relaton-nist 1.9.1 → 1.9.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.gitignore +1 -0
- data/README.adoc +19 -0
- data/lib/relaton_nist/data_fetcher.rb +221 -0
- data/lib/relaton_nist/hit_collection.rb +11 -10
- data/lib/relaton_nist/nist_bibliography.rb +1 -1
- data/lib/relaton_nist/processor.rb +5 -0
- data/lib/relaton_nist/version.rb +1 -1
- data/lib/relaton_nist.rb +1 -0
- metadata +3 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 76cfec1954dfd58bf622a6a47e34bdbcfe4cf471106eb7ad19582654078a6d38
|
4
|
+
data.tar.gz: 9769f406d5b98840b5bc099d78ab811388170d1fae5872211a7a0c9ed26d869f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0e3deefff699c77103afb631a03283697dc05f5c952b60b3602961df37df2095102b16c32e229aeeceb76da12cfda09e43e6b0788b6a4c1f02b74dea8a49f818
|
7
|
+
data.tar.gz: 3244707d2595b5b45bab973399a04b8cc791d3b008e2ef05fcc99d9355cec6915556aea8528e5f992e4ba0452af82bda09fb93737741a72c08a64e7a0039d161
|
data/.gitignore
CHANGED
data/README.adoc
CHANGED
@@ -159,6 +159,25 @@ RelatonNist::NistBibliographicItem.from_hash hash
|
|
159
159
|
...
|
160
160
|
----
|
161
161
|
|
162
|
+
=== Fetch data
|
163
|
+
|
164
|
+
This gem uses the https://raw.githubusercontent.com/usnistgov/NIST-Tech-Pubs/nist-pages/xml/allrecords.xml dataset as one of data sources.
|
165
|
+
|
166
|
+
The method `RelatonNist::DataFetcher.fetch(output: "data", format: "yaml")` fetches all the documents from the datast and save them to the `./data` folder in YAML format.
|
167
|
+
Arguments:
|
168
|
+
|
169
|
+
- `output` - folder to save documents (default './data').
|
170
|
+
- `format` - format in which the documents are saved. Possimle formats are: `yaml`, `xml` (default `yaml`).
|
171
|
+
|
172
|
+
[source,ruby]
|
173
|
+
----
|
174
|
+
RelatonNist::DataFetcher.fetch
|
175
|
+
Started at: 2021-09-01 18:01:01 +0200
|
176
|
+
Stopped at: 2021-09-01 18:01:43 +0200
|
177
|
+
Done in: 42 sec.
|
178
|
+
=> nil
|
179
|
+
----
|
180
|
+
|
162
181
|
== Development
|
163
182
|
|
164
183
|
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
@@ -0,0 +1,221 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# require 'English'
|
4
|
+
# require 'mechanize'
|
5
|
+
# require "fileutils"
|
6
|
+
require "yaml"
|
7
|
+
# require "open-uri"
|
8
|
+
# require "nokogiri"
|
9
|
+
# require "relaton_nist"
|
10
|
+
|
11
|
+
module RelatonNist
|
12
|
+
class DataFetcher
|
13
|
+
RELATION_TYPES = {
|
14
|
+
"replaces" => "obsoletes",
|
15
|
+
"isVersionOf" => "editionOf",
|
16
|
+
"hasTranslation" => "hasTranslation",
|
17
|
+
"isTranslationOf" => "translatedFrom",
|
18
|
+
"hasPreprint" => "hasReprint",
|
19
|
+
"isSupplementTo" => "complements",
|
20
|
+
}.freeze
|
21
|
+
URL = "https://raw.githubusercontent.com/usnistgov/NIST-Tech-Pubs/nist-pages/xml/allrecords.xml"
|
22
|
+
|
23
|
+
def initialize(output, format)
|
24
|
+
@output = output
|
25
|
+
@format = format
|
26
|
+
end
|
27
|
+
|
28
|
+
def parse_docid(doc)
|
29
|
+
doi = doc.at("doi_data/doi").text
|
30
|
+
id = doc.at("publisher_item/item_number", "publisher_item/identifier").text.sub(%r{^/}, "")
|
31
|
+
case doi
|
32
|
+
when "10.6028/NBS.CIRC.12e2revjune" then id.sub!("13e", "12e")
|
33
|
+
when "10.6028/NBS.CIRC.36e2" then id.sub!("46e", "36e")
|
34
|
+
when "10.6028/NBS.HB.67suppJune1967" then id.sub!("1965", "1967")
|
35
|
+
when "10.6028/NBS.HB.105-1r1990" then id.sub!("105-1-1990", "105-1r1990")
|
36
|
+
when "10.6028/NIST.HB.150-10-1995" then id.sub!(/150-10$/, "150-10-1995")
|
37
|
+
end
|
38
|
+
[{ type: "NIST", id: id }, { type: "DOI", id: doi }]
|
39
|
+
end
|
40
|
+
|
41
|
+
# @param doc [Nokogiri::XML::Element]
|
42
|
+
# @return [Array<RelatonBib::DocumentIdentifier>]
|
43
|
+
def fetch_docid(doc)
|
44
|
+
parse_docid(doc).map do |id|
|
45
|
+
RelatonBib::DocumentIdentifier.new(type: id[:type], id: id[:id])
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
# @param doc [Nokogiri::XML::Element]
|
50
|
+
# @return [RelatonBib::TypedTitleStringCollection, Array]
|
51
|
+
def fetch_title(doc)
|
52
|
+
t = doc.xpath("titles/title|titles/subtitle")
|
53
|
+
return [] unless t.any?
