relaton-omg 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.
@@ -0,0 +1,6 @@
1
+ module RelatonOmg
2
+ class HashConverter < RelatonBib::HashConverter
3
+ class << self
4
+ end
5
+ end
6
+ end
@@ -0,0 +1,55 @@
1
+ module RelatonOmg
2
+ class OmgBibliographicItem < RelatonBib::BibliographicItem
3
+ # @return [String, NilClass]
4
+ attr_reader :doctype
5
+
6
+ # @param doctype [String]
7
+ # @param keyword [Array<String>]
8
+ def initialize(**args)
9
+ @doctype = args.delete :doctype
10
+ # @keyword = args.delete(:keyword) || []
11
+ super
12
+ end
13
+
14
+ class << self
15
+ # @param file [String] path to YAML file
16
+ # @return [RelatonOmg::OmgBibliographicItem]
17
+ def from_yaml(file)
18
+ from_hash YAML.load_file(file)
19
+ end
20
+
21
+ # @param hash [Hash]
22
+ # @return [RelatonOmg::OmgBibliographicItem]
23
+ def from_hash(hash)
24
+ new RelatonOmg::HashConverter.hash_to_bib(hash)
25
+ end
26
+
27
+ # @param file [String] path to XML file
28
+ # @return [RelatonOmg::OmgBibliographicItem]
29
+ def from_xml(file)
30
+ XMLParser.from_xml File.read file, encoding: "UTF-8"
31
+ end
32
+ end
33
+
34
+ # @param builder
35
+ # @param opts [Hash]
36
+ # @option opts [Symbol, NilClass] :date_format (:short), :full
37
+ def to_xml(builder = nil, **opts)
38
+ opts[:date_format] ||= :short
39
+ super builder, **opts do |b|
40
+ # if opts[:bibdata]
41
+ # b.ext do
42
+ # b.doctype doctype if doctype
43
+ # end
44
+ # end
45
+ end
46
+ end
47
+
48
+ # @return [Hash]
49
+ def to_hash
50
+ hash = super
51
+ hash["doctype"] = doctype if doctype
52
+ hash
53
+ end
54
+ end
55
+ end
@@ -0,0 +1,22 @@
1
+ # frozen_string_literal:true
2
+
3
+ module RelatonOmg
4
+ # OMG bibliography module
5
+ module OmgBibliography
6
+ class << self
7
+ # @param code [String] the OMG standard reference
8
+ # @return [RelatonOmg::OmgBibliographicItem]
9
+ def search(text)
10
+ Scrapper.scrape_page text
11
+ end
12
+
13
+ # @param code [String] the OMG standard reference
14
+ # @param year [String] the year the standard was published (optional)
15
+ # @param opts [Hash] options
16
+ # @return [RelatonOmg::OmgBibliographicItem]
17
+ def get(code, _year = nil, _opts = {})
18
+ search code
19
+ end
20
+ end
21
+ end
22
+ end
@@ -0,0 +1,40 @@
1
+ require "relaton/processor"
2
+ require "relaton_omg/xml_parser"
3
+
4
+ module RelatonOmg
5
+ class Processor < Relaton::Processor
6
+ def initialize
7
+ @short = :relaton_omg
8
+ @prefix = "OMG"
9
+ @defaultprefix = /^OMG /
10
+ @idtype = "OMG"
11
+ end
12
+
13
+ # @param code [String]
14
+ # @param date [String, NilClass] year
15
+ # @param opts [Hash]
16
+ # @return [RelatonIetf::IetfBibliographicItem]
17
+ def get(code, date, opts)
18
+ ::RelatonOmg::OmgBibliography.get(code, date, opts)
19
+ end
20
+
21
+ # @param xml [String]
22
+ # @return [RelatonIetf::IetfBibliographicItem]
23
+ def from_xml(xml)
24
+ ::RelatonOmg::XMLParser.from_xml xml
25
+ end
26
+
27
+ # @param hash [Hash]
28
+ # @return [RelatonIetf::IetfBibliographicItem]
29
+ def hash_to_bib(hash)
30
