refactor: Update ruff and enable pyupgrade rules (#1367)

.pre-commit-config.yaml

@@ -13,7 +13,7 @@ repos:
       - id: end-of-file-fixer
       - id: trailing-whitespace
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.6.9
+    rev: v0.7.1
     hooks:
       - id: ruff
         files: datashader/

datashader/compiler.py

@@ -272,8 +272,7 @@ def traverse_aggregation(agg):
     """Yield a left->right traversal of an aggregation"""
     if isinstance(agg, summary):
         for a in agg.values:
-            for a2 in traverse_aggregation(a):
-                yield a2
+            yield from traverse_aggregation(a)
     else:
         yield agg
 

datashader/datashape/__init__.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import
 
 from . import lexer, parser              # noqa (API import)
 from .coretypes import *                 # noqa (API import)

datashader/datashape/coretypes.py

@@ -2,7 +2,6 @@
 This defines the DataShape type system, with unified
 shape and data type.
 """
-from __future__ import print_function, division, absolute_import
 
 import ctypes
 import operator
@@ -26,7 +25,7 @@ class Type(type):
     _registry = {}
 
     def __new__(meta, name, bases, dct):
-        cls = super(Type, meta).__new__(meta, name, bases, dct)
+        cls = super(Type, meta).__new__(meta, name, bases, dct)  # noqa: UP008
         # Don't register abstract classes
         if not dct.get('abstract'):
             Type._registry[name] = cls
@@ -223,7 +222,7 @@ def __init__(self, tz=None):
         self.tz = tz
 
     def __str__(self):
-        basename = super(Time, self).__str__()
+        basename = super().__str__()
         if self.tz is None:
             return basename
         else:
@@ -244,7 +243,7 @@ def __init__(self, tz=None):
         self.tz = tz
 
     def __str__(self):
-        basename = super(DateTime, self).__str__()
+        basename = super().__str__()
         if self.tz is None:
             return basename
         else:
@@ -340,20 +339,20 @@ class Bytes(Unit):
 
 
 _canonical_string_encodings = {
-    u'A': u'A',
-    u'ascii': u'A',
-    u'U8': u'U8',
-    u'utf-8': u'U8',
-    u'utf_8': u'U8',
-    u'utf8': u'U8',
-    u'U16': u'U16',
-    u'utf-16': u'U16',
-    u'utf_16': u'U16',
-    u'utf16': u'U16',
-    u'U32': u'U32',
-    u'utf-32': u'U32',
-    u'utf_32': u'U32',
-    u'utf32': u'U32',
+    'A': 'A',
+    'ascii': 'A',
+    'U8': 'U8',
+    'utf-8': 'U8',
+    'utf_8': 'U8',
+    'utf8': 'U8',
+    'U16': 'U16',
+    'utf-16': 'U16',
+    'utf_16': 'U16',
+    'utf16': 'U16',
+    'U32': 'U32',
+    'utf-32': 'U32',
+    'utf_32': 'U32',
+    'utf32': 'U32',
 }
 
 

datashader/datashape/discovery.py

@@ -1,4 +1,3 @@
-from __future__ import print_function, division, absolute_import
 
 from collections import OrderedDict
 from datetime import datetime, date, time, timedelta
@@ -435,10 +434,7 @@ def descendents(d, x):
 try:
     from unittest.mock import Mock
 except ImportError:
-    try:
-        from mock import Mock
-    except ImportError:
-        pass
+    pass
 
 if Mock is not None:
     @dispatch(Mock)

datashader/datashape/internal_utils.py

@@ -4,7 +4,6 @@
 Do not import datashape modules into this module.  See util.py in that case
 """
 
-from __future__ import print_function, division, absolute_import
 
 import keyword
 import re
@@ -76,7 +75,7 @@ def _toposort(edges):
     """
     incoming_edges = reverse_dict(edges)
     incoming_edges = dict((k, set(val)) for k, val in incoming_edges.items())
-    S = set((v for v in edges if v not in incoming_edges))
+    S = {v for v in edges if v not in incoming_edges}
     L = []
 
     while S:

datashader/datashape/lexer.py

@@ -2,7 +2,6 @@
 Lexer for the datashape grammar.
 """
 
