relaton-ietf 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 +13 -0
- data/.hound.yml +3 -0
- data/.rspec +3 -0
- data/.rubocop.yml +10 -0
- data/.travis.yml +17 -0
- data/Gemfile +9 -0
- data/Gemfile.lock +91 -0
- data/LICENSE.txt +25 -0
- data/README.adoc +124 -0
- data/Rakefile +6 -0
- data/appveyor.yml +35 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/relaton/processor.rb +23 -0
- data/lib/relaton_ietf.rb +11 -0
- data/lib/relaton_ietf/ietf_bibliographi_item.rb +25 -0
- data/lib/relaton_ietf/ietf_bibliography.rb +24 -0
- data/lib/relaton_ietf/scrapper.rb +255 -0
- data/lib/relaton_ietf/version.rb +3 -0
- data/lib/relaton_ietf/xml_parser.rb +24 -0
- data/relaton_ietf.gemspec +44 -0
- metadata +221 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: f9bf4b1db7471743fbce87d242ebd9f8a7a59630
|
4
|
+
data.tar.gz: deb0f7674386a76f577671a1f6f883249ffe0beb
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: fc38e9bdf1be20eaeb09b3b6b42783af101a40ac3f1e3238d46d23a1612cb5dbc8748d43079db05338c0d9dc28ae4998dcd1684f81236367297276675c398876
|
7
|
+
data.tar.gz: 38d10c12570ff5836b1421776b8eedde6f3ccc7118ef78b2db4fb25ef51a7a5229600a2eedc7ef5cee7d5a8b1f4e2be59bbc8b1b8d23e5ae8faab38fe6b05a2f
|
data/.gitignore
ADDED
data/.hound.yml
ADDED
data/.rspec
ADDED
data/.rubocop.yml
ADDED
@@ -0,0 +1,10 @@
|
|
1
|
+
# This project follows the Ribose OSS style guide.
|
2
|
+
# https://github.com/riboseinc/oss-guides
|
3
|
+
# All project-specific additions and overrides should be specified in this file.
|
4
|
+
|
5
|
+
inherit_from:
|
6
|
+
- https://raw.githubusercontent.com/riboseinc/oss-guides/master/ci/rubocop.yml
|
7
|
+
AllCops:
|
8
|
+
TargetRubyVersion: 2.3
|
9
|
+
Rails:
|
10
|
+
Enabled: true
|
data/.travis.yml
ADDED
@@ -0,0 +1,17 @@
|
|
1
|
+
# Auto-generated !!! Do not edit it manually
|
2
|
+
# use ci-master https://github.com/metanorma/metanorma-build-scripts
|
3
|
+
language: ruby
|
4
|
+
cache: bundler
|
5
|
+
os:
|
6
|
+
- linux
|
7
|
+
- osx
|
8
|
+
rvm:
|
9
|
+
- 2.5
|
10
|
+
- 2.4
|
11
|
+
- ruby-head
|
12
|
+
before_install:
|
13
|
+
- gem install bundler -v 2.0.1
|
14
|
+
- bundle update
|
15
|
+
matrix:
|
16
|
+
allow_failures:
|
17
|
+
- rvm: ruby-head
|
data/Gemfile
ADDED
@@ -0,0 +1,9 @@
|
|
1
|
+
Encoding.default_external = Encoding::UTF_8
|
2
|
+
Encoding.default_internal = Encoding::UTF_8
|
3
|
+
|
4
|
+
source "https://rubygems.org"
|
5
|
+
|
6
|
+
git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
|
7
|
+
|
8
|
+
# Specify your gem's dependencies in relaton_ietf.gemspec
|
9
|
+
gemspec
|
data/Gemfile.lock
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
relaton-ietf (0.1.0)
|
5
|
+
relaton-iso-bib (~> 0.1.0)
|
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 (11.0.1)
|
13
|
+
coderay (1.1.2)
|
14
|
+
crack (0.4.3)
|
15
|
+
safe_yaml (~> 1.0.0)
|
16
|
+
debase (0.2.2)
|
17
|
+
debase-ruby_core_source (>= 0.10.2)
|
18
|
+
debase-ruby_core_source (0.10.4)
|
19
|
+
diff-lcs (1.3)
|
20
|
+
docile (1.3.1)
|
21
|
+
equivalent-xml (0.6.0)
|
22
|
+
nokogiri (>= 1.4.3)
|
23
|
+
hashdiff (0.4.0)
|
24
|
+
isoics (0.1.7)
|
25
|
+
json (2.2.0)
|
26
|
+
method_source (0.9.2)
|
27
|
+
mini_portile2 (2.3.0)
|
28
|
+
nokogiri (1.8.5)
|
29
|
+
mini_portile2 (~> 2.3.0)
|
30
|
+
pry (0.12.2)
|
31
|
+
coderay (~> 1.1.0)
|
32
|
+
method_source (~> 0.9.0)
|
33
|
+
pry-byebug (3.7.0)
|
34
|
+
byebug (~> 11.0)
|
35
|
+
pry (~> 0.10)
|
36
|
+
public_suffix (3.1.0)
|
37
