nistbib 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +11 -0
- data/.rspec +3 -0
- data/.travis.yml +7 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +81 -0
- data/LICENSE.txt +21 -0
- data/README.md +39 -0
- data/Rakefile +6 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/nistbib/hit.rb +51 -0
- data/lib/nistbib/hit_collection.rb +70 -0
- data/lib/nistbib/nist_bibliography.rb +97 -0
- data/lib/nistbib/scrapper.rb +184 -0
- data/lib/nistbib/version.rb +3 -0
- data/lib/nistbib/workers_pool.rb +41 -0
- data/lib/nistbib.rb +7 -0
- data/lib/relaton/processor.rb +23 -0
- data/nistbib.gemspec +37 -0
- metadata +203 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: ef1ae9dcd37608cd47b565f151b291adcf85cca5
|
4
|
+
data.tar.gz: 953dce58fd24be8d0e39a3ec9622a3a5508bbb2c
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 25007561f152223a16046b5b05811312d4bda2feb5cb2663a351a61da64fe3cd2edee5ce104aeb21918203a1f44529ae4f5ace9f8c8c1f3299eed91966b3b4c7
|
7
|
+
data.tar.gz: 1e98dca81f2a883899b4f0ae7f3a8fc057293b208adce21b4e36186db813667e669e534bf8071685ee872d70ccca039918c1f145476c1e6890abe9eb9fe34faa
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,81 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
nistbib (0.1.0)
|
5
|
+
iso-bib-item (~> 0.4.2)
|
6
|
+
|
7
|
+
GEM
|
8
|
+
remote: https://rubygems.org/
|
9
|
+
specs:
|
10
|
+
addressable (2.6.0)
|
11
|
+
public_suffix (>= 2.0.2, < 4.0)
|
12
|
+
byebug (10.0.2)
|
13
|
+
coderay (1.1.2)
|
14
|
+
crack (0.4.3)
|
15
|
+
safe_yaml (~> 1.0.0)
|
16
|
+
diff-lcs (1.3)
|
17
|
+
docile (1.3.1)
|
18
|
+
equivalent-xml (0.6.0)
|
19
|
+
nokogiri (>= 1.4.3)
|
20
|
+
hashdiff (0.3.8)
|
21
|
+
iso-bib-item (0.4.4)
|
22
|
+
isoics (~> 0.1.6)
|
23
|
+
nokogiri (~> 1.8.4)
|
24
|
+
ruby_deep_clone (~> 0.8.0)
|
25
|
+
isoics (0.1.7)
|
26
|
+
json (2.1.0)
|
27
|
+
method_source (0.9.2)
|
28
|
+
mini_portile2 (2.3.0)
|
29
|
+
nokogiri (1.8.5)
|
30
|
+
mini_portile2 (~> 2.3.0)
|
31
|
+
pry (0.12.2)
|
32
|
+
coderay (~> 1.1.0)
|
33
|
+
method_source (~> 0.9.0)
|
34
|
+
pry-byebug (3.6.0)
|
35
|
+
byebug (~> 10.0)
|
36
|
+
pry (~> 0.10)
|
37
|
+
public_suffix (3.0.3)
|
38
|
+
rake (10.5.0)
|
39
|
+
rspec (3.8.0)
|
40
|
+
rspec-core (~> 3.8.0)
|
41
|
+
rspec-expectations (~> 3.8.0)
|
42
|
+
rspec-mocks (~> 3.8.0)
|
43
|
+
rspec-core (3.8.0)
|
44
|
+
rspec-support (~> 3.8.0)
|
45
|
+
rspec-expectations (3.8.2)
|
46
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
47
|
+
rspec-support (~> 3.8.0)
|
48
|
+
rspec-mocks (3.8.0)
|
49
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
50
|
+
rspec-support (~> 3.8.0)
|
51
|
+
rspec-support (3.8.0)
|
52
|
+
ruby_deep_clone (0.8.0)
|
53
|
+
safe_yaml (1.0.4)
|
54
|
+
simplecov (0.16.1)
|
55
|
+
docile (~> 1.1)
|
56
|
+
json (>= 1.8, < 3)
|
57
|
+
simplecov-html (~> 0.10.0)
|
58
|
+
simplecov-html (0.10.2)
|
59
|
+
vcr (4.0.0)
|
60
|
+
webmock (3.5.1)
|
61
|
+
addressable (>= 2.3.6)
|
62
|
+
crack (>= 0.3.2)
|
63
|
+
hashdiff
|
64
|
+
|
65
|
+
PLATFORMS
|
66
|
+
ruby
|
67
|
+
|
68
|
+
DEPENDENCIES
|
69
|
+
bundler (~> 2.0)
|
70
|
+
byebug
|
71
|
+
equivalent-xml (~> 0.6)
|
72
|
+
nistbib!
