rialto-etl 0.0.1 → 0.0.2
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/.gitignore +1 -0
- data/.rspec +2 -1
- data/.rubocop.yml +18 -0
- data/Gemfile +6 -2
- data/LICENSE +203 -0
- data/README.md +12 -1
- data/docs/CAP-organizations.md +258 -0
- data/lib/rialto/etl/configs/stanford_organizations.rb +9 -16
- data/lib/rialto/etl/extractors/abstract_stanford_extractor.rb +9 -1
- data/lib/rialto/etl/extractors/stanford_organizations.rb +1 -0
- data/lib/rialto/etl/extractors/stanford_researchers.rb +1 -0
- data/lib/rialto/etl/readers/stanford_organizations_json_reader.rb +36 -0
- data/lib/rialto/etl/transformers/stanford_organizations_to_vivo.rb +6 -2
- data/lib/rialto/etl/version.rb +1 -1
- data/lib/rialto/etl/writers/jsonld_writer.rb +40 -0
- data/lib/rialto/etl/writers/ntriples_writer.rb +32 -0
- data/mapping.md +43 -16
- data/rialto-etl.gemspec +3 -0
- metadata +49 -3
- data/lib/rialto/etl/stanford_organizations_json_reader.rb +0 -27
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 80d6ca761827682b6f4175965c61a24fe426fcd9
|
|
4
|
+
data.tar.gz: ed7045079818141034e35dc54e7b2bba1a2b20df
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2bb3c2df22a94341bf814c308d212849f3f3077eafc7cef08f0de82ae9965669d9abc8ceba12fb73b145f5dd3a142110d50fd2bc9569f9b1af5c0747e28afb29
|
|
7
|
+
data.tar.gz: 8dd23de023248b05b2da377041cdb76a5130d7dabd2d186ac6ca6c946e16532343d3b7d38686b12124fff683423838af6ca9e309ed975ced4d5066821124c2ef
|
data/.gitignore
CHANGED
data/.rspec
CHANGED
data/.rubocop.yml
CHANGED
|
@@ -1,8 +1,26 @@
|
|
|
1
|
+
require: rubocop-rspec
|
|
1
2
|
inherit_from: .rubocop_todo.yml
|
|
2
3
|
|
|
3
4
|
AllCops:
|
|
4
5
|
TargetRubyVersion: 2.3
|
|
5
6
|
|
|
7
|
+
Metrics/BlockLength:
|
|
8
|
+
Exclude:
|
|
9
|
+
- spec/**/*.rb
|
|
10
|
+
|
|
11
|
+
RSpec/FilePath:
|
|
12
|
+
Enabled: false
|
|
13
|
+
|
|
14
|
+
RSpec/IteratedExpectation:
|
|
15
|
+
Exclude:
|
|
16
|
+
- spec/readers/*.rb
|
|
17
|
+
|
|
18
|
+
RSpec/NestedGroups:
|
|
19
|
+
Max: 4
|
|
20
|
+
|
|
21
|
+
RSpec/SubjectStub:
|
|
22
|
+
Enabled: false
|
|
23
|
+
|
|
6
24
|
Style/MixinUsage:
|
|
7
25
|
Exclude:
|
|
8
26
|
- lib/rialto/etl/configs/stanford_organizations.rb
|
data/Gemfile
CHANGED
|
@@ -5,5 +5,9 @@ source 'https://rubygems.org'
|
|
|
5
5
|
# Specify your gem's dependencies in rialto-etl.gemspec
|
|
6
6
|
gemspec
|
|
7
7
|
|
|
8
|
-
|
|
9
|
-
gem '
|
|
8
|
+
group :development, :test do
|
|
9
|
+
gem 'coveralls', require: false
|
|
10
|
+
gem 'pry' unless ENV['CI']
|
|
11
|
+
gem 'pry-byebug' unless ENV['CI']
|
|
12
|
+
gem 'simplecov', require: false
|
|
13
|
+
end
|
data/LICENSE
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "{}"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright 2017 Stanford University
|
|
190
|
+
Additional copyright may be held by others, as reflected in the commit log
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
194
|
+
you may not use this file except in compliance with the License.
|
|
195
|
+
You may obtain a copy of the License at
|
|
196
|
+
|
|
197
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
198
|
+
|
|
199
|
+
Unless required by applicable law or agreed to in writing, software
|
|
200
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
201
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
202
|
+
See the License for the specific language governing permissions and
|
|
203
|
+
limitations under the License.
|
data/README.md
CHANGED
|
@@ -1,6 +1,12 @@
|
|
|
1
1
|
# Rialto::Etl
|
|
2
2
|
|
|
3
|
-
[](https://rubygems.org/gems/rialto-etl)
|
|
4
|
+
[](https://travis-ci.org/sul-dlss-labs/rialto-etl)
|
|
5
|
+
[](https://codeclimate.com/github/sul-dlss-labs/rialto-etl/maintainability)
|
|
6
|
+
[](https://coveralls.io/github/sul-dlss-labs/rialto-etl?branch=master)
|
|
7
|
+
[](https://inch-ci.org/github/sul-dlss-labs/rialto-etl)
|
|
8
|
+
[](http://rubydoc.info/gems/rialto-etl)
|
|
9
|
+
[](./LICENSE)
|
|
4
10
|
|
|
5
11
|
Rialto::Etl is a set of ETL tools for RIALTO, Stanford University Libraries' research intelligence project
|
|
6
12
|
|
|
@@ -53,6 +59,11 @@ TBD
|
|
|
53
59
|
-n, --name NAME Name of the transformer to run (REQUIRED)
|
|
54
60
|
-i, --input-file FILENAME Name of file holding data to be transformed (REQUIRED)
|
|
55
61
|
|
|
62
|
+
## Documentation
|
|
63
|
+
|
|
64
|
+
* [Mapping / Mapping Target](./mapping.md)
|
|
65
|
+
* [CAP Organizations to VIVO Mapping](./docs/CAP-organizations.md)
|
|
66
|
+
|
|
56
67
|
## Development
|
|
57
68
|
|
|
58
69
|
After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
|
|
@@ -0,0 +1,258 @@
|
|
|
1
|
+
# CAP Organizations to VIVO / RIALTO Stanford Organizations Mapping
|
|
2
|
+
|
|
3
|
+
This is mapping documentation for taking CAP API Organizations data (`http://api.stanford.edu/cap/v1/orgs/org-path-name`) and mapping them to our RIALTO model (based on VIVO-ISF Ontology) for `Organizations` (a subclass of `Agents`).