+ # item_hash = ::RelatonOmg::HashConverter.hash_to_bib(hash)
31
+ ::RelatonOmg::OmgBibliographicItem.from_hash hash
32
+ end
33
+
34
+ # Returns hash of XML grammar
35
+ # @return [String]
36
+ def grammar_hash
37
+ @grammar_hash ||= ::RelatonOmg.grammar_hash
38
+ end
39
+ end
40
+ end
@@ -0,0 +1,124 @@
1
+ require "nokogiri"
2
+
3
+ module RelatonOmg
4
+ module Scrapper
5
+ URL_PATTERN = "https://www.omg.org/spec/"
6
+
7
+ class << self
8
+ def scrape_page(ref)
9
+ %r{OMG (?<acronym>[^\s]+)\s?(?<version>.*)} =~ ref
10
+ return unless acronym
11
+
12
+ url = URL_PATTERN + acronym
13
+ url += "/" + version if version
14
+ doc = Nokogiri::HTML open(URI(url))
15
+ OmgBibliographicItem.new item(doc, acronym)
16
+ rescue OpenURI::HTTPError => e
17
+ if e.io.status[0] == "404"
18
+ warn %{[relaton-omg] no document found for "#{ref}" reference.}
19
+ return
20
+ end
21
+
22
+ raise RelatonBib::RequestError, "Unable acces #{url} (#{e.io.status.join(" ")}"
23
+ end
24
+
25
+ private
26
+
27
+ def item(doc, acronym)
28
+ {
29
+ id: fetch_id(doc, acronym),
30
+ fetched: Date.today.to_s,
31
+ docid: fetch_docid(doc, acronym),
32
+ title: fetch_title(doc),
33
+ abstract: fetch_abstract(doc),
34
+ version: fetch_version(doc),
35
+ date: fetch_date(doc),
36
+ docstatus: fetch_status(doc),
37
+ link: fetch_link(doc),
38
+ relation: fetch_relation(doc),
39
+ keyword: fetch_keyword(doc),
40
+ license: fetch_license(doc)
41
+ }
42
+ end
43
+
44
+ def fetch_id(doc, acronym)
45
+ acronym + version(doc)
46
+ end
47
+
48
+ def fetch_title(doc)
49
+ content = doc.at('//dt[.="Title:"]/following-sibling::dd').text
50
+ title = RelatonBib::FormattedString.new content: content, language: "en", script: "Latn"
51
+ [RelatonBib::TypedTitleString.new(type: "main", title: title)]
52
+ end
53
+
54
+ def fetch_docid(doc, acronym)
55
+ id = [acronym]
56
+ if (ver = version(doc))
57
+ id << ver
58
+ end
59
+ [RelatonBib::DocumentIdentifier.new(id: id.join(" "), type: "OMG")]
60
+ end
61
+
62
+ def fetch_abstract(doc)
63
+ content = doc.at('//section[@id="document-metadata"]/p').text
64
+ [{ content: content, language: "en", script: "Latn" }]
65
+ end
66
+
67
+ def fetch_version(doc)
68
+ RelatonBib::BibliographicItem::Version.new pub_date(doc), [version(doc)]
69
+ end
70
+
71
+ def version(doc)
72
+ doc.at('//dt[.="Version:"]/following-sibling::dd/p/text()').text.strip
73
+ end
74
+
75
+ def fetch_date(doc)
76
+ [type: "published", on: pub_date(doc).to_s]
77
+ end
78
+
79
+ def pub_date(doc)
80
+ Date.parse doc.at('//dt[.="Publication Date:"]/following-sibling::dd').text.strip
81
+ end
82
+
83
+ def fetch_status(doc)
84
+ status = doc.at('//dt[.="Document Status:"]/following-sibling::dd')
85
+ stage = status.text.strip.match(/\w+/).to_s
86
+ RelatonBib::DocumentStatus.new(stage: stage)
87
+ end
88
+
89
+ def fetch_link(doc)
90
+ links = []
91
+ a = doc.at('//dt[.="This Document:"]/following-sibling::dd/a')
92
+ links << { type: "src", content: a[:href] } if a
93
+ pdf = doc.at('//a[@class="download-document"]')
94
+ links << { type: "pdf", content: pdf[:href] } if pdf
95
