research_metadata_announcement 0.4.2 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +3 -11
- data/README.md +17 -25
- data/lib/research_metadata_announcement.rb +1 -1
- data/lib/research_metadata_announcement/transformer/base.rb +17 -49
- data/lib/research_metadata_announcement/transformer/dataset.rb +1 -11
- data/lib/research_metadata_announcement/transformer/research_output.rb +20 -0
- data/lib/research_metadata_announcement/version.rb +1 -1
- data/research_metadata_announcement.gemspec +1 -1
- metadata +5 -5
- data/lib/research_metadata_announcement/transformer/publication.rb +0 -30
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: b4e9c9fd7ba55dbdb831bf9fc25fc4c6df3785ba
|
4
|
+
data.tar.gz: 280d4111796b2ea9ad96b72076891027608bbac2
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 0599597e515308ad7183fddb3d59791fd596c25c5d02bb9dc1c2ec0487241618f957f72765bab6cf4dd293919b4eb77f40ae22913c844e763ee461f4f46cac00
|
7
|
+
data.tar.gz: 4ff2e913fb3b5621226d36b5c429be46fde5e3491df8dc275df97a8fe90ef09b71b5b02bbe0c9a6422898de5a0f45ba9fb584aa1f636479659fe83c6a07ef196
|
data/CHANGELOG.md
CHANGED
@@ -2,20 +2,12 @@
|
|
2
2
|
All notable changes to this project will be documented in this file.
|
3
3
|
This project adheres to [Semantic Versioning](http://semver.org/).
|
4
4
|
|
5
|
-
## 0.
|
5
|
+
## 0.5.0 - 2018-01-11
|
6
6
|
### Changed
|
7
|
-
|
7
|
+
- For Pure API 59.
|
8
8
|
|
9
|
-
## 0.4.1 - 2018-01-17
|
10
9
|
### Added
|
11
|
-
- Testing
|
12
|
-
|
13
|
-
### Fixed
|
14
|
-
- Ellipsis after truncated title.
|
15
|
-
|
16
|
-
### Changed
|
17
|
-
- Handle missing resolver in DOI.
|
18
|
-
- Handle full stop in title.
|
10
|
+
- Testing against known live data.
|
19
11
|
|
20
12
|
## 0.4.0 - 2017-10-10
|
21
13
|
### Changed
|
data/README.md
CHANGED
@@ -5,8 +5,7 @@ Metadata extraction from the Pure Research Information System and transformation
|
|
5
5
|
## Status
|
6
6
|
|
7
7
|
[![Gem Version](https://badge.fury.io/rb/research_metadata_announcement.svg)](https://badge.fury.io/rb/research_metadata_announcement)
|
8
|
-
[![
|
9
|
-
[![Code Climate](https://codeclimate.com/github/lulibrary/research_metadata_announcement/badges/gpa.svg)](https://codeclimate.com/github/lulibrary/research_metadata_announcement)
|
8
|
+
[![Maintainability](https://api.codeclimate.com/v1/badges/79ba809b90fc85508aa6/maintainability)](https://codeclimate.com/github/lulibrary/research_metadata_announcement/maintainability)
|
10
9
|
|
11
10
|
## Installation
|
12
11
|
|
@@ -29,18 +28,11 @@ Or install it yourself as:
|
|
29
28
|
Create a hash for passing to a transformer.
|
30
29
|
|
31
30
|
```ruby
|
32
|
-
# Pure host with authentication.
|
33
31
|
config = {
|
34
|
-
url:
|
35
|
-
username:
|
36
|
-
password:
|
37
|
-
|
38
|
-
```
|
39
|
-
|
40
|
-
```ruby
|
41
|
-
# Pure host without authentication.
|
42
|
-
config = {
|
43
|
-
url: ENV['PURE_URL']
|
32
|
+
url: 'https://YOUR_HOST/ws/api/59',
|
33
|
+
username: 'YOUR_USERNAME',
|
34
|
+
password: 'YOUR_PASSWORD',
|
35
|
+
api_key: 'YOUR_API_KEY'
|
44
36
|
}
|
45
37
|
```
|
46
38
|
|
@@ -55,7 +47,7 @@ transformer = ResearchMetadataAnnouncement::Transformer::Dataset.new config
|
|
55
47
|
Give it a Pure identifier and get an announcement.
|
56
48
|
|
57
49
|
```ruby
|
58
|
-
transformer.transform
|
50
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
|
59
51
|
```
|
60
52
|
|
61
53
|
Optionally, use the ```:composition``` keyword argument to pass in an array of
|
@@ -88,34 +80,34 @@ Each example uses a different resource for illustrative purposes.