|
|
4
|
+
|
|
5
|
+
## Mapping
|
|
6
|
+
|
|
7
|
+
Reused Ontologies List (to be vetted):
|
|
8
|
+
- "bibo": "http://purl.org/ontology/bibo/"
|
|
9
|
+
- "c4o": "http://purl.org/spar/c4o/"
|
|
10
|
+
- "cito": "http://purl.org/spar/cito/"
|
|
11
|
+
- "dbpedia": "http://dbpedia.org/resource/"
|
|
12
|
+
- "dbo": "http://dbpedia.org/ontology/"
|
|
13
|
+
- "event": "http://purl.org/NET/c4dm/event.owl#"
|
|
14
|
+
- "fabio": "http://purl.org/spar/fabio/"
|
|
15
|
+
- "foaf": "http://xmlns.com/foaf/0.1/"
|
|
16
|
+
- "geo": "http://aims.fao.org/aos/geopolitical.owl#"
|
|
17
|
+
- "obo": "http://purl.obolibrary.org/obo/"
|
|
18
|
+
- "ocrer": "http://purl.org/net/OCRe/research.owl#"
|
|
19
|
+
- "ocresd": "http://purl.org/net/OCRe/study_design.owl#"
|
|
20
|
+
- "owl": "http://www.w3.org/2002/07/owl#"
|
|
21
|
+
- "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
|
22
|
+
- "rdfs": "http://www.w3.org/2000/01/rdf-schema#"
|
|
23
|
+
- "scires": "http://vivoweb.org/ontology/scientific-research#"
|
|
24
|
+
- "skos": "http://www.w3.org/2004/02/skos/core#"
|
|
25
|
+
- "vcard": "http://www.w3.org/2006/vcard/ns#"
|
|
26
|
+
- "vitro": "http://vitro.mannlib.cornell.edu/ns/vitro/0.7#"
|
|
27
|
+
- "vitro-public": "http://vitro.mannlib.cornell.edu/ns/vitro/public#"
|
|
28
|
+
- "vivo": "http://vivoweb.org/ontology/core#"
|
|
29
|
+
- "xsd": "http://www.w3.org/2001/XMLSchema#"
|
|
30
|
+
|
|
31
|
+
For a given organization hash:
|
|
32
|
+
|
|
33
|
+
| CAP key | RIALTO entry | Notes |
|
|
34
|
+
| ------------ | --------------------------------------------------------- | ----- |
|
|
35
|
+
| 'type' | `rdf:type` / `@type` for given organization at RIALTO URI | See mapping below. |
|
|
36
|
+
| 'alias' | `@id` `http://rialto.stanford.edu/individual/{alias}` | Domain may change. Want to confirm alias is consistent enough for use of minting resources that will be fed by all data sources. |
|
|
37
|
+
| 'alias' | `dbo:alias` then value as string | Capture the alias also in the metadata explicitly. |
|
|
38
|
+
| 'name' | `rdfs:label` then value as string | any alt labels? repeated labels? need to check. |
|
|
39
|
+
| 'orgCodes' | for each value, `dbo:code` then value as string | alternate identifiers? where will we look for later matching? |
|
|
40
|
+
| 'children' | `obo:BFO_0000051` (*has part*) then child's alias value as RIALTO URI | capture each presumed URI from the alias, but get the data for that specific organization from separate API calls...? See question above. |
|
|
41
|
+
| 'children' | for each child, `obo:BFO_000005` (*part of*) then parent's RIALTO URI | how to make sure this adds data to the child's graph without removing data the parent won't know about? Or just use Stanford / ROOT and add all data for all Organizations from that? |
|
|
42
|
+
| 'url' | `rdfs:seeAlso` then value as IRI | |
|
|
43
|
+
| 'browsable' | n/a | Ignore. |
|
|
44
|
+
| 'onboarding' | n/a | Ignore. |
|
|
45
|
+
|
|
46
|
+
| CAP Organization Type | RIALTO / VIVO Entity Type | Notes |
|
|
47
|
+
| --------------------- | ------------------------------------ | ----- |
|
|
48
|
+
| ROOT | vivo:University << foaf:Organization | |
|
|
49
|
+
| SCHOOL | vivo:School << foaf:Organization | |
|
|
50
|
+
| DEPARTMENT | vivo:Department << foaf:Organization | From VIVO for Department: "Use for any non-academic department" so this may not fit long-term. Seems like vivo:AcademicDepartment could be better, but departments in CAP are not consistently academic or other. |
|
|
51
|
+
| DIVISION | vivo:Division << foaf:Organization, vivo:ExtensionUnit | From VIVO: subclass of Extension Unit, "A unit devoted primarily to extension activities, whether for outreach or research", so this may not fit long term. |
|
|
52
|
+
| SUB_DIVISION | vivo:Division << foaf:Organization, vivo:ExtensionUnit | See note above. No requirement to distinguish sub-ness in RIALTO. |
|
|
53
|
+
|
|
54
|
+
## Sample Input
|
|
55
|
+
|
|
56
|
+
Sample source CAP data for a provided Organization is in [our fixtures (this has been shortened and any real values replace)](../spec/fixtures/cap/organization.json). See a simplified example of the JSON output below:
