.
|
216
|
+
# @param doc [Nokogiri::HTML::Document]
|
217
|
+
# @return [Hash]
|
218
|
+
def fetch_workgroup(doc)
|
219
|
+
wg = doc.at('//th/abbr[.="TC"]/../following-sibling::td/a').text
|
220
|
+
{
|
221
|
+
name: "International Electrotechnical Commission",
|
222
|
+
abbreviation: "IEC",
|
223
|
+
url: "webstore.iec.ch",
|
224
|
+
technical_committee: [{
|
225
|
+
name: wg,
|
226
|
+
type: "technicalCommittee",
|
227
|
+
number: wg.match(/\d+/)&.to_s&.to_i,
|
228
|
+
}],
|
229
|
+
}
|
230
|
+
end
|
231
|
+
|
232
|
+
# Fetch relations.
|
233
|
+
# @param doc [Nokogiri::HTML::Document]
|
234
|
+
# @return [Array<Hash>]
|
235
|
+
# rubocop:disable Metrics/MethodLength
|
236
|
+
def fetch_relations(doc)
|
237
|
+
doc.xpath('//ROW[STATUS[.!="PREPARING"]][STATUS[.!="PUBLISHED"]]').map do |r|
|
238
|
+
r_type = r.at("STATUS").text.downcase
|
239
|
+
type = case r_type
|
240
|
+
# when 'published' then 'obsoletes' # Valid
|
241
|
+
when "revised", "replaced" then "updates"
|
242
|
+
when "withdrawn" then "obsoletes"
|
243
|
+
else r_type
|
244
|
+
end
|
245
|
+
# url = DOMAIN + "/publication/" + r.at("PUB_ID").text
|
246
|
+
fref = RelatonBib::FormattedRef.new(
|
247
|
+
content: r.at("FULL_NAME").text, format: "text/plain",
|
248
|
+
)
|
249
|
+
bibitem = RelatonIsoBib::IsoBibliographicItem.new(
|
250
|
+
formattedref: fref,
|
251
|
+
)
|
252
|
+
{ type: type, bibitem: bibitem }
|
253
|
+
end
|
254
|
+
end
|
255
|
+
|
256
|
+
def fetch_status_relations(url)
|
257
|
+
pubid = url.match(/\d+$/).to_s
|
258
|
+
uri = URI DOMAIN + "/webstore/webstore.nsf/AjaxRequestXML?"\
|
259
|
+
"Openagent&url=http://www.iec.ch/dyn/www/f?"\
|
260
|
+
"p=103:390:::::P390_PUBLICATION_ID:" + pubid
|
261
|
+
resp = Net::HTTP.get_response uri
|
262
|
+
doc = Nokogiri::XML resp.body
|
263
|
+
status = fetch_status doc
|
264
|
+
relations = fetch_relations doc
|
265
|
+
[status, relations]
|
266
|
+
# doc.css('ul.steps li').inject([]) do |a, r|
|
267
|
+
# r_type = r.css('strong').text
|
268
|
+
# type = case r_type
|
269
|
+
# when 'Previously', 'Will be replaced by' then 'obsoletes'
|
270
|
+
# when 'Corrigenda/Amendments', 'Revised by', 'Now confirmed'
|
271
|
+
# 'updates'
|
272
|
+
# else r_type
|
273
|
+
# end
|
274
|
+
# if ['Now', 'Now under review'].include? type
|
275
|
+
# a
|
276
|
+
# else
|
277
|
+
# a + r.css('a').map do |id|
|
278
|
+
# { type: type, identifier: id.text, url: id['href'] }
|
279
|
+
# end
|
280
|
+
# end
|
281
|
+
# end
|
282
|
+
end
|
283
|
+
# rubocop:enable Metrics/MethodLength
|
284
|
+
|
285
|
+
# Fetch type.
|
286
|
+
# @param doc [Nokogiri::HTML::Document]
|
287
|
+
# @return [String]
|
288
|
+
def fetch_type(doc)
|
289
|
+
doc.at('//th[contains(., "Publication type")]/following-sibling::td/span')
|
290
|
+
.text.downcase.tr " ", "-"