|
+
rake (10.5.0)
|
38
|
+
relaton-bib (0.1.6)
|
39
|
+
addressable
|
40
|
+
nokogiri (~> 1.8.4)
|
41
|
+
relaton-iso-bib (0.1.0)
|
42
|
+
isoics (~> 0.1.6)
|
43
|
+
nokogiri (~> 1.8.4)
|
44
|
+
relaton-bib (~> 0.1.5)
|
45
|
+
ruby_deep_clone (~> 0.8.0)
|
46
|
+
rspec (3.8.0)
|
47
|
+
rspec-core (~> 3.8.0)
|
48
|
+
rspec-expectations (~> 3.8.0)
|
49
|
+
rspec-mocks (~> 3.8.0)
|
50
|
+
rspec-core (3.8.0)
|
51
|
+
rspec-support (~> 3.8.0)
|
52
|
+
rspec-expectations (3.8.3)
|
53
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
54
|
+
rspec-support (~> 3.8.0)
|
55
|
+
rspec-mocks (3.8.0)
|
56
|
+
diff-lcs (>= 1.2.0, < 2.0)
|
57
|
+
rspec-support (~> 3.8.0)
|
58
|
+
rspec-support (3.8.0)
|
59
|
+
ruby-debug-ide (0.6.1)
|
60
|
+
rake (>= 0.8.1)
|
61
|
+
ruby_deep_clone (0.8.0)
|
62
|
+
safe_yaml (1.0.5)
|
63
|
+
simplecov (0.16.1)
|
64
|
+
docile (~> 1.1)
|
65
|
+
json (>= 1.8, < 3)
|
66
|
+
simplecov-html (~> 0.10.0)
|
67
|
+
simplecov-html (0.10.2)
|
68
|
+
vcr (5.0.0)
|
69
|
+
webmock (3.5.1)
|
70
|
+
addressable (>= 2.3.6)
|
71
|
+
crack (>= 0.3.2)
|
72
|
+
hashdiff
|
73
|
+
|
74
|
+
PLATFORMS
|
75
|
+
ruby
|
76
|
+
|
77
|
+
DEPENDENCIES
|
78
|
+
bundler (~> 2.0.1)
|
79
|
+
debase
|
80
|
+
equivalent-xml (~> 0.6)
|
81
|
+
pry-byebug
|
82
|
+
rake (~> 10.0)
|
83
|
+
relaton-ietf!
|
84
|
+
rspec (~> 3.0)
|
85
|
+
ruby-debug-ide
|
86
|
+
simplecov
|
87
|
+
vcr
|
88
|
+
webmock
|
89
|
+
|
90
|
+
BUNDLED WITH
|
91
|
+
2.0.1
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,25 @@
|
|
1
|
+
BSD 2-Clause License
|
2
|
+
|
3
|
+
Copyright (c) 2018, Ribose
|
4
|
+
All rights reserved.
|
5
|
+
|
6
|
+
Redistribution and use in source and binary forms, with or without
|
7
|
+
modification, are permitted provided that the following conditions are met:
|
8
|
+
|
9
|
+
* Redistributions of source code must retain the above copyright notice, this
|
10
|
+
list of conditions and the following disclaimer.
|
11
|
+
|
12
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
13
|
+
this list of conditions and the following disclaimer in the documentation
|
14
|
+
and/or other materials provided with the distribution.
|
15
|
+
|
16
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
17
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
18
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
19
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
20
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
21
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
22
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
23
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
24
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
25
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
data/README.adoc
ADDED
@@ -0,0 +1,124 @@
|
|
1
|
+
= RelatonIetf
|
2
|
+
|
3
|
+
image:https://img.shields.io/gem/v/relaton-ietf.svg["Gem Version", link="https://rubygems.org/gems/relaton-ietf"]
|
4
|
+
image:https://img.shields.io/travis/metanorma/relaton-ietf/master.svg["Build Status", link="https://travis-ci.org/metanorma/relaton-ietf"]
|
5
|
+
image:https://ci.appveyor.com/api/projects/status/eirsba4v3nviejs4?svg=true["Appveyor Build Status", link="https://ci.appveyor.com/project/ribose/relaton-ietf"]
|
6
|
+
image:https://codeclimate.com/github/metanorma/relaton-ietf/badges/gpa.svg["Code Climate", link="https://codeclimate.com/github/metanorma/relaton-ietf"]
|
7
|
+
|
8
|
+
_Formerly known as_ `rfcbib`.