-from __future__ import absolute_import, division, print_function
 
 import re
 import ast

datashader/datashape/parser.py

@@ -2,7 +2,6 @@
 Parser for the datashape grammar.
 """
 
-from __future__ import absolute_import, division, print_function
 
 from . import lexer, error
 # TODO: Remove coretypes dependency, make 100% of interaction through

datashader/datashape/promote.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import
 
 import numpy as np
 from datashader import datashape

datashader/datashape/tests/test_coretypes.py

@@ -337,7 +337,7 @@ def test_record_string():
 
 
 def test_record_with_unicode_name_as_numpy_dtype():
-    r = Record([(str('a'), 'int32')])
+    r = Record([('a', 'int32')])
     assert r.to_numpy_dtype() == np.dtype([('a', 'i4')])
 
 
@@ -651,7 +651,7 @@ def test_invalid_record_literal(invalid):
     [
         (['foo', b'\xc4\x87'.decode('utf8')], str),
         (['foo', 'bar'], str),
-        (list(u'ab'), str)
+        (list('ab'), str)
     ]
 )
 def test_unicode_record_names(names, typ):

datashader/datashape/tests/test_creation.py

@@ -1,4 +1,3 @@
-from __future__ import absolute_import, division, print_function
 
 import ctypes
 import unittest

datashader/datashape/tests/test_discovery.py

@@ -336,10 +336,7 @@ def test_lowest_common_dshape_varlen_strings():
 
 
 def test_discover_mock():
-    try:
-        from unittest.mock import Mock
-    except ImportError:
-        from mock import Mock
+    from unittest.mock import Mock
 
     # This used to segfault because we were sending mocks into numpy
     with pytest.raises(NotImplementedError):

datashader/datashape/tests/test_lexer.py

@@ -2,7 +2,6 @@
 Test the DataShape lexer.
 """
 
-from __future__ import absolute_import, division, print_function
 
 import unittest
 
@@ -81,9 +80,9 @@ def test_string(self):
         self.check_isolated_token("'test'", 'STRING', 'test')
         # Valid escaped characters
         self.check_isolated_token(r'"\"\b\f\n\r\t\ub155"', 'STRING',
-                                  u'"\b\f\n\r\t\ub155')
+                                  '"\b\f\n\r\t\ub155')
         self.check_isolated_token(r"'\'\b\f\n\r\t\ub155'", 'STRING',
-                                  u"'\b\f\n\r\t\ub155")
+                                  "'\b\f\n\r\t\ub155")
         # A sampling of invalid escaped characters
         self.check_failing_token(r'''"\'"''')
         self.check_failing_token(r"""'\"'""")
@@ -95,8 +94,8 @@ def test_string(self):
         self.check_failing_token(r"'\u123g'")
         self.check_failing_token(r"'\u123'")
         # Some unescaped and escapted unicode characters
-        self.check_isolated_token(u'"\uc548\ub155 \\uc548\\ub155"', 'STRING',
-                                  u'\uc548\ub155 \uc548\ub155')
+        self.check_isolated_token('"\uc548\ub155 \\uc548\\ub155"', 'STRING',
+                                  '\uc548\ub155 \uc548\ub155')
 
     def test_failing_tokens(self):
         self.check_failing_token('~')

datashader/datashape/tests/test_parser.py

@@ -2,7 +2,6 @@
 Test the DataShape parser.
 """
 
