research_metadata_announcement 0.2.0 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +4 -0
- data/README.md +48 -16
- data/lib/research_metadata_announcement/transformer/base.rb +84 -147
- data/lib/research_metadata_announcement/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 6d646820ca8f080ad370ed466c22d23ccc35c480
|
|
4
|
+
data.tar.gz: cdbec817ebfa40fb55c32cc46cdc99b21786e7bf
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 7b5e9897a9d99d67627fe7371f6310c3169809b90b8c0d143d4df3fe362c1b6e57b0b5e521902bd8dbb429f2d7e45f0b52c1316f5d445113f0b39c77775ddbf4
|
|
7
|
+
data.tar.gz: 5679dbac4a6dc25b30ff422ebfbc219881e84bd340b90149024c38c8ccdf53893dab2ef308a8ab85d3a585168ff59dc651344f919f1a2d144ae0f084c8a4e367
|
data/CHANGELOG.md
CHANGED
data/README.md
CHANGED
|
@@ -52,38 +52,70 @@ Create a metadata transformer for a Pure dataset.
|
|
|
52
52
|
transformer = ResearchMetadataAnnouncement::Transformer::Dataset.new config
|
|
53
53
|
```
|
|
54
54
|
|
|
55
|
-
Give it a Pure identifier and
|
|
55
|
+
Give it a Pure identifier and get an announcement.
|
|
56
56
|
|
|
57
57
|
```ruby
|
|
58
|
-
transformer.
|
|
58
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
|
|
59
59
|
```
|
|
60
60
|
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
61
|
+
Optionally, use the ```:permutation``` keyword argument to pass in an array of
|
|
62
|
+
components (duplicates are ignored). The order of the components determines the
|
|
63
|
+
order of the metadata in the announcement.
|
|
64
|
+
|
|
65
|
+
Possible components:
|
|
64
66
|
|
|
65
67
|
```ruby
|
|
68
|
+
:new, :title, :keywords, :hashtags, :uri
|
|
69
|
+
```
|
|
70
|
+
|
|
71
|
+
Ideally, an announcement will be obtained using all the requested components,
|
|
72
|
+
with the following exceptions:
|
|
73
|
+
|
|
74
|
+
+ If the permutation includes ```:keywords``` or ```:hashtags``` and the
|
|
75
|
+
resource does not have any descriptors, the metadata is simply omitted.
|
|
66
76
|
|
|
67
|
-
|
|
68
|
-
|
|
77
|
+
+ If the permutation includes ```:uri```, the resource must have a URI for an
|
|
78
|
+
announcement to be returned.
|
|
69
79
|
|
|
70
|
-
|
|
71
|
-
|
|
80
|
+
+ If, after ```:title``` truncation/removal, the length still exceeds the
|
|
81
|
+
optional ```:max_length``` keyword argument, an announcement will not be returned.
|
|
82
|
+
|
|
83
|
+
If the permutation includes ```:new```, a phrase based upon the resource type
|
|
84
|
+
is generated e.g. New dataset. However, this gem does not determine whether
|
|
85
|
+
the resource is deemed to be new.
|
|
86
|
+
|
|
87
|
+
Each example uses a different resource for illustrative purposes.
|
|
88
|
+
|
|
89
|
+
```ruby
|
|
72
90
|
|
|
73
|
-
transformer.
|
|
91
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
|
|
92
|
+
#=> "New publication. 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
|
+
|
|
94
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', max_length: 140
|
|
95
|
+
#=> "New publication. The Parting of Burroughs and... #americancounterculture #arthurrimbaud. dx.doi.org/10.1179/1477570013Z.00000000045."
|
|
96
|
+
|
|
97
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:new, :title, :hashtags] # resource has no descriptors
|
|
98
|
+
#=> "New publication. Deductive and inductive data collection for agent-based modelling."
|
|
99
|
+
|
|
100
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:new, :title, :keywords, :uri]
|
|
101
|
+
#=> "New publication. 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
|
+
|
|
103
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:new, :title, :uri]
|
|
104
|
+
#=> "New dataset. Operating Nanobeams in a Quantum Fluid. dx.doi.org/10.17635/lancaster/researchdata/139."
|
|
105
|
+
|
|
106
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:uri, :title]
|
|
74
107
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/29. Herpes simplex virus 1 (HSV-1) evolution."
