relaton-gb 1.8.0 → 1.10.1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (18) hide show
  1. checksums.yaml +4 -4
  2. data/.github/workflows/rake.yml +1 -11
  3. data/.rubocop.yml +3 -1
  4. data/README.adoc +10 -0
  5. data/grammars/basicdoc.rng +26 -7
  6. data/grammars/biblio.rng +8 -5
  7. data/grammars/gbstandard.rng +4 -1
  8. data/grammars/isodoc.rng +686 -96
  9. data/grammars/isostandard.rng +42 -26
  10. data/grammars/reqt.rng +34 -5
  11. data/lib/relaton_gb/gb_bibliography.rb +7 -6
  12. data/lib/relaton_gb/gb_scrapper.rb +8 -9
  13. data/lib/relaton_gb/scrapper.rb +1 -1
  14. data/lib/relaton_gb/sec_scrapper.rb +3 -3
  15. data/lib/relaton_gb/t_scrapper.rb +2 -2
  16. data/lib/relaton_gb/version.rb +1 -1
  17. data/relaton_gb.gemspec +3 -5
  18. metadata +9 -9
data/grammars/isostandard.rng CHANGED
@@ -38,6 +38,9 @@
38
38
  </define>
39
39
  <define name="BibDataExtensionType">
40
40
  <ref name="doctype"/>
41
+ <optional>
42
+ <ref name="docsubtype"/>
43
+ </optional>
41
44
  <optional>
42
45
  <ref name="horizontal"/>
43
46
  </optional>
@@ -98,7 +101,11 @@
98
101
  <ref name="definitions"/>
99
102
  </optional>
100
103
  <oneOrMore>
101
- <ref name="clause"/>
104
+ <choice>
105
+ <ref name="clause"/>
106
+ <ref name="term-clause"/>
107
+ <ref name="terms"/>
108
+ </choice>
102
109
  </oneOrMore>
103
110
  </element>
104
111
  </define>
@@ -133,22 +140,17 @@
133
140
  <optional>
134
141
  <ref name="section-title"/>
135
142
  </optional>
136
- <group>
143
+ <choice>
137
144
  <choice>
138
- <group>
139
- <oneOrMore>
140
- <ref name="BasicBlock"/>
141
- </oneOrMore>
142
- <zeroOrMore>
143
- <ref name="note"/>
144
- </zeroOrMore>
145
- </group>
145
+ <oneOrMore>
146
+ <ref name="BasicBlock"/>
147
+ </oneOrMore>
146
148
  <ref name="amend"/>
147
149
  </choice>
148
150
  <oneOrMore>
149
151
  <ref name="clause-subsection"/>
150
152
  </oneOrMore>
151
- </group>
153
+ </choice>
152
154
  </define>
153
155
  <define name="term">
154
156
  <element name="term">
@@ -157,6 +159,20 @@
157
159
  <data type="ID"/>
158
160
  </attribute>
159
161
  </optional>
162
+ <optional>
163
+ <attribute name="language"/>
164
+ </optional>
165
+ <optional>
166
+ <attribute name="script"/>
167
+ </optional>
168
+ <optional>
169
+ <attribute name="tag"/>
170
+ </optional>
171
+ <optional>
172
+ <attribute name="multilingual-rendering">
173
+ <ref name="MultilingualRenderingType"/>
174
+ </attribute>
175
+ </optional>
160
176
  <ref name="preferred"/>
161
177
  <zeroOrMore>
162
178
  <ref name="admitted"/>
@@ -167,7 +183,7 @@
167
183
  <optional>
168
184
  <ref name="termdomain"/>
169
185
  </optional>
170
- <ref name="definition"/>
186
+ <ref name="termdefinition"/>
171
187
  <zeroOrMore>
172
188
  <ref name="termnote"/>
173
189
  </zeroOrMore>
@@ -177,6 +193,9 @@
177
193
  <zeroOrMore>
178
194
  <ref name="termsource"/>
179
195
  </zeroOrMore>
196
+ <zeroOrMore>
197
+ <ref name="term"/>
198
+ </zeroOrMore>
180
199
  </element>
181
200
  </define>
182
201
  <define name="annex">
@@ -215,9 +234,6 @@
215
234
  -->
216
235
  <ref name="BasicBlock"/>
217
236
  </zeroOrMore>
218
- <zeroOrMore>
219
- <ref name="note"/>
220
- </zeroOrMore>
221
237
  <zeroOrMore>
222
238
  <ref name="clause-hanging-paragraph-with-footnote"/>
223
239
  </zeroOrMore>
@@ -259,6 +275,14 @@
259
275
  <value>directive</value>
260
276
  </choice>
261
277
  </define>
278
+ <define name="DocumentSubtype">
279
+ <choice>
280
+ <value>specification</value>
281
+ <value>method-of-test</value>
282
+ <value>vocabulary</value>
283
+ <value>code-of-practice</value>
284
+ </choice>
285
+ </define>
262
286
  <define name="structuredidentifier">
263
287
  <element name="structuredidentifier">
264
288
  <optional>
@@ -333,14 +357,9 @@
333
357
  <ref name="section-title"/>
334
358
