kou commented on PR #14052:
URL: https://github.com/apache/arrow/pull/14052#issuecomment-1364579136

   @jorisvandenbossche `test-conda-python-3.7-hdfs-*` failures seem to related:
   
   
https://github.com/ursacomputing/crossbow/actions/runs/3765628706/jobs/6401304143#step:5:9344
   
   ```text
   =================================== FAILURES 
===================================
   _________________ TestLibHdfs.test_read_multiple_parquet_files 
_________________
   
   self = <pyarrow.tests.test_hdfs.TestLibHdfs 
testMethod=test_read_multiple_parquet_files>
   
       @pytest.mark.pandas
       @pytest.mark.parquet
       def test_read_multiple_parquet_files(self):
       
           tmpdir = pjoin(self.tmp_path, 'multi-parquet-' + guid())
       
           self.hdfs.mkdir(tmpdir)
       
           expected = self._write_multiple_hdfs_pq_files(tmpdir)
   >       result = self.hdfs.read_parquet(tmpdir)
   
   
opt/conda/envs/arrow/lib/python3.7/site-packages/pyarrow/tests/test_hdfs.py:318:
 
   _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
_ _ 
   opt/conda/envs/arrow/lib/python3.7/site-packages/pyarrow/filesystem.py:227: 
in read_parquet
       filesystem=self)
   
opt/conda/envs/arrow/lib/python3.7/site-packages/pyarrow/parquet/core.py:1759: 
in __new__
       thrift_container_size_limit=thrift_container_size_limit,
   
opt/conda/envs/arrow/lib/python3.7/site-packages/pyarrow/parquet/core.py:2402: 
in __init__
       filesystem, use_mmap=memory_map)
   _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
_ _ 
   
   filesystem = <pyarrow.hdfs.HadoopFileSystem object at 0x7ff3f8702d40>
   use_mmap = False, allow_legacy_filesystem = False
   
       def _ensure_filesystem(
           filesystem, use_mmap=False, allow_legacy_filesystem=False
       ):
           if isinstance(filesystem, FileSystem):
               return filesystem
           elif isinstance(filesystem, str):
               if use_mmap:
                   raise ValueError(
                       "Specifying to use memory mapping not supported for "
                       "filesystem specified as an URI string"
                   )
               return _filesystem_from_str(filesystem)
       
           # handle fsspec-compatible filesystems
           try:
               import fsspec
           except ImportError:
               pass
           else:
               if isinstance(filesystem, fsspec.AbstractFileSystem):
                   if type(filesystem).__name__ == 'LocalFileSystem':
                       # In case its a simple LocalFileSystem, use native arrow 
one
                       return LocalFileSystem(use_mmap=use_mmap)
                   return PyFileSystem(FSSpecHandler(filesystem))
       
           # map old filesystems to new ones
           import pyarrow.filesystem as legacyfs
       
           if isinstance(filesystem, legacyfs.LocalFileSystem):
               return LocalFileSystem(use_mmap=use_mmap)
           # TODO handle HDFS?
           if allow_legacy_filesystem and isinstance(filesystem, 
legacyfs.FileSystem):
               return filesystem
       
           raise TypeError(
               "Unrecognized filesystem: {}. `filesystem` argument must be a "
               "FileSystem instance or a valid file system URI'".format(
   >               type(filesystem))
           )
   E       TypeError: Unrecognized filesystem: <class 
'pyarrow.hdfs.HadoopFileSystem'>. `filesystem` argument must be a FileSystem 
instance or a valid file system URI'
   ```


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to