|
|
75
108
|
|
|
76
|
-
transformer.
|
|
109
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:keywords, :uri]
|
|
77
110
|
#=> "smart cities, sustainability. dx.doi.org/10.17635/lancaster/researchdata/35."
|
|
78
111
|
|
|
79
|
-
transformer.
|
|
112
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:hashtags, :uri]
|
|
80
113
|
#=> "#treatedhypertension #microvascularbloodflow. dx.doi.org/10.17635/lancaster/researchdata/148."
|
|
81
114
|
|
|
82
|
-
transformer.
|
|
115
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:uri, :keywords]
|
|
83
116
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/134. metagenomics, deep sequencing."
|
|
84
117
|
|
|
85
|
-
transformer.
|
|
118
|
+
transformer.transform uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx', permutation: [:uri, :hashtags], max_descriptors: 4
|
|
86
119
|
#=> "dx.doi.org/10.17635/lancaster/researchdata/111. #influenza #nasopharynx #virology #virus."
|
|
87
120
|
|
|
88
|
-
```
|
|
89
|
-
|
|
121
|
+
```
|
|
@@ -14,86 +14,102 @@ module ResearchMetadataAnnouncement
|
|
|
14
14
|
@config = config
|
|
15
15
|
end
|
|
16
16
|
|
|
17
|
-
#
|
|
18
|
-
#
|
|
19
|
-
# @param
|
|
20
|
-
# @param
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
|
|
17
|
+
# @param id [String] Pure ID.
|
|
18
|
+
# @param uuid [String] Pure UUID.
|
|
19
|
+
# @param permutation [Array<Symbol>] Metadata presentation sequence e.g. [:new, :title, :hashtags, :uri].
|
|
20
|
+
# @param max_length [Fixnum] Maximum length of announcement.
|
|
21
|
+
# @param max_descriptors [Fixnum] Maximum number of descriptors (common name for keywords, tags, hashtags).
|
|
22
|
+
# @return [String, nil] Announcement returned if the metadata is available and the announcement length does not exceed the max_length argument.
|
|
23
|
+
def transform(uuid: nil, id: nil, permutation: [:new, :title, :hashtags, :uri],
|
|
24
|
+
max_length: nil, max_descriptors: 2)
|
|
25
|
+
permutation.uniq!
|
|
26
|
+
extract uuid: uuid, id: id
|
|
27
|
+
return nil unless @resource
|
|
28
|
+
if permutation.include? :uri
|
|
29
|
+
return nil unless prepare_uri
|
|
26
30
|
end
|
|
27
|
-
|
|
31
|
+
title = @resource.title
|
|
32
|
+
keywords = @resource.keywords
|
|
28
33
|
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
34
|
+
# sizing
|
|
35
|
+
if length_constrained? max_length
|
|
36
|
+
chars_needed = 0
|
|
37
|
+
chars_component_end = 2
|
|
38
|
+
permutation.each do |component|
|
|
39
|
+
case component
|
|
40
|
+
when :new
|
|
41
|
+
resource = self.class.name.sub('ResearchMetadataAnnouncement::Transformer::', '')
|
|
42
|
+
phrase = "New research #{resource.downcase}"
|
|
43
|
+
chars_needed += phrase.size + chars_component_end
|
|
44
|
+
when :title
|
|
45
|
+
chars_needed += title.size + chars_component_end
|
|
46
|
+
when :keywords
|
|
47
|
+
chars_needed += build_keywords(keywords, max_descriptors).size + chars_component_end if !keywords.empty?
|
|
48
|
+
when :hashtags
|
|
49
|
+
chars_needed += build_hashtags(keywords, max_descriptors).size + chars_component_end if !keywords.empty?
|
|
50
|
+
when :uri
|
|
51
|
+
uri = prepare_uri
|
|
52
|
+
chars_needed += uri.size if uri
|
|
53
|
+
end
|
|
54
|
+
end
|
|
37
55
|
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
56
|
+
# determine if title needs truncating/removing before combining
|
|
57
|
+
if chars_needed > max_length
|
|
58
|
+
# truncate title
|
|
59
|
+
if permutation.include? :title
|
|
60
|
+
excess_chars = chars_needed - max_length
|
|
61
|
+
truncated_title_length = title.size - excess_chars
|
|
62
|
+
truncated_title_length = 0 if truncated_title_length < 0
|
|
63
|
+
title = title[0..truncated_title_length - 2].strip + '..'
