From 7af45f9eeaf0ac221ca2383cc3829882c7ac9abc Mon Sep 17 00:00:00 2001
From: Anas Khan <83116240+anxkhn@users.noreply.github.com>
Date: Mon, 29 Jun 2026 07:00:49 +0530
Subject: [PATCH] feat: support pyarrow float16 by widening to float on
 read/write

PyArrow's float16 (halffloat) raised UnsupportedPyArrowTypeException
during schema conversion because _ConvertToIceberg.primitive only
handled float32/float64. Iceberg has no half-precision float, but
float16 -> float32 is lossless, mirroring how int8/int16 already widen
to IntegerType. Map float16 to FloatType, and widen smaller float arrays
to the target type in ArrowProjectionVisitor._cast_if_needed (parallel
to the integer-widening branch) so float16 columns write as float32.
---
 pyiceberg/io/pyarrow.py          | 12 ++++++++++++
 tests/io/test_pyarrow.py         | 29 +++++++++++++++++++++++++++++
 tests/io/test_pyarrow_visitor.py |  6 ++++++
 3 files changed, 47 insertions(+)

diff --git a/pyiceberg/io/pyarrow.py b/pyiceberg/io/pyarrow.py
index 6259f311e9..45a6c00513 100644
--- a/pyiceberg/io/pyarrow.py
+++ b/pyiceberg/io/pyarrow.py
@@ -1438,6 +1438,9 @@ def primitive(self, primitive: pa.DataType) -> PrimitiveType:
             else:
                 # Does not exist (yet)
                 raise TypeError(f"Unsupported integer type: {primitive}")
+        elif pa.types.is_float16(primitive):
+            # Iceberg has no half-precision float; widen to single precision (lossless)
+            return FloatType()
         elif pa.types.is_float32(primitive):
             return FloatType()
         elif pa.types.is_float64(primitive):
@@ -1978,6 +1981,15 @@ def _cast_if_needed(self, field: NestedField, values: pa.Array) -> pa.Array:
                         target_width = target_type.bit_width
                         if source_width < target_width:
                             return values.cast(target_type)
+                elif isinstance(field.field_type, (FloatType, DoubleType)):
+                    # Cast smaller float types to target type for cross-platform compatibility
+                    # Only allow widening conversions (smaller bit width to larger), e.g. float16 -> float32
+                    # Narrowing conversions fall through to promote() handling below
+                    if pa.types.is_floating(values.type):
+                        source_width = values.type.bit_width
+                        target_width = target_type.bit_width
+                        if source_width < target_width:
+                            return values.cast(target_type)
 
             if field.field_type != file_field.field_type:
                 target_schema = schema_to_pyarrow(
diff --git a/tests/io/test_pyarrow.py b/tests/io/test_pyarrow.py
index 532311899d..dde3547350 100644
--- a/tests/io/test_pyarrow.py
+++ b/tests/io/test_pyarrow.py
@@ -3109,6 +3109,35 @@ def test__to_requested_schema_integer_promotion(
     assert result.column(0).to_pylist() == [1, 2, 3, None]
 
 
+@pytest.mark.parametrize(
+    "arrow_type,iceberg_type,expected_arrow_type",
+    [
+        (pa.float16(), FloatType(), pa.float32()),
+        (pa.float16(), DoubleType(), pa.float64()),
+        (pa.float32(), DoubleType(), pa.float64()),
+    ],
+)
+def test__to_requested_schema_float_promotion(
+    arrow_type: pa.DataType,
+    iceberg_type: PrimitiveType,
+    expected_arrow_type: pa.DataType,
+) -> None:
+    """Test that smaller float types are cast to target Iceberg type during write."""
+    requested_schema = Schema(NestedField(1, "col", iceberg_type, required=False))
+    file_schema = requested_schema
+
+    arrow_schema = pa.schema([pa.field("col", arrow_type)])
+    data = pa.array([1.5, 2.25, 3.0, None], type=arrow_type)
+    batch = pa.RecordBatch.from_arrays([data], schema=arrow_schema)
+
+    result = _to_requested_schema(
+        requested_schema, file_schema, batch, downcast_ns_timestamp_to_us=False, include_field_ids=False
+    )
+
+    assert result.schema[0].type == expected_arrow_type
+    assert result.column(0).to_pylist() == [1.5, 2.25, 3.0, None]
+
+
 def test_pyarrow_file_io_fs_by_scheme_cache() -> None:
     # It's better to set up multi-region minio servers for an integration test once `endpoint_url` argument
     # becomes available for `resolve_s3_region`
diff --git a/tests/io/test_pyarrow_visitor.py b/tests/io/test_pyarrow_visitor.py
index 6727b8c768..e98d76e262 100644
--- a/tests/io/test_pyarrow_visitor.py
+++ b/tests/io/test_pyarrow_visitor.py
@@ -128,6 +128,12 @@ def test_pyarrow_int64_to_iceberg() -> None:
     assert visit(converted_iceberg_type, _ConvertToArrowSchema()) == pyarrow_type
 
 
+def test_pyarrow_float16_to_iceberg() -> None:
+    pyarrow_type = pa.float16()
+    converted_iceberg_type = visit_pyarrow(pyarrow_type, _ConvertToIceberg())
+    assert converted_iceberg_type == FloatType()
+
+
 def test_pyarrow_float32_to_iceberg() -> None:
     pyarrow_type = pa.float32()
     converted_iceberg_type = visit_pyarrow(pyarrow_type, _ConvertToIceberg())