|
9
|
+
|
10
|
+
RelatonIetf is a Ruby gem that search and fetch standards from the https://www.ietf.org[Internet Engineering Task Force (IETF)], including RFCs.
|
11
|
+
|
12
|
+
The standards scrape form https://www.rfc-editor.org/search/rfc_search.php
|
13
|
+
|
14
|
+
== Installation
|
15
|
+
|
16
|
+
Add this line to your application's Gemfile:
|
17
|
+
|
18
|
+
[source, ruby]
|
19
|
+
----
|
20
|
+
gem 'relaton-ietf'
|
21
|
+
----
|
22
|
+
|
23
|
+
And then execute:
|
24
|
+
|
25
|
+
$ bundle
|
26
|
+
|
27
|
+
Or install it yourself as:
|
28
|
+
|
29
|
+
$ gem install relaton-ietf
|
30
|
+
|
31
|
+
== Usage
|
32
|
+
|
33
|
+
=== Search document
|
34
|
+
|
35
|
+
[source,ruby]
|
36
|
+
----
|
37
|
+
require 'relaton_ietf'
|
38
|
+
|
39
|
+
item = RelatonIetf::IetfBibliography.search 'RFC 8341'
|
40
|
+
=> #<RelatonIetf::IetfBibliographicItem:0x007fd1875e7f58
|
41
|
+
...
|
42
|
+
|
43
|
+
# Return nil if document doesn't exist.
|
44
|
+
RelatonIetf::IetfBibliography.search '1111'
|
45
|
+
1111.xml: not recognised for RFC
|
46
|
+
=> nil
|
47
|
+
----
|
48
|
+
|
49
|
+
=== Serialization
|
50
|
+
|
51
|
+
[source,ruby]
|
52
|
+
----
|
53
|
+
item.to_xml
|
54
|
+
=>"<bibitem id="RFC8341">
|
55
|
+
<fetched>2019-06-05</fetched>
|
56
|
+
<title format="text/plain" language="en" script="Latn">Network Configuration Access Control Model</title>
|
57
|
+
<uri type="src">https://www.rfc-editor.org/info/rfc8341</uri>
|
58
|
+
<docidentifier type="IETF">RFC 8341</docidentifier>
|
59
|
+
<docidentifier type="DOI">10.17487/RFC8341</docidentifier>
|
60
|
+
<date type="published">
|
61
|
+
<on>2018-03</on>
|
62
|
+
</date>
|
63
|
+
<contributor>
|
64
|
+
<role type="author"/>
|
65
|
+
<person>
|
66
|
+
<name>
|
67
|
+
<completename language="en">A. Bierman</completename>
|
68
|
+
</name>
|
69
|
+
<affiliation>
|
70
|
+
<organization>
|
71
|
+
<name>IETF</name>
|
72
|
+
<abbreviation>IETF</abbreviation>
|
73
|
+
</organization>
|
74
|
+
</affiliation>
|
75
|
+
</person>
|
76
|
+
</contributor>
|
77
|
+
<contributor>
|
78
|
+
<role type="author"/>
|
79
|
+
<person>
|
80
|
+
<name>
|
81
|
+
<completename language="en">M. Bjorklund</completename>
|
82
|
+
</name>
|
83
|
+
<affiliation>
|
84
|
+
<organization>
|
85
|
+
<name>IETF</name>
|
86
|
+
<abbreviation>IETF</abbreviation>
|
87
|
+
</organization>
|
88
|
+
</affiliation>
|
89
|
+
</person>
|
90
|
+
</contributor>
|
91
|
+
<language>en</language>
|
92
|
+
<script>Latn</script>
|
93
|
+
<series type="main">
|
94
|
+
<title format="text/plain" language="en" script="Latn">STD</title>
|
95
|
+
<number>91</number>
|
96
|
+
</series>
|
97
|
+
<series type="main">
|
98
|
+
<title format="text/plain" language="en" script="Latn">RFC</title>
|
99
|
+
<number>8341</number>
|
100
|
+
</series>
|
101
|
+
</bibitem>"
|
102
|
+
----
|
103
|
+
With `bibdata: true` option XML output wrapped with `bibdata` element and `ext` element added.
|
104
|
+
[source,ruby]
|
105
|
+
----
|
106
|
+
item.to_xml bibdata: true
|
107
|
+
=>"<bibdata>
|
108
|
+
<fetched>2019-06-05</fetched>
|
109
|
+
<title format="text/plain" language="en" script="Latn">Network Configuration Access Control Model</title>
|
110
|
+
<uri type="src">https://www.rfc-editor.org/info/rfc8341</uri>
|
111
|
+
...