  </optional>
335
359
  <choice>
336
- <group>
337
- <zeroOrMore>
338
- <ref name="BasicBlock"/>
339
- </zeroOrMore>
340
- <zeroOrMore>
341
- <ref name="note"/>
342
- </zeroOrMore>
343
- </group>
360
+ <zeroOrMore>
361
+ <ref name="BasicBlock"/>
362
+ </zeroOrMore>
344
363
  <oneOrMore>
345
364
  <ref name="content-subsection"/>
346
365
  </oneOrMore>
@@ -457,9 +476,6 @@
457
476
  <!-- allow hanging paragraphs in annexes: they introduce lists -->
458
477
  <ref name="BasicBlock"/>
459
478
  </zeroOrMore>
460
- <zeroOrMore>
461
- <ref name="note"/>
462
- </zeroOrMore>
463
479
  <zeroOrMore>
464
480
  <ref name="clause-hanging-paragraph-with-footnote"/>
465
481
  </zeroOrMore>
data/grammars/reqt.rng CHANGED
@@ -58,15 +58,23 @@
58
58
  <optional>
59
59
  <attribute name="type"/>
60
60
  </optional>
61
+ <optional>
62
+ <attribute name="tag"/>
63
+ </optional>
64
+ <optional>
65
+ <attribute name="multilingual-rendering">
66
+ <ref name="MultilingualRenderingType"/>
67
+ </attribute>
68
+ </optional>
61
69
  <optional>
62
70
  <ref name="reqtitle"/>
63
71
  </optional>
64
72
  <optional>
65
73
  <ref name="label"/>
66
74
  </optional>
67
- <optional>
75
+ <zeroOrMore>
68
76
  <ref name="subject"/>
69
- </optional>
77
+ </zeroOrMore>
70
78
  <zeroOrMore>
71
79
  <ref name="reqinherit"/>
72
80
  </zeroOrMore>
@@ -80,6 +88,7 @@
80
88
  <ref name="verification"/>
81
89
  <ref name="import"/>
82
90
  <ref name="description"/>
91
+ <ref name="component"/>
83
92
  </choice>
84
93
  </zeroOrMore>
85
94
  <optional>
@@ -100,17 +109,23 @@
100
109
  </define>
101
110
  <define name="label">
102
111
  <element name="label">
103
- <text/>
112
+ <oneOrMore>
113
+ <ref name="TextElement"/>
114
+ </oneOrMore>
104
115
  </element>
105
116
  </define>
106
117
  <define name="subject">
107
118
  <element name="subject">
108
- <text/>
119
+ <oneOrMore>
120
+ <ref name="TextElement"/>
121
+ </oneOrMore>
109
122
  </element>
110
123
  </define>
111
124
  <define name="reqinherit">
112
125
  <element name="inherit">
113
- <text/>
126
+ <oneOrMore>
127
+ <ref name="TextElement"/>
128
+ </oneOrMore>
114
129
  </element>
115
130
  </define>
116
131
  <define name="measurementtarget">
@@ -138,6 +153,12 @@
138
153
  <ref name="RequirementSubpart"/>
139
154
  </element>
140
155
  </define>
156
+ <define name="component">
157
+ <element name="component">
158
+ <attribute name="class"/>
159
+ <ref name="RequirementSubpart"/>
160
+ </element>
161
+ </define>
141
162
  <define name="reqt_references">
142
163
  <element name="references">
143
164
  <oneOrMore>
@@ -164,6 +185,14 @@
164
185
  <data type="boolean"/>
165
186
  </attribute>
166
187
  </optional>
188
+ <optional>
189
+ <attribute name="tag"/>
190
+ </optional>
191
+ <optional>
192
+ <attribute name="multilingual-rendering">
193
+ <ref name="MultilingualRenderingType"/>
194
+ </attribute>
195
+ </optional>
167
196
  <oneOrMore>
168
197
  <ref name="BasicBlock"/>
169
198
  </oneOrMore>
data/lib/relaton_gb/gb_bibliography.rb CHANGED
@@ -14,17 +14,18 @@ module RelatonGb
14
14
  # @param text [Strin] code of standard for search
15
15
  # @return [RelatonGb::HitCollection]
16
16
  def search(text)
17
- if text =~ /^(GB|GJ|GS)/
17
+ case text
18
+ when /^(GB|GJ|GS)/
18
19
  # Scrape national standards.
19
20
  require "relaton_gb/gb_scrapper"
20
21
  GbScrapper.scrape_page text
21
- elsif text =~ /^ZB/
22
+ when /^ZB/
22
23
  # Scrape proffesional.
23
- elsif text =~ /^DB/
24
+ when /^DB/
24
25
  # Scrape local standard.
25
- elsif text =~ %r{^Q\/}
26
+ when %r{^Q/}
26
27
  # Enterprise standard
27
- elsif text =~ %r{^T\/[^\s]{3,6}\s}
28
+ when %r{^T/[^\s]{3,6}\s}
28
29
  # Scrape social standard.
29
30
  require "relaton_gb/t_scrapper"
30
31
  TScrapper.scrape_page text
@@ -96,7 +97,7 @@ module RelatonGb
96
97
 
