Skip to content

Commit 60974a3

Browse files
feragferag
authored
Merge pull request #260 from IFCA-Advanced-Computing/ai4os_plugin
Ai4os plugin
2 parents ee842c8 + 9a359aa commit 60974a3

File tree

3 files changed

+1105
-455
lines changed

3 files changed

+1105
-455
lines changed

‎plugins/ai4os/config.ini

Lines changed: 80 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,80 @@
1+
[ai4os]
2+
#
3+
# Configuration for the AI4EOSC plugin. These values are used by the
4+
# Evaluator to determine which metadata elements contribute to the FAIR
5+
# indicators of richness, accessibility, interoperability and reuse.
6+
7+
identifier_term = [['title',''],]
8+
identifier_term_data = [['title', None]]
9+
10+
# Generic metadata terms that should be present to satisfy richness
11+
terms_quali_generic = [
12+
['title', None],
13+
['summary', None],
14+
['description', None],
15+
['tags', None],
16+
['libraries', None],
17+
['tasks', None]]
18+
# Disciplinary-specific richness terms (reuse generic for now)
19+
terms_quali_disciplinar = [
20+
['title', None],
21+
['summary', None],
22+
['description', None]]
23+
# Terms that provide access to (meta)data
24+
terms_access = [['links','source_code'], ['links','weights']]
25+
# Controlled vocabulary terms (libraries and tasks are often drawn from
26+
# controlled lists in AI4EOSC)
27+
terms_cv = [
28+
['provenance', None]]
29+
# Formats commonly used for AI models and datasets in AI4EOSC
30+
supported_data_formats = ['.zip', '.tar', '.pth', '.h5', '.onnx', '.pt']
31+
32+
# Terms linking to qualified references (e.g. other resources)
33+
terms_qualified_references = [['links', None]]
34+
35+
# Terms describing relations with other resources
36+
terms_relations = [['prov_hadMember', None]]
37+
38+
# Terms that define licensing information
39+
terms_license = [['license', '']]
40+
41+
# Metadata schemas applicable to AI4EOSC modules
42+
metadata_schemas = [{'ai4os': 'https://docs.ai4os.eu/en/latest/metadata.html'}]
43+
44+
metadata_access_manual = ['https://github.com/ai4os-eu/']
45+
data_access_manual = ['https://dashboard.cloud.ai4eosc.eu/catalog/modules']
46+
terms_access_protocols =['http','https']
47+
dict_vocabularies= {'ROR': 'https://ror.org/', 'PIC': 'https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/how-to-participate/participant-register', 'imtypes': 'https://www.iana.org/assignments/media-types/media-types.xhtml', 'TRL': 'TRL', 'temporal': 'https://www.iso.org/iso-8601-date-and-time-format.html', 'Rolecode': 'Rolecode', 'spdx': 'https://spdx.org/licenses/', 'ORCID': 'https://orcid.org/'}
48+
49+
metadata_standard = ['PROV-Ontology', 'DCAT-AP', 'DCAT-AP-ES']
50+
metadata_authentication = ['Open']
51+
52+
metadata_persistence = []
53+
54+
terms_vocabularies = [
55+
['license', ''],
56+
['description', ]]
57+
58+
terms_reusability_richness = [['availableFormats',''],
59+
['links','source_code'],
60+
['links','docker_image'],
61+
['links','ai4_template'],
62+
['links','dataset']]
63+
64+
[fairsharing]
65+
# username and password
66+
username = ['']
67+
68+
password = ['']
69+
70+
#_path is variable that stores the path to the file in which the fairsharing-approved metadatata standards or formasts are stored
71+
72+
metadata_path = ['static/fairsharing_metadata_standards20240214.json']
73+
74+
formats_path = ['static/fairsharing_formats20240226.txt']
75+
76+
77+
78+
[internet media types]
79+
#path to internet media files file
80+
path = ['static/internetmediatypes190224.csv']