-from __future__ import absolute_import, division, print_function
 
 import unittest
 import pytest
@@ -162,8 +161,8 @@ def assertExpectedParse(ds_str, expected):
         # String parameter (positional)
         assertExpectedParse('unary["test"]', 'test')
         assertExpectedParse("unary['test']", 'test')
-        assertExpectedParse('unary["\\uc548\\ub155"]', u'\uc548\ub155')
-        assertExpectedParse(u'unary["\uc548\ub155"]', u'\uc548\ub155')
+        assertExpectedParse('unary["\\uc548\\ub155"]', '\uc548\ub155')
+        assertExpectedParse('unary["\uc548\ub155"]', '\uc548\ub155')
         # DataShape parameter (positional)
         assertExpectedParse('unary[int8]', ct.DataShape(ct.int8))
         assertExpectedParse('unary[X]', ct.DataShape(ct.TypeVar('X')))
@@ -185,8 +184,8 @@ def assertExpectedParse(ds_str, expected):
         # String parameter (keyword)
         assertExpectedParse('unary[blah="test"]', 'test')
         assertExpectedParse("unary[blah='test']", 'test')
-        assertExpectedParse('unary[blah="\\uc548\\ub155"]', u'\uc548\ub155')
-        assertExpectedParse(u'unary[blah="\uc548\ub155"]', u'\uc548\ub155')
+        assertExpectedParse('unary[blah="\\uc548\\ub155"]', '\uc548\ub155')
+        assertExpectedParse('unary[blah="\uc548\ub155"]', '\uc548\ub155')
         # DataShape parameter (keyword)
         assertExpectedParse('unary[blah=int8]', ct.DataShape(ct.int8))
         assertExpectedParse('unary[blah=X]', ct.DataShape(ct.TypeVar('X')))

datashader/datashape/type_symbol_table.py

@@ -2,7 +2,6 @@
 A symbol table object to hold types for the parser.
 """
 
-from __future__ import absolute_import, division, print_function
 import ctypes
 from itertools import chain
 

datashader/datashape/user.py

@@ -1,4 +1,3 @@
-from __future__ import print_function, division, absolute_import
 from .dispatch import dispatch
 from .coretypes import (
     CType, Date, DateTime, DataShape, Record, String, Time, Var, from_numpy, to_numpy_dtype)

datashader/datashape/util/__init__.py

@@ -1,4 +1,3 @@
-from __future__ import print_function, division, absolute_import
 
 from itertools import chain
 import operator

datashader/glyphs/trimesh.py

@@ -18,7 +18,7 @@ class _PolygonLike(_PointLike):
             * interp (bool): Whether to interpolate (True), or to have one color per shape (False)
     """
     def __init__(self, x, y, z=None, weight_type=True, interp=True):
-        super(_PolygonLike, self).__init__(x, y)
+        super().__init__(x, y)
         if z is None:
             self.z = []
         else:

datashader/macros.py

@@ -13,7 +13,7 @@ class NameVisitor(ast.NodeVisitor):
     NodeVisitor that builds a set of all of the named identifiers in an AST
     """
     def __init__(self, *args, **kwargs):
-        super(NameVisitor, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.names = set()
 
     def visit_Name(self, node):
@@ -71,7 +71,7 @@ def __init__(self, starred_name, expand_names, *args, **kwargs):
             variable
 
         """
-        super(ExpandVarargTransformer, self).__init__(*args, **kwargs)
+        super().__init__(*args, **kwargs)
         self.starred_name = starred_name
         self.expand_names = expand_names
 

datashader/mpl_ext.py

@@ -92,7 +92,7 @@ def alpha_colormap(color, min_alpha=40, max_alpha=255, N=256):
 
 class EqHistNormalize(mpl.colors.Normalize):
     def __init__(self, vmin=None, vmax=None, clip=False, nbins=256 ** 2, ncolors=256):
-        super(EqHistNormalize, self).__init__(vmin, vmax, clip)
+        super().__init__(vmin, vmax, clip)
         self._nbins = nbins
         self._bin_edges = None
         self._ncolors = ncolors
@@ -164,15 +164,15 @@ def inverse(self, value):
         return np.interp([value], self._color_bins, self._bin_edges)[0]
 
     def autoscale(self, A):
-        super(EqHistNormalize, self).autoscale(A)
+        super().autoscale(A)
         self._bin_edges = self._binning(A, self._ncolors)
 
     def autoscale_None(self, A):
-        super(EqHistNormalize, self).autoscale_None(A)
+        super().autoscale_None(A)
         self._bin_edges = self._binning(A, self._ncolors)
 
