Update display of alumni (OBOFoundry#2150)

* Add alumni updater

* Add additional alumni metadata

Closes OBOFoundry#2134 and automatically enriches information from wikidata

Co-Authored-By: Jim Balhoff <[email protected]>
Co-Authored-By: Bill Duncan <[email protected]>

* Improve alumni display

* Update update_operations_metadata.py

* Update

* Update cli.py

* Make github tag optional

* Update alumni.yml

Co-authored-by: Jim Balhoff <[email protected]>
Co-authored-by: Bill Duncan <[email protected]>

Author: 3 people

_data/alumni.yml

@@ -1,35 +1,61 @@
 members:
 - name: Michael Ashburner
   orcid: 0000-0002-6962-2807
-- name: Colin Batchelor
+  wikidata: Q6828277
+- github: batchelorc
+  name: Colin Batchelor
   orcid: 0000-0001-5985-7429
-- name: Mathias Brochhausen
+  wikidata: Q28923515
+- github: mbrochhausen
+  name: Mathias Brochhausen
   orcid: 0000-0003-1834-3856
-- name: Melanie Courtot
+  wikidata: Q57161944
+- github: mcourtot
   link: http://purl.org/net/mcourtot
+  name: Melanie Courtot
   orcid: 0000-0002-9551-6370
-- name: Eric Douglass
-- name: Janna Hastings
+  wikidata: Q23809262
+- github: dougli1sqrd
+  name: Eric Douglass
+  orcid: 0000-0001-6946-1807
+  wikidata: Q114403167
+- github: jannahastings
+  name: Janna Hastings
   orcid: 0000-0002-3469-4923
-- name: Simon Jupp
+  wikidata: Q27902110
+- github: simonjupp
+  name: Simon Jupp
   note: OBO Industry Liaison
   orcid: 0000-0002-0643-3144
-- name: Suzanna Lewis
+  wikidata: Q54303148
+- github: suzialeksander
   link: https://github.com/selewis
+  name: Suzanna Lewis
   orcid: 0000-0002-8343-612X
-- name: James Malone
+  wikidata: Q7650732
+- github: jamesmalone
+  name: James Malone
   note: OBO Industry Liaison
   orcid: 0000-0002-1615-2899
-- name: Gareth Owen
-- name: Susanna-Assunta Sansone
+  wikidata: Q47502894
+- github: G-Owen
+  name: Gareth Owen
+  orcid: 0000-0001-7265-5776
+  wikidata: Q55095454
+- github: SusannaSansone
+  name: Susanna-Assunta Sansone
   orcid: 0000-0001-5306-5690
-- name: Carlo Tornial
+  wikidata: Q28913668
+- github: carlotorniai
+  name: Carlo Tornial
+  orcid: 0000-0002-3734-1859
+  wikidata: Q114403193
 - affiliation: La Jolla Institute for Immunology, La Jolla, CA
   country: USA
+  departed: 2022-10-04
   github: hectorguzor
   groups:
   - outreach
   name: Hector Guzman-Orozco
   orcid: 0000-0003-3430-8997
   wikidata: Q114354576
-  departed: 2022-10-04

docs/Membership.md

@@ -47,14 +47,19 @@ New members: follow the instructions on the [onboarding doc](https://docs.google
 <tr>
     <th role="columnheader">Name</th>
     <th role="columnheader">ORCID</th>
+    <th role="columnheader">GitHub</th>
+    <th role="columnheader">Departed</th>
     <th role="columnheader">Note</th>
 </tr>
 </thead>
 <tbody>
-{% for member in site.data.alumni.members %}
+{% assign alumni_members = site.data.alumni.members | sort: "name" %}
+{% for member in alumni_members %}
 <tr>
     <td>{% if member.link %}<a href="{{ member.link }}">{{ member.name }}</a>{% else %}{{ member.name }}{% endif %}</td>
-    <td>{% if member.orcid %}<a href="https://orcid.org/{{ member.orcid }}">{{ member.orcid }}</a>{% endif %}</td>
+    <td><a href="https://orcid.org/{{ member.orcid }}">{{ member.orcid }}</a></td>
+    <td>{% if member.github %}<a href="https://github.com/{{ member.github }}">{{ member.github }}</a>{% endif %}</td>
+    <td>{% if member.departed %}{{ member.departed }}{% endif %}</td>
     <td>{% if member.note %}{{ member.note }}{% endif %}</td>
 </tr>
 {% endfor %}

src/obofoundry/cli.py

@@ -13,7 +13,7 @@
 
 import click
 
-from . import update_operations_metadata
+from . import standardize_metadata, update_operations_metadata
 
 __all__ = [
     "main",
@@ -25,6 +25,7 @@ def main():
     """CLI for the OBO Foundry."""
 
 
+main.add_command(standardize_metadata.main)
 main.add_command(update_operations_metadata.main)
 
 if __name__ == "__main__":

src/obofoundry/constants.py

@@ -8,3 +8,4 @@
 DATA_DIRECTORY = ROOT.joinpath("_data")
 #: Path to the file containing metadata about members of the OBO Operations Committee
 OPERATIONS_METADATA_PATH = DATA_DIRECTORY.joinpath("operations.yml")
+ALUMNI_METADATA_PATH = DATA_DIRECTORY.joinpath("alumni.yml")

src/obofoundry/update_operations_metadata.py

@@ -1,33 +1,25 @@
 """Run this script to update the operations metadata."""
 