+ links
96
+ end
97
+
98
+ def fetch_relation(doc)
99
+ current_version = version(doc)
100
+ v = doc.xpath('//h2[.="History"]/following-sibling::section/div/table/tbody/tr')
101
+ v.reduce([]) do |mem, row|
102
+ ver = row.at("td").text
103
+ unless ver == current_version
104
+ acronym = row.at('td[3]/a')[:href].split("/")[4]
105
+ fref = RelatonBib::FormattedRef.new content: "OMG #{acronym} #{ver}"
106
+ bibitem = OmgBibliographicItem.new formattedref: fref
107
+ mem << { type: "obsoletes", bibitem: bibitem }
108
+ end
109
+ mem
110
+ end
111
+ end
112
+
113
+ def fetch_keyword(doc)
114
+ doc.xpath('//dt[.="Categories:"]/following-sibling::dd/ul/li/a/em').map &:text
115
+ end
116
+
117
+ def fetch_license(doc)
118
+ doc.xpath(
119
+ '//dt/span/a[contains(., "IPR Mode")]/../../following-sibling::dd/span'
120
+ ).map { |l| l.text.match(/[\w\s-]+/).to_s.strip }
121
+ end
122
+ end
123
+ end
124
+ end
@@ -0,0 +1,3 @@
1
+ module RelatonOmg
2
+ VERSION = "0.1.0"
3
+ end
@@ -0,0 +1,25 @@
1
+ require "nokogiri"
2
+
3
+ module RelatonOmg
4
+ class XMLParser < RelatonBib::XMLParser
5
+ class << self
6
+ def from_xml(xml)
7
+ doc = Nokogiri::XML(xml)
8
+ doc.remove_namespaces!
9
+ ietfitem = doc.at("/bibitem|/bibdata")
10
+ RelatonOmg::OmgBibliographicItem.new(item_data(ietfitem))
11
+ end
12
+
13
+ private
14
+
15
+ def item_data(ietfitem)
16
+ data = super
17
+ # ext = ietfitem.at "./ext"
18
+ # return data unless ext
19
+
20
+ # data[:doctype] = ext.at("./doctype")&.text
21
+ data
22
+ end
23
+ end
24
+ end
25
+ end
@@ -0,0 +1,19 @@
1
+ require "nokogiri"
2
+ require "relaton_bib"
3
+ require "relaton_omg/version"
4
+ require "relaton_omg/scrapper"
5
+ require "relaton_omg/omg_bibliography"
6
+ require "relaton_omg/omg_bibliographic_item"
7
+ require "relaton_omg/xml_parser"
8
+ require "relaton_omg/hash_converter"
9
+
10
+ module RelatonOmg
11
+ # Returns hash of XML reammar
12
+ # @return [String]
13
+ def self.grammar_hash
14
+ gem_path = File.expand_path "..", __dir__
15
+ grammars_path = File.join gem_path, "grammars", "*"
16
+ grammars = Dir[grammars_path].sort.map { |gp| File.read gp }.join
17
+ Digest::MD5.hexdigest grammars
18
+ end
19
+ end
@@ -0,0 +1,41 @@
1
+ require_relative 'lib/relaton_omg/version'
2
+
3
+ Gem::Specification.new do |spec|
4
+ spec.name = "relaton-omg"
5
+ spec.version = RelatonOmg::VERSION
6
+ spec.authors = ["Ribose Inc."]
7
+ spec.email = ["open.source@ribose.com"]
8
+
9
+ spec.summary = "RelatonOmg: retrieve OMG Standards for bibliographic use"\
10
+ "using the IsoBibliographicItem model"
11
+ spec.description = "RelatonOmg: retrieve OMG Standards for bibliographic use"\
12
+ "using the IsoBibliographicItem model"
13
+ spec.homepage = "https://github.com/relaton/relaton-ogn"
14
+ spec.license = "BSD-2-Clause"
15
+ spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
16
+
17
+ spec.metadata["homepage_uri"] = spec.homepage
18
+ spec.metadata["source_code_uri"] = "https://github.com/relaton/relaton-ogn"
19
+
20
+ # Specify which files should be added to the gem when it is released.
