DataFusion evaluates -0.0 >= 0.0 as false #22490

#!/usr/bin/env python3

from __future__ import annotations

import datafusion
import duckdb
import pyarrow as pa
from datafusion import SessionContext


def main() -> None:
    python_cmp = (-0.0 >= 0.0)
    duckdb_cmp = duckdb.connect(database=":memory:").execute(
        "SELECT (-0.0 >= 0.0)"
    ).fetchone()[0]

    ctx = SessionContext()
    batch = pa.RecordBatch.from_pylist(
        [{"id": 1, "y": 0.0}],
        schema=pa.schema([
            pa.field("id", pa.int64()),
            pa.field("y", pa.float64(), nullable=True),
        ]),
    )
    ctx.register_record_batches("t0", [[batch]])

    diagnostic = ctx.sql(
        "SELECT id, y * -1 AS m_0, (y * -1) >= 0.0 AS cmp FROM t0"
    ).to_pandas()

    filtered = ctx.sql(
        "SELECT id, y * -1 AS m_0 "
        "FROM t0 "
        "WHERE NOT (((y * -1) >= 0.0) IS TRUE)"
    ).to_pandas()

    print(f"datafusion={getattr(datafusion, '__version__', 'unknown')}")
    print(f"pyarrow={pa.__version__}")
    print(f"duckdb={duckdb.__version__}")

    print(f"python comparison: {python_cmp!r}")
    print(f"duckdb comparison: {duckdb_cmp!r}")

    print("datafusion diagnostic:")
    print(diagnostic)

    print("datafusion filtered rows:")
    print(filtered)

    assert python_cmp is True
    assert duckdb_cmp is True
    assert bool(diagnostic.iloc[0]["cmp"]) is True
    assert len(filtered) == 0


if __name__ == "__main__":
    main()