|
112
|
+
<ext>
|
113
|
+
<doctype>rfc</doctype>
|
114
|
+
</ext>
|
115
|
+
</bibdata>"
|
116
|
+
----
|
117
|
+
|
118
|
+
== Contributing
|
119
|
+
|
120
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/metanorma/relaton-ietf.
|
121
|
+
|
122
|
+
== License
|
123
|
+
|
124
|
+
The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
data/appveyor.yml
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# Auto-generated !!! Do not edit it manually
|
2
|
+
# use ci-master https://github.com/metanorma/metanorma-build-scripts
|
3
|
+
version: '{build}'
|
4
|
+
|
5
|
+
cache:
|
6
|
+
- vendor/bundle
|
7
|
+
|
8
|
+
environment:
|
9
|
+
matrix:
|
10
|
+
- RUBY_VERSION: 25
|
11
|
+
- RUBY_VERSION: 24
|
12
|
+
- RUBY_VERSION: _trunk
|
13
|
+
|
14
|
+
matrix:
|
15
|
+
allow_failures:
|
16
|
+
- RUBY_VERSION: _trunk
|
17
|
+
|
18
|
+
install:
|
19
|
+
- ps: . { iwr -useb https://raw.githubusercontent.com/metanorma/metanorma-build-scripts/master/appveyor.ps1 } | iex
|
20
|
+
- refreshenv
|
21
|
+
|
22
|
+
build_script:
|
23
|
+
- set PATH=C:\Ruby%RUBY_VERSION%\bin;%PATH%
|
24
|
+
- set GIT_TERMINAL_PROMPT=0
|
25
|
+
- bundle config --local path vendor/bundle
|
26
|
+
- bundle update
|
27
|
+
- bundle install
|
28
|
+
|
29
|
+
before_test:
|
30
|
+
- ruby -v
|
31
|
+
- gem -v
|
32
|
+
- bundle -v
|
33
|
+
|
34
|
+
test_script:
|
35
|
+
- bundle exec rake
|
data/bin/console
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require "bundler/setup"
|
4
|
+
require "relaton_ietf"
|
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
@@ -0,0 +1,23 @@
|
|
1
|
+
require "relaton/processor"
|
2
|
+
require "relaton_ietf/xml_parser"
|
3
|
+
|
4
|
+
module Relaton
|
5
|
+
module RelatonIetf
|
6
|
+
class Processor < Relaton::Processor
|
7
|
+
def initialize
|
8
|
+
@short = :relaton_ietf
|
9
|
+
@prefix = "IETF"
|
10
|
+
@defaultprefix = /^RFC /
|
11
|
+
@idtype = "IETF"
|
12
|
+
end
|
13
|
+
|
14
|
+
def get(code, date, opts)
|
15
|
+
::RelatonIetf::IetfBibliography.get(code, date, opts)
|
16
|
+
end
|
17
|
+
|
18
|
+
def from_xml(xml)
|
19
|
+
::RelatonIetf::XMLParser.from_xml xml
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
data/lib/relaton_ietf.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "relaton_ietf/version"
|
4
|
+
require "relaton_ietf/ietf_bibliography"
|
5
|
+
require "relaton_ietf/ietf_bibliographi_item"
|
6
|
+
require "relaton_ietf/xml_parser"
|
7
|
+
|
8
|
+
if defined? Relaton
|
9
|
+
require_relative "relaton/processor"
|
10
|
+
Relaton::Registry.instance.register(Relaton::RelatonIetf::Processor)
|
11
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
module RelatonIetf
|
2
|
+
class IetfBibliographicItem < RelatonBib::BibliographicItem
|
3
|
+
# @return [String, NilClass]
|
4
|
+
attr_reader :doctype
|
5
|
+
|
6
|
+
def initialize(**args)
|
7
|
+
@doctype = args.delete :doctype
|
8
|
+
super
|
9
|
+
end
|
10
|
+
|
11
|
+
# @param builder
|
12
|
+
# @param opts [Hash]
|
13
|
+
# @option opts [Symbol, NilClass] :date_format (:short), :full
|
14
|
+
def to_xml(builder = nil, **opts)
|
15
|
+
opts[:date_format] ||= :short
|
16
|
+
super builder, **opts do |b|
|
17
|
+
if opts[:bibdata]
|
18
|
+
b.ext do
|
19
|
+
b.doctype doctype if doctype
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# frozen_string_literal:true
|
2
|
+
|
3
|
+
require "relaton_ietf/scrapper"
|
4
|
+
|
5
|
+
module RelatonIetf
|
6
|
+
# IETF bibliography module
|
7
|
+
module IetfBibliography
|
8
|
+
class << self
|
9
|
+
# @param code [String] the ISO standard Code to look up (e..g "ISO 9000")
|