|
|
57
|
+
|
|
58
|
+
```JSON
|
|
59
|
+
{
|
|
60
|
+
"alias": "stanford-test",
|
|
61
|
+
"browsable": false,
|
|
62
|
+
"children": [{
|
|
63
|
+
"alias": "department-of-funny-walks",
|
|
64
|
+
"browsable": false,
|
|
65
|
+
"children": [{
|
|
66
|
+
"alias": "department-of-funny-walks/intercollegiate-walks",
|
|
67
|
+
"browsable": false,
|
|
68
|
+
"name": "Intercollegiate Walks",
|
|
69
|
+
"onboarding": true,
|
|
70
|
+
"orgCodes": [
|
|
71
|
+
"WALK",
|
|
72
|
+
"WALZ"
|
|
73
|
+
],
|
|
74
|
+
"type": "DEPARTMENT"
|
|
75
|
+
},
|
|
76
|
+
{
|
|
77
|
+
"alias": "department-of-funny-walks/walks-education",
|
|
78
|
+
"browsable": false,
|
|
79
|
+
"children": [{
|
|
80
|
+
"alias": "department-of-funny-walks/walks-education/adventure-walks",
|
|
81
|
+
"browsable": false,
|
|
82
|
+
"name": "Adventure Walks",
|
|
83
|
+
"onboarding": true,
|
|
84
|
+
"orgCodes": [
|
|
85
|
+
"ADVE"
|
|
86
|
+
],
|
|
87
|
+
"type": "DIVISION"
|
|
88
|
+
}
|
|
89
|
+
],
|
|
90
|
+
"name": "Walks Education",
|
|
91
|
+
"onboarding": true,
|
|
92
|
+
"orgCodes": [
|
|
93
|
+
"EDUC",
|
|
94
|
+
"WEDU",
|
|
95
|
+
"EDUW",
|
|
96
|
+
"WAED",
|
|
97
|
+
"EDWA"
|
|
98
|
+
],
|
|
99
|
+
"type": "DEPARTMENT"
|
|
100
|
+
}
|
|
101
|
+
],
|
|
102
|
+
"name": "Department of Funny Walks",
|
|
103
|
+
"onboarding": false,
|
|
104
|
+
"orgCodes": [
|
|
105
|
+
"HAAA"
|
|
106
|
+
],
|
|
107
|
+
"type": "SCHOOL"
|
|
108
|
+
},
|
|
109
|
+
{
|
|
110
|
+
"alias": "graduate-school-of-parrots",
|
|
111
|
+
"browsable": false,
|
|
112
|
+
"name": "Graduate School of Parrots",
|
|
113
|
+
"onboarding": true,
|
|
114
|
+
"orgCodes": [
|
|
115
|
+
"PARR"
|
|
116
|
+
],
|
|
117
|
+
"type": "SCHOOL",
|
|
118
|
+
"url": "http://parrots.python.pizza/"
|
|
119
|
+
}],
|
|
120
|
+
"name": "Stanford Test",
|
|
121
|
+
"onboarding": false,
|
|
122
|
+
"orgCodes": [
|
|
123
|
+
"STAN"
|
|
124
|
+
],
|
|
125
|
+
"type": "ROOT",
|
|
126
|
+
"url": "http://python.pizza/"
|
|
127
|
+
}
|
|
128
|
+
```
|
|
129
|
+
|
|
130
|
+
For any given Organization, these keys / fields appear in its Organization object:
|
|
131
|
+
|
|
132
|
+
| Key | Expectation | Definition | Notes |
|
|
133
|
+
| ------------ | ----------------------------- | ---------- | ----- |
|
|
134
|
+
| 'orgCodes' | Array of 4-letter strings | the Stanford-specific (for ... HR?) organization code or identifier | history / previous projects says these can be helpful but also reflect previous / no longer extent departments or relationships |
|
|
135
|
+
| 'type' | String, 1 of following values: `ROOT`, `SCHOOL`, `DEPARTMENT`, `DIVISION`, `SUB_DIVISION` | The type of organization within the University (aka the `ROOT`) | See mappings to RIALTO / VIVO types below |
|
|
136
|
+
| 'name' | String | Name or label for the organization represented by the present JSON Object | n/a |
|
|
137
|
+
| 'children' | Array of Organization Objects | Any organizations that are children of the organization represented by the present JSON Object | Should we iterate on these for data or just to know what orgs are children, then call their own API response separately? |
|
|
138
|
+
| 'browsable' | Boolean | Uncertain. If is public data? | n/a |
|
|
139
|
+
| 'alias' | String, API query path value | The API URL path value for the organization. | Is this used for anything other than the API? |
|
|
140
|
+
| 'url' | String, HTTP URL | URL provided for the given organization. | n/a |
|
|
141
|
+
| 'onboarding' | Boolean | Uncertain. If onboarding exists? | n/a |
|
|
142
|
+
|
|
143
|
+
## Sample Output
|
|
144
|
+
|
|
145
|
+
Sample output VIVO JSON-LD data for a provided Organization is in [our fixtures (this has been shortened and any real values replace)](../spec/fixtures/vivo/org-out.json). See a simplified example of the JSON output below:
|
|
146
|
+
|
|
147
|
+
```JSON
|
|
148
|
+
{
|
|
149
|
+
"@context": {
|
|
150
|
+
"dbpedia": "http://dbpedia.org/resource/",
|
|
151
|
+
"dbo": "http://dbpedia.org/ontology/",
|
|
152
|
+
"obo": "http://purl.obolibrary.org/obo/",
|
|
153
|
+
"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
|
|
154
|
+