|
73
|
+
pry-byebug
|
74
|
+
rake (~> 10.0)
|
75
|
+
rspec (~> 3.0)
|
76
|
+
simplecov
|
77
|
+
vcr
|
78
|
+
webmock
|
79
|
+
|
80
|
+
BUNDLED WITH
|
81
|
+
2.0.1
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2019 Andrei Kislichenko
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
# Nistbib
|
2
|
+
|
3
|
+
Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/nistbib`. To experiment with that code, run `bin/console` for an interactive prompt.
|
4
|
+
|
5
|
+
TODO: Delete this and the text above, and describe your gem
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
```ruby
|
12
|
+
gem 'nistbib'
|
13
|
+
```
|
14
|
+
|
15
|
+
And then execute:
|
16
|
+
|
17
|
+
$ bundle
|
18
|
+
|
19
|
+
Or install it yourself as:
|
20
|
+
|
21
|
+
$ gem install nistbib
|
22
|
+
|
23
|
+
## Usage
|
24
|
+
|
25
|
+
TODO: Write usage instructions here
|
26
|
+
|
27
|
+
## Development
|
28
|
+
|
29
|
+
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.
|
30
|
+
|
31
|
+
To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
|
32
|
+
|
33
|
+
## Contributing
|
34
|
+
|
35
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/nistbib.
|
36
|
+
|
37
|
+
## License
|
38
|
+
|
39
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "nistbib"
|
5
|
+
|
6
|
+
# You can add fixtures and/or initialization code here to make experimenting
|
7
|
+
# with your gem easier. You can also use a different console, if you like.
|
8
|
+
|
9
|
+
# (If you use this, don't forget to add pry to your Gemfile!)
|
10
|
+
# require "pry"
|
11
|
+
# Pry.start
|
12
|
+
|
13
|
+
require "irb"
|
14
|
+
IRB.start(__FILE__)
|
data/bin/setup
ADDED
data/lib/nistbib/hit.rb
ADDED
@@ -0,0 +1,51 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
module NistBib
|
4
|
+
# Hit.
|
5
|
+
class Hit
|
6
|
+
# @return [Isobib::HitCollection]
|
7
|
+
attr_reader :hit_collection
|
8
|
+
|
9
|
+
# @return [Array<Hash>]
|
10
|
+
attr_reader :hit
|
11
|
+
|
12
|
+
# @param hit [Hash]
|
13
|
+
# @param hit_collection [Isobib:HitCollection]
|
14
|
+
def initialize(hit, hit_collection = nil)