+from pathlib import Path
 from textwrap import dedent
 
 import click
-import requests
 import yaml
 from tqdm import tqdm
 
-from obofoundry.constants import OPERATIONS_METADATA_PATH
-
-#: WikiData SPARQL endpoint. See https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service#Interfacing
-WIKIDATA_SPARQL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql"
-
-
-def query_wikidata(query: str):
-    """Query the Wikidata SPARQL endpoint and return JSON."""
-    res = requests.get(
-        WIKIDATA_SPARQL,
-        params={"query": query, "format": "json"},
-    )
-    res.raise_for_status()
-    res_json = res.json()
-    return res_json["results"]["bindings"]
+from obofoundry.constants import ALUMNI_METADATA_PATH, OPERATIONS_METADATA_PATH
+from obofoundry.utils import query_wikidata
 
 
 @click.command(name="update-operations-metadata")
 def main():
     """Update the operations committee members metadata file by querying Wikidata."""
-    operations_metadata = yaml.safe_load(OPERATIONS_METADATA_PATH.read_text())
+    _main(ALUMNI_METADATA_PATH)
+    _main(OPERATIONS_METADATA_PATH)
+
+
+def _main(path: Path):
+    operations_metadata = yaml.safe_load(path.read_text())
     for member in tqdm(operations_metadata["members"]):
         orcid = member["orcid"]
         if "wikidata" not in member or "github" not in member:
@@ -51,7 +43,7 @@ def main():
                 github = res[0].get("github")
                 if github:
                     member["github"] = github["value"]
-            OPERATIONS_METADATA_PATH.write_text(
+            path.write_text(
                 yaml.safe_dump(
                     operations_metadata,
                     sort_keys=True,

src/obofoundry/utils.py

@@ -1,11 +1,13 @@
 """Test data integrity, beyond what's possible with the JSON schema."""
 
+import requests
 import yaml
 
 from obofoundry.constants import ONTOLOGY_DIRECTORY
 
 __all__ = [
     "get_data",
+    "query_wikidata",
 ]
 
 
@@ -24,3 +26,18 @@ def get_data():
         data["long_description"] = "".join(lines[idx:])
         ontologies[data["id"]] = data
     return ontologies
+
+
+#: WikiData SPARQL endpoint. See https://www.wikidata.org/wiki/Wikidata:SPARQL_query_service#Interfacing
+WIKIDATA_SPARQL = "https://query.wikidata.org/bigdata/namespace/wdq/sparql"
+
+
+def query_wikidata(query: str):
+    """Query the Wikidata SPARQL endpoint and return JSON."""
+    headers = {"User-Agent": "obofoundry/1.0 (https://obofoundry.org)"}
+    res = requests.get(
+        WIKIDATA_SPARQL, params={"query": query, "format": "json"}, headers=headers
+    )
+    res.raise_for_status()
+    res_json = res.json()
+    return res_json["results"]["bindings"]

tests/test_memberships.py

@@ -8,6 +8,8 @@
 import yaml
 from pydantic import BaseModel
 
+from obofoundry.constants import ALUMNI_METADATA_PATH, OPERATIONS_METADATA_PATH
+
 HERE = Path(__file__).parent.resolve()
 ROOT = HERE.parent.resolve()
 DATA = ROOT.joinpath("_data")
@@ -36,9 +38,16 @@ class TestMembershipData(unittest.TestCase):
 
     def test_data(self):
         """Test the working group data is clean."""
-        path = DATA.joinpath("operations").with_suffix(".yml")
-        res = Group.parse_obj(yaml.safe_load(path.read_text()))
+        res = Group.parse_obj(yaml.safe_load(OPERATIONS_METADATA_PATH.read_text()))
         self.assertIsNotNone(res)
         counter = Counter(member.orcid for member in res.members if member.orcid)
         counter = {orcid for orcid, count in counter.items() if count > 1}
         self.assertEqual(0, len(counter), msg=f"Duplicate: {counter}")
+
+    def test_alumni(self):
+        """Test the alumni data."""
+        data = yaml.safe_load(ALUMNI_METADATA_PATH.read_text())["members"]
+        for i, member in enumerate(data):
+            with self.subTest(row=i):
+                self.assertIn("name", member)
+                self.assertIn("orcid", member)

tox.ini

@@ -14,6 +14,7 @@ envlist =
     py
 
 [testenv]
+usedevelop = true
 extras =
     tests
 commands =