"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
|
|
155
|
+
"vivo": "http://vivoweb.org/ontology/core#"
|
|
156
|
+
},
|
|
157
|
+
"@graph": [
|
|
158
|
+
{
|
|
159
|
+
"@id": "http://rialto.stanford.edu/individual/stanford-test",
|
|
160
|
+
"@type": "vivo:University",
|
|
161
|
+
"dbo:alias": "stanford-test",
|
|
162
|
+
"rdfs:label": "Stanford Test",
|
|
163
|
+
"rdfs:seeAlso": "http://python.pizza/",
|
|
164
|
+
"dbo:code": [
|
|
165
|
+
"STAN"
|
|
166
|
+
],
|
|
167
|
+
"obo:BFO_0000051": [
|
|
168
|
+
{
|
|
169
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks"
|
|
170
|
+
},
|
|
171
|
+
{
|
|
172
|
+
"@id": "http://rialto.stanford.edu/individual/graduate-school-of-parrots"
|
|
173
|
+
}
|
|
174
|
+
],
|
|
175
|
+
"obo:RO_0001025": {
|
|
176
|
+
"@id": "dbpedia:Palo_Alto,_California"
|
|
177
|
+
}
|
|
178
|
+
},
|
|
179
|
+
{
|
|
180
|
+
"@id": "http://rialto.stanford.edu/individual/graduate-school-of-parrots",
|
|
181
|
+
"@type": "vivo:School",
|
|
182
|
+
"dbo:alias": "graduate-school-of-parrots",
|
|
183
|
+
"rdfs:label": "Graduate School of Parrots",
|
|
184
|
+
"rdfs:seeAlso": "http://parrots.python.pizza/",
|
|
185
|
+
"dbo:code": [
|
|
186
|
+
"PARR"
|
|
187
|
+
],
|
|
188
|
+
"obo:BFO_0000050": {
|
|
189
|
+
"@id": "http://rialto.stanford.edu/individual/stanford-test"
|
|
190
|
+
}
|
|
191
|
+
},
|
|
192
|
+
{
|
|
193
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks",
|
|
194
|
+
"@type": "vivo:School",
|
|
195
|
+
"dbo:alias": "department-of-funny-walks",
|
|
196
|
+
"rdfs:label": "Department of Funny Walks",
|
|
197
|
+
"dbo:code": [
|
|
198
|
+
"HAAA"
|
|
199
|
+
],
|
|
200
|
+
"obo:BFO_0000050": {
|
|
201
|
+
"@id": "http://rialto.stanford.edu/individual/stanford-test"
|
|
202
|
+
},
|
|
203
|
+
"obo:BFO_0000051": [
|
|
204
|
+
{
|
|
205
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/intercollegiate-walks"
|
|
206
|
+
},
|
|
207
|
+
{
|
|
208
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/walks-education"
|
|
209
|
+
}
|
|
210
|
+
]
|
|
211
|
+
},
|
|
212
|
+
{
|
|
213
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/intercollegiate-walks",
|
|
214
|
+
"@type": "vivo:Department",
|
|
215
|
+
"dbo:alias": "department-of-funny-walks/intercollegiate-walks",
|
|
216
|
+
"rdfs:label": "Intercollegiate Walks",
|
|
217
|
+
"dbo:code": [
|
|
218
|
+
"WALK",
|
|
219
|
+
"WALZ"
|
|
220
|
+
],
|
|
221
|
+
"obo:BFO_0000051": {
|
|
222
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks"
|
|
223
|
+
}
|
|
224
|
+
},
|
|
225
|
+
{
|
|
226
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/walks-education",
|
|
227
|
+
"@type": "vivo:Department",
|
|
228
|
+
"dbo:alias": "department-of-funny-walks/walks-education",
|
|
229
|
+
"rdfs:label": "Walks Education",
|
|
230
|
+
"dbo:code": [
|
|
231
|
+
"EDUC",
|
|
232
|
+
"WEDU",
|
|
233
|
+
"EDUW",
|
|
234
|
+
"WAED",
|
|
235
|
+
"EDWA"
|
|
236
|
+
],
|
|
237
|
+
"obo:BFO_0000051": {
|
|
238
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks"
|
|
239
|
+
},
|
|
240
|
+
"obo:BFO_0000050": {
|
|
241
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/walks-education/adventure-walks"
|
|
242
|
+
}
|
|
243
|
+
},
|
|
244
|
+
{
|
|
245
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/walks-education/adventure-walks",
|
|
246
|
+
"@type": "vivo:Division",
|
|
247
|
+
"dbo:alias": "department-of-funny-walks/walks-education/adventure-walks",
|
|
248
|
+
"rdfs:label": "Adventure Walks",
|
|
249
|
+
"dbo:code": [
|
|
250
|
+
"ADVE"
|
|
251
|
+
],
|
|
252
|
+
"obo:BFO_0000051": {
|
|
253
|
+
"@id": "http://rialto.stanford.edu/individual/department-of-funny-walks/walks-education"
|
|
254
|
+
}
|
|
255
|
+
}
|
|
256
|
+
]
|
|
257
|
+
}
|
|
258
|
+
```
|
|
@@ -1,26 +1,19 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
+
require 'traject_plus'
|
|
4
|
+
require 'rialto/etl/readers/stanford_organizations_json_reader'
|
|
5
|
+
require 'rialto/etl/writers/ntriples_writer'
|
|
6
|
+
|
|
3
7
|
extend TrajectPlus::Macros
|
|
4
8
|
extend TrajectPlus::Macros::JSON
|
|
5
9
|
|
|
6
10
|
settings do
|
|
7
|
-
provide 'writer_class_name', '
|
|
8
|
-
provide 'reader_class_name', 'Rialto::Etl::StanfordOrganizationsJsonReader'
