Remove py2 compat (#2645)

* strip out PY2 compat code from pycompat.py

* isort

* remove 2 unused imports

* remove extra import

* no more future

* no unicode literals

* no more ReprMixin

* cleanup merge

* remove deprecated imports from collections

* 2 more cleanups from shoyer

Author: Joe Hamman

setup.py

@@ -15,8 +15,6 @@
     'Operating System :: OS Independent',
     'Intended Audience :: Science/Research',
     'Programming Language :: Python',
-    'Programming Language :: Python :: 2',
-    'Programming Language :: Python :: 2.7',
     'Programming Language :: Python :: 3',
     'Programming Language :: Python :: 3.5',
     'Programming Language :: Python :: 3.6',

xarray/__init__.py

@@ -1,7 +1,4 @@
 # flake8: noqa
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
 
 from ._version import get_versions
 __version__ = get_versions()['version']

xarray/backends/api.py

@@ -1,18 +1,16 @@
-from __future__ import absolute_import, division, print_function
-
 import os.path
 import warnings
 from glob import glob
 from io import BytesIO
 from numbers import Number
+from pathlib import Path
 
 import numpy as np
 
 from .. import Dataset, backends, conventions
 from ..core import indexing
 from ..core.combine import (
     _CONCAT_DIM_DEFAULT, _auto_combine, _infer_concat_order_from_positions)
-from ..core.pycompat import basestring, path_type
 from ..core.utils import close_on_error, is_grib_path, is_remote_uri
 from .common import ArrayWriter
 from .locks import _get_scheduler
@@ -99,7 +97,7 @@ def _normalize_path(path):
 def _validate_dataset_names(dataset):
     """DataArray.name and Dataset keys must be a string or None"""
     def check_name(name):
-        if isinstance(name, basestring):
+        if isinstance(name, str):
             if not name:
                 raise ValueError('Invalid name for DataArray or Dataset key: '
                                  'string must be length 1 or greater for '
@@ -117,7 +115,7 @@ def _validate_attrs(dataset):
     a string, an ndarray or a list/tuple of numbers/strings.
     """
     def check_attr(name, value):
-        if isinstance(name, basestring):
+        if isinstance(name, str):
             if not name:
                 raise ValueError('Invalid name for attr: string must be '
                                  'length 1 or greater for serialization to '
@@ -126,7 +124,7 @@ def check_attr(name, value):
             raise TypeError("Invalid name for attr: {} must be a string for "
                             "serialization to netCDF files".format(name))
 
-        if not isinstance(value, (basestring, Number, np.ndarray, np.number,
+        if not isinstance(value, (str, Number, np.ndarray, np.number,
                                   list, tuple)):
             raise TypeError('Invalid value for attr: {} must be a number, '
                             'a string, an ndarray or a list/tuple of '
@@ -279,7 +277,7 @@ def maybe_decode_store(store, lock=False):
             from dask.base import tokenize
             # if passed an actual file path, augment the token with
             # the file modification time
-            if (isinstance(filename_or_obj, basestring) and
+            if (isinstance(filename_or_obj, str) and
                     not is_remote_uri(filename_or_obj)):
                 mtime = os.path.getmtime(filename_or_obj)
             else:
@@ -295,13 +293,13 @@ def maybe_decode_store(store, lock=False):
 
         return ds2
 
-    if isinstance(filename_or_obj, path_type):
+    if isinstance(filename_or_obj, Path):
         filename_or_obj = str(filename_or_obj)
 
     if isinstance(filename_or_obj, backends.AbstractDataStore):
         store = filename_or_obj
         ds = maybe_decode_store(store)
-    elif isinstance(filename_or_obj, basestring):
+    elif isinstance(filename_or_obj, str):
 
         if (isinstance(filename_or_obj, bytes) and
                 filename_or_obj.startswith(b'\x89HDF')):
@@ -310,7 +308,7 @@ def maybe_decode_store(store, lock=False):
                 filename_or_obj.startswith(b'CDF')):
             # netCDF3 file images are handled by scipy
             pass
-        elif isinstance(filename_or_obj, basestring):
+        elif isinstance(filename_or_obj, str):
             filename_or_obj = _normalize_path(filename_or_obj)
 
         if engine is None:
@@ -352,7 +350,7 @@ def maybe_decode_store(store, lock=False):
 