|
15
|
+
@hit = hit
|
16
|
+
@hit_collection = hit_collection
|
17
|
+
end
|
18
|
+
|
19
|
+
# Parse page.
|
20
|
+
# @return [Isobib::IsoBibliographicItem]
|
21
|
+
def fetch
|
22
|
+
@fetch ||= Scrapper.parse_page @hit
|
23
|
+
end
|
24
|
+
|
25
|
+
# @return [String]
|
26
|
+
def to_s
|
27
|
+
inspect
|
28
|
+
end
|
29
|
+
|
30
|
+
# @return [String]
|
31
|
+
def inspect
|
32
|
+
"<#{self.class}:#{format('%#.14x', object_id << 1)} "\
|
33
|
+
"@text=\"#{@hit_collection&.text}\" "\
|
34
|
+
"@fetched=\"#{!@fetch.nil?}\" "\
|
35
|
+
"@fullIdentifier=\"#{@fetch&.shortref(nil)}\" "\
|
36
|
+
"@title=\"#{@hit[:code]}\">"
|
37
|
+
end
|
38
|
+
|
39
|
+
# @return [String]
|
40
|
+
def to_xml(opts = {})
|
41
|
+
#if builder
|
42
|
+
#fetch.to_xml builder, opts
|
43
|
+
#else
|
44
|
+
builder = Nokogiri::XML::Builder.new(encoding: 'UTF-8') do |xml|
|
45
|
+
fetch.to_xml xml, opts
|
46
|
+
end
|
47
|
+
builder.doc.root.to_xml
|
48
|
+
#end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
@@ -0,0 +1,70 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require 'nistbib/hit'
|
4
|
+
require 'nistbib/workers_pool'
|
5
|
+
require "addressable/uri"
|
6
|
+
require 'open-uri'
|
7
|
+
|
8
|
+
module NistBib
|
9
|
+
# Page of hit collection.
|
10
|
+
class HitCollection < Array
|
11
|
+
|
12
|
+
DOMAIN = 'https://csrc.nist.gov'
|
13
|
+
|
14
|
+
# @return [TrueClass, FalseClass]
|
15
|
+
attr_reader :fetched
|
16
|
+
|
17
|
+
# @return [String]
|
18
|
+
attr_reader :text
|
19
|
+
|
20
|
+
# @return [String]
|
21
|
+
attr_reader :year
|
22
|
+
|
23
|
+
# @param ref_nbr [String]
|
24
|
+
# @param year [String]
|
25
|
+
def initialize(ref_nbr, year = nil) #(text, hit_pages = nil)
|
26
|
+
@text = ref_nbr
|
27
|
+
@year = year
|
28
|
+
from, to = nil
|
29
|
+
if year
|
30
|
+
d = Date.strptime year, '%Y'
|
31
|
+
from = d.strftime '%m/%d/%Y'
|
32
|
+
to = d.next_year.prev_day.strftime '%m/%d/%Y'
|
33
|
+
end
|
34
|
+
url = "#{DOMAIN}/publications/search?keywords-lg=#{ref_nbr}&dateFrom-lg=#{from}&dateTo-lg=#{to}"
|
35
|
+
doc = Nokogiri::HTML OpenURI.open_uri(::Addressable::URI.parse(url).normalize)
|
36
|
+
hits = doc.css('table.publications-table > tbody > tr').map do |h|
|
37
|
+
link = h.at('td/div/strong/a')
|
38
|
+
code = h.at('td[2]').text.strip
|
39
|
+
title = link.text
|
40
|
+
url = DOMAIN + link[:href]
|
41
|
+
Hit.new({ code: code, title: title, url: url }, self)
|
42
|
+
end
|
43
|
+
concat hits
|
44
|
+
# concat(hits.map { |h| Hit.new(h, self) })
|
45
|
+
@fetched = false
|
46
|
+
# @hit_pages = hit_pages
|
47
|
+
end
|
48
|
+
|
49
|
+
# @return [Iecbib::HitCollection]
|
50
|
+
def fetch
|
51
|
+
workers = WorkersPool.new 4
|
52
|
+
workers.worker(&:fetch)
|
53
|
+
each do |hit|
|
54
|
+
workers << hit
|
55
|
+
end
|
56
|
+
workers.end
|
57
|
+
workers.result
|
58
|
+
@fetched = true
|
59
|
+
self
|
60
|
+
end
|
61
|
+
|
62
|
+
def to_s
|
63
|
+
inspect
|
64
|
+
end
|
65
|
+
|
66
|
+
def inspect
|
67
|
+
"<#{self.class}:#{format('%#.14x', object_id << 1)} @fetched=#{@fetched}>"
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
@@ -0,0 +1,97 @@
|
|
1
|
+
require 'nistbib/scrapper'
|
2
|
+
require 'nistbib/hit_collection'
|
3
|
+
|
4
|
+
module NistBib
|
5
|
+
class NistBibliography
|
6
|
+
class << self
|
7
|
+
# @param text [String]
|
8
|
+
# @return [NistBib::HitCollection]
|
9
|
+
def search(text, year = nil)
|
10
|
+
HitCollection.new text, year
|
11
|
+
rescue
|
12
|
+
warn "Could not access https://www.nist.gov"
|
13
|
+
[]
|
14
|
+
end
|
15
|
+
|
16
|
+
# @param code [String] the NIST standard Code to look up (e..g "8200")
|
17
|
+
# @param year [String] the year the standard was published (optional)
|
18
|
+
# @param opts [Hash] options; restricted to :all_parts if all-parts reference is required
|
19
|
+
# @return [String] Relaton XML serialisation of reference
|
20
|
+
def get(code, year, opts)
|
21
|
+
code += '-1' if opts[:all_parts]
|
22
|
+
ret = nistbib_get1(code, year, opts)
|
23
|
+
return nil if ret.nil?
