[pre-commit.ci] pre-commit autoupdate (#1890)

* [pre-commit.ci] pre-commit autoupdate

updates:
- [github.com/astral-sh/ruff-pre-commit: v0.15.22 → v0.16.0](astral-sh/ruff-pre-commit@v0.15.22...v0.16.0)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* fix: restore CI after Ruff 0.16 upgrade

* fix: clean up safe Ruff 0.16 findings

* fix: pass plain string to UdfSignatureError

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>

Author: pre-commit-ci[bot]

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       - id: trailing-whitespace
         exclude: '^LICENSES/'
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: 'v0.15.22'
+    rev: 'v0.16.0'
     hooks:
       - id: ruff
         args: [--fix, --exit-non-zero-on-fix]

pyproject.toml

@@ -243,6 +243,7 @@ explicit-preview-rules = true
 ignore = [
   "S101",  # assert
   "PLR2004",  # magic-value-comparison
+  "PLR0917",  # too-many-positional-arguments
   "PLW2901",  # redefined-loop-name
   "ISC001",  # single-line-implicit-string-concatenation, incompatible with ruff format
   "RET502",  # implicit-return-value

src/datachain/lib/listing.py

@@ -296,7 +296,7 @@ def get_listing(
     # - if an exact listing exists it will have the same name as `ds_name`
     #   anyway below
     if listings and not update:
-        listing = sorted(listings, key=lambda ls: ls.created_at)[-1]
+        listing = max(listings, key=lambda ls: ls.created_at)
 
     # for local file system we need to fix listing path / prefix
     # if we are reusing existing listing

src/datachain/lib/signal_schema.py

@@ -473,7 +473,7 @@ def _resolve_type(  # noqa: PLR0911
             return None
 
         bracket_idx = type_name.find("[")
-        subtypes: tuple[object | None | types.EllipsisType, ...] | None = None
+        subtypes: tuple[object | types.EllipsisType | None, ...] | None = None
         if bracket_idx > -1:
             if bracket_idx == 0:
                 raise ValueError("Type cannot start with '['")
@@ -1374,7 +1374,7 @@ def __contains__(self, name: str):
 
     @staticmethod
     def _type_to_str(
-        type_: type | None | types.EllipsisType, subtypes: list | None = None
+        type_: type | types.EllipsisType | None, subtypes: list | None = None
     ) -> str:
         """Convert a type to a string-based representation."""
 

src/datachain/lib/udf_signature.py

@@ -37,10 +37,8 @@ def parse(
         if len(signal_map) > 1:
             raise UdfSignatureError(
                 chain,
-                (
-                    f"multiple signals '{keys}' are not supported in processors."
-                    " Chain multiple processors instead.",
-                ),
+                f"multiple signals '{keys}' are not supported in processors."
+                " Chain multiple processors instead.",
             )
         udf_func: UDFBase | Callable
         if len(signal_map) == 1:

src/datachain/lib/utils.py

@@ -171,7 +171,7 @@ def _to_posix(path: str) -> str:
 
 
 def type_to_str(  # noqa: C901, PLR0911, PLR0912
-    type_: type | None | types.EllipsisType,
+    type_: type | types.EllipsisType | None,
     subtypes: list | None = None,
     *,
     warn_with: Callable[[str], None] | None = None,

src/datachain/query/dataset.py

@@ -1631,7 +1631,7 @@ def calculate_unprocessed_rows(
         self,
         input_query: Select,
         partial_table: "Table",
-        incomplete_input_ids: None | list[int] = None,
+        incomplete_input_ids: list[int] | None = None,
     ) -> Select:
         """
         Calculate which input rows haven't been processed yet.

tests/func/test_datachain.py

@@ -475,8 +475,11 @@ def test_show_transpose(capsys, test_session):
 def test_show_truncate(capsys, test_session):
     client = ["Alice A", "Bob B", "Charles C"]
     details = [
-        "This is a very long piece of text that would not fit in the default output "
-        "because pandas will truncate the column",
+        (
+            "This is a very long piece of text that would not fit in the default "
+            "output "
+            "because pandas will truncate the column"
+        ),
         "Gives good tips",
         "Not very nice",
     ]
@@ -499,8 +502,11 @@ def test_show_truncate(capsys, test_session):
 def test_show_no_truncate(capsys, test_session):
     client = ["Alice A", "Bob B", "Charles C"]
     details = [
-        "This is a very long piece of text that would not fit in the default output "
-        "because pandas will truncate the column",
+        (
+            "This is a very long piece of text that would not fit in the default "
+            "output "
+            "because pandas will truncate the column"
+        ),
         "Gives good tips",
         "Not very nice",
     ]

tests/func/test_read_dataset_remote.py

@@ -54,8 +54,10 @@ def remote_dataset_version_v1(
         "schema": remote_dataset_schema,
         "sources": "",
         "query_script": (
-            "from datachain.query.dataset import DatasetQuery\n"
-            'DatasetQuery(path="s3://test-bucket")',
+            (
+                "from datachain.query.dataset import DatasetQuery\n"
+                'DatasetQuery(path="s3://test-bucket")'
+            ),
         ),
         "created_by_id": 1,
         "_preview_loaded": True,
@@ -84,8 +86,10 @@ def remote_dataset_version_v2(
         "schema": remote_dataset_schema,
         "sources": "",
         "query_script": (
-            "from datachain.query.dataset import DatasetQuery\n"
-            'DatasetQuery(path="s3://test-bucket")',
+            (
+                "from datachain.query.dataset import DatasetQuery\n"
+                'DatasetQuery(path="s3://test-bucket")'
+            ),
         ),
         "created_by_id": 1,
         "_preview_loaded": True,
@@ -192,8 +196,10 @@ def _mock_export_response(request, context):
         return {
             "export_id": 1,
             "signed_urls": [
-                f"https://studio-blobvault.s3.amazonaws.com/"
-                f"datachain_ds_export_{version_file}.parquet.lz4"
+                (
+                    "https://studio-blobvault.s3.amazonaws.com/"
+                    f"datachain_ds_export_{version_file}.parquet.lz4"
+                )
             ],
         }