Merge pull request #252 from IFCA-Advanced-Computing/dev/gbif

Improving GBIF

Author: ferag

.pre-commit-config.yaml

@@ -5,7 +5,7 @@ repos:
   - id: trailing-whitespace
   - id: end-of-file-fixer
   - id: check-yaml
-  - id: check-added-large-files
+  # - id: check-added-large-files
 - repo: https://github.com/psf/black-pre-commit-mirror
   rev: 24.3.0
   hooks:

api/evaluator.py

@@ -1794,14 +1794,16 @@ def rda_r1_3_01d(self, **kwargs):
         terms_reusability_richness_list = terms_reusability_richness["list"]
         terms_reusability_richness_metadata = terms_reusability_richness["metadata"]
 
-        element = terms_reusability_richness_metadata.loc[
-            terms_reusability_richness_metadata["element"].isin(["availableFormats"]),
-            "text_value",
-        ].values[0]
-        for form in element:
-            availableFormats.append(form["label"])
-
         try:
+            element = terms_reusability_richness_metadata.loc[
+                terms_reusability_richness_metadata["element"].isin(
+                    ["availableFormats"]
+                ),
+                "text_value",
+            ].values[0]
+            for form in element:
+                availableFormats.append(form["label"])
+
             f = open(path)
             f.close()
 

api/utils.py

@@ -577,10 +577,10 @@ def orcid_basic_info(orcid):
         item = xmlTree.findall(
             ".//{http://www.orcid.org/ns/common}assertion-origin-name"
         )
+        basic_info = "ORCID Name: %s" % item[0].text
     except Exception as e:
         logging.error(e)
         return basic_info
-    basic_info = "ORCID Name: %s" % item[0].text
     return basic_info
 
 

plugins/gbif/config.ini

@@ -1,51 +1,99 @@
 [Generic]
 doi_url = https://doi.org/
+# Relative path to the API config file
 api_config = fair-api.yaml
-endpoint= https://api.gbif.org/v1
+endpoint=https://api.gbif.org/v1/
+
 [local]
 only_local = false
 repo = digital_csic
+logo_url = 'https://ifca.unican.es'
+title = FAIR EVA: Evaluator, Validator & Advisor
 
 [Repositories]
 #Name in plugin, name in tag
 oai-pmh = 'Evaluator'
 digital_csic = 'Digital.CSIC'
 dspace7 = 'DSpace7'
+epos= 'epos'
 example_plugin = Example_Plugin
-gbif = 'Plugin'
+signposting = Signposting
+gbif = 'gbif'
+
+[dublin-core]
+# Aligned with Dublin Core Metadata for Resource Discovery (properties in the /elements/1.1/ namespace)
+# https://www.dublincore.org/specifications/dublin-core/dcmi-terms/#section-3
+terms_findability_richness = ['Title',
+                              'Subject',
+                              'Description',
+                              'Type',
+                              'Source',
+                              'Relation',
+                              'Coverage',
+                              'Creator',
+                              'Publisher',
+                              'Contributor',
+                              'Rights',
+                              'Date',
+                              'Format',
+                              'Identifier',
+                              'Language']
 
 [gbif]
-# Metadata terms to find the resource identifier
-identifier_term = [['alternateIdentifier','']]
-
-# Metadata terms to find the data identifier
-identifier_term_data = [['alternateIdentifier','']]
+# (meta)data terms to find the resource identifier
+identifier_term = [['dataset','alternateIdentifier']]
+identifier_term_data = [['dataset','alternateIdentifier']]
 
 # Metadata terms to check richness (generic). These terms should be included [term, qualifier]. None means no qualifier
-terms_quali_generic = [['contributor',None],
-                       ['date', None],
-                       ['description', None],
-                       ['identifier', None],
-                       ['publisher', None],
-                       ['rights', None],
-                       ['title', None],
-                       ['subject', None]]
+terms_quali_generic = [['dataset.creator', 'givenName'],
+                       ['dataset.creator', 'surName'],
+                       ['dataset', 'pubDate'],
+                       ['dataset.abstract', 'para'],
+                       ['dataset.intellectualRights.para.ulink', 'citetitle'],
+                       ['dataset', 'title'],
+                       ['dataset.keywordSet', 'keyword']]
 