|
24
|
+
ret.to_most_recent_reference unless year || opts[:keep_year]
|
25
|
+
ret.to_all_parts if opts[:all_parts]
|
26
|
+
ret
|
27
|
+
end
|
28
|
+
|
29
|
+
private
|
30
|
+
|
31
|
+
def nistbib_get1(code, year, opts)
|
32
|
+
result = nistbib_search_filter(code, year) or return nil
|
33
|
+
ret = nistbib_results_filter(result, year)
|
34
|
+
return ret[:ret] if ret[:ret]
|
35
|
+
fetch_ref_err(code, year, ret[:years])
|
36
|
+
end
|
37
|
+
|
38
|
+
# Sort through the results from Isobib, fetching them three at a time,
|
39
|
+
# and return the first result that matches the code,
|
40
|
+
# matches the year (if provided), and which # has a title (amendments do not).
|
41
|
+
# Only expects the first page of results to be populated.
|
42
|
+
# Does not match corrigenda etc (e.g. ISO 3166-1:2006/Cor 1:2007)
|
43
|
+
# If no match, returns any years which caused mismatch, for error reporting
|
44
|
+
def nistbib_results_filter(result, year)
|
45
|
+
missed_years = []
|
46
|
+
result.each_slice(3) do |s| # ISO website only allows 3 connections
|
47
|
+
fetch_pages(s, 3).each_with_index do |r, i|
|
48
|
+
return { ret: r } if !year
|
49
|
+
r.dates.select { |d| d.type == "published" }.each do |d|
|
50
|
+
return { ret: r } if year.to_i == d.on.year
|
51
|
+
missed_years << d.on.year
|
52
|
+
end
|
53
|
+
end
|
54
|
+
end
|
55
|
+
{ years: missed_years }
|
56
|
+
end
|
57
|
+
|
58
|
+
def fetch_pages(s, n)
|
59
|
+
workers = WorkersPool.new n
|
60
|
+
workers.worker { |w| { i: w[:i], hit: w[:hit].fetch } }
|
61
|
+
s.each_with_index { |hit, i| workers << { i: i, hit: hit } }
|
62
|
+
workers.end
|
63
|
+
workers.result.sort { |x, y| x[:i] <=> y[:i] }.map { |x| x[:hit] }
|
64
|
+
end
|
65
|
+
|
66
|
+
def nistbib_search_filter(code, year)
|
67
|
+
# docidrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+}
|
68
|
+
# corrigrx = %r{^(ISO|IEC)[^0-9]*\s[0-9-]+:[0-9]+/}
|
69
|
+
warn "fetching #{code}..."
|
70
|
+
result = search(code, year)
|
71
|
+
result.select do |i|
|
72
|
+
!i.hit[:code].empty?
|
73
|
+
# i.hit[:code] &&
|
74
|
+
# i.hit[:code].match(docidrx).to_s == code &&
|
75
|
+
# corrigrx !~ i.hit[:code]
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
def fetch_ref_err(code, year, missed_years)
|
80
|
+
id = year ? "#{code}:#{year}" : code
|
81
|
+
warn "WARNING: no match found online for #{id}. "\
|
82
|
+
"The code must be exactly like it is on the standards website."
