fix(inspect): handle 4-byte bounds in _readable_bound after int/float type promotion (#3744)

pyiceberg/table/inspect.py

@@ -26,7 +26,7 @@
 from pyiceberg.manifest import DataFile, DataFileContent, ManifestContent, ManifestFile, PartitionFieldSummary
 from pyiceberg.partitioning import PartitionSpec
 from pyiceberg.table.snapshots import Snapshot, ancestors_of
-from pyiceberg.types import PrimitiveType
+from pyiceberg.types import DoubleType, FloatType, IntegerType, LongType, PrimitiveType
 from pyiceberg.utils.concurrent import ExecutorFactory
 from pyiceberg.utils.singleton import _convert_to_hashable_type
 
@@ -39,7 +39,13 @@
 
 
 def _readable_bound(field_type: PrimitiveType, bound: bytes | None) -> Any | None:
-    return from_bytes(field_type, bound) if bound is not None else None
+    if bound is None:
+        return None
+    if isinstance(field_type, LongType) and len(bound) == 4:
+        return from_bytes(IntegerType(), bound)
+    if isinstance(field_type, DoubleType) and len(bound) == 4:
+        return from_bytes(FloatType(), bound)
+    return from_bytes(field_type, bound)
 
 
 class InspectTable:
@@ -183,7 +189,6 @@ def _readable_metrics_struct(bound_type: PrimitiveType) -> pa.StructType:
                         "value_count": value_counts.get(field.field_id),
                         "null_value_count": null_value_counts.get(field.field_id),
                         "nan_value_count": nan_value_counts.get(field.field_id),
-                        # Makes them readable
                         "lower_bound": _readable_bound(field.field_type, lower_bounds.get(field.field_id)),
                         "upper_bound": _readable_bound(field.field_type, upper_bounds.get(field.field_id)),
                     }
@@ -420,7 +425,7 @@ def _partition_summaries_to_rows(
                 lower_bound = (
                     (
                         field.transform.to_human_string(
-                            partition_field_type, from_bytes(partition_field_type, field_summary.lower_bound)
+                            partition_field_type, _readable_bound(partition_field_type, field_summary.lower_bound)
                         )
                     )
                     if field_summary.lower_bound
@@ -429,7 +434,7 @@ def _partition_summaries_to_rows(
                 upper_bound = (
                     (
                         field.transform.to_human_string(
-                            partition_field_type, from_bytes(partition_field_type, field_summary.upper_bound)
+                            partition_field_type, _readable_bound(partition_field_type, field_summary.upper_bound)
                         )
                     )
                     if field_summary.upper_bound

tests/table/test_inspect.py

@@ -14,7 +14,6 @@
 # KIND, either express or implied.  See the License for the
 # specific language governing permissions and limitations
 # under the License.
-
 from pathlib import PosixPath
 
 import pyarrow as pa
@@ -23,7 +22,7 @@
 from pyiceberg.conversions import to_bytes
 from pyiceberg.schema import Schema
 from pyiceberg.table.inspect import _readable_bound
-from pyiceberg.types import NestedField, StringType
+from pyiceberg.types import DoubleType, LongType, NestedField, StringType
 from tests.catalog.test_base import InMemoryCatalog
 
 
@@ -68,3 +67,66 @@ def test_inspect_entries_and_files_render_null_bound(catalog: InMemoryCatalog) -
     files_metrics = tbl.inspect.files().to_pydict()["readable_metrics"][0]["s"]
     assert files_metrics["lower_bound"] is None
     assert files_metrics["upper_bound"] is None
+
+
+def test_readable_bound_type_promotions() -> None:
+    # 4-byte LE representation of integer 10 -> b'\x0a\x00\x00\x00'
+    four_byte_int_bound = b"\x0a\x00\x00\x00"
+
+    # 4-byte LE representation of float 10.0 -> b'\x00\x00\x20\x41'
+    four_byte_float_bound = b"\x00\x00\x20\x41"
+
+    # Test int -> long promotion decoding
+    assert _readable_bound(LongType(), four_byte_int_bound) == 10
+
+    # Test float -> double promotion decoding
+    assert _readable_bound(DoubleType(), four_byte_float_bound) == 10.0
+
+
+def test_inspect_files_type_promoted_bounds_e2e() -> None:
+    import shutil
+    import tempfile
+
+    import pyarrow as pa
+
+    from pyiceberg.catalog.sql import SqlCatalog
+    from pyiceberg.schema import Schema
+    from pyiceberg.types import IntegerType, LongType, NestedField, StringType
+
+    warehouse = tempfile.mkdtemp(prefix="iceberg_test_e2e_")
+    try:
+        catalog = SqlCatalog("test_e2e", uri=f"sqlite:///{warehouse}/catalog.db", warehouse=f"file://{warehouse}")
+        catalog.create_namespace("ns")
+
+        tbl = catalog.create_table(
+            "ns.t",
+            schema=Schema(
+                NestedField(1, "name", StringType(), required=False),
+                NestedField(2, "qty", IntegerType(), required=False),
+            ),
+        )
+
+        tbl.append(
+            pa.Table.from_pylist(
+                [{"name": "a", "qty": 10}],
+                schema=pa.schema([pa.field("name", pa.string()), pa.field("qty", pa.int32())]),
+            )
+        )
+
+        # Promote int -> long
+        with tbl.update_schema() as update:
+            update.update_column("qty", field_type=LongType())
+
+        tbl = catalog.load_table("ns.t")
+
+        # Test metadata inspection tables
+        files_df = tbl.inspect.files()
+        assert files_df.num_rows == 1
+
+        entries_df = tbl.inspect.entries()
+        assert entries_df.num_rows == 1
+
+        manifests_df = tbl.inspect.manifests()
+        assert manifests_df.num_rows >= 1
+    finally:
+        shutil.rmtree(warehouse, ignore_errors=True)