21
+ # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
22
+ spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
23
+ `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
24
+ end
25
+ spec.bindir = "exe"
26
+ spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
27
+ spec.require_paths = ["lib"]
28
+
29
+ spec.add_development_dependency "byebug"
30
+ spec.add_development_dependency "debase"
31
+ spec.add_development_dependency "equivalent-xml", "~> 0.6"
32
+ spec.add_development_dependency "pry-byebug"
33
+ spec.add_development_dependency "rake", "~> 10.0"
34
+ spec.add_development_dependency "ruby-debug-ide"
35
+ spec.add_development_dependency "ruby-jing"
36
+ spec.add_development_dependency "simplecov"
37
+ spec.add_development_dependency "vcr"
38
+ spec.add_development_dependency "webmock"
39
+
40
+ spec.add_dependency "relaton-bib", "~> 0.7.0"
41
+ end
metadata ADDED
@@ -0,0 +1,224 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: relaton-omg
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Ribose Inc.
8
+ autorequire:
9
+ bindir: exe
10
+ cert_chain: []
11
+ date: 2020-02-17 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: byebug
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ">="
18
+ - !ruby/object:Gem::Version
19
+ version: '0'
20
+ type: :development
21
+ prerelease: false
22
+ version_requirements: !ruby/object:Gem::Requirement
23
+ requirements:
24
+ - - ">="
25
+ - !ruby/object:Gem::Version
26
+ version: '0'
27
+ - !ruby/object:Gem::Dependency
28
+ name: debase
29
+ requirement: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - ">="
32
+ - !ruby/object:Gem::Version
33
+ version: '0'
34
+ type: :development
35
+ prerelease: false
36
+ version_requirements: !ruby/object:Gem::Requirement
37
+ requirements:
38
+ - - ">="
39
+ - !ruby/object:Gem::Version
40
+ version: '0'
41
+ - !ruby/object:Gem::Dependency
42
+ name: equivalent-xml
43
+ requirement: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - "~>"
46
+ - !ruby/object:Gem::Version
47
+ version: '0.6'
48
+ type: :development
49
+ prerelease: false
50
+ version_requirements: !ruby/object:Gem::Requirement
51
+ requirements:
52
+ - - "~>"
53
+ - !ruby/object:Gem::Version
54
+ version: '0.6'
55
+ - !ruby/object:Gem::Dependency
56
+ name: pry-byebug
57
+ requirement: !ruby/object:Gem::Requirement
58
+ requirements:
59
+ - - ">="
60
+ - !ruby/object:Gem::Version
61
+ version: '0'
62
+ type: :development
63
+ prerelease: false
64
+ version_requirements: !ruby/object:Gem::Requirement
65
+ requirements:
66
+ - - ">="
67
+ - !ruby/object:Gem::Version
68
+ version: '0'
69
+ - !ruby/object:Gem::Dependency
70
+ name: rake
71
+ requirement: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - "~>"
74
+ - !ruby/object:Gem::Version
75
+ version: '10.0'
76
+ type: :development
77
+ prerelease: false
78
+ version_requirements: !ruby/object:Gem::Requirement
79
+ requirements:
80
+ - - "~>"
81
+ - !ruby/object:Gem::Version
82
+ version: '10.0'
83
+ - !ruby/object:Gem::Dependency
84
+ name: ruby-debug-ide
85
+ requirement: !ruby/object:Gem::Requirement
86
+ requirements:
87
+ - - ">="
88
+ - !ruby/object:Gem::Version
89
+ version: '0'
90
+ type: :development
91
+ prerelease: false
92
+ version_requirements: !ruby/object:Gem::Requirement
93
+ requirements:
94
+ - - ">="
95
+ - !ruby/object:Gem::Version
96
+ version: '0'
97
+ - !ruby/object:Gem::Dependency
98
+ name: ruby-jing
99
+ requirement: !ruby/object:Gem::Requirement
100
+ requirements:
101
+ - - ">="
102
+ - !ruby/object:Gem::Version