|
54
|
+
|
55
|
+
RelatonBib::TypedTitleString.from_string t.map(&:text).join(" "), "en", "Latn"
|
56
|
+
end
|
57
|
+
|
58
|
+
# @param doc [Nokogiri::XML::Element]
|
59
|
+
# @return [Array<RelatonBib::BibliographicDate>]
|
60
|
+
def fetch_date(doc)
|
61
|
+
doc.xpath("publication_date|approval_date").map do |dt|
|
62
|
+
on = dt.at("year").text
|
63
|
+
if (m = dt.at "month")
|
64
|
+
on += "-#{m.text}"
|
65
|
+
d = dt.at "day"
|
66
|
+
on += "-#{d.text}" if d
|
67
|
+
end
|
68
|
+
type = dt.name == "publication_date" ? "published" : "confirmed"
|
69
|
+
RelatonBib::BibliographicDate.new(type: type, on: on)
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
# @param doc [Nokogiri::XML::Element]
|
74
|
+
# @return [String]
|
75
|
+
def fetch_edition(doc)
|
76
|
+
doc.at("edition_number")&.text
|
77
|
+
end
|
78
|
+
|
79
|
+
# @param doc [Nokogiri::XML::Element]
|
80
|
+
# @return [Array<Hash>]
|
81
|
+
def fetch_relation(doc)
|
82
|
+
ns = "http://www.crossref.org/relations.xsd"
|
83
|
+
doc.xpath("./ns:program/ns:related_item", ns: ns).map do |rel|
|
84
|
+
doi = rel.at_xpath("ns:intra_work_relation|ns:inter_work_relation", ns: ns)
|
85
|
+
# ref = doi_to_id doi.text
|
86
|
+
# ref, = parse_docid doc
|
87
|
+
fref = RelatonBib::FormattedRef.new content: doi.text
|
88
|
+
bibitem = RelatonBib::BibliographicItem.new formattedref: fref
|
89
|
+
type = RELATION_TYPES[doi["relationship-type"]]
|
90
|
+
{ type: type, bibitem: bibitem }
|
91
|
+
end
|
92
|
+
end
|
93
|
+
|
94
|
+
# @param doc [Nokogiri::XML::Element]
|
95
|
+
# @return [Array<RelatonBib::TypedUri>]
|
96
|
+
def fetch_link(doc)
|
97
|
+
url = doc.at("doi_data/resource").text
|
98
|
+
[RelatonBib::TypedUri.new(type: "doi", content: url)]
|
99
|
+
end
|
100
|
+
|
101
|
+
# @param doc [Nokogiri::XML::Element]
|
102
|
+
# @return [Array<RelatonBib::FormattedString>]
|
103
|
+
def fetch_abstract(doc)
|
104
|
+
doc.xpath("jats:abstract/jats:p", "jats" => "http://www.ncbi.nlm.nih.gov/JATS1").map do |a|
|
105
|
+
RelatonBib::FormattedString.new(content: a.text, language: doc["language"], script: "Latn")
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
# @param doc [Nokogiri::XML::Element]
|
110
|
+
# @return [Array<Hash>]
|
111
|
+
def fetch_contributor(doc) # rubocop:disable Metrics/AbcSize,Metrics/MethodLength,Metrics/CyclomaticComplexity,Metrics/PerceivedComplexity
|
112
|
+
contribs = doc.xpath("contributors/person_name").map do |p|
|
113
|
+
forename = []
|
114
|
+
initial = []
|
115
|
+
p.at("given_name")&.text&.split&.each do |fn|
|
116
|
+
if /^(?<init>\w)\.?$/ =~ fn
|
117
|
+
initial << RelatonBib::LocalizedString.new(init, doc["language"], "Latn")
|
118
|
+
else
|
119
|
+
forename << RelatonBib::LocalizedString.new(fn, doc["language"], "Latn")
|
120
|
+
end
|
121
|
+
end
|
122
|
+
sname = p.at("surname").text
|
123
|
+
surname = RelatonBib::LocalizedString.new sname, doc["language"], "Latn"
|
124
|
+
initial = []
|
125
|
+
ident = p.xpath("ORCID").map do |id|
|
126
|
+
RelatonBib::PersonIdentifier.new "orcid", id.text
|
127
|
+
end
|
128
|
+
fullname = RelatonBib::FullName.new(
|
129
|
+
