fix: add regression test for working with dotted-named columns in Python

Somewhere along the line, our handling of this behavior improved, so
this issue is resolved

Closes #2624

Signed-off-by: R. Tyler Croy <[email protected]>

Author: rtyler

python/deltalake/writer/writer.py

@@ -97,7 +97,7 @@ def write_deltalake(
         configuration: A map containing configuration options for the metadata action.
         schema_mode: If set to "overwrite", allows replacing the schema of the table. Set to "merge" to merge with existing schema.
         storage_options: options passed to the native delta filesystem.
-        predicate: When using `Overwrite` mode, replace data that matches a predicate. Only used in rust engine.'
+        predicate: When using `Overwrite` mode, replace data that matches a predicate.'
         target_file_size: Override for target file size for data files written to the delta table. If not passed, it's taken from `delta.targetFileSize`.
         writer_properties: Pass writer properties to the Rust parquet writer.
         post_commithook_properties: properties for the post commit hook. If None, default values are used.

python/pyproject.toml

@@ -70,7 +70,7 @@ ignore = ["E501", "ANN401", "RUF040"]
 known-first-party = ["deltalake"]
 
 [tool.pytest.ini_options]
-addopts = "-v -m 'not integration and not benchmark and not no_pyarrow'"
+addopts = "-v -x -m 'not integration and not benchmark and not no_pyarrow'"
 testpaths = ["tests", "deltalake"]
 markers = [
     "integration: marks tests as integration tests (deselect with '-m \"not integration\"')",

python/tests/test_writer.py

@@ -2510,3 +2510,49 @@ def test_tilde_path_works_with_writes():
         expanded_path = os.path.expanduser(tilde_path)
         if os.path.exists(expanded_path):
             shutil.rmtree(expanded_path)
+
+
+@pytest.mark.pyarrow
+def test_dots_in_column_names_2624(tmp_path: pathlib.Path):
+    """
+    <https://github.com/delta-io/delta-rs/issues/2624>
+    """
+    import pyarrow as pa
+    initial = pa.Table.from_pydict(
+        {
+            "Product.Id": ['x-0', 'x-1', 'x-2', 'x-3'],
+            'Cost' : [10, 11, 12, 13],
+        }
+    )
+
+    write_deltalake(
+        table_or_uri=tmp_path,
+        data=initial,
+        partition_by=["Product.Id"],
+    )
+
+    update = pa.Table.from_pydict(
+        {
+            "Product.Id": ['x-1'],
+            'Cost' : [101],
+        }
+    )
+
+    write_deltalake(
+        table_or_uri=tmp_path,
+        data=update,
+        partition_by=["Product.Id"],
+        mode="overwrite",
+        predicate="\"Product.Id\" = 'x-1'"
+    )
+
+    dt = DeltaTable(tmp_path)
+    expected = pa.Table.from_pydict(
+        {
+            "Product.Id": ['x-0', 'x-1', 'x-2', 'x-3'],
+            'Cost' : [10, 101, 12, 13],
+        }
+    )
+    # Sorting just to make sure the equivalency matches up
+    actual = dt.to_pyarrow_table().sort_by('Product.Id')
+    assert expected == actual