10
|
+
# @return [RelatonIetf::IetfBibliographicItem]
|
11
|
+
def search(text)
|
12
|
+
Scrapper.scrape_page text
|
13
|
+
end
|
14
|
+
|
15
|
+
# @param code [String] the ISO standard Code to look up (e..g "ISO 9000")
|
16
|
+
# @param year [String] the year the standard was published (optional)
|
17
|
+
# @param opts [Hash] options; restricted to :all_parts if all-parts reference is required
|
18
|
+
# @return [RelatonIetf::IetfBibliographicItem] Relaton of reference
|
19
|
+
def get(code, _year = nil, _opts = {})
|
20
|
+
search code
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,255 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
require "net/http"
|
4
|
+
require "nokogiri"
|
5
|
+
require "relaton_bib"
|
6
|
+
|
7
|
+
module RelatonIetf
|
8
|
+
# rubocop:disable Metrics/ModuleLength
|
9
|
+
|
10
|
+
# Scrapper module
|
11
|
+
module Scrapper
|
12
|
+
RFC_URI_PATTERN = "https://xml2rfc.tools.ietf.org/public/rfc/bibxml/reference.CODE"
|
13
|
+
ID_URI_PATTERN = "https://xml2rfc.tools.ietf.org/public/rfc/bibxml-ids/reference.CODE"
|
14
|
+
|
15
|
+
class << self
|
16
|
+
# @param text [String]
|
17
|
+
# @return [RelatonIetf::IetfBibliographicItem]
|
18
|
+
def scrape_page(text)
|
19
|
+
# Remove initial "IETF " string if specified
|
20
|
+
ref = text.
|
21
|
+
gsub(/^IETF /, "").
|
22
|
+
sub(" ", ".") + ".xml"
|
23
|
+
|
24
|
+
case ref
|
25
|
+
when /^RFC/
|
26
|
+
uri = RFC_URI_PATTERN.dup
|
27
|
+
doctype = "rfc"
|
28
|
+
when /^I-D/
|
29
|
+
uri = ID_URI_PATTERN.dup
|
30
|
+
doctype = "internet-draft"
|
31
|
+
else
|
32
|
+
warn "#{ref}: not recognised for RFC"
|
33
|
+
return
|
34
|
+
end
|
35
|
+
|
36
|
+
uri = uri.gsub("CODE", ref)
|
37
|
+
begin
|
38
|
+
res = Net::HTTP.get_response(URI(uri))
|
39
|
+
if res.code != "200"
|
40
|
+
warn "No document found at #{uri}"
|
41
|
+
return
|
42
|
+
end
|
43
|
+
doc = Nokogiri::HTML Net::HTTP.get(URI(uri))
|
44
|
+
reference = doc.at("//reference")
|
45
|
+
return unless reference
|
46
|
+
|
47
|
+
bib_item reference, doctype
|
48
|
+
rescue Timeout::Error, Errno::EINVAL, Errno::ECONNRESET, EOFError,
|
49
|
+
Net::HTTPBadResponse, Net::HTTPHeaderSyntaxError, Net::ProtocolError
|
50
|
+
warn "No document found at #{uri}"
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
private
|
55
|
+
|
56
|
+
# rubocop:disable Metrics/MethodLength
|
57
|
+
|
58
|
+
# @return [RelatonIetf::IetfBibliographicItem]
|
59
|
+
def bib_item(reference, doctype)
|
60
|
+
RelatonIetf::IetfBibliographicItem.new(
|
61
|
+
fetched: Date.today.to_s,
|
62
|
+
id: reference[:anchor],
|
63
|
+
docid: docids(reference),
|
64
|
+
status: status(reference),
|
65
|
+
language: [language(reference)],
|
66
|
+
script: ["Latn"],
|
67
|
+
link: [{ type: "src", content: reference[:target] }],
|
68
|
+
titles: titles(reference),
|
69
|
+
contributors: contributors(reference),
|
70
|
+
dates: dates(reference),
|
71
|
+
series: series(reference),
|
72
|
+
doctype: doctype,
|
73
|
+
)
|
74
|
+
end
|
75
|
+
# rubocop:enable Metrics/MethodLength
|
76
|
+
|
77
|
+
# @return [String]
|
78
|
+
def language(reference)
|
79
|
+
reference[:lang] || "en"
|
80
|
+
end
|
81
|
+
|
82
|
+
# @return [Array<Hash>]
|
83
|
+
def titles(reference)
|
84
|
+
title = reference.at("./front/title")
|
85
|
+
[{ content: title.text, language: language(reference), script: "Latn" }]
|
86
|
+
end
|
87
|
+
|
88
|
+
# @return [Array<Hash>]
|
89
|
+
def contributors(reference)
|
90
|
+
persons(reference) + organizations(reference)
|
91
|
+
end