‎plugins/ai4os/config.ini.template

Lines changed: 77 additions & 204 deletions
Original file line numberDiff line numberDiff line change
@@ -1,206 +1,79 @@
1-
[Generic]
2-
doi_url = https://doi.org/
3-
4-
# Relative path to the API config file
5-
api_config = fair-api.yaml
6-
7-
# Supported CVs
8-
controlled_vocabularies = {
9-
'Identifier': {'DOI': 'https://doi.org/api/handles', 'Handle': 'https://hdl.handle.net/'},
10-
'Format': {'imtypes': 'https://www.iana.org/assignments/media-types/media-types.xhtml'},
11-
'Temporal Coverage': {'iso8601': 'https://www.iso.org/iso-8601-date-and-time-format.html'},
12-
'License': {'spdx': 'https://spdx.org/licenses/'},
13-
'Person Identifier': {'ORCID': 'https://orcid.org/'},
14-
'Organisation Identifier': {'ROR': 'https://ror.org/', 'PIC': 'https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/how-to-participate/participant-register'}}
15-
16-
[local]
17-
only_local = False
18-
repo = digital_csic
19-
logo_url = 'https://ifca.unican.es'
20-
title = FAIR EVA: Evaluator, Validator & Advisor
21-
22-
[dublin-core]
23-
# Aligned with Dublin Core Metadata for Resource Discovery (properties in the /elements/1.1/ namespace)
24-
# https://www.dublincore.org/specifications/dublin-core/dcmi-terms/#section-3
25-
terms_findability_richness = ['Title',
26-
'Subject',
27-
'Description',
28-
'Type',
29-
'Source',
30-
'Relation',
31-
'Coverage',
32-
'Creator',
33-
'Publisher',
34-
'Contributor',
35-
'Rights',
36-
'Date',
37-
'Format',
38-
'Identifier',
39-
'Language']
40-
41-
[Repositories]
42-
#Name in plugin, name in tag
43-
oai-pmh = 'Evaluator'
44-
digital_csic = 'Digital.CSIC'
45-
dspace7 = 'DSpace7'
46-
epos= 'epos'
47-
example_plugin = Example_Plugin
48-
signposting = Signposting
49-
ai4os = AI4OS
50-
51-
[vocabularies:iana_media_types]
52-
enable_remote_check = True
53-
property_key_xml = {http://www.iana.org/assignments}file
54-
remote_path = https://www.iana.org/assignments/media-types/media-types.xml
55-
local_path = static/controlled_vocabularies/IANA-media-types.xml
56-
57-
[vocabularies:fairsharing]
58-
enable_remote_check = True
59-
remote_username =
60-
remote_password =
61-
remote_path = https://api.fairsharing.org/search/fairsharing_records
62-
local_path = static/controlled_vocabularies/fairsharing.json
63-
64-
[dspace7]
65-
base_url = http://localhost:8080/server/
66-
67-
# Metadata terms to find the resource identifier
68-
identifier_term = ['identifier']
69-
70-
# Metadata terms to check richness (generic). These terms should be included [term, qualifier]. None means no qualifier
71-
terms_quali_generic = [['contributor',None],
72-
['date', None],
73-
['description', None],
74-
['identifier', None],
75-
['publisher', None],
76-
['rights', None],
77-
['title', None],
78-
['subject', None]]
79-
80-
# Metadata terms to check richness (disciplinar). These terms should be included [term, qualifier]
81-
terms_quali_disciplinar = [['contributor', None],
82-
['date', None],
83-
['description', None],
84-
['identifier', None],
85-
['publisher', None],
86-
['rights', None],
87-
['title', None],
88-
['subject', None]]
89-
90-
# Metadata terms that defines accessibility
91-
terms_access = [['access', ''], ['rights', '']]
92-
93-
# Metadata terms wich includes controlled vocabularies. More controlled vocabularies can be imlpemented in plugins
94-
terms_cv = [['coverage', 'spatial'], ['subject', 'lcsh']]
95-
96-
# List of data formats that are standard for the community
97-
supported_data_formats = [".txt", ".pdf", ".csv", ".nc", ".doc", ".xls", ".zip", ".rar", ".tar", ".png", ".jpg"]
98-
99-
