Add cython-lint to pre-commit checks. (#12020)

Adds `cython-lint` (https://github.com/MarcoGorelli/cython-lint) to the list of pre-commit checks. It is most similar to flake8 but with support for Cython syntax -- the rule set it enforces is fairly short, it mostly helps identify unused imports in Cython files.

Authors:
  - Bradley Dice (https://github.com/bdice)

Approvers:
  - GALI PREM SAGAR (https://github.com/galipremsagar)

URL: #12020

.pre-commit-config.yaml

@@ -26,6 +26,10 @@ repos:
                 types: [file]
                 types_or: [python, cython]
                 additional_dependencies: ["flake8-force"]
+      - repo: https://github.com/MarcoGorelli/cython-lint
+        rev: v0.1.10
+        hooks:
+              - id: cython-lint
       - repo: https://github.com/pre-commit/mirrors-mypy
         rev: 'v0.971'
         hooks:

python/cudf/cudf/_lib/aggregation.pyx

@@ -2,20 +2,13 @@
 
 from enum import Enum, IntEnum
 
-import numba
-import numpy as np
 import pandas as pd
 
-from libcpp.memory cimport unique_ptr
 from libcpp.string cimport string
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
-from cudf._lib.types import (
-    LIBCUDF_TO_SUPPORTED_NUMPY_TYPES,
-    SUPPORTED_NUMPY_TO_LIBCUDF_TYPES,
-    NullHandling,
-)
+from cudf._lib.types import SUPPORTED_NUMPY_TO_LIBCUDF_TYPES, NullHandling
 from cudf.utils import cudautils
 
 from cudf._lib.types cimport (

python/cudf/cudf/_lib/binaryop.pyx

@@ -2,16 +2,13 @@
 
 from enum import IntEnum
 
-import numpy as np
-
 from libcpp.memory cimport unique_ptr
 from libcpp.string cimport string
 from libcpp.utility cimport move
 
 from cudf._lib.binaryop cimport underlying_type_t_binary_operator
 from cudf._lib.column cimport Column
 
-from cudf._lib.replace import replace_nulls
 from cudf._lib.scalar import as_device_scalar
 
 from cudf._lib.scalar cimport DeviceScalar

python/cudf/cudf/_lib/column.pyx

@@ -2,39 +2,23 @@
 
 import cupy as cp
 import numpy as np
-import pandas as pd
 
 import rmm
 
 import cudf
 import cudf._lib as libcudf
-from cudf.api.types import is_categorical_dtype, is_list_dtype, is_struct_dtype
+from cudf.api.types import is_categorical_dtype
 from cudf.core.buffer import Buffer, DeviceBufferLike, as_device_buffer_like
 
 from cpython.buffer cimport PyObject_CheckBuffer
 from libc.stdint cimport uintptr_t
-from libcpp cimport bool
 from libcpp.memory cimport make_unique, unique_ptr
-from libcpp.pair cimport pair
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
 from rmm._lib.device_buffer cimport DeviceBuffer
 
-from cudf._lib.cpp.strings.convert.convert_integers cimport (
-    from_integers as cpp_from_integers,
-)
-
-from cudf._lib.types import (
-    LIBCUDF_TO_SUPPORTED_NUMPY_TYPES,
-    SUPPORTED_NUMPY_TO_LIBCUDF_TYPES,
-)
-
-from cudf._lib.types cimport (
-    dtype_from_column_view,
-    dtype_to_data_type,
-    underlying_type_t_type_id,
-)
+from cudf._lib.types cimport dtype_from_column_view, dtype_to_data_type
 
 from cudf._lib.null_mask import bitmask_allocation_size_bytes
 
@@ -46,7 +30,6 @@ from cudf._lib.cpp.column.column_factories cimport (
     make_numeric_column,
 )
 from cudf._lib.cpp.column.column_view cimport column_view
-from cudf._lib.cpp.lists.lists_column_view cimport lists_column_view
 from cudf._lib.cpp.scalar.scalar cimport scalar
 from cudf._lib.scalar cimport DeviceScalar
 