|
92
|
+
|
93
|
+
# @return [Array<Hash{Symbol=>RelatonBib::Person,Symbol=>Array<String>}>]
|
94
|
+
def persons(reference)
|
95
|
+
reference.xpath("./front/author").map do |author|
|
96
|
+
entity = RelatonBib::Person.new(
|
97
|
+
name: full_name(author, reference),
|
98
|
+
affiliation: [affiliation(author)],
|
99
|
+
contacts: contacts(author.at("./address")),
|
100
|
+
)
|
101
|
+
{ entity: entity, roles: [contributor_role(author)] }
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
# @return [Array<Hash{Symbol=>RelatonBib::Organization,Symbol=>Array<String>}>]
|
106
|
+
def organizations(reference)
|
107
|
+
reference.xpath("./seriesinfo").map do |si|
|
108
|
+
next unless si[:stream]
|
109
|
+
|
110
|
+
entity = RelatonBib::Organization.new name: si[:stream]
|
111
|
+
{ entity: entity, roles: ["author"] }
|
112
|
+
end.compact
|
113
|
+
end
|
114
|
+
|
115
|
+
# @param author [Nokogiri::XML::Document]
|
116
|
+
# @param ref [Nokogiri::XML::Document]
|
117
|
+
# @return [RelatonBib::FullName]
|
118
|
+
def full_name(author, ref)
|
119
|
+
RelatonBib::FullName.new(
|
120
|
+
completename: localized_string(author[:fullname], ref),
|
121
|
+
initials: [localized_string(author[:initials], ref)],
|
122
|
+
surname: [localized_string(author[:surname], ref)],
|
123
|
+
)
|
124
|
+
end
|
125
|
+
|
126
|
+
# @param content [String]
|
127
|
+
# @return [RelatonBib::LocalizedString]
|
128
|
+
def localized_string(content, ref)
|
129
|
+
RelatonBib::LocalizedString.new(content, language(ref))
|
130
|
+
end
|
131
|
+
|
132
|
+
# @param postal [Nokogiri::XML::Document]
|
133
|
+
# @return [Array<RelatonBib::Address, RelatonBib::Phone>]
|
134
|
+
def contacts(addr)
|
135
|
+
contacts = []
|
136
|
+
return contacts unless addr
|
137
|
+
|
138
|
+
postal = addr.at("./postal")
|
139
|
+
contacts << address(postal) if postal
|
140
|
+
add_contact(contacts, "phone", addr.at("./phone"))
|
141
|
+
add_contact(contacts, "email", addr.at("./email"))
|
142
|
+
add_contact(contacts, "uri", addr.at("./uri"))
|
143
|
+
contacts
|
144
|
+
end
|
145
|
+
|
146
|
+
# @param postal [Nokogiri::XML::Document]
|
147
|
+
# @rerurn [RelatonBib::Address]
|
148
|
+
def address(postal)
|
149
|
+
RelatonBib::Address.new(
|
150
|
+
street: [(postal.at("./postalLine") || postal.at("./street"))&.text],
|
151
|
+
city: postal.at("./city")&.text,
|
152
|
+
postcode: postal.at("./code")&.text,
|
153
|
+
country: postal.at("./country")&.text,
|
154
|
+
state: postal.at("./region")&.text,
|
155
|
+
)
|
156
|
+
end
|
157
|
+
|
158
|
+
# @param type [String] allowed "phone", "email" or "uri"
|
159
|
+
# @param value [String]
|
160
|
+
def add_contact(contacts, type, value)
|
161
|
+
return unless value
|
162
|
+
|
163
|
+
contacts << RelatonBib::Contact.new(type: type, value: value.text)
|
164
|
+
end
|
165
|
+
|
166
|
+
# @param author [Nokogiri::XML::Document]
|
167
|
+
# @return [RelatonBib::Affilation]
|
168
|
+
def affiliation(author)
|
169
|
+
organization = author.at("./organization")
|
170
|
+
RelatonBib::Affilation.new RelatonBib::Organization.new(
|
171
|
+
name: organization.text.empty? ? "IETF" : organization.text,
|
172
|
+
abbreviation: organization[:abbrev] || "IETF",
|
173
|
+
)
|
174
|
+
end
|
175
|
+
|
176
|
+
# @param author [Nokogiri::XML::Document]
|
177
|
+
# @return [String]
|
178
|
+
def contributor_role(author)
|
179
|
+
author[:role] || "author"
|
180
|
+
end
|
181
|
+
|
182
|
+
def month(mon)
|
183
|
+
return mon if /^\d+$/ =~ mon
|
184
|
+
|
185
|
+
Date::MONTHNAMES.index(mon)