# Metadata terms that defines links or relation with authors, contributors (preferebly in ORCID format)
100-
terms_qualified_references = ['contributor']
101-
102-
# Metadata terms that defines links or relation with other resources, (preferebly in ORCID format, URIs or persistent identifiers)
103-
terms_relations = ['relation']
104-
105-
# Metadata terms that defines the license type
106-
terms_license = [['license', '', '']]
107-
108-
#Metadata chemas to check
109-
metadata_schemas = [{'dc': 'http://www.openarchives.org/OAI/2.0/oai_dc/'}]
110-
111-
[digital_csic]
112-
db_host =
113-
db_port =
114-
oai_ep =
115-
116-
[oai-pmh]
117-
# Metadata terms to find the resource identifier
118-
identifier_term = ['identifier']
119-
120-
# Metadata terms to check richness (generic). These terms should be included [term, qualifier]. None means no qualifier
121-
terms_quali_generic = [['contributor', None],
122-
['date', None],
123-
['description', None],
124-
['identifier', None],
125-
['publisher', None],
126-
['rights', None],
127-
['title', None],
128-
['subject', None]]
129-
130-
# Metadata terms to check richness (disciplinar). These terms should be included [term, qualifier]
131-
terms_quali_disciplinar = [['contributor', None],
132-
['date', None],
133-
['description', None],
134-
['identifier', None],
135-
['publisher', None],
136-
['rights', None],
137-
['title', None],
138-
['subject', None]]
139-
140-
# Metadata terms that defines accessibility
141-
terms_access = [['access', ''], ['rights', '']]
142-
143-
# Metadata terms wich includes controlled vocabularies. More controlled vocabularies can be imlpemented in plugins
144-
terms_cv = [['coverage', 'spatial'], ['subject', 'lcsh']]
145-
146-
# List of data formats that are standard for the community
147-
supported_data_formats = [".txt", ".pdf", ".csv", ".nc", ".doc", ".xls", ".zip", ".rar", ".tar", ".png", ".jpg"]
148-
149-
# Metadata terms that defines links or relation with authors, contributors (preferebly in ORCID format)
150-
terms_qualified_references = ['contributor']
151-
152-
# Metadata terms that defines links or relation with other resources, (preferebly in ORCID format, URIs or persistent identifiers)
153-
terms_relations = ['relation']
154-
155-
# Metadata terms that defines the license type
156-
terms_license = [['license', '', '']]
157-
158-
metadata_schemas = [{'xml': 'http://datacite.org/schema/kernel-4'}]
159-
160-
[epos]
161-
# Metadata terms to find the resource identifier
162-
identifier_term = [['id'],]
163-
164-
#DOI
165-
doi= [['DOI'],]
166-
167-
# Metadata terms to check richness (generic). These terms should be included [term, qualifier]. None means no qualifier
168-
terms_quali_generic = [['paths', 'serviceSpatial'],
169-
['startDate', 'serviceTemporalCoverage'],
170-
['serviceDescription', None],
171-
['hasQualityAnnotation', None],
172-
['dataProvider', None],
173-
['license', None],
174-
['title', None],
175-
['keywords', None]]
176-
177-
# Metadata terms to check richness (disciplinar). These terms should be included [term, qualifier]
178-
terms_quali_disciplinar = [['paths', 'serviceSpatial'],
179-
['startDate', 'serviceTemporalCoverage'],
180-
['serviceDescription', None],
181-
['hasQualityAnnotation', None],
182-
['dataProvider', None],
183-
['license', None],
184-
['title', None],
185-
['keywords', None]]
186-
187-
# Metadata terms that defines accessibility
188-
terms_access = [['downloadURL','']]
1+
[ai4os]
2+
#
3+
# Configuration for the AI4EOSC plugin. These values are used by the
4+
# Evaluator to determine which metadata elements contribute to the FAIR
5+
# indicators of richness, accessibility, interoperability and reuse.
1896

