CLN: PY3 String/BytesIO (#25954)

Author: mroeschke

pandas/_libs/tslibs/parsing.pyx

@@ -2,9 +2,9 @@
 """
 Parsing functions for datetime and datetime-like strings.
 """
-import sys
 import re
 import time
+from io import StringIO
 
 from cpython.datetime cimport datetime
 
@@ -13,13 +13,6 @@ import numpy as np
 
 import six
 
-# Avoid import from outside _libs
-if sys.version_info.major == 2:
-    from StringIO import StringIO
-else:
-    from io import StringIO
-
-
 # dateutil compat
 from dateutil.tz import (tzoffset,
                          tzlocal as _dateutil_tzlocal,

pandas/compat/__init__.py

@@ -39,16 +39,9 @@
 
 try:
     import __builtin__ as builtins
-    # not writeable when instantiated with string, doesn't handle unicode well
-    from cStringIO import StringIO as cStringIO
-    # always writeable
-    from StringIO import StringIO
-    BytesIO = StringIO
     import httplib
 except ImportError:
     import builtins
-    from io import StringIO, BytesIO
-    cStringIO = StringIO
     import http.client as httplib
 
 from pandas.compat.chainmap import DeepChainMap

pandas/core/computation/expr.py

@@ -3,13 +3,14 @@
 
 import ast
 from functools import partial, reduce
+from io import StringIO
 import itertools as it
 import operator
 import tokenize
 
 import numpy as np
 
-from pandas.compat import StringIO, lmap
+from pandas.compat import lmap
 
 import pandas as pd
 from pandas import compat

pandas/core/computation/scope.py

@@ -4,6 +4,7 @@
 
 import datetime
 import inspect
+from io import StringIO
 import itertools
 import pprint
 import struct
@@ -12,7 +13,7 @@
 import numpy as np
 
 from pandas._libs.tslibs import Timestamp
-from pandas.compat import DeepChainMap, StringIO
+from pandas.compat import DeepChainMap
 
 from pandas.core.base import StringMixin
 import pandas.core.computation as compu

pandas/core/frame.py

@@ -13,6 +13,7 @@
 import collections
 from collections import OrderedDict, abc
 import functools
+from io import StringIO
 import itertools
 import sys
 import warnings
@@ -33,7 +34,7 @@
                                      validate_axis_style_args)
 
 from pandas import compat
-from pandas.compat import PY36, StringIO, lmap, lzip, raise_with_traceback
+from pandas.compat import PY36, lmap, lzip, raise_with_traceback
 from pandas.compat.numpy import function as nv
 from pandas.core.dtypes.cast import (
     maybe_upcast,

pandas/core/series.py

@@ -2,6 +2,7 @@
 Data structure for 1-dimensional cross-sectional and time series data
 """
 from collections import OrderedDict, abc
+from io import StringIO
 from shutil import get_terminal_size
 from textwrap import dedent
 import warnings
@@ -12,7 +13,7 @@
 
 from pandas._libs import iNaT, index as libindex, lib, tslibs
 import pandas.compat as compat
-from pandas.compat import PY36, StringIO
+from pandas.compat import PY36
 from pandas.compat.numpy import function as nv
 from pandas.util._decorators import Appender, Substitution, deprecate
 from pandas.util._validators import validate_bool_kwarg

pandas/io/clipboards.py

@@ -1,8 +1,8 @@
 """ io on the clipboard """
+from io import StringIO
 import warnings
 
 import pandas.compat as compat
-from pandas.compat import StringIO
 
 from pandas.core.dtypes.generic import ABCDataFrame
 

pandas/io/common.py

@@ -5,6 +5,7 @@
 import csv
 import gzip
 from http.client import HTTPException  # noqa
+from io import BytesIO
 import lzma
 import mmap
 import os
@@ -16,7 +17,6 @@
 import zipfile
 
 import pandas.compat as compat
-from pandas.compat import BytesIO
 from pandas.errors import (  # noqa
     AbstractMethodError, DtypeWarning, EmptyDataError, ParserError,
     ParserWarning)
@@ -411,7 +411,7 @@ def _get_handle(path_or_buf, mode, encoding=None, compression=None,
     return f, handles
 