     def scaled(self):
-        return super(EqHistNormalize, self).scaled() and self._bin_edges is not None
+        return super().scaled() and self._bin_edges is not None
 
 
 class DSArtist(_ImageBase):

datashader/reductions.py

@@ -1105,7 +1105,7 @@ def uses_cuda_mutex(self) -> UsesCudaMutex:
         return UsesCudaMutex.Global
 
     def _build_append(self, dshape, schema, cuda, antialias, self_intersect):
-        return super(m2, self)._build_append(dshape, schema, cuda, antialias, self_intersect)
+        return super()._build_append(dshape, schema, cuda, antialias, self_intersect)
 
     def _build_create(self, required_dshape):
         return self._create_float64_zero
@@ -1263,7 +1263,7 @@ class count_cat(by):
         categories present.
     """
     def __init__(self, column):
-        super(count_cat, self).__init__(column, count())
+        super().__init__(column, count())
 
 
 class mean(Reduction):

datashader/tests/test_colors.py

@@ -15,10 +15,8 @@ def test_hex_to_rgb():
 
 
 def test_rgb():
-    assert rgb(u'#FAFBFC') == (250, 251, 252)
     assert rgb('#FAFBFC') == (250, 251, 252)
     assert rgb('blue') == (0, 0, 255)
-    assert rgb(u'blue') == (0, 0, 255)
     assert rgb((255, 255, 255)) == (255, 255, 255)
     with pytest.raises(ValueError):
         rgb((255, 256, 255))

datashader/tests/test_geopandas.py

@@ -14,6 +14,8 @@
     pytest.param(False, id="dask"),
 ]
 
+_extras = ["spatialpandas.dask", "dask_geopandas.backends", "dask_geopandas"]
+
 with contextlib.suppress(ImportError):
     import dask_geopandas
 
@@ -23,12 +25,12 @@
 
 @pytest.fixture(params=_backends)
 def dask_both(request):
-    with dask_switcher(query=request.param, extras=["spatialpandas.dask", "dask_geopandas.backends", "dask_geopandas"]): ...
+    with dask_switcher(query=request.param, extras=_extras): ...
     return request.param
 
 @pytest.fixture
 def dask_classic(request):
-    with dask_switcher(query=False, extras=["spatialpandas.dask", "dask_geopandas.backends", "dask_geopandas"]): ...
+    with dask_switcher(query=False, extras=_extras): ...
 
 try:
     import dask_geopandas

datashader/tests/test_mpl_ext.py

@@ -16,8 +16,8 @@
 
 df = pd.DataFrame(
     {
-        "x": np.array(([0.0] * 10 + [1] * 10)),
-        "y": np.array(([0.0] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
+        "x": np.array([0.0] * 10 + [1] * 10),
+        "y": np.array([0.0] * 5 + [1] * 5 + [0] * 5 + [1] * 5),
     }
 )
 

datashader/tests/test_pandas.py

@@ -34,10 +34,10 @@ def _pandas():
     plusminus  0 -1 nan -3  4  -5   6 -7  8 -9  10 -11 12 -13 14  -15 16 -17 18 -19
     cat2       a  b   c  d  a   b   c  d  a  b   c   d  a   b  c    d  a   b  c   d
     """
-    df_pd = pd.DataFrame({'x': np.array(([0.] * 10 + [1] * 10)),
-                      'y': np.array(([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5)),
-                      'log_x': np.array(([1.] * 10 + [10] * 10)),
-                      'log_y': np.array(([1.] * 5 + [10] * 5 + [1] * 5 + [10] * 5)),
+    df_pd = pd.DataFrame({'x': np.array([0.] * 10 + [1] * 10),
+                      'y': np.array([0.] * 5 + [1] * 5 + [0] * 5 + [1] * 5),
+                      'log_x': np.array([1.] * 10 + [10] * 10),
+                      'log_y': np.array([1.] * 5 + [10] * 5 + [1] * 5 + [10] * 5),
                       'i32': np.arange(20, dtype='i4'),
                       'i64': np.arange(20, dtype='i8'),
                       'f32': np.arange(20, dtype='f4'),