103
+ version: '0'
104
+ type: :development
105
+ prerelease: false
106
+ version_requirements: !ruby/object:Gem::Requirement
107
+ requirements:
108
+ - - ">="
109
+ - !ruby/object:Gem::Version
110
+ version: '0'
111
+ - !ruby/object:Gem::Dependency
112
+ name: simplecov
113
+ requirement: !ruby/object:Gem::Requirement
114
+ requirements:
115
+ - - ">="
116
+ - !ruby/object:Gem::Version
117
+ version: '0'
118
+ type: :development
119
+ prerelease: false
120
+ version_requirements: !ruby/object:Gem::Requirement
121
+ requirements:
122
+ - - ">="
123
+ - !ruby/object:Gem::Version
124
+ version: '0'
125
+ - !ruby/object:Gem::Dependency
126
+ name: vcr
127
+ requirement: !ruby/object:Gem::Requirement
128
+ requirements:
129
+ - - ">="
130
+ - !ruby/object:Gem::Version
131
+ version: '0'
132
+ type: :development
133
+ prerelease: false
134
+ version_requirements: !ruby/object:Gem::Requirement
135
+ requirements:
136
+ - - ">="
137
+ - !ruby/object:Gem::Version
138
+ version: '0'
139
+ - !ruby/object:Gem::Dependency
140
+ name: webmock
141
+ requirement: !ruby/object:Gem::Requirement
142
+ requirements:
143
+ - - ">="
144
+ - !ruby/object:Gem::Version
145
+ version: '0'
146
+ type: :development
147
+ prerelease: false
148
+ version_requirements: !ruby/object:Gem::Requirement
149
+ requirements:
150
+ - - ">="
151
+ - !ruby/object:Gem::Version
152
+ version: '0'
153
+ - !ruby/object:Gem::Dependency
154
+ name: relaton-bib
155
+ requirement: !ruby/object:Gem::Requirement
156
+ requirements:
157
+ - - "~>"
158
+ - !ruby/object:Gem::Version
159
+ version: 0.7.0
160
+ type: :runtime
161
+ prerelease: false
162
+ version_requirements: !ruby/object:Gem::Requirement
163
+ requirements:
164
+ - - "~>"
165
+ - !ruby/object:Gem::Version
166
+ version: 0.7.0
167
+ description: 'RelatonOmg: retrieve OMG Standards for bibliographic useusing the IsoBibliographicItem
168
+ model'
169
+ email:
170
+ - open.source@ribose.com
171
+ executables: []
172
+ extensions: []
173
+ extra_rdoc_files: []
174
+ files:
175
+ - ".github/workflows/macos.yml"
176
+ - ".github/workflows/ubuntu.yml"
177
+ - ".github/workflows/windows.yml"
178
+ - ".gitignore"
179
+ - ".rspec"
180
+ - ".rubocop.yml"
181
+ - Gemfile
182
+ - LICENSE.txt
183
+ - README.adoc
184
+ - Rakefile
185
+ - bin/console
186
+ - bin/rspec
187
+ - bin/setup
188
+ - grammars/biblio.rng
189
+ - lib/relaton_omg.rb
190
+ - lib/relaton_omg/hash_converter.rb
191
+ - lib/relaton_omg/omg_bibliographic_item.rb
192
+ - lib/relaton_omg/omg_bibliography.rb
193
+ - lib/relaton_omg/processor.rb
194
+ - lib/relaton_omg/scrapper.rb
195
+ - lib/relaton_omg/version.rb
196
+ - lib/relaton_omg/xml_parser.rb
197
+ - relaton_omg.gemspec
198
+ homepage: https://github.com/relaton/relaton-ogn
199
+ licenses:
200
+ - BSD-2-Clause
201
+ metadata:
202
+ homepage_uri: https://github.com/relaton/relaton-ogn
203
+ source_code_uri: https://github.com/relaton/relaton-ogn
204
+ post_install_message:
205
+ rdoc_options: []
206
+ require_paths:
207
+ - lib
208
+ required_ruby_version: !ruby/object:Gem::Requirement
209
+ requirements:
210
+ - - ">="
211
+ - !ruby/object:Gem::Version
212
+ version: 2.4.0
213
+ required_rubygems_version: !ruby/object:Gem::Requirement
214
+ requirements:
215
+ - - ">="
216
+ - !ruby/object:Gem::Version
217
+ version: '0'
218
+ requirements: []
219
+ rubygems_version: 3.0.6
220
+ signing_key:
221
+ specification_version: 4
222
+ summary: 'RelatonOmg: retrieve OMG Standards for bibliographic useusing the IsoBibliographicItem
223
+ model'
224
+ test_files: []