|
|
64
|
+
permutation -= [:title] if title.size <= 5 # give up on title if just too small
|
|
65
|
+
end
|
|
66
|
+
end
|
|
67
|
+
end
|
|
45
68
|
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
69
|
+
# get data for combining
|
|
70
|
+
buffer = []
|
|
71
|
+
permutation.each do |component|
|
|
72
|
+
case component
|
|
73
|
+
when :new
|
|
74
|
+
resource = self.class.name.sub('ResearchMetadataAnnouncement::Transformer::', '')
|
|
75
|
+
phrase = "New #{resource.downcase}"
|
|
76
|
+
buffer << phrase
|
|
77
|
+
when :title
|
|
78
|
+
buffer << title
|
|
79
|
+
when :keywords
|
|
80
|
+
buffer << build_keywords(keywords, max_descriptors) if !keywords.empty?
|
|
81
|
+
when :hashtags
|
|
82
|
+
buffer << build_hashtags(keywords, max_descriptors) if !keywords.empty?
|
|
83
|
+
when :uri
|
|
84
|
+
uri = prepare_uri
|
|
85
|
+
buffer << uri if uri
|
|
86
|
+
end
|
|
87
|
+
end
|
|
56
88
|
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
# @see #keywords_uri
|
|
60
|
-
def uri_keywords(max_length: nil, max_descriptors: 2)
|
|
61
|
-
descriptors_formats format: :uri_keywords_format,
|
|
62
|
-
max_length: max_length,
|
|
63
|
-
max_descriptors: max_descriptors
|
|
64
|
-
end
|
|
89
|
+
# combine, separate by period
|
|
90
|
+
str = buffer.join('. ')
|
|
65
91
|
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
|
|
69
|
-
def hashtags_uri(max_length: nil, max_descriptors: 2)
|
|
70
|
-
descriptors_formats format: :hashtags_uri_format,
|
|
71
|
-
max_length: max_length,
|
|
72
|
-
max_descriptors: max_descriptors
|
|
73
|
-
end
|
|
92
|
+
# make phrase ending grammatically correct
|
|
93
|
+
str = str.gsub('?.', '?')
|
|
94
|
+
str = str.gsub('!.', '!')
|
|
74
95
|
|
|
75
|
-
|
|
76
|
-
|
|
77
|
-
|
|
78
|
-
|
|
79
|
-
descriptors_formats format: :uri_hashtags_format,
|
|
80
|
-
max_length: max_length,
|
|
81
|
-
max_descriptors: max_descriptors
|
|
96
|
+
# terminate entire announcement
|
|
97
|
+
str << '.'
|
|
98
|
+
|
|
99
|
+
validate_string_length str, max_length unless str.empty?
|
|
82
100
|
end
|
|
83
101
|
|
|
84
102
|
private
|
|
85
103
|
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
end
|
|
94
|
-
end
|
|
104
|
+
# Extract metadata from Pure
|
|
105
|
+
#
|
|
106
|
+
# @param id [String]
|
|
107
|
+
# @param uuid [String]
|
|
108
|
+
def extract(uuid: nil, id: nil)
|
|
109
|
+
if !uuid.nil?
|
|
110
|
+
@resource = @resource_extractor.find uuid: uuid
|
|
95
111
|
else
|
|
96
|
-
|
|
112
|
+
@resource = @resource_extractor.find id: id
|
|
97
113
|
end
|
|
98
114
|
end
|
|
99
115
|
|
|
@@ -105,30 +121,6 @@ module ResearchMetadataAnnouncement
|
|
|
105
121
|
max_length && max_length > 0
|
|
106
122
|
end
|
|
107
123
|
|
|
108
|
-
def title_formats(format:, max_length:)
|
|
109
|
-
return nil unless @resource
|
|
110
|
-
uri = prepare_uri
|
|
111
|
-
return nil unless uri
|
|
112
|
-
title = @resource.title
|
|
113
|
-
build_title_formats(format: format,
|
|
114
|
-
uri: uri,
|
|
115
|
-
title: title,
|
|
116
|
-
max_length: max_length)
|
|
117
|
-
end
|
|
118
|
-
|
|
119
|
-
def descriptors_formats(format:, max_length:, max_descriptors:)
|
|
120
|
-
return nil unless @resource
|
|
121
|
-
uri = prepare_uri
|
|
122
|
-
return nil unless uri
|
|
123
|
-
keywords = @resource.keywords
|
|
124
|
-
return nil if keywords.empty?
