Class: FAIRChampionHarvester::DOI

Inherits:
Object
  • Object
show all
Defined in:
lib/doi.rb

Class Method Summary collapse

Class Method Details

.check_affiliation_information_from_crossref(doi, meta) ⇒ Object 



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
 
# File 'lib/doi.rb', line 99

def self.check_affiliation_information_from_crossref(doi, meta)
  # https://api.crossref.org/works/10.1063/5.0095229
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.crossref.org/works/#{doi}"
  meta.comments << "INFO:  Looking for affiliation information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  # warn "headers #{_headers} #{url}"
  # abort
  return false unless body

  # normal author
  meta.comments << "INFO:  parsing affiliation info from response\n"
  json = JSON.parse(body)
  auths = json.dig("message", "author")
  auths&.each do |auth|
    if auth["affiliation"]&.first # cant be empty list
      meta.comments << "INFO:  At least one author has affiliation information\n"
      return true
    end
  end

  # grant author
  # "investigator": [
  #           {
  #             "given": "Manka",
  #             "family": "Varghese",
  #             "affiliation": [
  #               {
  #                 "name": "University of Washington"
  #               }
  #             ]
  #           },
  # ...

  #  "lead-investigator": [
  #           {
  #             "given": "Jessica",
  #             "family": "Thompson",
  #             "affiliation": [
  #               {
  #                 "name": "University of Washington"
  #               }
  #             ]
  #           }
  #         ],
  meta.comments << "INFO:  checking for investigator or lead investigator in grant information\n"
  json = JSON.parse(body)
  projects = json.dig("message", "project") # returns a list
  projects&.each do |proj|
    investigators = proj["investigator"] # two possibilities
    investigators << proj["lead-investigator"]
    investigators&.each do |inv|
      if inv["affiliation"]&.first
        meta.comments << "INFO:  At least one investigator has affiliation information\n"
        return true
      end
    end
  end

  meta.comments << "WARN:  no authors had affiliation information\n"
  false
end

.check_affiliation_information_from_datacite(doi, meta) ⇒ Object 



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
 
# File 'lib/doi.rb', line 164

def self.check_affiliation_information_from_datacite(doi, meta)
  # https://api.datacite.org/dois/10.15151/ESRF-ES-2303075148
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.datacite.org/dois/#{doi}"
  meta.comments << "INFO:  Looking for author affiliation information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  return false unless body

  # warn body

  meta.comments << "INFO:  parsing affiliation info from response\n"
  data = JSON.parse(body)

  auths = data.dig("data", "attributes", "creators")
  auths&.each do |auth|
    if auth["affiliation"]
      meta.comments << "INFO:  At least one author has affiliation information\n"
      return true
    end
  end
  meta.comments << "WARN:  no authors had affiliation information\n"
  false
end

.check_license_information_from_crossref(doi, meta) ⇒ Object 



214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
 
# File 'lib/doi.rb', line 214

def self.check_license_information_from_crossref(doi, meta)
  # https://api.crossref.org/works/10.1063/5.0095229
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.crossref.org/works/#{doi}"
  meta.comments << "INFO:  Looking for license information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  # warn "headers #{_headers} #{url}"
  # abort
  return false unless body

  # normal author
  meta.comments << "INFO:  parsing license info from response\n"
  json = JSON.parse(body)
  lics = json.dig("message", "license")
  if lics&.first
    meta.comments << "INFO:  found license information\n"
    return true
  end
  meta.comments << "WARN:  no licsense information found\n"
  false
end

.check_license_information_from_datacite(doi, meta) ⇒ Object 



190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
 
# File 'lib/doi.rb', line 190

def self.check_license_information_from_datacite(doi, meta)
  # https://api.datacite.org/dois/10.15151/ESRF-ES-2303075148
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.datacite.org/dois/#{doi}"
  meta.comments << "INFO:  Looking for license information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  return false unless body

  # warn body

  meta.comments << "INFO:  parsing license info from response\n"
  data = JSON.parse(body)

  rights = data.dig("data", "attributes", "rightsList") # may return empty list - for a fail
  if rights&.first
    meta.comments << "INFO:  license information found\n"
    return true
  end
  meta.comments << "WARN:  no license information found\n"
  false
end