 
-class BytesZipFile(zipfile.ZipFile, BytesIO):
+class BytesZipFile(zipfile.ZipFile, BytesIO):  # type: ignore
     """
     Wrapper for standard library class ZipFile and allow the returned file-like
     handle to accept byte strings via `write` method.

pandas/io/formats/csvs.py

@@ -4,14 +4,14 @@
 """
 
 import csv as csvlib
+from io import StringIO
 import os
 import warnings
 from zipfile import ZipFile
 
 import numpy as np
 
 from pandas._libs import writers as libwriters
-from pandas.compat import StringIO
 
 from pandas.core.dtypes.generic import (
     ABCDatetimeIndex, ABCIndexClass, ABCMultiIndex, ABCPeriodIndex)

pandas/io/formats/format.py

@@ -5,6 +5,7 @@
 """
 
 from functools import partial
+from io import StringIO
 from shutil import get_terminal_size
 from unicodedata import east_asian_width
 
@@ -15,7 +16,7 @@
 from pandas._libs import lib
 from pandas._libs.tslib import format_array_from_datetime
 from pandas._libs.tslibs import NaT, Timedelta, Timestamp, iNaT
-from pandas.compat import StringIO, lzip
+from pandas.compat import lzip
 
 from pandas.core.dtypes.common import (
     is_categorical_dtype, is_datetime64_dtype, is_datetime64tz_dtype,

pandas/io/json/json.py

@@ -1,12 +1,13 @@
 # pylint: disable-msg=E1101,W0613,W0603
+from io import StringIO
 from itertools import islice
 import os
 
 import numpy as np
 
 import pandas._libs.json as json
 from pandas._libs.tslibs import iNaT
-from pandas.compat import StringIO, to_str
+from pandas.compat import to_str
 from pandas.errors import AbstractMethodError
 
 from pandas.core.dtypes.common import is_period_dtype

pandas/io/packers.py

@@ -39,14 +39,14 @@
 """
 
 from datetime import date, datetime, timedelta
+from io import BytesIO
 import os
 from textwrap import dedent
 import warnings
 
 from dateutil.parser import parse
 import numpy as np
 
-import pandas.compat as compat
 from pandas.errors import PerformanceWarning
 from pandas.util._move import (
     BadMove as _BadMove, move_into_mutable_buffer as _move_into_mutable_buffer)
@@ -150,7 +150,7 @@ def writer(fh):
         with open(path_or_buf, mode) as fh:
             writer(fh)
     elif path_or_buf is None:
-        buf = compat.BytesIO()
+        buf = BytesIO()
         writer(buf)
         return buf.getvalue()
     else:
@@ -207,7 +207,7 @@ def read(fh):
         # treat as a binary-like
         fh = None
         try:
-            fh = compat.BytesIO(path_or_buf)
+            fh = BytesIO(path_or_buf)
             return read(fh)
         finally:
             if fh is not None:
@@ -802,12 +802,12 @@ def __iter__(self):
                 if path_exists:
                     fh = open(self.path, 'rb')
                 else:
-                    fh = compat.BytesIO(self.path)
+                    fh = BytesIO(self.path)
 
             else:
 
                 if not hasattr(self.path, 'read'):
-                    fh = compat.BytesIO(self.path)
+                    fh = BytesIO(self.path)
 
                 else:
 

pandas/io/parsers.py

@@ -5,6 +5,7 @@
 from collections import defaultdict
 import csv
 import datetime
+from io import StringIO
 import re
 import sys
 from textwrap import fill
@@ -17,7 +18,7 @@
 import pandas._libs.parsers as parsers
 from pandas._libs.tslibs import parsing
 import pandas.compat as compat
-from pandas.compat import StringIO, lrange, lzip
+from pandas.compat import lrange, lzip
 from pandas.errors import (
     AbstractMethodError, EmptyDataError, ParserError, ParserWarning)
 from pandas.util._decorators import Appender

