chore: assert df index is unique before generating hash ID column (#644)

chanzuckerberg · Sep 26, 2023 · 40d56c8 · 40d56c8
1 parent 0cefd85
commit 40d56c8
Showing 1 changed file with 3 additions and 3 deletions.
diff --git a/cellxgene_schema_cli/cellxgene_schema/utils.py b/cellxgene_schema_cli/cellxgene_schema/utils.py
@@ -154,10 +154,10 @@ def get_hash_digest_column(dataframe):
     """
     Get column with hash digest for each row in dataframe.
     """
-
+    df_index = dataframe.index.to_series()
+    assert df_index.is_unique
     return (
-        dataframe.index.to_series()
-        .map(xxh3_64_intdigest)
+        df_index.map(xxh3_64_intdigest)
         .astype(np.uint64)
         .apply(lambda v: b85encode(v.to_bytes(8, "big")).decode("ascii"))
     )