|
|
88
80
|
|
89
81
|
```ruby
|
90
82
|
|
91
|
-
transformer.transform
|
83
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
|
92
84
|
#=> "New journal article. Can poly-parameter linear-free energy relationships (pp-LFERs) improve modelling bioaccumulation in fish? #partitioncoefficients #pplfer. dx.doi.org/10.1016/j.chemosphere.2017.10.007."
|
93
85
|
|
94
|
-
transformer.transform
|
95
|
-
#=> "New journal article. The Parting of Burroughs and
|
86
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', max_length: 140
|
87
|
+
#=> "New journal article. The Parting of Burroughs and... #americancounterculture #arthurrimbaud. dx.doi.org/10.1179/1477570013Z.00000000045."
|
96
88
|
|
97
|
-
transformer.transform
|
89
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:new, :title, :hashtags] # research output has no descriptors
|
98
90
|
#=> "New conference paper. Deductive and inductive data collection for agent-based modelling."
|
99
91
|
|
100
|
-
transformer.transform
|
92
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:new, :title, :keywords, :uri]
|
101
93
|
#=> "New journal article. Torsion pairs in a triangulated category generated by a spherical object. Auslander–Reiten theory, Calabi–Yau triangulated category. dx.doi.org/10.1016/j.jalgebra.2015.09.011."
|
102
94
|
|
103
|
-
transformer.transform
|
95
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:new, :title, :uri]
|
104
96
|
#=> "New dataset. Operating Nanobeams in a Quantum Fluid. dx.doi.org/10.17635/lancaster/researchdata/139."
|
105
97
|
|
106
|
-
transformer.transform
|
98
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:uri, :title]
|
107
99
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/29. Herpes simplex virus 1 (HSV-1) evolution."
|
108
100
|
|
109
|
-
transformer.transform
|
101
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:keywords, :uri]
|
110
102
|
#=> "smart cities, sustainability. dx.doi.org/10.17635/lancaster/researchdata/35."
|
111
103
|
|
112
|
-
transformer.transform
|
104
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:hashtags, :uri]
|
113
105
|
#=> "#treatedhypertension #microvascularbloodflow. dx.doi.org/10.17635/lancaster/researchdata/148."
|
114
106
|
|
115
|
-
transformer.transform
|
107
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:uri, :keywords]
|
116
108
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/134. metagenomics, deep sequencing."
|
117
109
|
|
118
|
-
transformer.transform
|
110
|
+
transformer.transform id: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', composition: [:uri, :hashtags], max_descriptors: 4
|
119
111
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/111. #influenza #nasopharynx #virology #virus."
|
120
112
|
|
121
113
|
```
|
@@ -2,7 +2,7 @@ require 'puree'
|
|
2
2
|
|
3
3
|
require 'research_metadata_announcement/transformer/base'
|
4
4
|
require 'research_metadata_announcement/transformer/dataset'
|
5
|
-
require 'research_metadata_announcement/transformer/
|
5
|
+
require 'research_metadata_announcement/transformer/research_output'
|
6
6
|
require 'research_metadata_announcement/version'
|
7
7
|
|
8
8
|
# Metadata extraction from the Pure Research Information System and
|
@@ -6,29 +6,30 @@ module ResearchMetadataAnnouncement
|
|
6
6
|
class Base
|
7
7
|
|
8
8
|
# @param config [Hash]
|
9
|
-
# @option config [String] :url
|
10
|
-
# @option config [String] :username
|
11
|
-
# @option config [String] :password
|
12
|
-
|
9
|
+
# @option config [String] :url URL of the Pure host
|
10
|
+
# @option config [String] :username Username of the Pure host account
|
11
|
+
# @option config [String] :password Password of the Pure host account
|
12
|
+
# @option config [String] :api_key API key of the Pure host account
|
13
13
|
def initialize(config)
|
14
14
|
@config = config
|
15
15
|
end
|
16
16
|
|
17
|
-
# @param id [String] Pure
|
18
|
-
# @param uuid [String] Pure UUID.
|
17
|
+
# @param id [String] Pure identifier.
|
19
18
|
# @param composition [Array<Symbol>] Metadata presentation sequence e.g. [:new, :title, :hashtags, :uri].
|
20
19
|
# @param max_length [Fixnum] Maximum length of announcement.
|
21
20
|
# @param max_descriptors [Fixnum] Maximum number of descriptors (common name for keywords, tags, hashtags).
|
22
21
|
# @return [String, nil] Announcement returned if the metadata is available and the announcement length does not exceed the max_length argument.
|
23
|
-
def transform(
|
22
|
+
def transform(id:, composition: [:new, :title, :hashtags, :uri],
|
24
23
|
max_length: nil, max_descriptors: 2)
|
25
24
|
composition.uniq!