|
|
11
|
+
provide 'writer_class_name', 'Rialto::Etl::Writers::NtriplesWriter'
|
|
12
|
+
provide 'reader_class_name', 'Rialto::Etl::Readers::StanfordOrganizationsJsonReader'
|
|
9
13
|
end
|
|
10
14
|
|
|
11
|
-
# context_object = {
|
|
12
|
-
# '@context' => {
|
|
13
|
-
# obo: 'http://purl.obolibrary.org/obo/',
|
|
14
|
-
# rdfs: 'http://www.w3.org/2000/01/rdf-schema#',
|
|
15
|
-
# vcard: 'http://www.w3.org/2006/vcard/ns#',
|
|
16
|
-
# vivo: 'http://vivoweb.org/ontology/core#',
|
|
17
|
-
# stanford: 'http://authorities.stanford.edu/orgs#'
|
|
18
|
-
# }
|
|
19
|
-
# }
|
|
20
|
-
|
|
21
|
-
# puts context_object.to_json
|
|
22
15
|
to_field '@id', extract_json('$.alias'), transform: transform(prepend: 'http://authorities.stanford.edu/orgs#'), single: true
|
|
23
16
|
to_field '@type', extract_json('$.type', translation_map: 'stanford_organizations_to_vivo_types'), single: true
|
|
24
|
-
to_field '
|
|
25
|
-
to_field '
|
|
26
|
-
to_field '
|
|
17
|
+
to_field 'http://www.w3.org/2000/01/rdf-schema#label', extract_json('$.name'), single: true
|
|
18
|
+
to_field 'http://www.w3.org/2000/01/rdf-schema#seeAlso', extract_json('$.url'), single: true
|
|
19
|
+
to_field 'http://vivoweb.org/ontology/core#abbreviation', extract_json('$.orgCodes'), single: true
|
|
@@ -10,8 +10,10 @@ module Rialto
|
|
|
10
10
|
module Extractors
|
|
11
11
|
# Abstract class hitting Stanford APIs using Stanford authz
|
|
12
12
|
class AbstractStanfordExtractor
|
|
13
|
+
# Time at which access token expires (as integer)
|
|
13
14
|
attr_reader :access_token_expiry_time
|
|
14
15
|
|
|
16
|
+
# Hit an API endpoint and return the results
|
|
15
17
|
def extract
|
|
16
18
|
raise NotImplementedError, 'Implement #extract in a child class'
|
|
17
19
|
end
|
|
@@ -28,7 +30,6 @@ module Rialto
|
|
|
28
30
|
Faraday.new(uri, headers: connection_headers) do |connection|
|
|
29
31
|
connection.request :retry, max: 3, interval: 0.8, interval_randomness: 0.2, backoff_factor: 2
|
|
30
32
|
connection.ssl.update(verify: true, verify_mode: OpenSSL::SSL::VERIFY_PEER)
|
|
31
|
-
connection.use Faraday::Response::RaiseError
|
|
32
33
|
connection.adapter :httpclient
|
|
33
34
|
connection.options.timeout = 500
|
|
34
35
|
connection.options.open_timeout = 10
|
|
@@ -53,6 +54,9 @@ module Rialto
|
|
|
53
54
|
end
|
|
54
55
|
end
|
|
55
56
|
|
|
57
|
+
# Set the access token to `nil` to force retrieving a new one
|
|
58
|
+
#
|
|
59
|
+
# @return [void]
|
|
56
60
|
def reset_access_token!
|
|
57
61
|
@access_token = nil
|
|
58
62
|
end
|
|
@@ -63,6 +67,10 @@ module Rialto
|
|
|
63
67
|
true
|
|
64
68
|
end
|
|
65
69
|
|
|
70
|
+
# Set token expiry time to a new value based on current time
|
|
71
|
+
#
|
|
72
|
+
# @param expires_in [#to_i] time instance dictating when token expires
|
|
73
|
+
# @return [void]
|
|
66
74
|
def reset_expiry_time!(expires_in:)
|
|
67
75
|
@access_token_expiry_time = current_time + expires_in.to_i
|
|
68
76
|
end
|
|
@@ -7,6 +7,7 @@ module Rialto
|
|
|
7
7
|
module Extractors
|
|
8
8
|
# Stanford CAP API for orgs
|
|
9
9
|
class StanfordOrganizations < AbstractStanfordExtractor
|
|
10
|
+
# Hit an API endpoint and return the results
|
|
10
11
|
def extract
|
|
11
12
|
client.get('/cap/v1/orgs/stanford?p=1&ps=10').body
|
|
12
13
|
rescue StandardError => exception
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require 'traject_plus'
|
|
4
|
+
|
|
5
|
+
module Rialto
|
|
6
|
+
module Etl
|
|
7
|
+
# Holds readers for use in Traject mappings
|
|
8
|
+
module Readers
|
|
9
|
+
# Read JSON that maps to Stanford orgs
|
|
10
|
+
class StanfordOrganizationsJsonReader < TrajectPlus::JsonReader
|
|
11
|
+
# Overrides the implementation inherited from superclass
|
|
12
|
+
#
|
|
13
|
+
# @param block [#call] a block that is executed on each organization
|
|
14
|
+
# @return [String] JSON representation of an organization
|
|
15
|
+
def each(&block)
|
|
16
|
+
yield_children(json, block)
|
|
17
|
+
end
|
|
18
|
+
|
|
19
|
+
private
|
|
20
|
+
|
|
21
|
+
def yield_children(hash, block)
|
|
22
|
+
block.call(hash)
|
|
23
|
+
children = children_path(hash)
|
|
24
|
+
return if children.blank?