97
98
  def search_filter(code)
98
99
  # search filter needs to incorporate year
99
- docidrx = %r{^[^\s]+\s[\d\.-]+}
100
+ docidrx = %r{^[^\s]+\s[\d.-]+}
100
101
  warn "[relaton-gb] (\"#{code}\") fetching..."
101
102
  result = search(code)
102
103
  result.select do |hit|
data/lib/relaton_gb/gb_scrapper.rb CHANGED
@@ -14,10 +14,9 @@ module RelatonGb
14
14
  class << self
15
15
  # @param text [Strin] code of standard for serarch
16
16
  # @return [RelatonGb::HitCollection]
17
- def scrape_page(text)
18
- search_html = OpenURI.open_uri(
19
- "http://openstd.samr.gov.cn/bzgk/gb/std_list?p.p2=" + text,
20
- )
17
+ def scrape_page(text) # rubocop:disable Metrics/MethodLength, Metrics/AbcSize
18
+ host = "http://openstd.samr.gov.cn/bzgk/gb/std_list"
19
+ search_html = OpenURI.open_uri("#{host}?p.p2=#{text}")
21
20
  result = Nokogiri::HTML search_html
22
21
  hits = result.xpath(
23
22
  "//table[contains(@class, 'result_list')]/tbody[2]/tr",
@@ -28,17 +27,17 @@ module RelatonGb
28
27
  Hit.new pid: pid, docref: ref.text, scrapper: self, release_date: rdate
29
28
  end
30
29
  HitCollection.new hits.sort_by(&:release_date).reverse
31
- rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError
32
- raise RelatonBib::RequestError, "Cannot access http://www.std.gov.cn/bzgk/gb/std_list"
30
+ rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError, Net::OpenTimeout
31
+ raise RelatonBib::RequestError, "Cannot access #{host}"
33
32
  end
34
33
 