 # Metadata terms to check richness (disciplinar). These terms should be included [term, qualifier]
-terms_quali_disciplinar = [['contributor', None],
-                           ['date', None],
-                           ['description', None],
-                           ['identifier', None],
-                           ['publisher', None],
-                           ['rights', None],
-                           ['title', None],
-                           ['subject', None]]
-
-# Metadata terms that defines accessibility
-terms_access = [['access', ''], ['rights', '']]
+terms_quali_disciplinar = [['dataset.coverage.geographicCoverage', 'geographicDescription'],
+                           ['dataset.coverage.temporalCoverage.rangeOfDates.beginDate', 'calendarDate'],
+                           ['dataset.coverage.temporalCoverage.rangeOfDates.endDate', 'calendarDate'],
+                           ['dataset.coverage.taxonomicCoverage.taxonomicClassification', 'taxonRankValue']]
+
+# Metadata terms that defines accessibility (case sensitive)
+terms_access = [['dataset.intellectualRights.para.ulink', 'citetitle']]
+
+# Metadata terms to check discoverability richness.
+#
+# Dublin Core element   DT-GEO element                          EPOS element
+# -------------------   --------------                          ------------
+# Title                 Name                                    title
+# Subject               Keywords                                keywords
+# Description           Description                             description
+# Type                  Type                                    type
+# Source                Related DA (relationship)               NA
+# Relation              Related DA                              NA
+# Coverage              Spatial relevance, Temporal relevance   spatial, temporalCoverage
+# Creator               Organisation/Person role                NA
+# Publisher             Organisation (name)                     serviceProvider
+# Contributor           Organisation/Person role                NA
+# Rights                Licensing constraints                   license
+# Date                  Temporal relevance                      temporalCoverage
+# Format                File format                             availableFormats
+# Identifier            Data Unique ID                          DOI
+# Language              NA                                      NA
+terms_findability_richness = [['dataset', 'title']],
+                              ['dataset.keywordSet', 'keyword'],
+                              ['dataset.abstract', 'para'],
+                              ['dataset.coverage.geographicCoverage', 'geographicDescription'],
+                              ['dataset.coverage.temporalCoverage.rangeOfDates.beginDate', 'calendarDate'],
+                              ['dataset.coverage.temporalCoverage.rangeOfDates.endDate', 'calendarDate'],
+                              ['dataset.intellectualRights.para.ulink', 'citetitle'],
+                              ['dataset','alternateIdentifier']]
+
+# Metadata terms to check reusability richness
+terms_reusability_richness = [['dataset','alternateIdentifier'],
+                              ['additionalMetadata.metadata.gbif', 'hierarchyLevel']]
 
-# Accepted access protocols
-terms_access_protocols =['http','https','ftp']
 
 # Manual metadata access
 metadata_access_manual = ['TODO']
@@ -72,47 +120,76 @@ terms_vocabularies=[['identifiers','relatedDataProducts'],
                    ['contactPoints','relatedDataProducts']]
 
 # Metadata terms wich includes controlled vocabularies. More controlled vocabularies can be imlpemented in plugins
-terms_cv = [['coverage', 'spatial'], ['subject', 'lcsh']]
+terms_cv = [['dataset.creator', 'userId']]
 
 # List of data formats that are standard for the community
 supported_data_formats = [".txt", ".pdf", ".csv", ".nc", ".doc", ".xls", ".zip", ".rar", ".tar", ".png", ".jpg"]
 
 # Metadata terms that defines links or relation with authors, contributors (preferebly in ORCID format)
-terms_qualified_references = [['contributor', None]]
+terms_qualified_references = [['dataset.creator', 'userId'],
+                              ['dataset.contact', 'userId'],
+                              ['dataset.project.personnel', 'userId'],
+                              ['dataset.metadataProvider', 'userId' ]]
 
 # Metadata terms that defines links or relation with other resources, (preferebly in ORCID format, URIs or persistent identifiers)
-terms_relations = [['relation', None]]
-
-# Metadata terms to check reusability richness
-terms_reusability_richness = [['rigths',''],
-                              ['license','']]
+terms_relations = [['dataset.creator', 'userId']]
 
 # Metadata terms that defines the license type
-terms_license = [['rights', '']]
+terms_license = [['dataset.intellectualRights.para.ulink', 'citetitle']]
+
+# Metadata terms that defines metadata about provenance
+terms_provenance =[['curationAndProvenanceObligations','']]
 
-metadata_schemas = [{'eml': 'eml://ecoinformatics.org/eml-2.1.1'}]
+# Accepted access protocols
+terms_access_protocols =['http','https','ftp']
+
+# Manual metadata access
+metadata_access_manual = ['https://techdocs.gbif.org/en/openapi/']
+
+# Manual data access
+data_access_manual = ['https://techdocs.gbif.org/en/openapi/']
+
+# Data model information
+terms_data_model = []
 
 #metadata standard
 metadata_standard = ['XML']
 
-# Api auth
-api_mail = [email protected]
-api_user = mag848
-api_pass = stcDPwfQfrnwiQsHNMPRKV7RY
+
+#Policy of metadata persistence
+metadata_persistence = []
+
+#Authentication for EPOS
+metadata_authentication = []
+
+#terms that use vocabularies and vocabularies used
+dict_vocabularies= {'ORCID': 'https://orcid.org/'}
+
+terms_vocabularies=[['identifiers','relatedDataProducts'],
+                   ['',''],
+                   ['availableFormats',''],
+                   ['',''],
+                   ['temporalCoverage','relatedDataProducts'],#no temporal metatdata
+                   ['',''],
+                   ['license',''],
+                   ['contactPoints','relatedDataProducts']]
+
+api_mail =
+api_user =
+api_pass =
+
 
 [fairsharing]
 # username and password
 username = ['']
 
 password = ['']
-#Path is the folder path ehere the netadata or fomats is stored
-#Or if the username or password is given is what you are looking in
-metadata_path = ['static/fairsharing_metadata_standards140224.json']
 
-formats_path = ['static/fairsharing_formats260224.txt']
+#_path is variable that stores the path to the file in which the fairsharing-approved metadatata standards or formasts are stored
 
+metadata_path = ['static/fairsharing_metadata_standards20240214.json']
 
-fairsharing_formats_path = ['static/fairsharing_formats150224.json']
+formats_path = ['static/fairsharing_formats20240226.txt']