|
26
|
-
|
25
|
+
|
26
|
+
@resource = @resource_extractor.find id
|
27
|
+
|
27
28
|
return nil unless @resource
|
28
29
|
if composition.include? :uri
|
29
30
|
return nil unless prepare_uri
|
30
31
|
end
|
31
|
-
title =
|
32
|
+
title = @resource.title
|
32
33
|
keywords = @resource.keywords
|
33
34
|
|
34
35
|
# sizing
|
@@ -38,7 +39,7 @@ module ResearchMetadataAnnouncement
|
|
38
39
|
composition.each do |component|
|
39
40
|
case component
|
40
41
|
when :new
|
41
|
-
phrase =
|
42
|
+
phrase = new_phrase(@resource)
|
42
43
|
chars_needed += phrase.size + chars_component_end
|
43
44
|
when :title
|
44
45
|
chars_needed += title.size + chars_component_end
|
@@ -48,16 +49,10 @@ module ResearchMetadataAnnouncement
|
|
48
49
|
chars_needed += build_hashtags(keywords, max_descriptors).size + chars_component_end if !keywords.empty?
|
49
50
|
when :uri
|
50
51
|
uri = prepare_uri
|
51
|
-
chars_needed += uri.size
|
52
|
+
chars_needed += uri.size if uri
|
52
53
|
end
|
53
54
|
end
|
54
55
|
|
55
|
-
# since the arrangement of the composition is unknown, after sizing
|
56
|
-
# chars_needed has two extra spaces allocated
|
57
|
-
# one is used for the terminating full stop
|
58
|
-
# one is not needed
|
59
|
-
chars_needed -= 1
|
60
|
-
|
61
56
|
# determine if title needs truncating/removing before combining
|
62
57
|
if chars_needed > max_length
|
63
58
|
# truncate title
|
@@ -65,7 +60,7 @@ module ResearchMetadataAnnouncement
|
|
65
60
|
excess_chars = chars_needed - max_length
|
66
61
|
truncated_title_length = title.size - excess_chars
|
67
62
|
truncated_title_length = 0 if truncated_title_length < 0
|
68
|
-
title = title[0..truncated_title_length -
|
63
|
+
title = title[0..truncated_title_length - 2].strip + '..'
|
69
64
|
composition -= [:title] if title.size <= 5 # give up on title if just too small
|
70
65
|
end
|
71
66
|
end
|
@@ -104,25 +99,6 @@ module ResearchMetadataAnnouncement
|
|
104
99
|
|
105
100
|
private
|
106
101
|
|
107
|
-
def handle_resolver(uri)
|
108
|
-
return unless uri
|
109
|
-
resolver = 'doi.org'
|
110
|
-
if uri.include? resolver
|
111
|
-
uri
|
112
|
-
else
|
113
|
-
File.join resolver, uri
|
114
|
-
end
|
115
|
-
end
|
116
|
-
|
117
|
-
def remove_full_stop(str)
|
118
|
-
arr = str.split('')
|
119
|
-
if arr.pop == '.' && arr.pop != '.'
|
120
|
-
return str.chomp('.')
|
121
|
-
else
|
122
|
-
return str
|
123
|
-
end
|
124
|
-
end
|
125
|
-
|
126
102
|
def new_phrase(resource)
|
127
103
|
part_1 = 'New'
|
128
104
|
part_2 = ''
|
@@ -130,7 +106,7 @@ module ResearchMetadataAnnouncement
|
|
130
106
|
case resource.class.to_s
|
131
107
|
when 'Puree::Model::Dataset'
|
132
108
|
part_2 = 'dataset'
|
133
|
-
when 'Puree::Model::
|
109
|
+
when 'Puree::Model::ResearchOutput'
|
134
110
|
part_2 = resource.type.downcase
|
135
111
|
end
|
136
112
|
if part_2.empty?
|
@@ -140,16 +116,8 @@ module ResearchMetadataAnnouncement
|
|
140
116
|
end
|
141
117
|
end
|
142
118
|
|
143
|
-
|
144
|
-
|
145
|
-
# @param id [String]
|
146
|
-
# @param uuid [String]
|
147
|
-
def extract(uuid: nil, id: nil)
|
148
|
-
if !uuid.nil?