35
34
  # @param hit [RelatonGb::Hit] standard's page id
36
35
  # @return [RelatonGb::GbBibliographicItem]
37
36
  def scrape_doc(hit)
38
- src = "http://openstd.samr.gov.cn/bzgk/gb/newGbInfo?hcno=" + hit.pid
37
+ src = "http://openstd.samr.gov.cn/bzgk/gb/newGbInfo?hcno=#{hit.pid}"
39
38
  doc = Nokogiri::HTML OpenURI.open_uri(src)
40
- GbBibliographicItem.new **scrapped_data(doc, src, hit)
41
- rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError
39
+ GbBibliographicItem.new(**scrapped_data(doc, src, hit))
40
+ rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError, Net::OpenTimeout
42
41
  raise RelatonBib::RequestError, "Cannot access #{src}"
43
42
  end
44
43
 
data/lib/relaton_gb/scrapper.rb CHANGED
@@ -43,7 +43,7 @@ module RelatonGb
43
43
  # @param docref [String]
44
44
  # @return [Array<RelatonBib::DocumentIdentifier>]
45
45
  def get_docid(docref)
46
- [RelatonBib::DocumentIdentifier.new(id: docref, type: "Chinese Standard")]
46
+ [RelatonBib::DocumentIdentifier.new(id: docref, type: "Chinese Standard", primary: true)]
47
47
  end
48
48
 
49
49
  # @param docref [String]
data/lib/relaton_gb/sec_scrapper.rb CHANGED
@@ -32,7 +32,7 @@ module RelatonGb
32
32
  HitCollection.new hits
33
33
  rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET, EOFError,
34
34
  Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError, Net::ProtocolError,
35
- OpenSSL::SSL::SSLError, Errno::ETIMEDOUT
35
+ OpenSSL::SSL::SSLError, Errno::ETIMEDOUT, Net::OpenTimeout
36
36
  raise RelatonBib::RequestError, "Cannot access #{uri}"
37
37
  end
38
38
 
@@ -42,10 +42,10 @@ module RelatonGb
42
42
  src = "http://hbba.sacinfo.org.cn/stdDetail/#{hit.pid}"
43
43
  page_uri = URI src
44
44
  doc = Nokogiri::HTML Net::HTTP.get(page_uri)
45
- GbBibliographicItem.new **scrapped_data(doc, src, hit)
45
+ GbBibliographicItem.new(**scrapped_data(doc, src, hit))
46
46
  rescue SocketError, Timeout::Error, Errno::EINVAL, Errno::ECONNRESET, EOFError,
47
47
  Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError, Net::ProtocolError,
48
- OpenSSL::SSL::SSLError, Errno::ETIMEDOUT
48
+ OpenSSL::SSL::SSLError, Errno::ETIMEDOUT, Net::OpenTimeout
49
49
  raise RelatonBib::RequestError, "Cannot access #{src}"
50
50
  end
51
51
 
data/lib/relaton_gb/t_scrapper.rb CHANGED
@@ -33,7 +33,7 @@ module RelatonGb
33
33
  Hit.new pid: pid, docref: docref, status: status, scrapper: self
34
34
  end
35
35
  HitCollection.new hits
36
- rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError
36
+ rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError, Net::OpenTimeout
37
37
  raise RelatonBib::RequestError, "Cannot access http://www.ttbz.org.cn/Home/Standard"
38
38
  end
39
39
  # rubocop:enable Metrics/MethodLength, Metrics/AbcSize
@@ -44,7 +44,7 @@ module RelatonGb
44
44
  src = "http://www.ttbz.org.cn#{hit.pid}"
45
45
  doc = Nokogiri::HTML OpenURI.open_uri(src), nil, Encoding::UTF_8.to_s
46
46
  GbBibliographicItem.new **scrapped_data(doc, src, hit)
47
- rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError
47
+ rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError, Net::OpenTimeout
48
48
  raise RelatonBib::RequestError, "Cannot access #{src}"
49
49
  end
50
50
 