.get_funding_information_from_crossref(doi, meta) ⇒ Object 



48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
 
# File 'lib/doi.rb', line 48

def self.get_funding_information_from_crossref(doi, meta)
  # https://api.crossref.org/works/10.1063/5.0095229
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.crossref.org/works/#{doi}"
  meta.comments << "INFO:  Looking for funding information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  return false unless body

  meta.comments << "INFO:  parsing funding info from response\n"
  json = JSON.parse(body)
  funding_refs = json.dig("message", "funder")
  first_funding = funding_refs&.dig(0) # safe navigation + dig

  if first_funding
    meta.comments << "INFO:  funding info block found\n"
    first_funding
  else
    meta.comments << "WARN:  no funding information block found\n"
    false
  end
end

.get_funding_information_from_datacite(doi, meta) ⇒ Object 



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
 
# File 'lib/doi.rb', line 72

def self.get_funding_information_from_datacite(doi, meta)
  # https://api.datacite.org/dois/10.15151/ESRF-ES-2303075148
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://api.datacite.org/dois/#{doi}"
  meta.comments << "INFO:  Looking for funding information\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  return false unless body

  # warn body

  meta.comments << "INFO:  parsing funding info from response\n"
  data = JSON.parse(body)

  funding_refs = data.dig("data", "attributes", "fundingReferences")
  first_funding = funding_refs&.dig(0) # safe navigation + dig

  if first_funding
    meta.comments << "INFO:  funding info block found\n"
    first_funding
  else
    meta.comments << "WARN:  no funding information block found\n"
    false
  end
end

.resolve_doi(guid, meta) ⇒ Object 



3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
 
# File 'lib/doi.rb', line 3

def self.resolve_doi(guid, meta)
  guid.downcase!
  type, url = Core.convertToURL(guid)
  meta.guidtype = type if meta.guidtype.nil?
  meta.comments << "INFO:  Found a DOI.\n"

  meta.comments << "INFO:  Attempting to resolve #{url} using HTTP Headers #{FAIRChampionHarvester::Utils::AcceptHeader}.\n"
  FAIRChampionHarvester::URL.resolve_url(guid: url, meta: meta, nolinkheaders: false) # specifically metadataguid: link, meta: meta, nolinkheaders: true
  meta.comments << "INFO:  Attempting to resolve #{url} using HTTP Headers {\"Accept\"=>\"*/*\"}.\n"
  FAIRChampionHarvester::URL.resolve_url(guid: url, meta: meta, nolinkheaders: false, headers: { "Accept" => "*/*" }) # whatever is default

  # CrossRef and DataCite both "intercept" the normal redirect process, when a URI has a content-type
  # Accept header that they understand.  This prevents the owner of the data from providing their own
  # metadata of that type, when using the DOI as their GUID.  Here
  # we have let the redirect process go all the way to the final URL, and we then
  # treat that as a new GUID.
  finalURI = meta.finalURI.last
  if finalURI =~ %r{\w+://}
    meta.comments << "INFO:  DOI resolution captures content-negotiation before reaching final data owner.  Now re-attempting the full suite of content negotiation on final redirect URI #{finalURI}.\n"
    FAIRChampionHarvester::Uri.resolve_uri(finalURI, meta)
  end

  meta
end

.resolve_doi_to_registration_agency(doi, meta) ⇒ Object

this should only be called AFTER the general resolve above



29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
 
# File 'lib/doi.rb', line 29

def self.resolve_doi_to_registration_agency(doi, meta)
  doi.downcase!
  doi.gsub!(%r{https?://[^/+]/}, "")
  doi.strip!
  url = "https://doi.org/doiRA/#{doi}"
  meta.comments << "INFO:  Finding DOI registration agency.\n"

  meta.comments << "INFO:  Attempting to resolve #{url} using HTTP Headers {\"Accept\"=>\"*/*\"}.\n"
  _headers, body = Core.fetch(guid: url, headers: FAIRChampionHarvester::Utils::AcceptDefaultHeader)
  if body
    meta.comments << "INFO:  parsing agency from response\n"
    json = JSON.parse(body)
    json.dig(0, "RA")
  else
    meta.comments << "WARN:  doiRA did not return JSON.  Aborting.\n"
    false
  end
end