text-splitters: Add ruff rule UP (pyupgrade) (#31841)

See https://docs.astral.sh/ruff/rules/#pyupgrade-up
All auto-fixed except `typing.AbstractSet` -> `collections.abc.Set`

libs/text-splitters/tests/unit_tests/conftest.py

@@ -1,7 +1,7 @@
 """Configuration for unit tests."""
 
+from collections.abc import Sequence
 from importlib import util
-from typing import Dict, Sequence
 
 import pytest
 from pytest import Config, Function, Parser
@@ -39,7 +39,7 @@ def pytest_collection_modifyitems(config: Config, items: Sequence[Function]) ->
     """
     # Mapping from the name of a package to whether it is installed or not.
     # Used to avoid repeated calls to `util.find_spec`
-    required_pkgs_info: Dict[str, bool] = {}
+    required_pkgs_info: dict[str, bool] = {}
 
     only_extended = config.getoption("--only-extended") or False
     only_core = config.getoption("--only-core") or False

libs/text-splitters/tests/unit_tests/test_text_splitters.py

@@ -3,7 +3,7 @@
 import random
 import re
 import string
-from typing import Any, Callable, List, Tuple
+from typing import Any, Callable
 
 import pytest
 from langchain_core.documents import Document
@@ -282,7 +282,7 @@ def test_create_documents_with_metadata() -> None:
     ],
 )
 def test_create_documents_with_start_index(
-    splitter: TextSplitter, text: str, expected_docs: List[Document]
+    splitter: TextSplitter, text: str, expected_docs: list[Document]
 ) -> None:
     """Test create documents method."""
     docs = splitter.create_documents([text])
@@ -333,7 +333,7 @@ def test_iterative_text_splitter_discard_separator() -> None:
     ]
 
 
-def __test_iterative_text_splitter(chunk_size: int, keep_separator: bool) -> List[str]:
+def __test_iterative_text_splitter(chunk_size: int, keep_separator: bool) -> list[str]:
     chunk_size += 1 if keep_separator else 0
 
     splitter = RecursiveCharacterTextSplitter(
@@ -2224,7 +2224,7 @@ def test_haskell_code_splitter() -> None:
 @pytest.fixture
 @pytest.mark.requires("bs4")
 def html_header_splitter_splitter_factory() -> Callable[
-    [List[Tuple[str, str]]], HTMLHeaderTextSplitter
+    [list[tuple[str, str]]], HTMLHeaderTextSplitter
 ]:
     """
     Fixture to create an HTMLHeaderTextSplitter instance with given headers.
@@ -2232,7 +2232,7 @@ def html_header_splitter_splitter_factory() -> Callable[
     """
 
     def _create_splitter(
-        headers_to_split_on: List[Tuple[str, str]],
+        headers_to_split_on: list[tuple[str, str]],
     ) -> HTMLHeaderTextSplitter:
         return HTMLHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
 
@@ -2426,9 +2426,9 @@ def html_header_splitter_splitter_factory() -> Callable[
 @pytest.mark.requires("bs4")
 def test_html_header_text_splitter(
     html_header_splitter_splitter_factory: Any,
-    headers_to_split_on: List[Tuple[str, str]],
+    headers_to_split_on: list[tuple[str, str]],
     html_input: str,
-    expected_documents: List[Document],
+    expected_documents: list[Document],
     test_case: str,
 ) -> None:
     """
@@ -2582,9 +2582,9 @@ def test_html_header_text_splitter(
 @pytest.mark.requires("bs4")
 def test_additional_html_header_text_splitter(
     html_header_splitter_splitter_factory: Any,
-    headers_to_split_on: List[Tuple[str, str]],
+    headers_to_split_on: list[tuple[str, str]],
     html_content: str,
-    expected_output: List[Document],
+    expected_output: list[Document],
     test_case: str,
 ) -> None:
     """
@@ -2653,9 +2653,9 @@ def test_additional_html_header_text_splitter(
 @pytest.mark.requires("bs4")
 def test_html_no_headers_with_multiple_splitters(
     html_header_splitter_splitter_factory: Any,
-    headers_to_split_on: List[Tuple[str, str]],
+    headers_to_split_on: list[tuple[str, str]],
     html_content: str,
-    expected_output: List[Document],
+    expected_output: list[Document],
     test_case: str,
 ) -> None:
     """
@@ -3572,7 +3572,7 @@ def test_character_text_splitter_chunk_size_effect(
     is_regex: bool,
     text: str,
     chunk_size: int,
-    expected: List[str],
+    expected: list[str],
 ) -> None:
     splitter = CharacterTextSplitter(
         separator=separator,