pandas/io/pickle.py

@@ -1,10 +1,11 @@
 """ pickle compat """
+from io import BytesIO
 import pickle
 import warnings
 
 from numpy.lib.format import read_array
 
-from pandas.compat import BytesIO, pickle_compat as pc
+from pandas.compat import pickle_compat as pc
 
 from pandas.io.common import _get_handle, _stringify_path
 

pandas/io/sas/sas_xport.py

@@ -9,6 +9,7 @@
 """
 
 from datetime import datetime
+from io import BytesIO
 import struct
 import warnings
 
@@ -17,7 +18,6 @@
 from pandas.util._decorators import Appender
 
 import pandas as pd
-from pandas import compat
 
 from pandas.io.common import BaseIterator, get_filepath_or_buffer
 
@@ -249,7 +249,7 @@ def __init__(self, filepath_or_buffer, index=None, encoding='ISO-8859-1',
                 contents = contents.encode(self._encoding)
             except UnicodeEncodeError:
                 pass
-            self.filepath_or_buffer = compat.BytesIO(contents)
+            self.filepath_or_buffer = BytesIO(contents)
 
         self._read_header()
 

pandas/io/stata.py

@@ -12,6 +12,7 @@
 
 from collections import OrderedDict
 import datetime
+from io import BytesIO
 import os
 import struct
 import sys
@@ -23,7 +24,7 @@
 from pandas._libs.lib import infer_dtype
 from pandas._libs.tslibs import NaT, Timestamp
 from pandas._libs.writers import max_len_string_array
-from pandas.compat import BytesIO, lmap, lrange, lzip
+from pandas.compat import lmap, lrange, lzip
 from pandas.util._decorators import Appender, deprecate_kwarg
 
 from pandas.core.dtypes.common import (

pandas/tests/dtypes/test_inference.py

@@ -9,6 +9,7 @@
 from datetime import date, datetime, time, timedelta
 from decimal import Decimal
 from fractions import Fraction
+from io import StringIO
 from numbers import Number
 import re
 
@@ -17,7 +18,7 @@
 import pytz
 
 from pandas._libs import iNaT, lib, missing as libmissing
-from pandas.compat import StringIO, lrange
+from pandas.compat import lrange
 import pandas.util._test_decorators as td
 
 from pandas.core.dtypes import inference

pandas/tests/extension/base/io.py

@@ -1,8 +1,8 @@
+from io import StringIO
+
 import numpy as np
 import pytest
 
-from pandas.compat import StringIO
-
 import pandas as pd
 
 from .base import BaseExtensionTests

pandas/tests/frame/test_block_internals.py

@@ -1,13 +1,12 @@
 # -*- coding: utf-8 -*-
 
 from datetime import datetime, timedelta
+from io import StringIO
 import itertools
 
 import numpy as np
 import pytest
 
-from pandas.compat import StringIO
-
 import pandas as pd
 from pandas import (
     Categorical, DataFrame, Series, Timestamp, compat, date_range,

pandas/tests/frame/test_query_eval.py

@@ -1,11 +1,11 @@
 # -*- coding: utf-8 -*-
-
+from io import StringIO
 import operator
 
 import numpy as np
 import pytest
 
-from pandas.compat import StringIO, lrange
+from pandas.compat import lrange
 import pandas.util._test_decorators as td
 
 import pandas as pd

pandas/tests/frame/test_replace.py

@@ -1,12 +1,13 @@
 # -*- coding: utf-8 -*-
 
 from datetime import datetime
+from io import StringIO
 import re
 
 import numpy as np
 import pytest
 
-from pandas.compat import StringIO, lrange
+from pandas.compat import lrange
 
 import pandas as pd
 from pandas import DataFrame, Index, Series, Timestamp, compat, date_range