Set sulpub pmid column to string

sul-dlss-labs · Jul 18, 2024 · 5259179 · 5259179
1 parent a27a5a5
commit 5259179
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/rialto_airflow/harvest/merge_pubs.py b/rialto_airflow/harvest/merge_pubs.py
@@ -88,7 +88,7 @@ def sulpub_df(sul_pub):
     """
     Create a sulpub LazyFrame and rename columns
     """
-    df = pl.scan_csv(sul_pub, schema_overrides={"year": pl.String})
+    df = pl.scan_csv(sul_pub, schema_overrides={"year": pl.String, "pmid": pl.String})
     df = df.drop_nulls("doi")
     df = df.with_columns(
         pl.col("doi").map_elements(normalize_doi, return_dtype=pl.String)