|
|
25
|
+
children.each do |child|
|
|
26
|
+
yield_children(child, block)
|
|
27
|
+
end
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def children_path(hash)
|
|
31
|
+
JsonPath.on(hash, '$.children').first
|
|
32
|
+
end
|
|
33
|
+
end
|
|
34
|
+
end
|
|
35
|
+
end
|
|
36
|
+
end
|
|
@@ -1,19 +1,23 @@
|
|
|
1
1
|
# frozen_string_literal: true
|
|
2
2
|
|
|
3
|
-
require '
|
|
4
|
-
require 'rialto/etl/stanford_organizations_json_reader'
|
|
3
|
+
require 'traject'
|
|
5
4
|
|
|
6
5
|
module Rialto
|
|
7
6
|
module Etl
|
|
8
7
|
module Transformers
|
|
9
8
|
# Transformer turning Stanford org info into Vivo format
|
|
10
9
|
class StanfordOrganizationsToVivo
|
|
10
|
+
# A valid file path
|
|
11
11
|
attr_reader :input
|
|
12
12
|
|
|
13
|
+
# Initialize a new instance of the transformer
|
|
14
|
+
#
|
|
15
|
+
# @param input [String] valid file path
|
|
13
16
|
def initialize(input:)
|
|
14
17
|
@input = input
|
|
15
18
|
end
|
|
16
19
|
|
|
20
|
+
# Transform a stream into a new representation, using Traject
|
|
17
21
|
def transform
|
|
18
22
|
File.open(input, 'r') do |stream|
|
|
19
23
|
transformer.process(stream)
|
data/lib/rialto/etl/version.rb
CHANGED
|
@@ -0,0 +1,40 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
module Rialto
|
|
4
|
+
module Etl
|
|
5
|
+
# Holds writers for use in Traject mappings
|
|
6
|
+
module Writers
|
|
7
|
+
# Write JSON-LD records. This writer conforms to Traject's
|
|
8
|
+
# writer class interface, supporting #initialize, #put, and
|
|
9
|
+
# #close
|
|
10
|
+
class JsonldWriter
|
|
11
|
+
# Traject settings object
|
|
12
|
+
|
|
13
|
+
# Constructor
|
|
14
|
+
def initialize(_); end
|
|
15
|
+
|
|
16
|
+
# Append the hash representing a single mapped record to the
|
|
17
|
+
# list of records held in memory
|
|
18
|
+
#
|
|
19
|
+
# @param context [Traject::Indexer::Context] a Traject context
|
|
20
|
+
# object containing the output of the mapping
|
|
21
|
+
# @return [Array] a list of all records mapped
|
|
22
|
+
def put(context)
|
|
23
|
+
records << context.output_hash
|
|
24
|
+
end
|
|
25
|
+
|
|
26
|
+
# Print a JSON representation of the records with the
|
|
27
|
+
# JSON-LD context object attached
|
|
28
|
+
def close
|
|
29
|
+
$stdout.puts records.to_json
|
|
30
|
+
end
|
|
31
|
+
|
|
32
|
+
private
|
|
33
|
+
|
|
34
|
+
def records
|
|
35
|
+
@records ||= []
|
|
36
|
+
end
|
|
37
|
+
end
|
|
38
|
+
end
|
|
39
|
+
end
|
|
40
|
+
end
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# frozen_string_literal: true
|
|
2
|
+
|
|
3
|
+
require 'rdf'
|
|
4
|
+
require 'traject'
|
|
5
|
+
|
|
6
|
+
module Rialto
|
|
7
|
+
module Etl
|
|
8
|
+
# Holds writers for use in Traject mappings
|
|
9
|
+
module Writers
|
|
10
|
+
# Write NTriples records
|
|
11
|
+
class NtriplesWriter < Traject::LineWriter
|
|
12
|
+
# Overrides the serialization routine from superclass
|
|
13
|
+
#
|
|
14
|
+
# @param context [Traject::Indexer::Context] a Traject context
|
|
15
|
+
# object containing the output of the mapping
|
|
16
|
+
# @return [String] NTriples representation of the mapping
|
|
17
|
+
def serialize(context)
|
|
18
|
+
hash = context.output_hash
|
|
19
|
+
subject = RDF::URI.new(hash.delete('@id'))
|
|
20
|
+
type = RDF::URI.new(hash.delete('@type'))
|
|
21
|
+
graph = RDF::Graph.new << [subject, RDF.type, type]
|
|
22
|
+
hash.each_pair do |field, values|
|
|
23
|
+
Array(values).each do |value|
|
|
24
|
+
graph << [subject, RDF::URI.new(field), value]
|
|
25
|
+
end
|
|
26
|
+
end
|
|
27
|
+
graph.dump(:ntriples)
|
|
28
|
+
end
|
|
29
|
+
end
|
|
30
|
+
end
|
|
31
|
+
end
|
|
32
|
+
end
|
data/mapping.md
CHANGED
|
@@ -1,22 +1,49 @@
|
|
|
1
|
-
|
|
1
|
+
# RIALTO / VIVO Mapping & Mapping Target
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
This is mapping documentation for the end result of our selected sources to RIALTO / VIVO models. See more information in our [docs folder](docs). This will be iterated on as sources and types are mapped.
