FM / pyarrow

/usr/local/lib64/python3.6/site-packages/pyarrow/

/usr/local/lib64/python3.6/site-packages/pyarrow

Name	Size	Mode	Actions
include/	-	0755	rm
includes/	-	0755	rm
tensorflow/	-	0755	rm
tests/	-	0755	rm
vendored/	-	0755	rm
__pycache__/	-	0755	rm
array.pxi	79609	0644	edit dl rm
benchmark.pxi	869	0644	edit dl rm
benchmark.py	856	0644	edit dl rm
builder.pxi	2688	0644	edit dl rm
cffi.py	2178	0644	edit dl rm
compat.pxi	1810	0644	edit dl rm
compat.py	1076	0644	edit dl rm
compute.py	22837	0644	edit dl rm
config.pxi	2613	0644	edit dl rm
csv.py	962	0644	edit dl rm
cuda.py	1087	0644	edit dl rm
dataset.py	33333	0644	edit dl rm
error.pxi	7807	0644	edit dl rm
feather.py	9258	0644	edit dl rm
filesystem.py	14468	0644	edit dl rm
flight.py	1794	0644	edit dl rm
fs.py	13444	0644	edit dl rm
gandiva.pyx	18447	0644	edit dl rm
hdfs.py	7527	0644	edit dl rm
io.pxi	64495	0644	edit dl rm
ipc.pxi	28821	0644	edit dl rm
ipc.py	8029	0644	edit dl rm
json.py	858	0644	edit dl rm
jvm.py	9593	0644	edit dl rm
lib.cpython-36m-x86_64-linux-gnu.so	3760528	0755	edit dl rm
lib.pxd	14442	0644	edit dl rm
lib.pyx	4373	0644	edit dl rm
libarrow.so.600	48162600	0755	edit dl rm
libarrow_dataset.so.600	2541120	0755	edit dl rm
libarrow_flight.so.600	12999784	0755	edit dl rm
libarrow_python.so.600	1848920	0755	edit dl rm
libarrow_python_flight.so.600	112728	0755	edit dl rm
libparquet.so.600	4458552	0755	edit dl rm
libplasma.so.600	251296	0755	edit dl rm
lib_api.h	19153	0644	edit dl rm
memory.pxi	7451	0644	edit dl rm
orc.py	5269	0644	edit dl rm
pandas-shim.pxi	7987	0644	edit dl rm
pandas_compat.py	42243	0644	edit dl rm
parquet.py	86844	0644	edit dl rm
plasma-store-server	482776	0755	edit dl rm
plasma.py	6075	0644	edit dl rm
public-api.pxi	12814	0644	edit dl rm
scalar.pxi	29182	0644	edit dl rm
serialization.pxi	19086	0644	edit dl rm
serialization.py	18202	0644	edit dl rm
table.pxi	72277	0644	edit dl rm
tensor.pxi	34311	0644	edit dl rm
types.pxi	79432	0644	edit dl rm
types.py	10381	0644	edit dl rm
util.py	5001	0644	edit dl rm
_compute.cpython-36m-x86_64-linux-gnu.so	717312	0755	edit dl rm
_compute.pxd	1149	0644	edit dl rm
_compute.pyx	41759	0644	edit dl rm
_csv.cpython-36m-x86_64-linux-gnu.so	312168	0755	edit dl rm
_csv.pxd	1602	0644	edit dl rm
_csv.pyx	39297	0644	edit dl rm
_cuda.pxd	1922	0644	edit dl rm
_cuda.pyx	34731	0644	edit dl rm
_dataset.cpython-36m-x86_64-linux-gnu.so	1080168	0755	edit dl rm
_dataset.pxd	1644	0644	edit dl rm
_dataset.pyx	120054	0644	edit dl rm
_dataset_orc.cpython-36m-x86_64-linux-gnu.so	52536	0755	edit dl rm
_dataset_orc.pyx	1345	0644	edit dl rm
_feather.cpython-36m-x86_64-linux-gnu.so	94280	0755	edit dl rm
_feather.pyx	3623	0644	edit dl rm
_flight.cpython-36m-x86_64-linux-gnu.so	1124664	0755	edit dl rm
_flight.pyx	93532	0644	edit dl rm
_fs.cpython-36m-x86_64-linux-gnu.so	469992	0755	edit dl rm
_fs.pxd	2484	0644	edit dl rm
_fs.pyx	40017	0644	edit dl rm
_generated_version.py	142	0644	edit dl rm
_hdfs.cpython-36m-x86_64-linux-gnu.so	127352	0755	edit dl rm
_hdfs.pyx	5471	0644	edit dl rm
_hdfsio.cpython-36m-x86_64-linux-gnu.so	208096	0755	edit dl rm
_hdfsio.pyx	13681	0644	edit dl rm
_json.cpython-36m-x86_64-linux-gnu.so	90616	0755	edit dl rm
_json.pyx	8406	0644	edit dl rm
_orc.cpython-36m-x86_64-linux-gnu.so	109776	0755	edit dl rm
_orc.pxd	2350	0644	edit dl rm
_orc.pyx	5151	0644	edit dl rm
_parquet.cpython-36m-x86_64-linux-gnu.so	507792	0755	edit dl rm
_parquet.pxd	22084	0644	edit dl rm
_parquet.pyx	47997	0644	edit dl rm
_plasma.cpython-36m-x86_64-linux-gnu.so	259168	0755	edit dl rm
_plasma.pyx	29495	0644	edit dl rm
_s3fs.cpython-36m-x86_64-linux-gnu.so	199496	0755	edit dl rm
_s3fs.pyx	11662	0644	edit dl rm
__init__.pxd	2195	0644	edit dl rm
__init__.py	21263	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/pyarrow/hdfs.py (7527B)