data/lib/relaton_gb/version.rb CHANGED
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module RelatonGb
4
- VERSION = "1.8.0"
4
+ VERSION = "1.10.1"
5
5
  end
data/relaton_gb.gemspec CHANGED
@@ -22,14 +22,12 @@ Gem::Specification.new do |spec|
22
22
  spec.bindir = "exe"
23
23
  spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
24
24
  spec.require_paths = ["lib"]
25
- spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
25
+ spec.required_ruby_version = Gem::Requirement.new(">= 2.5.0")
26
26
 
27
- # spec.add_development_dependency "debase"
28
27
  spec.add_development_dependency "equivalent-xml", "~> 0.6"
29
28
  spec.add_development_dependency "pry-byebug"
30
- spec.add_development_dependency "rake", "~> 10.0"
29
+ spec.add_development_dependency "rake", "~> 13.0"
31
30
  spec.add_development_dependency "rspec", "~> 3.0"
32
- # spec.add_development_dependency "ruby-debug-ide"
33
31
  spec.add_development_dependency "ruby-jing"
34
32
  spec.add_development_dependency "simplecov"
35
33
  spec.add_development_dependency "vcr"
@@ -37,5 +35,5 @@ Gem::Specification.new do |spec|
37
35
 
38
36
  spec.add_dependency "cnccs", "~> 0.1.1"
39
37
  spec.add_dependency "gb-agencies", "~> 0.0.1"
40
- spec.add_dependency "relaton-iso-bib", ">= 1.8.0"
38
+ spec.add_dependency "relaton-iso-bib", "~> 1.10.1"
41
39
  end
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: relaton-gb
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.8.0
4
+ version: 1.10.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ribose Inc.
8
8
  autorequire:
9
9
  bindir: exe
10
10
  cert_chain: []
11
- date: 2021-05-17 00:00:00.000000000 Z
11
+ date: 2022-02-09 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: equivalent-xml
@@ -44,14 +44,14 @@ dependencies:
44
44
  requirements:
45
45
  - - "~>"
46
46
  - !ruby/object:Gem::Version
47
- version: '10.0'
47
+ version: '13.0'
48
48
  type: :development
49
49
  prerelease: false
50
50
  version_requirements: !ruby/object:Gem::Requirement
51
51
  requirements:
52
52
  - - "~>"
53
53
  - !ruby/object:Gem::Version
54
- version: '10.0'
54
+ version: '13.0'
55
55
  - !ruby/object:Gem::Dependency
56
56
  name: rspec
57
57
  requirement: !ruby/object:Gem::Requirement
@@ -154,16 +154,16 @@ dependencies:
154
154
  name: relaton-iso-bib
155
155
  requirement: !ruby/object:Gem::Requirement
156
156
  requirements:
157
- - - ">="
157
+ - - "~>"
158
158
  - !ruby/object:Gem::Version
159
- version: 1.8.0
159
+ version: 1.10.1
160
160
  type: :runtime
161
161
  prerelease: false
162
162
  version_requirements: !ruby/object:Gem::Requirement
163
163
  requirements:
164
- - - ">="
164
+ - - "~>"
165
165
  - !ruby/object:Gem::Version
166
- version: 1.8.0
166
+ version: 1.10.1
167
167
  description: 'RelatonGb: retrieve Chinese GB Standards for bibliographic use using
168
168
  the BibliographicItem model.'
169
169
  email:
@@ -220,7 +220,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
220
220
  requirements:
221
221
  - - ">="
222
222
  - !ruby/object:Gem::Version
223
- version: 2.4.0
223
+ version: 2.5.0
224
224
  required_rubygems_version: !ruby/object:Gem::Requirement
225
225
  requirements:
226
226
  - - ">="