This is an automated email from the ASF dual-hosted git repository.
JingsongLi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new aa1439867a [python] Fix CachingFileIO bypassing delegate for several
FileIO methods (#7983)
aa1439867a is described below
commit aa1439867a22431ec326cb58cca63bf8170be0d2
Author: XiaoHongbo <[email protected]>
AuthorDate: Tue May 26 22:57:50 2026 +0800
[python] Fix CachingFileIO bypassing delegate for several FileIO methods
(#7983)
---
.../pypaimon/filesystem/caching_file_io.py | 25 ++++++++++++++++++++++
.../pypaimon/tests/caching_file_io_test.py | 24 +++++++++++++++++++++
2 files changed, 49 insertions(+)
diff --git a/paimon-python/pypaimon/filesystem/caching_file_io.py
b/paimon-python/pypaimon/filesystem/caching_file_io.py
index f5141a76e3..d583adb4e0 100644
--- a/paimon-python/pypaimon/filesystem/caching_file_io.py
+++ b/paimon-python/pypaimon/filesystem/caching_file_io.py
@@ -382,6 +382,31 @@ class CachingFileIO(FileIO):
def is_dir(self, path: str) -> bool:
return self._delegate.is_dir(path)
+ # FileIO base has raising / no-op defaults that block __getattr__ —
forward explicitly.
+ def to_filesystem_path(self, path: str) -> str:
+ return self._delegate.to_filesystem_path(path)
+
+ def try_to_write_atomic(self, *args, **kwargs):
+ return self._delegate.try_to_write_atomic(*args, **kwargs)
+
+ def write_parquet(self, *args, **kwargs):
+ return self._delegate.write_parquet(*args, **kwargs)
+
+ def write_orc(self, *args, **kwargs):
+ return self._delegate.write_orc(*args, **kwargs)
+
+ def write_avro(self, *args, **kwargs):
+ return self._delegate.write_avro(*args, **kwargs)
+
+ def write_lance(self, *args, **kwargs):
+ return self._delegate.write_lance(*args, **kwargs)
+
+ def write_blob(self, *args, **kwargs):
+ return self._delegate.write_blob(*args, **kwargs)
+
+ def write_vortex(self, *args, **kwargs):
+ return self._delegate.write_vortex(*args, **kwargs)
+
def __getattr__(self, name):
return getattr(self._delegate, name)
diff --git a/paimon-python/pypaimon/tests/caching_file_io_test.py
b/paimon-python/pypaimon/tests/caching_file_io_test.py
index 048f70589d..5f22c8934e 100644
--- a/paimon-python/pypaimon/tests/caching_file_io_test.py
+++ b/paimon-python/pypaimon/tests/caching_file_io_test.py
@@ -385,6 +385,30 @@ class CachingFileIOTest(unittest.TestCase):
caching_io.new_output_stream("/out")
delegate.new_output_stream.assert_called_once_with("/out")
+ def test_to_filesystem_path_forwarded_to_delegate(self):
+ delegate = MagicMock()
+ delegate.to_filesystem_path.side_effect = lambda p:
p.replace("oss://", "")
+ cache = LocalDiskCacheManager(self.cache_dir, 2 ** 63 - 1,
block_size=64)
+ caching_io = CachingFileIO(delegate, cache)
+
+ self.assertEqual("bucket/key",
caching_io.to_filesystem_path("oss://bucket/key"))
+ delegate.to_filesystem_path.assert_called_once_with("oss://bucket/key")
+
+ def test_write_parquet_when_enable_local_cache(self):
+ import pyarrow as pa
+ from pypaimon.filesystem.local_file_io import LocalFileIO
+
+ delegate = LocalFileIO()
+ cache = LocalDiskCacheManager(self.cache_dir, 2 ** 63 - 1,
block_size=64)
+ caching_io = CachingFileIO(delegate, cache)
+
+ out_path = os.path.join(self.cache_dir, "data.parquet")
+ table = pa.table({"a": [1, 2, 3]})
+ caching_io.write_parquet(out_path, table)
+
+ self.assertTrue(os.path.exists(out_path))
+ self.assertEqual(table, pa.parquet.read_table(out_path))
+
class ConfigOptionsTest(unittest.TestCase):
