Merge pull request #38 from sul-dlss-labs/t22-rialto-orgs-orcids

Get rialto orgs author ORCIDs

README.md

@@ -59,6 +59,9 @@ for i in `vault kv list -format yaml puppet/application/rialto-airflow/dev | sed
 done
 ```
 
+5. The harvest DAG requires a CSV file of authors from rialto-orgs to be available. This is not yet automatically available, so to set up locally, download the file at
+https://sul-rialto-dev.stanford.edu/authors?action=index&commit=Search&controller=authors&format=csv&orcid_filter=&q=. Put the `authors.csv` file in the `data/` directory. 
+
 ## Development
 
 ### Set-up
@@ -76,6 +79,7 @@ This will create the virtual environment at the default location of `.venv/`. `u
 source .venv/bin/activate
 ```
 
+
 ### Install dependencies
 ```
 uv pip install -r requirements.txt

rialto_airflow/utils.py

@@ -1,5 +1,5 @@
+import csv
 import datetime
-
 from pathlib import Path
 
 
@@ -14,3 +14,22 @@ def create_snapshot_dir(data_dir):
     snapshot_dir.mkdir()
 
     return str(snapshot_dir)
+
+
+def rialto_authors_file(data_dir):
+    """Get the path to the rialto-orgs authors.csv"""
+    authors_file = Path(data_dir) / "authors.csv"
+
+    return authors_file
+
+
+def rialto_authors_orcids(rialto_authors_file):
+    """Extract the orcidid column from the authors.csv file"""
+    orcids = []
+    with open(rialto_authors_file, "r") as file:
+        reader = csv.reader(file)
+        header = next(reader)
+        orcidid = header.index("orcidid")
+        for row in reader:
+            orcids.append(row[orcidid])
+    return orcids

test/test_utils.py

@@ -1,8 +1,27 @@
+import csv
 from pathlib import Path
+import pytest
+from rialto_airflow.utils import create_snapshot_dir, rialto_authors_orcids
 
-from rialto_airflow.utils import create_snapshot_dir
+
+@pytest.fixture
+def authors_csv(tmp_path):
+    # Create a fixture authors CSV file
+    fixture_file = tmp_path / "authors.csv"
+    with open(fixture_file, "w", newline="") as csvfile:
+        writer = csv.writer(csvfile)
+        writer.writerow(["sunetid", "orcidid"])
+        writer.writerow(["author1", "https://orcid.org/0000-0000-0000-0001"])
+        writer.writerow(["author2", "https://orcid.org/0000-0000-0000-0002"])
+    return fixture_file
 
 
 def test_create_snapshot_dir(tmpdir):
     snap_dir = Path(create_snapshot_dir(tmpdir))
     assert snap_dir.is_dir()
+
+
+def test_rialto_authors_orcids(tmp_path, authors_csv):
+    orcids = rialto_authors_orcids(authors_csv)
+    assert len(orcids) == 2
+    assert "https://orcid.org/0000-0000-0000-0001" in orcids