190-
# Metadata terms wich includes controlled vocabularies. More controlled vocabularies can be imlpemented in plugins
191-
terms_cv = [['coverage', 'spatial'], ['subject', 'lcsh']]
7+
identifier_term = [['title',''],]
8+
identifier_term_data = [['title', None]]
1929

193-
# List of data formats that are standard for the community
194-
supported_data_formats = [".txt", ".pdf", ".csv", ".nc", ".doc", ".xls", ".zip", ".rar", ".tar", ".png", ".jpg"]
195-
196-
# Metadata terms that defines links or relation with authors, contributors (preferebly in ORCID format)
197-
terms_qualified_references = ['contributor']
198-
199-
# Metadata terms that defines links or relation with other resources, (preferebly in ORCID format, URIs or persistent identifiers)
200-
terms_relations = ['dataProviderUrl','frequencyUpdate']
201-
202-
# Metadata terms that defines the license type
203-
terms_license = [['license', '', '']]
204-
205-
[example_plugin]
206-
base_url = localhost
10+
# Generic metadata terms that should be present to satisfy richness
11+
terms_quali_generic = [
12+
['title', None],
13+
['summary', None],
14+
['description', None],
15+
['tags', None],
16+
['libraries', None],
17+
['tasks', None]]
18+
# Disciplinary-specific richness terms (reuse generic for now)
19+
terms_quali_disciplinar = [
20+
['title', None],
21+
['summary', None],
22+
['description', None]]
23+
# Terms that provide access to (meta)data
24+
terms_access = [['links','source_code'], ['links','weights']]
25+
# Controlled vocabulary terms (libraries and tasks are often drawn from
26+
# controlled lists in AI4EOSC)
27+
terms_cv = [
28+
['provenance', None]]
29+
# Formats commonly used for AI models and datasets in AI4EOSC
30+
supported_data_formats = ['.zip', '.tar', '.pth', '.h5', '.onnx', '.pt']
31+
32+
# Terms linking to qualified references (e.g. other resources)
33+
terms_qualified_references = [['links', None]]
34+
35+
# Terms describing relations with other resources
36+
terms_relations = [['prov_hadMember', None]]
37+
38+
# Terms that define licensing information
39+
terms_license = [['license', '']]
40+
41+
# Metadata schemas applicable to AI4EOSC modules
42+
metadata_schemas = [{'ai4os': 'https://docs.ai4os.eu/en/latest/metadata.html'}]
43+
44+
metadata_access_manual = ['https://github.com/ai4os-eu/']
45+
data_access_manual = ['https://dashboard.cloud.ai4eosc.eu/catalog/modules']
46+
terms_access_protocols =['http','https']
47+
dict_vocabularies= {'ROR': 'https://ror.org/', 'PIC': 'https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/how-to-participate/participant-register', 'imtypes': 'https://www.iana.org/assignments/media-types/media-types.xhtml', 'TRL': 'TRL', 'temporal': 'https://www.iso.org/iso-8601-date-and-time-format.html', 'Rolecode': 'Rolecode', 'spdx': 'https://spdx.org/licenses/', 'ORCID': 'https://orcid.org/'}
48+
49+
metadata_standard = ['PROV-Ontology', 'DCAT-AP', 'DCAT-AP-ES']
50+
metadata_authentication = ['Open']
51+
52+
metadata_persistence = []
53+
54+
terms_vocabularies = [
55+
['license', ''],
56+
['description', ]]
57+
58+
terms_reusability_richness = [['links','source_code'],
59+
['links','docker_image'],
60+
['links','ai4_template'],
61+
['links','dataset']]
62+
63+
[fairsharing]
64+
# username and password
65+
username = ['']
66+
67+
password = ['']
68+
69+
#_path is variable that stores the path to the file in which the fairsharing-approved metadatata standards or formasts are stored
70+
71+
metadata_path = ['static/fairsharing_metadata_standards20240214.json']
72+
73+
formats_path = ['static/fairsharing_formats20240226.txt']
74+
75+
76+
77+
[internet media types]
78+
#path to internet media files file
79+
path = ['static/internetmediatypes190224.csv']

0 commit comments

Comments
 (0)