|
83
|
+
warn "(There was no match for #{year}, though there were matches "\
|
84
|
+
"found for #{missed_years.join(', ')}.)" unless missed_years.empty?
|
85
|
+
if /\d-\d/ =~ code
|
86
|
+
warn "The provided document part may not exist, or the document "\
|
87
|
+
"may no longer be published in parts."
|
88
|
+
else
|
89
|
+
warn "If you wanted to cite all document parts for the reference, "\
|
90
|
+
"use \"#{code} (all parts)\".\nIf the document is not a standard, "\
|
91
|
+
"use its document type abbreviation (TS, TR, PAS, Guide)."
|
92
|
+
end
|
93
|
+
nil
|
94
|
+
end
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
@@ -0,0 +1,184 @@
|
|
1
|
+
require 'iso_bib_item'
|
2
|
+
|
3
|
+
module NistBib
|
4
|
+
module Scrapper
|
5
|
+
class << self
|
6
|
+
DOMAIN = 'https://csrc.nist.gov'
|
7
|
+
|
8
|
+
# Parse page.
|
9
|
+
# @param hit_data [Hash]
|
10
|
+
# @return [Hash]
|
11
|
+
# rubocop:disable Metrics/AbcSize, Metrics/MethodLength
|
12
|
+
def parse_page(hit_data)
|
13
|
+
doc = get_page hit_data[:url]
|
14
|
+
|
15
|
+
IsoBibItem::IsoBibliographicItem.new(
|
16
|
+
docid: fetch_docid(doc),
|
17
|
+
edition: nil,
|
18
|
+
language: ['en'],
|
19
|
+
script: ['Latn'],
|
20
|
+
titles: fetch_titles(hit_data),
|
21
|
+
type: nil,
|
22
|
+
docstatus: fetch_status(doc),
|
23
|
+
ics: [],
|
24
|
+
dates: fetch_dates(doc),
|
25
|
+
contributors: fetch_contributors,
|
26
|
+
workgroup: nil,
|
27
|
+
abstract: fetch_abstract(doc),
|
28
|
+
copyright: fetch_copyright(doc),
|
29
|
+
link: fetch_link(doc, hit_data[:url]),
|
30
|
+
relations: fetch_relations(doc)
|
31
|
+
)
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
# Get page.
|
37
|
+
# @param path [String] page's path
|
38
|
+
# @return [Array<Nokogiri::HTML::Document, String>]
|
39
|
+
def get_page(url)
|
40
|
+
uri = URI url
|
41
|
+
resp = Net::HTTP.get_response(uri)#.encode("UTF-8")
|
42
|
+
Nokogiri::HTML(resp.body)
|
43
|
+
end
|
44
|
+
|
45
|
+
# Fetch docid.
|
46
|
+
# @param doc [Nokogiri::HTML::Document]
|
47
|
+
# @return [Hash]
|
48
|
+
def fetch_docid(doc)
|
49
|
+
item_ref = doc.at("//div[contains(@class, 'publications-detail')]/h3").text.strip
|
50
|
+
unless item_ref
|
51
|
+
return { project_number: '?', part_number: '', prefix: nil, type: 'NIST', id: '?' }
|
52
|
+
end
|
53
|
+
m = item_ref.match(/(?<=\s)(?<project>[\d-]+)(?<vol>\sVol\.\s)?(?<part>(?(<vol>)\d+|))/)