|
|
4
4
|
|
|
5
|
-
|
|
6
|
-
browsable (boolean) => ignore
|
|
7
|
-
children (array) => keep track of parent, iterate over values (for each obo:BFO\_0000050/partOf) and map, keep track of children for obo:BFO\_0000051/hasPart
|
|
8
|
-
name (string) => rdfs:label
|
|
9
|
-
onboarding (boolean) => ignore
|
|
10
|
-
orgCodes (array) => vivo:abbreviation
|
|
11
|
-
type (string) => see type mappings
|
|
12
|
-
url (string) => rdfs:seeAlso
|
|
5
|
+
# Reused Ontologies List (to be further vetted)
|
|
13
6
|
|
|
14
|
-
|
|
7
|
+
- "dbpedia": "http://dbpedia.org/resource/"
|
|
8
|
+
- "dbo": "http://dbpedia.org/ontology/"
|
|
9
|
+
- "foaf": "http://xmlns.com/foaf/0.1/"
|
|
10
|
+
- "obo": "http://purl.obolibrary.org/obo/"
|
|
11
|
+
- "owl": "http://www.w3.org/2002/07/owl#"
|
|
12
|
+
- "rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#"
|
|
13
|
+
- "rdfs": "http://www.w3.org/2000/01/rdf-schema#"
|
|
14
|
+
- "skos": "http://www.w3.org/2004/02/skos/core#"
|
|
15
|
+
- "vivo": "http://vivoweb.org/ontology/core#"
|
|
16
|
+
- "xsd": "http://www.w3.org/2001/XMLSchema#"
|
|
15
17
|
|
|
16
|
-
|
|
17
|
-
SUB_DIVISION @type: http://vivoweb.org/ontology/core#Division
|
|
18
|
-
ROOT @type: http://vivoweb.org/ontology/core#University
|
|
19
|
-
SCHOOL @type: http://vivoweb.org/ontology/core#School
|
|
20
|
-
DEPARTMENT @type: http://vivoweb.org/ontology/core#Department
|
|
18
|
+
## Overarching RIALTO Model
|
|
21
19
|
|
|
20
|
+
TBD
|
|
22
21
|
|
|
22
|
+
## Mappings to RIALTO
|
|
23
|
+
|
|
24
|
+
### For Organizations
|
|
25
|
+
|
|
26
|
+
| Source & key | RIALTO entry | Notes |
|
|
27
|
+
| -------------- | --------------------------------------------------------- | ----- |
|
|
28
|
+
| CAP 'type' | `rdf:type` / `@type` for given organization at RIALTO URI | See mapping below. |
|
|
29
|
+
| CAP 'alias' | `@id` `http://rialto.stanford.edu/individual/{alias}` | Domain may change. Want to confirm alias is consistent enough for use of minting resources that will be fed by all data sources. |
|
|
30
|
+
| CAP 'alias' | `dbo:alias` then value as string | Capture the alias also in the metadata explicitly. |
|
|
31
|
+
| CAP 'name' | `rdfs:label` then value as string | any alt labels? repeated labels? need to check. |
|
|
32
|
+
| CAP 'orgCodes' | for each value, `dbo:code` then value as string | alternate identifiers? where will we look for later matching? |
|
|
33
|
+
| CAP 'children' | `obo:BFO_0000051` (*has part*) then child's alias value as RIALTO URI | capture each presumed URI from the alias, but get the data for that specific organization from separate API calls...? See question above. |
|
|
34
|
+
| CAP 'children' | for each child, `obo:BFO_000005` (*part of*) then parent's RIALTO URI | how to make sure this adds data to the child's graph without removing data the parent won't know about? Or just use Stanford / ROOT and add all data for all Organizations from that? |
|
|
35
|
+
| CAP 'url' | `rdfs:seeAlso` then value as IRI | |
|
|
36
|
+
|
|
37
|
+
### RIALTO Organization Types Mapping
|
|
38
|
+
|
|
39
|
+
| Source & Type | RIALTO / VIVO Entity Type | Notes |
|
|
40
|
+
| --------------------- | ------------------------------------ | ----- |
|
|
41
|
+
| CAP@type ROOT | vivo:University << foaf:Organization | |
|
|
42
|
+
| CAP@type SCHOOL | vivo:School << foaf:Organization | |
|
|
43
|
+
| CAP@type DEPARTMENT | vivo:Department << foaf:Organization | From VIVO for Department: "Use for any non-academic department" so this may not fit long-term. Seems like vivo:AcademicDepartment could be better, but departments in CAP are not consistently academic or other. |
|
|
44
|
+
| CAP@type DIVISION | vivo:Division << foaf:Organization, vivo:ExtensionUnit | From VIVO: subclass of Extension Unit, "A unit devoted primarily to extension activities, whether for outreach or research", so this may not fit long term. |
|
|
45
|
+
| CAP@type SUB_DIVISION | vivo:Division << foaf:Organization, vivo:ExtensionUnit | See note above. No requirement to distinguish sub-ness in RIALTO. |
|
|
46
|
+
|
|
47
|
+
## Sample RIALTO Graph
|
|
48
|
+
|
|
49
|
+
Sample output VIVO JSON-LD data for a provided Organization is in [our fixtures (this has been shortened and any real values replace)](spec/fixtures/vivo/org-out.json). A larger file with a fuller graph generated from multiple sources will be added in the near future.