|
|
125
|
-
build_descriptors_formats(format: format,
|
|
126
|
-
keywords: keywords,
|
|
127
|
-
uri: uri,
|
|
128
|
-
max_length: max_length,
|
|
129
|
-
max_descriptors: max_descriptors)
|
|
130
|
-
end
|
|
131
|
-
|
|
132
124
|
def validate_string_length(str, max_length)
|
|
133
125
|
if length_constrained? max_length
|
|
134
126
|
str if str.size <= max_length
|
|
@@ -137,61 +129,6 @@ module ResearchMetadataAnnouncement
|
|
|
137
129
|
end
|
|
138
130
|
end
|
|
139
131
|
|
|
140
|
-
def build_descriptors_formats(format:, keywords:, uri:, max_length:, max_descriptors:)
|
|
141
|
-
case format
|
|
142
|
-
when :keywords_uri_format
|
|
143
|
-
str = append_sentence(build_keywords(keywords, max_descriptors), uri)
|
|
144
|
-
when :uri_keywords_format
|
|
145
|
-
str = append_sentence(uri, build_keywords(keywords, max_descriptors))
|
|
146
|
-
when :hashtags_uri_format
|
|
147
|
-
str = append_sentence(build_hashtags(keywords, max_descriptors), uri)
|
|
148
|
-
when :uri_hashtags_format
|
|
149
|
-
str = append_sentence(uri, build_hashtags(keywords, max_descriptors))
|
|
150
|
-
end
|
|
151
|
-
validate_string_length str, max_length
|
|
152
|
-
end
|
|
153
|
-
|
|
154
|
-
def build_title_format(format:, title:, uri:)
|
|
155
|
-
case format
|
|
156
|
-
when :title_uri_format
|
|
157
|
-
append_sentence title, uri
|
|
158
|
-
when :uri_title_format
|
|
159
|
-
append_sentence uri, title
|
|
160
|
-
end
|
|
161
|
-
end
|
|
162
|
-
|
|
163
|
-
def build_title_format_truncated(format:, title:, uri:, available_chars:)
|
|
164
|
-
truncated_title = title[0..available_chars-3].strip + '...'
|
|
165
|
-
case format
|
|
166
|
-
when :title_uri_format
|
|
167
|
-
"#{truncated_title} #{uri}."
|
|
168
|
-
when :uri_title_format
|
|
169
|
-
"#{uri}. #{truncated_title}"
|
|
170
|
-
end
|
|
171
|
-
end
|
|
172
|
-
|
|
173
|
-
def build_title_formats(format:, title:, uri:, max_length:)
|
|
174
|
-
if length_constrained? max_length
|
|
175
|
-
available_chars = max_length - (uri.size + 3)
|
|
176
|
-
available_chars = 0 if available_chars < 0
|
|
177
|
-
if title.size <= available_chars
|
|
178
|
-
return build_title_format(format: format,
|
|
179
|
-
title: title,
|
|
180
|
-
uri: uri)
|
|
181
|
-
end
|
|
182
|
-
if available_chars - 3 > 0
|
|
183
|
-
return build_title_format_truncated(format: format,
|
|
184
|
-
title: title,
|
|
185
|
-
uri: uri,
|
|
186
|
-
available_chars: available_chars)
|
|
187
|
-
end
|
|
188
|
-
else
|
|
189
|
-
build_title_format(format: format,
|
|
190
|
-
title: title,
|
|
191
|
-
uri: uri)
|
|
192
|
-
end
|
|
193
|
-
end
|
|
194
|
-
|
|
195
132
|
def build_keywords(keywords, max)
|
|
196
133
|
keywords[0..max - 1].join ', '
|
|
197
134
|
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: 0.3.0
|
|
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: 2017-09
|
|
11
|
+
date: 2017-10-09 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: puree
|