|
54
|
+
{
|
55
|
+
project_number: m[:project],
|
56
|
+
part_number: m[:part],
|
57
|
+
subpart_number: nil,
|
58
|
+
prefix: nil,
|
59
|
+
type: 'NIST',
|
60
|
+
id: item_ref
|
61
|
+
}
|
62
|
+
end
|
63
|
+
|
64
|
+
# Fetch status.
|
65
|
+
# @param doc [Nokogiri::HTML::Document]
|
66
|
+
# @param status [String]
|
67
|
+
# @return [Hash]
|
68
|
+
def fetch_status(doc)
|
69
|
+
withdrawn = doc.at "//p/strong[text()='Withdrawn:']"
|
70
|
+
return { status: 'withdrawn', stage: '95', substage: '99' } if withdrawn
|
71
|
+
|
72
|
+
item_ref = doc.at("//div[contains(@class, 'publications-detail')]/h3").text.strip
|
73
|
+
wip = item_ref.match(/(?<=\()\w+/).to_s
|
74
|
+
case wip
|
75
|
+
when 'DRAFT'
|
76
|
+
{ status: 'working-draft', stage: '20', substage: '20' }
|
77
|
+
# when 'RETIRED DRAFT'
|
78
|
+
# { status: 'committee-draft', stage: '30', substage: '00' }
|
79
|
+
else
|
80
|
+
{ status: 'published', stage: '60', substage: '60' }
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
# Fetch titles.
|
85
|
+
# @param hit_data [Hash]
|
86
|
+
# @return [Array<Hash>]
|
87
|
+
def fetch_titles(hit_data)
|
88
|
+
titles = hit_data[:title].split ' - '
|
89
|
+
# case titles.size
|
90
|
+
# when 0
|
91
|
+
# intro, main, part = nil, "", nil
|
92
|
+
# when 1
|
93
|
+
intro, main, part = nil, titles[0], nil
|
94
|
+
# when 2
|
95
|
+
# if /^(Part|Partie) \d+:/ =~ titles[1]
|
96
|
+
# intro, main, part = nil, titles[0], titles[1]
|
97
|
+
# else
|
98
|
+
# intro, main, part = titles[0], titles[1], nil
|
99
|
+
# end
|
100
|
+
# when 3
|
101
|
+
# intro, main, part = titles[0], titles[1], titles[2]
|
102
|
+
# else
|
103
|
+
# intro, main, part = titles[0], titles[1], titles[2..-1]&.join(" -- ")
|
104
|
+
# end
|
105
|
+
[{
|
106
|
+
title_intro: intro,
|
107
|
+
title_main: main,
|
108
|
+
title_part: part,
|
109
|
+
language: 'en',
|
110
|
+
script: 'Latn'
|
111
|
+
}]
|
112
|
+
end
|
113
|
+
|
114
|
+
# Fetch dates
|
115
|
+
# @param doc [Nokogiri::HTML::Document]
|
116
|
+
# @return [Array<Hash>]
|
117
|
+
def fetch_dates(doc)
|
118
|
+
dates = []
|
119
|
+
d = doc.at("//strong[text()='Date Published:']/../text()[2]").text.strip
|
120
|
+
publish_date = Date.strptime(d, '%B %Y').to_s
|
121
|
+
unless publish_date.empty?
|
122
|
+
dates << { type: 'published', on: publish_date }
|
123
|
+
end
|
124
|
+
dates
|
125
|
+
end
|
126
|
+
|
127
|
+
def fetch_contributors
|
128
|
+
name = 'National Institute of Standards and Technology'
|
129
|
+
url = 'www.nist.gov'
|
130
|
+
[{ entity: { name: name, url: url, abbreviation: 'NIST' }, roles: ['publisher'] }]
|
131
|
+
end
|
132
|
+
|
133
|
+
# Fetch abstracts.
|
134
|
+
# @param doc [Nokigiri::HTML::Document]
|
135
|
+
# @return [Array<Array>]
|
136
|
+
def fetch_abstract(doc)
|
137
|
+
abstract_content = doc.xpath('//div[contains(@class, "pub-abstract-callout")]/div[1]/p').text
|
138
|
+
[{
|
139
|
+
content: abstract_content,
|
140
|
+
language: 'en',
|
141
|
+
script: 'Latn'
|
142
|
+
}]
|
143
|
+
end
|
144
|
+
|
145
|
+
# Fetch copyright.
|
146
|
+
# @param title [String]
|
147
|
+
# @return [Hash]
|
148
|
+
def fetch_copyright(doc)
|
149
|
+
name = 'National Institute of Standards and Technology'
|
150
|
+
url = 'www.nist.gov'