python/cudf/cudf/_lib/copying.pyx

@@ -3,9 +3,7 @@
 import pickle
 import warnings
 
-import pandas as pd
-
-from libc.stdint cimport int32_t, int64_t, uint8_t, uintptr_t
+from libc.stdint cimport int32_t, uint8_t, uintptr_t
 from libcpp cimport bool
 from libcpp.memory cimport make_shared, make_unique, shared_ptr, unique_ptr
 from libcpp.utility cimport move
@@ -42,7 +40,6 @@ from cudf._lib.utils cimport (
     columns_from_table_view,
     columns_from_unique_ptr,
     data_from_table_view,
-    data_from_unique_ptr,
     table_view_from_columns,
 )
 

python/cudf/cudf/_lib/csv.pyx

@@ -2,13 +2,13 @@
 
 from libcpp cimport bool
 from libcpp.map cimport map
-from libcpp.memory cimport make_unique, unique_ptr
+from libcpp.memory cimport unique_ptr
 from libcpp.string cimport string
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
 cimport cudf._lib.cpp.types as libcudf_types
-from cudf._lib.cpp.types cimport data_type, type_id
+from cudf._lib.cpp.types cimport data_type
 from cudf._lib.io.datasource cimport Datasource, NativeFileDatasource
 from cudf._lib.types cimport dtype_to_data_type
 
@@ -45,11 +45,7 @@ from cudf._lib.cpp.io.types cimport (
 )
 from cudf._lib.cpp.table.table_view cimport table_view
 from cudf._lib.io.utils cimport make_sink_info, make_source_info
-from cudf._lib.utils cimport (
-    data_from_unique_ptr,
-    table_view_from_columns,
-    table_view_from_table,
-)
+from cudf._lib.utils cimport data_from_unique_ptr, table_view_from_table
 
 from pyarrow.lib import NativeFile
 
@@ -121,8 +117,6 @@ cdef csv_reader_options make_csv_reader_options(
 ) except *:
     cdef source_info c_source_info = make_source_info([datasource])
     cdef compression_type c_compression
-    cdef size_type c_header
-    cdef string c_prefix
     cdef vector[string] c_names
     cdef size_t c_byte_range_offset = (
         byte_range[0] if byte_range is not None else 0

python/cudf/cudf/_lib/expressions.pyx

@@ -5,7 +5,6 @@ from enum import Enum
 from cython.operator cimport dereference
 from libc.stdint cimport int64_t
 from libcpp.memory cimport make_unique, unique_ptr
-from libcpp.utility cimport move
 
 from cudf._lib.cpp cimport expressions as libcudf_exp
 from cudf._lib.cpp.types cimport size_type

python/cudf/cudf/_lib/filling.pyx

@@ -1,8 +1,5 @@
 # Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
-import numpy as np
-
-from libcpp cimport bool
 from libcpp.memory cimport unique_ptr
 from libcpp.utility cimport move
 
@@ -15,11 +12,7 @@ from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view
 from cudf._lib.cpp.types cimport size_type
 from cudf._lib.scalar cimport DeviceScalar
-from cudf._lib.utils cimport (
-    columns_from_unique_ptr,
-    data_from_unique_ptr,
-    table_view_from_columns,
-)
+from cudf._lib.utils cimport columns_from_unique_ptr, table_view_from_columns
 
 
 def fill_in_place(Column destination, int begin, int end, DeviceScalar value):
@@ -64,7 +57,6 @@ def repeat(list inp, object count):
 def _repeat_via_column(list inp, Column count):
     cdef table_view c_inp = table_view_from_columns(inp)
     cdef column_view c_count = count.view()
-    cdef bool c_check_count = False
     cdef unique_ptr[table] c_result
 
     with nogil:

python/cudf/cudf/_lib/groupby.pyx

@@ -1,12 +1,7 @@
 # Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
-from collections import defaultdict
-
-import numpy as np
 from pandas.core.groupby.groupby import DataError
 