|
data/rialto-etl.gemspec
CHANGED
|
@@ -20,10 +20,13 @@ Gem::Specification.new do |spec|
|
|
|
20
20
|
|
|
21
21
|
spec.add_dependency 'faraday'
|
|
22
22
|
spec.add_dependency 'httpclient'
|
|
23
|
+
spec.add_dependency 'rdf'
|
|
23
24
|
spec.add_dependency 'traject_plus', '>= 0.0.2'
|
|
24
25
|
|
|
25
26
|
spec.add_development_dependency 'bundler', '~> 1.11'
|
|
26
27
|
spec.add_development_dependency 'rake', '~> 10.0'
|
|
27
28
|
spec.add_development_dependency 'rspec', '~> 3.0'
|
|
28
29
|
spec.add_development_dependency 'rubocop', '~> 0.52.0'
|
|
30
|
+
spec.add_development_dependency 'rubocop-rspec', '~> 1.21.0'
|
|
31
|
+
spec.add_development_dependency 'webmock'
|
|
29
32
|
end
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: rialto-etl
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Michael J. Giarlo
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date:
|
|
11
|
+
date: 2018-01-22 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: faraday
|
|
@@ -38,6 +38,20 @@ dependencies:
|
|
|
38
38
|
- - ">="
|
|
39
39
|
- !ruby/object:Gem::Version
|
|
40
40
|
version: '0'
|
|
41
|
+
- !ruby/object:Gem::Dependency
|
|
42
|
+
name: rdf
|
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
|
44
|
+
requirements:
|
|
45
|
+
- - ">="
|
|
46
|
+
- !ruby/object:Gem::Version
|
|
47
|
+
version: '0'
|
|
48
|
+
type: :runtime
|
|
49
|
+
prerelease: false
|
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
51
|
+
requirements:
|
|
52
|
+
- - ">="
|
|
53
|
+
- !ruby/object:Gem::Version
|
|
54
|
+
version: '0'
|
|
41
55
|
- !ruby/object:Gem::Dependency
|
|
42
56
|
name: traject_plus
|
|
43
57
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -108,6 +122,34 @@ dependencies:
|
|
|
108
122
|
- - "~>"
|
|
109
123
|
- !ruby/object:Gem::Version
|
|
110
124
|
version: 0.52.0
|
|
125
|
+
- !ruby/object:Gem::Dependency
|
|
126
|
+
name: rubocop-rspec
|
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
|
128
|
+
requirements:
|
|
129
|
+
- - "~>"
|
|
130
|
+
- !ruby/object:Gem::Version
|
|
131
|
+
version: 1.21.0
|
|
132
|
+
type: :development
|
|
133
|
+
prerelease: false
|
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
135
|
+
requirements:
|
|
136
|
+
- - "~>"
|
|
137
|
+
- !ruby/object:Gem::Version
|
|
138
|
+
version: 1.21.0
|
|
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'
|
|
111
153
|
description:
|
|
112
154
|
email:
|
|
113
155
|
- mjgiarlo@stanford.edu
|
|
@@ -121,22 +163,26 @@ files:
|
|
|
121
163
|
- ".rubocop_todo.yml"
|
|
122
164
|
- ".travis.yml"
|
|
123
165
|
- Gemfile
|
|
166
|
+
- LICENSE
|
|
124
167
|
- README.md
|
|
125
168
|
- Rakefile
|
|
126
169
|
- bin/console
|
|
127
170
|
- bin/extract
|
|
128
171
|
- bin/setup
|
|
129
172
|
- bin/transform
|
|
173
|
+
- docs/CAP-organizations.md
|
|
130
174
|
- lib/rialto/etl.rb
|
|
131
175
|
- lib/rialto/etl/configs/stanford_organizations.rb
|
|
132
176
|
- lib/rialto/etl/extractors.rb
|
|
133
177
|
- lib/rialto/etl/extractors/abstract_stanford_extractor.rb
|
|
134
178
|
- lib/rialto/etl/extractors/stanford_organizations.rb
|
|
135
179
|
- lib/rialto/etl/extractors/stanford_researchers.rb
|
|
136
|
-
- lib/rialto/etl/stanford_organizations_json_reader.rb
|
|
180
|
+
- lib/rialto/etl/readers/stanford_organizations_json_reader.rb
|
|
137
181
|
- lib/rialto/etl/transformers.rb
|
|
138
182
|
- lib/rialto/etl/transformers/stanford_organizations_to_vivo.rb
|
|
139
183
|
- lib/rialto/etl/version.rb
|
|
184
|
+
- lib/rialto/etl/writers/jsonld_writer.rb
|
|
185
|
+
- lib/rialto/etl/writers/ntriples_writer.rb
|
|
140
186
|
- lib/translation_maps/stanford_organizations_to_vivo_types.yaml
|
|
141
187
|
- mapping.md
|
|
142
188
|
- rialto-etl.gemspec
|
|
@@ -1,27 +0,0 @@
|
|
|
1
|
-
# frozen_string_literal: true
|
|
2
|
-
|
|
3
|
-
module Rialto
|
|
4
|
-
module Etl
|
|
5
|
-
# Read JSON that maps to Stanford orgs
|
|
6
|
-
class StanfordOrganizationsJsonReader < TrajectPlus::JsonReader
|
|
7
|
-
def each(&block)
|
|
8
|
-
yield_children(json, block)
|
|
9
|
-
end
|
|
10
|
-
|
|
11
|
-
private
|
|
12
|
-
|
|
13
|
-
def yield_children(hash, block)
|
|
14
|
-
block.call(hash)
|
|
15
|
-
children = children_path(hash)
|
|
16
|
-
return if children.blank?
|
|
17
|
-
children.each do |child|
|
|
18
|
-
yield_children(child, block)
|
|
19
|
-
end
|
|
20
|
-
end
|
|
21
|
-
|
|
22
|
-
def children_path(hash)
|
|
23
|
-
JsonPath.on(hash, '$.children').first
|
|
24
|
-
end
|
|
25
|
-
end
|
|
26
|
-
end
|
|
27
|
-
end
|