     # Ensure source filename always stored in dataset object (GH issue #2550)
     if 'source' not in ds.encoding:
-        if isinstance(filename_or_obj, basestring):
+        if isinstance(filename_or_obj, str):
             ds.encoding['source'] = filename_or_obj
 
     return ds
@@ -588,15 +586,15 @@ def open_mfdataset(paths, chunks=None, concat_dim=_CONCAT_DIM_DEFAULT,
     .. [1] http://xarray.pydata.org/en/stable/dask.html
     .. [2] http://xarray.pydata.org/en/stable/dask.html#chunking-and-performance
     """  # noqa
-    if isinstance(paths, basestring):
+    if isinstance(paths, str):
         if is_remote_uri(paths):
             raise ValueError(
                 'cannot do wild-card matching for paths that are remote URLs: '
                 '{!r}. Instead, supply paths as an explicit list of strings.'
                 .format(paths))
         paths = sorted(glob(paths))
     else:
-        paths = [str(p) if isinstance(p, path_type) else p for p in paths]
+        paths = [str(p) if isinstance(p, Path) else p for p in paths]
 
     if not paths:
         raise IOError('no files to open')
@@ -681,7 +679,7 @@ def to_netcdf(dataset, path_or_file=None, mode='w', format=None, group=None,
 
     The ``multifile`` argument is only for the private use of save_mfdataset.
     """
-    if isinstance(path_or_file, path_type):
+    if isinstance(path_or_file, Path):
         path_or_file = str(path_or_file)
 
     if encoding is None:
@@ -698,7 +696,7 @@ def to_netcdf(dataset, path_or_file=None, mode='w', format=None, group=None,
             raise NotImplementedError(
                 'to_netcdf() with compute=False is not yet implemented when '
                 'returning bytes')
-    elif isinstance(path_or_file, basestring):
+    elif isinstance(path_or_file, str):
         if engine is None:
             engine = _get_default_engine(path_or_file)
         path_or_file = _normalize_path(path_or_file)
@@ -733,7 +731,7 @@ def to_netcdf(dataset, path_or_file=None, mode='w', format=None, group=None,
 
     if unlimited_dims is None:
         unlimited_dims = dataset.encoding.get('unlimited_dims', None)
-    if isinstance(unlimited_dims, basestring):
+    if isinstance(unlimited_dims, str):
         unlimited_dims = [unlimited_dims]
 
     writer = ArrayWriter()
@@ -896,7 +894,7 @@ def to_zarr(dataset, store=None, mode='w-', synchronizer=None, group=None,
 
     See `Dataset.to_zarr` for full API docs.
     """
-    if isinstance(store, path_type):
+    if isinstance(store, Path):
         store = str(store)
     if encoding is None:
         encoding = {}

xarray/backends/cfgrib_.py

@@ -1,5 +1,3 @@
-from __future__ import absolute_import, division, print_function
-
 import numpy as np
 
 from .. import Variable

xarray/backends/common.py

@@ -1,16 +1,15 @@
-from __future__ import absolute_import, division, print_function
-
 import logging
 import time
 import traceback
 import warnings
-from collections import Mapping, OrderedDict
+from collections import OrderedDict
+from collections.abc import Mapping
 
 import numpy as np
 
 from ..conventions import cf_encoder
 from ..core import indexing
-from ..core.pycompat import dask_array_type, iteritems
+from ..core.pycompat import dask_array_type
 from ..core.utils import FrozenOrderedDict, NdimSizeLenMixin
 
 # Create a logger object, but don't add any handlers. Leave that to user code.
@@ -109,9 +108,9 @@ class SuffixAppendingDataStore(AbstractDataStore):
                 def load(self):
                     variables, attributes = AbstractDataStore.load(self)
                     variables = {'%s_suffix' % k: v
-                                 for k, v in iteritems(variables)}
+                                 for k, v in variables.items()}
                     attributes = {'%s_suffix' % k: v
-                                  for k, v in iteritems(attributes)}
+                                  for k, v in attributes.items()}
                     return variables, attributes
 
         This function will be called anytime variables or attributes
@@ -275,7 +274,7 @@ def set_attributes(self, attributes):
         attributes : dict-like
             Dictionary of key/value (attribute name / attribute) pairs
         """
-        for k, v in iteritems(attributes):
+        for k, v in attributes.items():
             self.set_attribute(k, v)
 
     def set_variables(self, variables, check_encoding_set, writer,
@@ -297,7 +296,7 @@ def set_variables(self, variables, check_encoding_set, writer,
             dimensions.
         """
 
-        for vn, v in iteritems(variables):
+        for vn, v in variables.items():
             name = _encode_variable_name(vn)
             check = vn in check_encoding_set
             target, source = self.prepare_variable(

xarray/backends/h5netcdf_.py

@@ -1,12 +1,10 @@
-from __future__ import absolute_import, division, print_function
-
 import functools
+from collections import OrderedDict
 
 import numpy as np
 
 from .. import Variable
 from ..core import indexing
-from ..core.pycompat import OrderedDict, bytes_type, iteritems, unicode_type
 from ..core.utils import FrozenOrderedDict, close_on_error
 from .common import WritableCFDataStore
 from .file_manager import CachingFileManager
@@ -32,7 +30,7 @@ def _getitem(self, key):
 
 
 def maybe_decode_bytes(txt):
-    if isinstance(txt, bytes_type):
+    if isinstance(txt, bytes):
         return txt.decode('utf-8')
     else:
         return txt
@@ -124,7 +122,7 @@ def open_store_variable(self, name, var):
         encoding['original_shape'] = var.shape
 