-import rmm
-
 from cudf.api.types import (
     is_categorical_dtype,
     is_decimal_dtype,
@@ -22,16 +17,9 @@ from libcpp.pair cimport pair
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
-import cudf
-
 from cudf._lib.column cimport Column
 from cudf._lib.scalar cimport DeviceScalar
-from cudf._lib.utils cimport (
-    columns_from_unique_ptr,
-    data_from_unique_ptr,
-    table_view_from_columns,
-    table_view_from_table,
-)
+from cudf._lib.utils cimport columns_from_unique_ptr, table_view_from_columns
 
 from cudf._lib.scalar import as_device_scalar
 
@@ -44,13 +32,11 @@ from cudf._lib.aggregation cimport (
     make_groupby_scan_aggregation,
 )
 from cudf._lib.cpp.column.column cimport column
-from cudf._lib.cpp.column.column_view cimport column_view
 from cudf._lib.cpp.libcpp.functional cimport reference_wrapper
 from cudf._lib.cpp.replace cimport replace_policy
 from cudf._lib.cpp.scalar.scalar cimport scalar
 from cudf._lib.cpp.table.table cimport table, table_view
 from cudf._lib.cpp.types cimport size_type
-from cudf._lib.cpp.utilities.host_span cimport host_span
 
 # The sets below define the possible aggregations that can be performed on
 # different dtypes. These strings must be elements of the AggregationKind enum.

python/cudf/cudf/_lib/hash.pyx

@@ -1,7 +1,5 @@
 # Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
-from libc.stdint cimport uint32_t
-from libcpp cimport bool
 from libcpp.memory cimport unique_ptr
 from libcpp.pair cimport pair
 from libcpp.utility cimport move

python/cudf/cudf/_lib/interop.pyx

@@ -1,11 +1,7 @@
 # Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
-import cudf
-
 from cpython cimport pycapsule
-from libcpp cimport bool
 from libcpp.memory cimport shared_ptr, unique_ptr
-from libcpp.string cimport string
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
 from pyarrow.lib cimport CTable, pyarrow_unwrap_table, pyarrow_wrap_table
@@ -18,7 +14,6 @@ from cudf._lib.cpp.interop cimport (
     to_arrow as cpp_to_arrow,
     to_dlpack as cpp_to_dlpack,
 )
-from cudf._lib.cpp.io.types cimport column_in_metadata
 from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view
 from cudf._lib.utils cimport columns_from_unique_ptr, table_view_from_columns

python/cudf/cudf/_lib/io/utils.pyx

@@ -2,9 +2,7 @@
 
 from cpython.buffer cimport PyBUF_READ
 from cpython.memoryview cimport PyMemoryView_FromMemory
-from libcpp.map cimport map
 from libcpp.memory cimport unique_ptr
-from libcpp.pair cimport pair
 from libcpp.string cimport string
 from libcpp.utility cimport move
 from libcpp.vector cimport vector
@@ -15,7 +13,6 @@ from cudf._lib.cpp.io.types cimport (
     data_sink,
     datasource,
     host_buffer,
-    io_type,
     sink_info,
     source_info,
 )
@@ -26,7 +23,6 @@ import errno
 import io
 import os
 
-import cudf
 from cudf.api.types import is_struct_dtype
 
 

python/cudf/cudf/_lib/join.pyx

@@ -1,19 +1,12 @@
 # Copyright (c) 2020-2022, NVIDIA CORPORATION.
 
-from itertools import chain
-
-import cudf
-
-from libcpp cimport bool
 from libcpp.memory cimport make_unique, unique_ptr
 from libcpp.pair cimport pair
 from libcpp.utility cimport move
-from libcpp.vector cimport vector
 
 cimport cudf._lib.cpp.join as cpp_join
 from cudf._lib.column cimport Column
 from cudf._lib.cpp.column.column cimport column
-from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view
 from cudf._lib.cpp.types cimport data_type, size_type, type_id
 from cudf._lib.utils cimport table_view_from_columns

python/cudf/cudf/_lib/json.pyx

@@ -2,7 +2,6 @@
 
 # cython: boundscheck = False
 
-
 import io
 import os
 from collections import abc
@@ -16,13 +15,12 @@ from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
 cimport cudf._lib.cpp.io.types as cudf_io_types
-cimport cudf._lib.cpp.types as libcudf_types
 from cudf._lib.cpp.io.json cimport (
     json_reader_options,
     read_json as libcudf_read_json,
     schema_element,
 )
-from cudf._lib.cpp.types cimport data_type, size_type, type_id
+from cudf._lib.cpp.types cimport data_type, size_type
 from cudf._lib.io.utils cimport make_source_info, update_struct_field_names
 from cudf._lib.types cimport dtype_to_data_type
 from cudf._lib.utils cimport data_from_unique_ptr

python/cudf/cudf/_lib/labeling.pyx

@@ -1,18 +1,10 @@
-# Copyright (c) 2021, NVIDIA CORPORATION.
+# Copyright (c) 2021-2022, NVIDIA CORPORATION.
 
-from enum import IntEnum
-
-import numpy as np
-
-from libc.stdint cimport uint32_t
 from libcpp cimport bool as cbool
 from libcpp.memory cimport unique_ptr
 from libcpp.utility cimport move
 
 from cudf._lib.column cimport Column
-
-from cudf._lib.replace import replace_nulls
-
 from cudf._lib.cpp.column.column cimport column
 from cudf._lib.cpp.column.column_view cimport column_view
 from cudf._lib.cpp.labeling cimport inclusive, label_bins as cpp_label_bins

python/cudf/cudf/_lib/lists.pyx

@@ -12,10 +12,12 @@ from cudf._lib.cpp.lists.combine cimport (
     concatenate_null_policy,
     concatenate_rows as cpp_concatenate_rows,
 )
+from cudf._lib.cpp.lists.contains cimport contains, index_of as cpp_index_of
 from cudf._lib.cpp.lists.count_elements cimport (
     count_elements as cpp_count_elements,
 )
 from cudf._lib.cpp.lists.explode cimport explode_outer as cpp_explode_outer
+from cudf._lib.cpp.lists.extract cimport extract_list_element
 from cudf._lib.cpp.lists.lists_column_view cimport lists_column_view
 from cudf._lib.cpp.lists.sorting cimport sort_lists as cpp_sort_lists
 from cudf._lib.cpp.lists.stream_compaction cimport distinct as cpp_distinct
@@ -26,20 +28,10 @@ from cudf._lib.cpp.types cimport (
     nan_equality,
     null_equality,
     null_order,
-    null_policy,
     order,
     size_type,
 )
 from cudf._lib.scalar cimport DeviceScalar
-from cudf._lib.types cimport (
-    underlying_type_t_null_order,
-    underlying_type_t_order,
-)
-
-from cudf.core.dtypes import ListDtype
-
-from cudf._lib.cpp.lists.contains cimport contains, index_of as cpp_index_of
-from cudf._lib.cpp.lists.extract cimport extract_list_element
 from cudf._lib.utils cimport columns_from_unique_ptr, table_view_from_columns
 
 

python/cudf/cudf/_lib/merge.pyx

@@ -6,7 +6,6 @@ from libcpp.utility cimport move
 from libcpp.vector cimport vector
 
 cimport cudf._lib.cpp.types as libcudf_types
-from cudf._lib.column cimport Column
 from cudf._lib.cpp.merge cimport merge as cpp_merge
 from cudf._lib.cpp.table.table cimport table
 from cudf._lib.cpp.table.table_view cimport table_view