|
186
|
+
end
|
187
|
+
|
188
|
+
#
|
189
|
+
# Extract date from reference.
|
190
|
+
#
|
191
|
+
# @return [Array<RelatonBib::BibliographicDate>] published data.
|
192
|
+
#
|
193
|
+
def dates(reference)
|
194
|
+
return unless (date = reference.at "./front/date")
|
195
|
+
|
196
|
+
d = [date[:year], month(date[:month]),
|
197
|
+
(date[:day] || "01")].compact.join "-"
|
198
|
+
date = Time.parse(d).strftime "%Y-%m-%d"
|
199
|
+
[RelatonBib::BibliographicDate.new(type: "published", on: date)]
|
200
|
+
end
|
201
|
+
|
202
|
+
#
|
203
|
+
# Extract document identifiers from reference
|
204
|
+
#
|
205
|
+
# @return [Array<RelatonBib::DocumentIdentifier>]
|
206
|
+
#
|
207
|
+
def docids(reference)
|
208
|
+
id = reference[:anchor].sub(/^(RFC)/, "\\1 ")
|
209
|
+
ret = []
|
210
|
+
ret << RelatonBib::DocumentIdentifier.new(type: "IETF", id: id)
|
211
|
+
ret + reference.xpath("./seriesinfo").map do |si|
|
212
|
+
next unless si[:name] == "DOI"
|
213
|
+
|
214
|
+
RelatonBib::DocumentIdentifier.new(id: si[:value], type: si[:name])
|
215
|
+
end.compact
|
216
|
+
end
|
217
|
+
|
218
|
+
#
|
219
|
+
# Extract series form reference
|
220
|
+
# @param reference [Nokogiri::XML::Document]
|
221
|
+
#
|
222
|
+
# @return [Array<RelatonBib::Series>]
|
223
|
+
#
|
224
|
+
def series(reference)
|
225
|
+
reference.xpath("./seriesinfo").map do |si|
|
226
|
+
next if si[:name] == "DOI" || si[:stream] || si[:status]
|
227
|
+
|
228
|
+
RelatonBib::Series.new(
|
229
|
+
title: RelatonBib::TypedTitleString.new(
|
230
|
+
content: si[:name], language: language(reference), script: "Latn",
|
231
|
+
),
|
232
|
+
number: si[:value],
|
233
|
+
type: "main",
|
234
|
+
)
|
235
|
+
end.compact
|
236
|
+
end
|
237
|
+
|
238
|
+
#
|
239
|
+
# extract status
|
240
|
+
# @param reference [Nokogiri::XML::Document]
|
241
|
+
#
|
242
|
+
# @return [RelatonBib::DocumentStatus]
|
243
|
+
#
|
244
|
+
def status(reference)
|
245
|
+
st = reference.at("./seriesinfo[@status]")
|
246
|
+
return unless st
|
247
|
+
|
248
|
+
RelatonBib::DocumentStatus.new(
|
249
|
+
stage: st[:status],
|
250
|
+
)
|
251
|
+
end
|
252
|
+
end
|
253
|
+
end
|
254
|
+
# rubocop:enable Metrics/ModuleLength
|
255
|
+
end
|
@@ -0,0 +1,24 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
|
3
|
+
module RelatonIetf
|
4
|
+
class XMLParser < RelatonBib::XMLParser
|
5
|
+
class << self
|
6
|
+
def from_xml(xml)
|
7
|
+
doc = Nokogiri::XML(xml)
|
8
|
+
ietfitem = doc.at("/bibitem|/bibdata")
|
9
|
+
RelatonIetf::IetfBibliographicItem.new(item_data(ietfitem))
|
10
|
+
end
|
11
|
+
|
12
|
+
private
|
13
|
+
|
14
|
+
def item_data(ietfitem)
|
15
|
+
data = super
|
16
|
+
ext = ietfitem.at "./ext"
|
17
|
+
return data unless ext
|
18
|
+
|
19
|
+
data[:doctype] = ext.at("./doctype")&.text
|
20
|
+
data
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
# frozen_string_literal: true
|
2
|
+
|
3
|
+
lib = File.expand_path("lib", __dir__)
|
4
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
5
|
+
require "relaton_ietf/version"
|
6
|
+
|
7
|
+
Gem::Specification.new do |spec|
|
8
|
+
spec.name = "relaton-ietf"
|
9
|
+
spec.version = RelatonIetf::VERSION
|
10
|
+
spec.authors = ["Ribose Inc."]