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.

import os
import posixpath
import sys
import warnings

from pyarrow.util import implements, _DEPR_MSG
from pyarrow.filesystem import FileSystem
import pyarrow._hdfsio as _hdfsio

class HadoopFileSystem(_hdfsio.HadoopFileSystem, FileSystem):
    """
    DEPRECATED: FileSystem interface for HDFS cluster.

See pyarrow.hdfs.connect for full connection details

.. deprecated:: 2.0
        ``pyarrow.hdfs.HadoopFileSystem`` is deprecated,
        please use ``pyarrow.fs.HadoopFileSystem`` instead.
    """

def __init__(self, host="default", port=0, user=None, kerb_ticket=None,
                 driver='libhdfs', extra_conf=None):
        warnings.warn(
            _DEPR_MSG.format(
                "hdfs.HadoopFileSystem", "2.0.0", "fs.HadoopFileSystem"),
            FutureWarning, stacklevel=2)
        if driver == 'libhdfs':
            _maybe_set_hadoop_classpath()

self._connect(host, port, user, kerb_ticket, extra_conf)

def __reduce__(self):
        return (HadoopFileSystem, (self.host, self.port, self.user,
                                   self.kerb_ticket, self.extra_conf))

def _isfilestore(self):
        """
        Return True if this is a Unix-style file store with directories.
        """
        return True

@implements(FileSystem.isdir)
    def isdir(self, path):
        return super().isdir(path)

@implements(FileSystem.isfile)
    def isfile(self, path):
        return super().isfile(path)

@implements(FileSystem.delete)
    def delete(self, path, recursive=False):
        return super().delete(path, recursive)

def mkdir(self, path, **kwargs):
        """
        Create directory in HDFS.

Parameters
        ----------
        path : str
            Directory path to create, including any parent directories.

Notes
        -----
        libhdfs does not support create_parents=False, so we ignore this here
        """
        return super().mkdir(path)

@implements(FileSystem.rename)
    def rename(self, path, new_path):
        return super().rename(path, new_path)

@implements(FileSystem.exists)
    def exists(self, path):
        return super().exists(path)

def ls(self, path, detail=False):
        """
        Retrieve directory contents and metadata, if requested.

Parameters
        ----------
        path : str
            HDFS path to retrieve contents of.
        detail : bool, default False
            If False, only return list of paths.

Returns
        -------
        result : list of dicts (detail=True) or strings (detail=False)
        """
        return super().ls(path, detail)

def walk(self, top_path):
        """
        Directory tree generator for HDFS, like os.walk.