|
151
|
+
d = doc.at("//strong[text()='Date Published:']/../text()[2]").text.strip
|
152
|
+
from = d.match(/\d{4}$/).to_s
|
153
|
+
{ owner: { name: name, abbreviation: 'NIST', url: url }, from: from }
|
154
|
+
end
|
155
|
+
|
156
|
+
# Fetch links.
|
157
|
+
# @param doc [Nokogiri::HTML::Document]
|
158
|
+
# @param url [String]
|
159
|
+
# @return [Array<Hash>]
|
160
|
+
def fetch_link(doc, url)
|
161
|
+
links = [{ type: 'src', content: url }]
|
162
|
+
obp_elms = doc.at_css('a[data-identity="first-link-display"]')
|
163
|
+
links << { type: 'obp', content: obp_elms[:href] } if obp_elms
|
164
|
+
links
|
165
|
+
end
|
166
|
+
|
167
|
+
# Fetch relations.
|
168
|
+
# @param doc [Nokogiri::HTML::Document]
|
169
|
+
# @return [Array<Hash>]
|
170
|
+
# rubocop:disable Metrics/MethodLength
|
171
|
+
def fetch_relations(doc)
|
172
|
+
relations = doc.xpath('//strong[text()="Other Parts of this Publication:"]/following-sibling::a').map do |r|
|
173
|
+
{ type: 'partOf', identifier: r.text, url: DOMAIN + r[:href] }
|
174
|
+
end
|
175
|
+
|
176
|
+
doc.xpath('//strong[text()="Related NIST Publications:"]/following-sibling::a').map do |r|
|
177
|
+
relations << { type: 'updates', identifier: r.text, url: DOMAIN + r[:href] }
|
178
|
+
end
|
179
|
+
|
180
|
+
relations
|
181
|
+
end
|
182
|
+
end
|
183
|
+
end
|
184
|
+
end
|
@@ -0,0 +1,41 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
# Workers poll.
|
4
|
+
class WorkersPool
|
5
|
+
attr_accessor :nb_hits
|
6
|
+
|
7
|
+
def initialize(num_workers = 2)
|
8
|
+
@num_workers = num_workers < 2 ? 2 : num_workers
|
9
|
+
@queue = SizedQueue.new(num_workers * 2)
|
10
|
+
@result = []
|
11
|
+
@nb_hits = 0
|
12
|
+
end
|
13
|
+
|
14
|
+
def worker(&block)
|
15
|
+
@threads = Array.new @num_workers do
|
16
|
+
Thread.new do
|
17
|
+
until (item = @queue.pop) == :END
|
18
|
+
@result << yield(item) if block
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
def result
|
25
|
+
@threads.each(&:join)
|
26
|
+
@result
|
27
|
+
end
|
28
|
+
|
29
|
+
def <<(item)
|
30
|
+
@queue << item
|
31
|
+
self
|
32
|
+
end
|
33
|
+
|
34
|
+
def end
|
35
|
+
@num_workers.times { @queue << :END }
|
36
|
+
end
|
37
|
+
|
38
|
+
# def size
|
39
|
+
# @result.size
|
40
|
+
# end
|
41
|
+
end
|
data/lib/nistbib.rb
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
require "relaton/processor"
|
2
|
+
|
3
|
+
module Relaton
|
4
|
+
module Isobib
|
5
|
+
class Processor < Relaton::Processor
|
6
|
+
|
7
|
+
def initialize
|
8
|
+
@short = :nistbib
|
9
|
+
@prefix = "NIST"
|
10
|
+
@defaultprefix = %r{^(NIST)[ /]}
|
11
|
+
@idtype = "NIST"
|
12
|
+
end
|
13
|
+
|
14
|
+
def get(code, date, opts)
|
15
|
+
::Nistbib::NistBibliography.get(code, date, opts)
|
16
|
+
end
|
17
|
+
|
18
|
+
def from_xml(xml)
|
19
|
+
IsoBibItem::XMLParser.from_xml xml
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/nistbib.gemspec
ADDED
@@ -0,0 +1,37 @@
|
|
1
|
+
|
2
|
+
lib = File.expand_path("../lib", __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require "nistbib/version"
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "nistbib"
|
8
|
+
spec.version = NistBib::VERSION
|
9
|
+
spec.authors = ["Ribose Inc."]