|
11
|
+
spec.email = ["open.source@ribose.com"]
|
12
|
+
|
13
|
+
spec.summary = "RelatonIetf: retrieve IETF Standards for bibliographic use "\
|
14
|
+
"using the BibliographicItem model"
|
15
|
+
spec.description = <<~DESCRIPTION
|
16
|
+
RelatonIetf: retrieve IETF Standards for bibliographic use
|
17
|
+
using the BibliographicItem model.
|
18
|
+
|
19
|
+
Formerly known as rfcbib.
|
20
|
+
DESCRIPTION
|
21
|
+
spec.homepage = "https://github.com/metanorma/relaton-ietf"
|
22
|
+
spec.license = "BSD-2-Clause"
|
23
|
+
|
24
|
+
spec.files = `git ls-files -z`.split("\x0").reject do |f|
|
25
|
+
f.match(%r{^(test|spec|features)/})
|
26
|
+
end
|
27
|
+
spec.bindir = "exe"
|
28
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
29
|
+
spec.require_paths = ["lib"]
|
30
|
+
spec.required_ruby_version = Gem::Requirement.new(">= 2.4.0")
|
31
|
+
|
32
|
+
spec.add_development_dependency "bundler", "~> 2.0.1"
|
33
|
+
spec.add_development_dependency "debase"
|
34
|
+
spec.add_development_dependency "equivalent-xml", "~> 0.6"
|
35
|
+
spec.add_development_dependency "pry-byebug"
|
36
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
37
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
38
|
+
spec.add_development_dependency "ruby-debug-ide"
|
39
|
+
spec.add_development_dependency "simplecov"
|
40
|
+
spec.add_development_dependency "vcr"
|
41
|
+
spec.add_development_dependency "webmock"
|
42
|
+
|
43
|
+
spec.add_dependency "relaton-iso-bib", "~> 0.1.0"
|
44
|
+
end
|
metadata
ADDED
@@ -0,0 +1,221 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: relaton-ietf
|
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: 2019-06-05 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: 2.0.1
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 2.0.1
|
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: 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: ruby-debug-ide
|
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-iso-bib
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - "~>"
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: 0.1.0
|
160
|
+
type: :runtime
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - "~>"
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: 0.1.0
|
167
|
+
description: "RelatonIetf: retrieve IETF Standards for bibliographic use \nusing the
|
168
|
+
BibliographicItem model.\n\nFormerly known as rfcbib.\n"
|
169
|
+
email:
|
170
|
+
- open.source@ribose.com
|
171
|
+
executables: []
|
172
|
+
extensions: []
|
173
|
+
extra_rdoc_files: []
|
174
|
+
files:
|
175
|
+
- ".gitignore"
|
176
|
+
- ".hound.yml"
|
177
|
+
- ".rspec"
|
178
|
+
- ".rubocop.yml"
|
179
|
+
- ".travis.yml"
|
180
|
+
- Gemfile
|
181
|
+
- Gemfile.lock
|
182
|
+
- LICENSE.txt
|
183
|
+
- README.adoc
|
184
|
+
- Rakefile
|
185
|
+
- appveyor.yml
|
186
|
+
- bin/console
|
187
|
+
- bin/setup
|
188
|
+
- lib/relaton/processor.rb
|
189
|
+
- lib/relaton_ietf.rb
|
190
|
+
- lib/relaton_ietf/ietf_bibliographi_item.rb
|
191
|
+
- lib/relaton_ietf/ietf_bibliography.rb
|
192
|
+
- lib/relaton_ietf/scrapper.rb
|
193
|
+
- lib/relaton_ietf/version.rb
|
194
|
+
- lib/relaton_ietf/xml_parser.rb
|
195
|
+
- relaton_ietf.gemspec
|
196
|
+
homepage: https://github.com/metanorma/relaton-ietf
|
197
|
+
licenses:
|
198
|
+
- BSD-2-Clause
|
199
|
+
metadata: {}
|
200
|
+
post_install_message:
|
201
|
+
rdoc_options: []
|
202
|
+
require_paths:
|
203
|
+
- lib
|
204
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
205
|
+
requirements:
|
206
|
+
- - ">="
|
207
|
+
- !ruby/object:Gem::Version
|
208
|
+
version: 2.4.0
|
209
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
210
|
+
requirements:
|
211
|
+
- - ">="
|
212
|
+
- !ruby/object:Gem::Version
|
213
|
+
version: '0'
|
214
|
+
requirements: []
|
215
|
+
rubyforge_project:
|
216
|
+
rubygems_version: 2.6.12
|
217
|
+
signing_key:
|
218
|
+
specification_version: 4
|
219
|
+
summary: 'RelatonIetf: retrieve IETF Standards for bibliographic use using the BibliographicItem
|
220
|
+
model'
|
221
|
+
test_files: []
|