Merge branch 'branch-24.06' into 15678

.pre-commit-config.yaml

@@ -2,7 +2,7 @@
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.5.0
+    rev: v4.6.0
     hooks:
       - id: trailing-whitespace
         exclude: |
@@ -24,11 +24,11 @@ repos:
         files: python/.*
         types_or: [python, cython, pyi]
   - repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.16.0
+    rev: v0.16.2
     hooks:
       - id: cython-lint
   - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: 'v1.3.0'
+    rev: 'v1.10.0'
     hooks:
       - id: mypy
         additional_dependencies: [types-cachetools]
@@ -39,7 +39,7 @@ repos:
                "python/dask_cudf/dask_cudf"]
         pass_filenames: false
   - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.7.1
+    rev: 1.8.5
     hooks:
       - id: nbqa-isort
         # Use the cudf_kafka isort orderings in notebooks so that dask
@@ -52,7 +52,7 @@ repos:
         types_or: [c, c++, cuda]
         args: ["-fallback-style=none", "-style=file", "-i"]
   - repo: https://github.com/sirosen/texthooks
-    rev: 0.6.3
+    rev: 0.6.6
     hooks:
       - id: fix-smartquotes
         exclude: |
@@ -124,12 +124,12 @@ repos:
             ^CHANGELOG.md$
           )
   - repo: https://github.com/rapidsai/dependency-file-generator
-    rev: v1.8.0
+    rev: v1.13.4
     hooks:
       - id: rapids-dependency-file-generator
         args: ["--clean"]
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.3.4
+    rev: v0.4.3
     hooks:
       - id: ruff
         files: python/.*$

ci/cudf_pandas_scripts/pandas-tests/diff.sh

@@ -17,10 +17,8 @@ MAIN_ARTIFACT=$(rapids-s3-path)cuda12_$(arch)_py${PY_VER}.main-${RAPIDS_FULL_VER
 PR_ARTIFACT=$(rapids-s3-path)cuda12_$(arch)_py${PY_VER}.pr-${RAPIDS_FULL_VERSION}-results.json
 
 rapids-logger "Fetching latest available results from nightly"
-aws s3api list-objects-v2 --bucket rapids-downloads --prefix "nightly/" --query "sort_by(Contents[?ends_with(Key, '_py${PY_VER}.main-${RAPIDS_FULL_VERSION}-results.json')], &LastModified)[::-1].[Key]" --output text > s3_output.txt
-
-read -r COMPARE_ENV < s3_output.txt
-export COMPARE_ENV
+aws s3api list-objects-v2 --bucket rapids-downloads --prefix "nightly/" --query "sort_by(Contents[?ends_with(Key, '_py${PY_VER}.main-${RAPIDS_FULL_VERSION}-results.json')], &LastModified)[::].[Key]" --output text  | tee s3_output.txt
+COMPARE_ENV=$(tail -n 1 s3_output.txt)
 rapids-logger "Latest available results from nightly: ${COMPARE_ENV}"
 
 aws s3 cp "s3://rapids-downloads/${COMPARE_ENV}" main-results.json

cpp/src/strings/combine/join.cu

@@ -162,16 +162,16 @@ std::unique_ptr<column> join_strings(strings_column_view const& input,
     return std::move(*chars_data);
   }();
 
+  // API returns a single output row which cannot exceed row limit(max of size_type).
+  CUDF_EXPECTS(chars.size() < static_cast<std::size_t>(std::numeric_limits<size_type>::max()),
+               "The output exceeds the row size limit",
+               std::overflow_error);
+
   // build the offsets: single string output has offsets [0,chars-size]
   auto offsets_column = [&] {
-    if (chars.size() < static_cast<std::size_t>(get_offset64_threshold())) {
-      auto offsets32 = cudf::detail::make_device_uvector_async(
-        std::vector<int32_t>({0, static_cast<int32_t>(chars.size())}), stream, mr);
-      return std::make_unique<column>(std::move(offsets32), rmm::device_buffer{}, 0);
-    }
-    auto offsets64 = cudf::detail::make_device_uvector_async(
-      std::vector<int64_t>({0L, static_cast<int64_t>(chars.size())}), stream, mr);
-    return std::make_unique<column>(std::move(offsets64), rmm::device_buffer{}, 0);
+    auto offsets = cudf::detail::make_device_uvector_async(
+      std::vector<size_type>({0, static_cast<size_type>(chars.size())}), stream, mr);
+    return std::make_unique<column>(std::move(offsets), rmm::device_buffer{}, 0);
   }();
 
   // build the null mask: only one output row so it is either all-valid or all-null

python/cudf/cudf/core/column/column.py

@@ -2211,7 +2211,7 @@ def _mask_from_cuda_array_interface_desc(obj, cai_mask) -> Buffer:
         raise NotImplementedError(f"Cannot infer mask from typestr {typestr}")
 
 
-def serialize_columns(columns) -> Tuple[List[dict], List]:
+def serialize_columns(columns: list[ColumnBase]) -> Tuple[List[dict], List]:
     """
     Return the headers and frames resulting
     from serializing a list of Column

python/cudf/cudf/pandas/fast_slow_proxy.py

@@ -1093,7 +1093,7 @@ def _replace_closurevars(
     f: types.FunctionType,
     attribute_name: Literal["_fsproxy_slow", "_fsproxy_fast"],
     seen: Set[int],
-) -> types.FunctionType:
+) -> Callable[..., Any]:
     """
     Return a copy of `f` with its closure variables replaced with
     their corresponding slow (or fast) types.
@@ -1133,12 +1133,11 @@ def _replace_closurevars(
         argdefs=f.__defaults__,
         closure=g_closure,
     )
-    g = functools.update_wrapper(
+    return functools.update_wrapper(
         g,
         f,
         assigned=functools.WRAPPER_ASSIGNMENTS + ("__kwdefaults__",),
     )
-    return g
 
 
 _SPECIAL_METHODS: Set[str] = {