Parameters
        ----------
        top_path : str
            Root directory for tree traversal.

Returns
        -------
        Generator yielding 3-tuple (dirpath, dirnames, filename)
        """
        contents = self.ls(top_path, detail=True)

directories, files = _libhdfs_walk_files_dirs(top_path, contents)
        yield top_path, directories, files
        for dirname in directories:
            yield from self.walk(self._path_join(top_path, dirname))

def _maybe_set_hadoop_classpath():
    import re

if re.search(r'hadoop-common[^/]+.jar', os.environ.get('CLASSPATH', '')):
        return

if 'HADOOP_HOME' in os.environ:
        if sys.platform != 'win32':
            classpath = _derive_hadoop_classpath()
        else:
            hadoop_bin = '{}/bin/hadoop'.format(os.environ['HADOOP_HOME'])
            classpath = _hadoop_classpath_glob(hadoop_bin)
    else:
        classpath = _hadoop_classpath_glob('hadoop')

os.environ['CLASSPATH'] = classpath.decode('utf-8')

def _derive_hadoop_classpath():
    import subprocess

find_args = ('find', '-L', os.environ['HADOOP_HOME'], '-name', '*.jar')
    find = subprocess.Popen(find_args, stdout=subprocess.PIPE)
    xargs_echo = subprocess.Popen(('xargs', 'echo'),
                                  stdin=find.stdout,
                                  stdout=subprocess.PIPE)
    jars = subprocess.check_output(('tr', "' '", "':'"),
                                   stdin=xargs_echo.stdout)
    hadoop_conf = os.environ["HADOOP_CONF_DIR"] \
        if "HADOOP_CONF_DIR" in os.environ \
        else os.environ["HADOOP_HOME"] + "/etc/hadoop"
    return (hadoop_conf + ":").encode("utf-8") + jars

def _hadoop_classpath_glob(hadoop_bin):
    import subprocess

hadoop_classpath_args = (hadoop_bin, 'classpath', '--glob')
    return subprocess.check_output(hadoop_classpath_args)

def _libhdfs_walk_files_dirs(top_path, contents):
    files = []
    directories = []
    for c in contents:
        scrubbed_name = posixpath.split(c['name'])[1]
        if c['kind'] == 'file':
            files.append(scrubbed_name)
        else:
            directories.append(scrubbed_name)

return directories, files

def connect(host="default", port=0, user=None, kerb_ticket=None,
            extra_conf=None):
    """
    DEPRECATED: Connect to an HDFS cluster.

All parameters are optional and should only be set if the defaults need
    to be overridden.

Authentication should be automatic if the HDFS cluster uses Kerberos.
    However, if a username is specified, then the ticket cache will likely
    be required.

.. deprecated:: 2.0
        ``pyarrow.hdfs.connect`` is deprecated,
        please use ``pyarrow.fs.HadoopFileSystem`` instead.

Parameters
    ----------
    host : NameNode. Set to "default" for fs.defaultFS from core-site.xml.
    port : NameNode's port. Set to 0 for default or logical (HA) nodes.
    user : Username when connecting to HDFS; None implies login user.
    kerb_ticket : Path to Kerberos ticket cache.
    extra_conf : dict, default None
      extra Key/Value pairs for config; Will override any
      hdfs-site.xml properties

Notes
    -----
    The first time you call this method, it will take longer than usual due
    to JNI spin-up time.

Returns
    -------
    filesystem : HadoopFileSystem
    """
    warnings.warn(
        _DEPR_MSG.format("hdfs.connect", "2.0.0", "fs.HadoopFileSystem"),
        FutureWarning, stacklevel=2
    )
    return _connect(
        host=host, port=port, user=user, kerb_ticket=kerb_ticket,
        extra_conf=extra_conf
    )

def _connect(host="default", port=0, user=None, kerb_ticket=None,
             extra_conf=None):
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        fs = HadoopFileSystem(host=host, port=port, user=user,
                              kerb_ticket=kerb_ticket,
                              extra_conf=extra_conf)
    return fs

cmd: