Bump ruff and codespell pre-commit checks

.pre-commit-config.yaml

@@ -113,7 +113,7 @@ repos:
         pass_filenames: false
         verbose: true
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.2
+    rev: v2.2.6
     hooks:
       - id: codespell
         additional_dependencies: [tomli]
@@ -129,7 +129,7 @@ repos:
       - id: rapids-dependency-file-generator
         args: ["--clean"]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.13
+    rev: v0.3.4
     hooks:
       - id: ruff
         files: python/.*$

cpp/include/cudf/io/detail/parquet.hpp

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2023, NVIDIA CORPORATION.
+ * Copyright (c) 2020-2024, NVIDIA CORPORATION.
  *
  * Licensed under the Apache License, Version 2.0 (the "License");
  * you may not use this file except in compliance with the License.
@@ -110,7 +110,7 @@ class chunked_reader : private reader {
    * The chunk_read_limit parameter controls the size of the output chunks produces.  If the user
    * specifies 100 MB of data, the reader will attempt to return chunks containing tables that have
    * a total bytes size (over all columns) of 100 MB or less.  This is a soft limit and the code
-   * will not fail if it cannot satisfy the limit.  It will make a best-effort atttempt only.
+   * will not fail if it cannot satisfy the limit.  It will make a best-effort attempt only.
    *
    * The pass_read_limit parameter controls how much temporary memory is used in the process of
    * decoding the file.  The primary contributor to this memory usage is the uncompressed size of

cpp/src/copying/contiguous_split.cu

@@ -1139,7 +1139,7 @@ struct packed_src_and_dst_pointers {
 
 /**
  * @brief Create an instance of `packed_src_and_dst_pointers` populating destination
- * partitition buffers (if any) from `out_buffers`. In the chunked_pack case
+ * partition buffers (if any) from `out_buffers`. In the chunked_pack case
  * `out_buffers` is empty, and the destination pointer is provided separately
  * to the `copy_partitions` kernel.
  *

cpp/src/io/orc/aggregate_orc_metadata.cpp

@@ -194,7 +194,7 @@ aggregate_orc_metadata::select_stripes(
   } else {
     int64_t count            = 0;
     int64_t stripe_skip_rows = 0;
-    // Iterate all source files, each source file has corelating metadata
+    // Iterate all source files, each source file has correlating metadata
     for (size_t src_file_idx = 0;
          src_file_idx < per_file_metadata.size() && count < rows_to_skip + rows_to_read;
          ++src_file_idx) {

pyproject.toml

@@ -19,7 +19,7 @@ exclude = [
 skip = "./.git,./.github,./cpp/build,.*egg-info.*,./.mypy_cache,./cpp/tests,./python/cudf/cudf/tests,./java/src/test,./cpp/include/cudf_test/cxxopts.hpp"
 # ignore short words, and typename parameters like OffsetT
 ignore-regex = "\\b(.{1,4}|[A-Z]\\w*T)\\b"
-ignore-words-list = "inout,unparseable,falsy"
+ignore-words-list = "inout,unparseable,falsy,couldn,Couldn"
 builtin = "clear"
 quiet-level = 3
 

python/cudf/cudf/core/buffer/buffer.py

@@ -181,7 +181,7 @@ def _from_host_memory(cls, data: Any) -> Self:
         Parameters
         ----------
         data : Any
-            An object that represens host memory.
+            An object that represents host memory.
 
         Returns
         -------

python/cudf/cudf/core/buffer/spillable_buffer.py

@@ -154,7 +154,7 @@ def _from_host_memory(cls, data: Any) -> Self:
         Parameters
         ----------
         data : Any
-            An object that represens host memory.
+            An object that represents host memory.
 
         Returns
         -------

python/cudf/cudf/utils/dtypes.py

@@ -587,7 +587,7 @@ def find_common_type(dtypes):
 def _dtype_pandas_compatible(dtype):
     """
     A utility function, that returns `str` instead of `object`
-    dtype when pandas comptibility mode is enabled.
+    dtype when pandas compatibility mode is enabled.
     """
     if cudf.get_option("mode.pandas_compatible") and dtype == cudf.dtype("O"):
         return "str"