Merge branch 'main' of github.com:delta-io/delta-sharing into pranavs…

…uku-test-release-github

python/delta_sharing/reader.py

@@ -137,6 +137,8 @@ def __to_pandas_kernel(self):
         dump(deltaMetadata, json_file)
         json_file.write("\n")
 
+        num_files = len(lines)
+
         # Write the add file actions to the log file
         for line in lines:
             line_json = loads(line)
@@ -151,6 +153,12 @@ def __to_pandas_kernel(self):
         table = delta_kernel_python.Table(table_path)
         snapshot = table.snapshot(interface)
         scan = delta_kernel_python.ScanBuilder(snapshot).build()
+
+        # The table is empty so use the schema to return an empty table with correct col names
+        if (num_files == 0):
+            schema = scan.execute(interface).schema
+            return pd.DataFrame(columns=schema.names)
+
         table = pa.Table.from_batches(scan.execute(interface))
         result = table.to_pandas()
 

python/delta_sharing/tests/test_delta_sharing.py

@@ -711,6 +711,30 @@ def test_load_as_pandas_success_dv_and_cm(
     pd.testing.assert_frame_equal(pdf, expected)
 
 
+@pytest.mark.skipif(not ENABLE_INTEGRATION, reason=SKIP_MESSAGE)
+@pytest.mark.parametrize(
+    "fragments,limit,version,expected",
+    [
+        pytest.param(
+            "share8.default.dv_and_cm_table",
+            0,
+            None,
+            pd.DataFrame(columns=["id", "rand", "partition_col"]),
+            id="test empty table share",
+        )
+    ],
+)
+def test_load_as_pandas_success_empty_dv_and_cm(
+    profile_path: str,
+    fragments: str,
+    limit: Optional[int],
+    version: Optional[int],
+    expected: pd.DataFrame
+):
+    pdf = load_as_pandas(f"{profile_path}#{fragments}", limit, version, None)
+    pd.testing.assert_frame_equal(pdf, expected)
+
+
 # We will test predicates with the table share8.default.cdf_table_with_partition
 # This table is partitioned by birthday column of type date.
 # There are two partitions: 2020-02-02, and 2020-01-01.