|
10
|
+
spec.email = ["open.source@ribose.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{NistBib: retrive NIST standards.}
|
13
|
+
spec.description = %q{NistBib: retrive NIST standards.}
|
14
|
+
spec.homepage = "https://github.com/riboseinc/nistbib"
|
15
|
+
spec.license = "MIT"
|
16
|
+
|
17
|
+
# Specify which files should be added to the gem when it is released.
|
18
|
+
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
19
|
+
spec.files = Dir.chdir(File.expand_path('..', __FILE__)) do
|
20
|
+
`git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
21
|
+
end
|
22
|
+
spec.bindir = "exe"
|
23
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
24
|
+
spec.require_paths = ["lib"]
|
25
|
+
|
26
|
+
spec.add_development_dependency "bundler", "~> 2.0"
|
27
|
+
spec.add_development_dependency 'equivalent-xml', '~> 0.6'
|
28
|
+
spec.add_development_dependency "pry-byebug"
|
29
|
+
spec.add_development_dependency "byebug"
|
30
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
31
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
32
|
+
spec.add_development_dependency 'simplecov'
|
33
|
+
spec.add_development_dependency 'vcr'
|
34
|
+
spec.add_development_dependency 'webmock'
|
35
|
+
|
36
|
+
spec.add_dependency 'iso-bib-item', '~> 0.4.2'
|
37
|
+
end
|
metadata
ADDED
@@ -0,0 +1,203 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nistbib
|
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: 2019-02-07 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '2.0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '2.0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: equivalent-xml
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0.6'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.6'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: pry-byebug
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: 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: rspec
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.0'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: simplecov
|
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: vcr
|
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: webmock
|
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: iso-bib-item
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: 0.4.2
|
146
|
+
type: :runtime
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - "~>"
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: 0.4.2
|
153
|
+
description: 'NistBib: retrive NIST standards.'
|
154
|
+
email:
|
155
|
+
- open.source@ribose.com
|
156
|
+
executables: []
|
157
|
+
extensions: []
|
158
|
+
extra_rdoc_files: []
|
159
|
+
files:
|
160
|
+
- ".gitignore"
|
161
|
+
- ".rspec"
|
162
|
+
- ".travis.yml"
|
163
|
+
- Gemfile
|
164
|
+
- Gemfile.lock
|
165
|
+
- LICENSE.txt
|
166
|
+
- README.md
|
167
|
+
- Rakefile
|
168
|
+
- bin/console
|
169
|
+
- bin/setup
|
170
|
+
- lib/nistbib.rb
|
171
|
+
- lib/nistbib/hit.rb
|
172
|
+
- lib/nistbib/hit_collection.rb
|
173
|
+
- lib/nistbib/nist_bibliography.rb
|
174
|
+
- lib/nistbib/scrapper.rb
|
175
|
+
- lib/nistbib/version.rb
|
176
|
+
- lib/nistbib/workers_pool.rb
|
177
|
+
- lib/relaton/processor.rb
|
178
|
+
- nistbib.gemspec
|
179
|
+
homepage: https://github.com/riboseinc/nistbib
|
180
|
+
licenses:
|
181
|
+
- MIT
|
182
|
+
metadata: {}
|
183
|
+
post_install_message:
|
184
|
+
rdoc_options: []
|
185
|
+
require_paths:
|
186
|
+
- lib
|
187
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
188
|
+
requirements:
|
189
|
+
- - ">="
|
190
|
+
- !ruby/object:Gem::Version
|
191
|
+
version: '0'
|
192
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
193
|
+
requirements:
|
194
|
+
- - ">="
|
195
|
+
- !ruby/object:Gem::Version
|
196
|
+
version: '0'
|
197
|
+
requirements: []
|
198
|
+
rubyforge_project:
|
199
|
+
rubygems_version: 2.6.12
|
200
|
+
signing_key:
|
201
|
+
specification_version: 4
|
202
|
+
summary: 'NistBib: retrive NIST standards.'
|
203
|
+
test_files: []
|