surname: surname, forename: forename, initial: initial, identifier: ident,
|
130
|
+
)
|
131
|
+
person = RelatonBib::Person.new name: fullname
|
132
|
+
{ entity: person, role: [{ type: p["contributor_role"] }] }
|
133
|
+
end
|
134
|
+
contribs + doc.xpath("publisher").map do |p|
|
135
|
+
abbr = p.at("../institution/institution_acronym")&.text
|
136
|
+
org = RelatonBib::Organization.new(name: p.at("publisher_name").text, abbreviation: abbr)
|
137
|
+
{ entity: org, role: [{ type: "publisher" }] }
|
138
|
+
end
|
139
|
+
end
|
140
|
+
|
141
|
+
# @param doc [Nokogiri::XML::Element]
|
142
|
+
# @return [Array<String>]
|
143
|
+
def fetch_place(doc)
|
144
|
+
doc.xpath("institution/institution_place").map(&:text)
|
145
|
+
end
|
146
|
+
|
147
|
+
#
|
148
|
+
# Save document
|
149
|
+
#
|
150
|
+
# @param bib [RelatonNist::NistBibliographicItem]
|
151
|
+
#
|
152
|
+
def write_file(bib) # rubocop:disable Metrics/AbcSize,Metrics/MethodLength
|
153
|
+
id = bib.docidentifier[0].id.gsub(%r{[/\s:.]}, "_").upcase.sub(/^NIST_IR/, "NISTIR")
|
154
|
+
file = File.join(@output, "#{id}.#{@format}")
|
155
|
+
if File.exist? file
|
156
|
+
warn "File #{file} exists. Docid: #{bib.docidentifier[0].id}"
|
157
|
+
# warn "Link: #{bib.link.detect { |l| l.type == 'src' }.content}"
|
158
|
+
else
|
159
|
+
output = case @format
|
160
|
+
when "yaml" then bib.to_hash.to_yaml
|
161
|
+
when "xml" then bib.to_xml bibdata: true
|
162
|
+
end
|
163
|
+
File.write file, output, encoding: "UTF-8"
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
#
|
168
|
+
# Create a document instance an save it.
|
169
|
+
#
|
170
|
+
# @param doc [Nokogiri::XML::Element]
|
171
|
+
#
|
172
|
+
# @raise [StandardError]
|
173
|
+
#
|
174
|
+
def parse_doc(doc) # rubocop:disable Metrics/MethodLength,Metrics/AbcSize
|
175
|
+
# mtd = doc.at('doi_record/report-paper/report-paper_metadata')
|
176
|
+
item = RelatonNist::NistBibliographicItem.new(
|
177
|
+
type: "standard", docid: fetch_docid(doc), title: fetch_title(doc),
|
178
|
+
link: fetch_link(doc), abstract: fetch_abstract(doc),
|
179
|
+
date: fetch_date(doc), edition: fetch_edition(doc),
|
180
|
+
contributor: fetch_contributor(doc), relation: fetch_relation(doc),
|
181
|
+
place: fetch_place(doc),
|
182
|
+
language: [doc["language"]], script: ["Latn"], doctype: "standard"
|
183
|
+
)
|
184
|
+
write_file item
|
185
|
+
rescue StandardError => e
|
186
|
+
warn "Document: #{doc.at('doi').text}"
|
187
|
+
warn e.message
|
188
|
+
raise e
|
189
|
+
end
|
190
|
+
|
191
|
+
#
|
192
|
+
# Fetch all the documnts from dataset
|
193
|
+
#
|
194
|
+
def fetch # rubocop:disable Metrics/AbcSize,Metrics/MethodLength
|
195
|
+
t1 = Time.now
|
196
|
+
puts "Started at: #{t1}"
|
197
|
+
|
198
|
+
docs = Nokogiri::XML OpenURI.open_uri URL
|
199
|
+
FileUtils.mkdir @output unless Dir.exist? @output
|
200
|
+
FileUtils.rm Dir[File.join(@output, "*.#{@format}")]
|
201
|
+
docs.xpath("/body/query/doi_record/report-paper/report-paper_metadata")
|
202
|
+
.each { |doc| parse_doc doc }
|
203
|
+
|
204
|
+
t2 = Time.now
|
205
|
+
puts "Stopped at: #{t2}"
|
206
|
+
puts "Done in: #{(t2 - t1).round} sec."