         vlen_dtype = h5py.check_dtype(vlen=var.dtype)
-        if vlen_dtype is unicode_type:
+        if vlen_dtype is str:
             encoding['dtype'] = str
         elif vlen_dtype is not None:  # pragma: no cover
             # xarray doesn't support writing arbitrary vlen dtypes yet.
@@ -136,7 +134,7 @@ def open_store_variable(self, name, var):
 
     def get_variables(self):
         return FrozenOrderedDict((k, self.open_store_variable(k, v))
-                                 for k, v in iteritems(self.ds.variables))
+                                 for k, v in self.ds.variables.items())
 
     def get_attrs(self):
         return FrozenOrderedDict(_read_attributes(self.ds))
@@ -182,7 +180,7 @@ def prepare_variable(self, name, variable, check_encoding=False,
                 'NC_CHAR type.' % name)
 
         if dtype is str:
-            dtype = h5py.special_dtype(vlen=unicode_type)
+            dtype = h5py.special_dtype(vlen=str)
 
         encoding = _extract_h5nc_encoding(variable,
                                           raise_on_invalid=check_encoding)
@@ -221,7 +219,7 @@ def prepare_variable(self, name, variable, check_encoding=False,
         else:
             nc4_var = self.ds[name]
 
-        for k, v in iteritems(attrs):
+        for k, v in attrs.items():
             nc4_var.attrs[k] = v
 
         target = H5NetCDFArrayWrapper(name, self)

xarray/backends/lru_cache.py

@@ -1,8 +1,6 @@
 import collections
 import threading
 
-from ..core.pycompat import move_to_end
-
 
 class LRUCache(collections.MutableMapping):
     """Thread-safe LRUCache based on an OrderedDict.
@@ -41,7 +39,7 @@ def __getitem__(self, key):
         # record recent use of the key by moving it to the front of the list
         with self._lock:
             value = self._cache[key]
-            move_to_end(self._cache, key)
+            self._cache.move_to_end(key)
             return value
 
     def _enforce_size_limit(self, capacity):

xarray/backends/memory.py

@@ -1,10 +1,8 @@
-from __future__ import absolute_import, division, print_function
-
 import copy
+from collections import OrderedDict
 
 import numpy as np
 
-from ..core.pycompat import OrderedDict
 from ..core.variable import Variable
 from .common import AbstractWritableDataStore
 

xarray/backends/netCDF4_.py

@@ -1,16 +1,15 @@
-from __future__ import absolute_import, division, print_function
-
 import functools
 import operator
 import warnings
+from collections import OrderedDict
+from contextlib import suppress
 from distutils.version import LooseVersion
 
 import numpy as np
 
 from .. import Variable, coding
 from ..coding.variables import pop_to
 from ..core import indexing
-from ..core.pycompat import PY3, OrderedDict, basestring, iteritems, suppress
 from ..core.utils import FrozenOrderedDict, close_on_error, is_remote_uri
 from .common import (
     BackendArray, WritableCFDataStore, find_root, robust_getitem)
@@ -81,9 +80,6 @@ def _getitem(self, key):
             msg = ('The indexing operation you are attempting to perform '
                    'is not valid on netCDF4.Variable object. Try loading '
                    'your data into memory first by calling .load().')
-            if not PY3:
-                import traceback
-                msg += '\n\nOriginal traceback:\n' + traceback.format_exc()
             raise IndexError(msg)
         return array
 
@@ -141,7 +137,7 @@ def _nc4_require_group(ds, group, mode, create_group=_netcdf4_create_group):
         return ds
     else:
         # make sure it's a string
-        if not isinstance(group, basestring):
+        if not isinstance(group, str):
             raise ValueError('group must be a string or None')
         # support path-like syntax
         path = group.strip('/').split('/')
@@ -392,7 +388,7 @@ def open_store_variable(self, name, var):
     def get_variables(self):
         dsvars = FrozenOrderedDict((k, self.open_store_variable(k, v))
                                    for k, v in
-                                   iteritems(self.ds.variables))
+                                   self.ds.variables.items())
         return dsvars
 
     def get_attrs(self):
@@ -402,7 +398,7 @@ def get_attrs(self):
 
     def get_dimensions(self):
         dims = FrozenOrderedDict((k, len(v))
-                                 for k, v in iteritems(self.ds.dimensions))
+                                 for k, v in self.ds.dimensions.items())
         return dims
 
     def get_encoding(self):
@@ -467,7 +463,7 @@ def prepare_variable(self, name, variable, check_encoding=False,
                 fill_value=fill_value)
             _disable_auto_decode_variable(nc4_var)
 
-        for k, v in iteritems(attrs):
+        for k, v in attrs.items():
             # set attributes one-by-one since netCDF4<1.0.10 can't handle
             # OrderedDict as the input to setncatts
             _set_nc_attribute(nc4_var, k, v)