|
149
|
-
@resource = @resource_extractor.find uuid: uuid
|
150
|
-
else
|
151
|
-
@resource = @resource_extractor.find id: id
|
152
|
-
end
|
119
|
+
def prepare_uri
|
120
|
+
strip_uri_scheme @resource.doi if @resource && @resource.doi
|
153
121
|
end
|
154
122
|
|
155
123
|
def strip_uri_scheme(uri)
|
@@ -181,7 +149,7 @@ module ResearchMetadataAnnouncement
|
|
181
149
|
end
|
182
150
|
|
183
151
|
def make_extractor(resource_type)
|
184
|
-
resource_class = "Puree::Extractor::#{resource_type
|
152
|
+
resource_class = "Puree::Extractor::#{Puree::Util::String.titleize(resource_type)}"
|
185
153
|
@resource_extractor = Object.const_get(resource_class).new @config
|
186
154
|
end
|
187
155
|
|
@@ -7,22 +7,12 @@ module ResearchMetadataAnnouncement
|
|
7
7
|
#
|
8
8
|
class Dataset < ResearchMetadataAnnouncement::Transformer::Base
|
9
9
|
|
10
|
-
# @
|
11
|
-
# @option config [String] :url The URL of the Pure host.
|
12
|
-
# @option config [String] :username The username of the Pure host account.
|
13
|
-
# @option config [String] :password The password of the Pure host account.
|
10
|
+
# @option (see ResearchMetadataAnnouncement::Transformer::Base::Resource#initialize)
|
14
11
|
def initialize(config)
|
15
12
|
super
|
16
13
|
make_extractor :dataset
|
17
14
|
end
|
18
15
|
|
19
|
-
private
|
20
|
-
|
21
|
-
def prepare_uri
|
22
|
-
uri = strip_uri_scheme @resource.doi if @resource && @resource.doi
|
23
|
-
handle_resolver uri
|
24
|
-
end
|
25
|
-
|
26
16
|
end
|
27
17
|
|
28
18
|
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
module ResearchMetadataAnnouncement
|
2
|
+
|
3
|
+
module Transformer
|
4
|
+
|
5
|
+
# Extracts research output metadata from the Pure Research Information System and
|
6
|
+
# converts it into an announcement
|
7
|
+
#
|
8
|
+
class ResearchOutput < ResearchMetadataAnnouncement::Transformer::Base
|
9
|
+
|
10
|
+
# @option (see ResearchMetadataAnnouncement::Transformer::Base::Resource#initialize)
|
11
|
+
def initialize(config)
|
12
|
+
super
|
13
|
+
make_extractor :research_output
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
17
|
+
|
18
|
+
end
|
19
|
+
|
20
|
+
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: research_metadata_announcement
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.5.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Adrian Albin-Clark
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2018-01-
|
11
|
+
date: 2018-01-11 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: puree
|
@@ -16,14 +16,14 @@ dependencies:
|
|
16
16
|
requirements:
|
17
17
|
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: '
|
19
|
+
version: '2.0'
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
24
|
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version: '
|
26
|
+
version: '2.0'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: minitest-reporters
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
@@ -53,7 +53,7 @@ files:
|
|
53
53
|
- lib/research_metadata_announcement.rb
|
54
54
|
- lib/research_metadata_announcement/transformer/base.rb
|
55
55
|
- lib/research_metadata_announcement/transformer/dataset.rb
|
56
|
-
- lib/research_metadata_announcement/transformer/
|
56
|
+
- lib/research_metadata_announcement/transformer/research_output.rb
|
57
57
|
- lib/research_metadata_announcement/transformer/transformer.rb
|
58
58
|
- lib/research_metadata_announcement/version.rb
|
59
59
|
- research_metadata_announcement.gemspec
|
@@ -1,30 +0,0 @@
|
|
1
|
-
module ResearchMetadataAnnouncement
|
2
|
-
|
3
|
-
module Transformer
|
4
|
-
|
5
|
-
# Extracts publication metadata from the Pure Research Information System and
|
6
|
-
# converts it into an announcement
|
7
|
-
#
|
8
|
-
class Publication < ResearchMetadataAnnouncement::Transformer::Base
|
9
|
-
|
10
|
-
# @param config [Hash]
|
11
|
-
# @option config [String] :url The URL of the Pure host.
|
12
|
-
# @option config [String] :username The username of the Pure host account.
|
13
|
-
# @option config [String] :password The password of the Pure host account.
|
14
|
-
def initialize(config)
|
15
|
-
super
|
16
|
-
make_extractor :publication
|
17
|
-
end
|
18
|
-
|
19
|
-
private
|
20
|
-
|
21
|
-
def prepare_uri
|
22
|
-
uri = strip_uri_scheme @resource.dois[0] if @resource && @resource.dois[0]
|
23
|
-
handle_resolver uri
|
24
|
-
end
|
25
|
-
|
26
|
-
end
|
27
|
-
|
28
|
-
end
|
29
|
-
|
30
|
-
end
|