|
207
|
+
rescue StandardError => e
|
208
|
+
warn e.message
|
209
|
+
end
|
210
|
+
|
211
|
+
#
|
212
|
+
# Fetch all the documnts from dataset
|
213
|
+
#
|
214
|
+
# @param [String] output foldet name to save the documents
|
215
|
+
# @param [String] format format to save the documents
|
216
|
+
#
|
217
|
+
def self.fetch(output: "data", format: "yaml")
|
218
|
+
new(output, format).fetch
|
219
|
+
end
|
220
|
+
end
|
221
|
+
end
|
@@ -15,17 +15,19 @@ module RelatonNist
|
|
15
15
|
DATAFILE = File.expand_path "pubs-export.zip", DATAFILEDIR
|
16
16
|
GHNISTDATA = "https://raw.githubusercontent.com/relaton/relaton-data-nist/main/data/"
|
17
17
|
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
def
|
23
|
-
super ref_nbr, year
|
24
|
-
|
25
|
-
# /(?<docid>(?:SP|FIPS)\s[0-9-]+)/ =~ text
|
18
|
+
def self.search(text, year = nil, opts = {})
|
19
|
+
new(text, year).search(opts)
|
20
|
+
end
|
21
|
+
|
22
|
+
def search(opts)
|
26
23
|
@array = from_json(**opts)
|
27
24
|
@array = from_ga unless @array.any?
|
25
|
+
sort_hits!
|
26
|
+
end
|
28
27
|
|
28
|
+
private
|
29
|
+
|
30
|
+
def sort_hits!
|
29
31
|
@array.sort! do |a, b|
|
30
32
|
if a.sort_value == b.sort_value
|
31
33
|
(b.hit[:release_date] - a.hit[:release_date]).to_i
|
@@ -33,10 +35,9 @@ module RelatonNist
|
|
33
35
|
b.sort_value - a.sort_value
|
34
36
|
end
|
35
37
|
end
|
38
|
+
self
|
36
39
|
end
|
37
40
|
|
38
|
-
private
|
39
|
-
|
40
41
|
def from_ga # rubocop:disable Metrics/AbcSize
|
41
42
|
fn = text.gsub(%r{[/\s:.]}, "_").upcase
|
42
43
|
yaml = OpenURI.open_uri "#{GHNISTDATA}#{fn}.yaml"
|
@@ -14,7 +14,7 @@ module RelatonNist
|
|
14
14
|
# @param text [String]
|
15
15
|
# @return [RelatonNist::HitCollection]
|
16
16
|
def search(text, year = nil, opts = {})
|
17
|
-
HitCollection.
|
17
|
+
HitCollection.search text, year, opts
|
18
18
|
rescue OpenURI::HTTPError, SocketError, OpenSSL::SSL::SSLError => e
|
19
19
|
raise RelatonBib::RequestError, e.message
|
20
20
|
end
|
@@ -7,6 +7,7 @@ module RelatonNist
|
|
7
7
|
@prefix = "NIST"
|
8
8
|
@defaultprefix = %r{^(NIST|NISTGCR|ITL Bulletin|JPCRD|NISTIR|CSRC|FIPS)(/[^\s])?\s}
|
9
9
|
@idtype = "NIST"
|
10
|
+
@datasets = %w[nist-tech-pubs]
|
10
11
|
end
|
11
12
|
|
12
13
|
# @param code [String]
|
@@ -17,6 +18,10 @@ module RelatonNist
|
|
17
18
|
::RelatonNist::NistBibliography.get(code, date, opts)
|
18
19
|
end
|
19
20
|
|
21
|
+
def fetch_data(_source, opts)
|
22
|
+
DataFetcher.fetch(**opts)
|
23
|
+
end
|
24
|
+
|
20
25
|
# @param xml [String]
|
21
26
|
# @return [RelatonNist::GbBibliographicItem]
|
22
27
|
def from_xml(xml)
|
data/lib/relaton_nist/version.rb
CHANGED
data/lib/relaton_nist.rb
CHANGED
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: relaton-nist
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.9.
|
4
|
+
version: 1.9.2
|
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-
|
11
|
+
date: 2021-09-03 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: equivalent-xml
|
@@ -175,6 +175,7 @@ files:
|
|
175
175
|
- grammars/reqt.rng
|
176
176
|
- lib/relaton_nist.rb
|
177
177
|
- lib/relaton_nist/comment_period.rb
|
178
|
+
- lib/relaton_nist/data_fetcher.rb
|
178
179
|
- lib/relaton_nist/document_relation.rb
|
179
180
|
- lib/relaton_nist/document_status.rb
|
180
181
|
- lib/relaton_nist/hash_converter.rb
|