|
291
|
+
# type_match = title.match(%r{^(ISO|IWA|IEC)(?:(/IEC|/IEEE|/PRF|
|
292
|
+
# /NP)*\s|/)(TS|TR|PAS|AWI|CD|FDIS|NP|DIS|WD|R|Guide|(?=\d+))}x)
|
293
|
+
# #return "international-standard" if type_match.nil?
|
294
|
+
# if TYPES[type_match[2]]
|
295
|
+
# TYPES[type_match[2]]
|
296
|
+
# elsif type_match[1]
|
297
|
+
# elsif type_match[1] == 'ISO'
|
298
|
+
# 'international-standard'
|
299
|
+
# elsif type_match[1] == 'IWA'
|
300
|
+
# 'international-workshop-agreement'
|
301
|
+
# end
|
302
|
+
# # rescue => _e
|
303
|
+
# # puts 'Unknown document type: ' + title
|
304
|
+
end
|
305
|
+
|
306
|
+
# Fetch titles.
|
307
|
+
# @param hit_data [Hash]
|
308
|
+
# @return [Array<Hash>]
|
309
|
+
def fetch_titles(hit_data)
|
310
|
+
titles = hit_data[:title].split " - "
|
311
|
+
case titles.size
|
312
|
+
when 0
|
313
|
+
intro, main, part = nil, "", nil
|
314
|
+
when 1
|
315
|
+
intro, main, part = nil, titles[0], nil
|
316
|
+
when 2
|
317
|
+
if /^(Part|Partie) \d+:/ =~ titles[1]
|
318
|
+
intro, main, part = nil, titles[0], titles[1]
|
319
|
+
else
|
320
|
+
intro, main, part = titles[0], titles[1], nil
|
321
|
+
end
|
322
|
+
when 3
|
323
|
+
intro, main, part = titles[0], titles[1], titles[2]
|
324
|
+
else
|
325
|
+
intro, main, part = titles[0], titles[1], titles[2..-1]&.join(" -- ")
|
326
|
+
end
|
327
|
+
[{
|
328
|
+
title_intro: intro,
|
329
|
+
title_main: main,
|
330
|
+
title_part: part,
|
331
|
+
language: "en",
|
332
|
+
script: "Latn"
|
333
|
+
}]
|
334
|
+
end
|
335
|
+
|
336
|
+
# Return ISO script code.
|
337
|
+
# @param lang [String]
|
338
|
+
# @return [String]
|
339
|
+
# def script(lang)
|
340
|
+
# case lang
|
341
|
+
# when 'en', 'fr' then 'Latn'
|
342
|
+
# end
|
343
|
+
# end
|
344
|
+
|
345
|
+
# Fetch dates
|
346
|
+
# @param doc [Nokogiri::HTML::Document]
|
347
|
+
# @return [Array<Hash>]
|
348
|
+
def fetch_dates(doc)
|
349
|
+
dates = []
|
350
|
+
publish_date = doc.at("//span[@itemprop='releaseDate']").text
|
351
|
+
unless publish_date.empty?
|
352
|
+
dates << { type: "published", on: publish_date }
|
353
|
+
end
|
354
|
+
dates
|
355
|
+
end
|
356
|
+
|
357
|
+
def fetch_contributors(code)
|
358
|
+
code.sub(/\s.*/, "").split("/").map do |abbrev|
|
359
|
+
case abbrev
|
360
|
+
when "ISO"
|
361
|
+
name = "International Organization for Standardization"
|
362
|
+
url = "www.iso.org"
|
363
|
+
when "IEC"
|
364
|
+
name = "International Electrotechnical Commission"
|
365
|
+
url = "www.iec.ch"
|
366
|
+
end
|
367
|
+
{ entity: { name: name, url: url, abbreviation: abbrev },
|
368
|
+
roles: ["publisher"] }
|
369
|
+
end
|
370
|
+
end
|
371
|
+
|
372
|
+
# Fetch ICS.
|
373
|
+
# @param doc [Nokogiri::HTML::Document]
|
374
|
+
# @return [Array<Hash>]
|
375
|
+
def fetch_ics(doc)
|
376
|
+
doc.xpath('//th[contains(text(), "ICS")]/following-sibling::td/a').map do |i|
|
377
|
+
code = i.text.match(/[\d\.]+/).to_s.split "."
|
378
|
+
{ field: code[0], group: code[1], subgroup: code[2] }
|
379
|
+
end
|
380
|
+
end
|
381
|
+
|
382
|
+
# Fetch links.
|
383
|
+
# @param doc [Nokogiri::HTML::Document]
|
384
|
+
# @param url [String]
|
385
|
+
# @return [Array<Hash>]
|
386
|
+
def fetch_link(doc, url)
|
387
|
+
links = [{ type: "src", content: url }]
|
388
|
+
obp_elms = doc.at_css("p.btn-preview a")
|
389
|
+
links << { type: "obp", content: obp_elms[:href] } if obp_elms
|
390
|
+
links
|
391
|
+
end
|
392
|
+
|
393
|
+
# Fetch copyright.
|
394
|
+
# @param title [String]
|
395
|
+
# @return [Hash]
|
396
|
+
def fetch_copyright(code, doc)
|
397
|
+
abbreviation = code.match(/.*?(?=\s)/).to_s
|
398
|
+
case abbreviation
|
399
|
+
when "IEC"
|
400
|
+
name = "International Electrotechnical Commission"
|
401
|
+
url = "www.iec.ch"
|
402
|
+
end
|
403
|
+
from = code.match(/(?<=:)\d{4}/).to_s
|
404
|
+
if from.empty?
|
405
|
+
from = doc.xpath("//span[@itemprop='releaseDate']").text
|
406
|
+
.match(/\d{4}/).to_s
|
407
|
+
end
|
408
|
+
{ owner: { name: name, abbreviation: abbreviation, url: url }, from: from }
|
409
|
+
end
|
410
|
+
end
|
411
|
+
end
|
412
|
+
# rubocop:enable Metrics/ModuleLength
|
413
|
+
end
|