github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-18 08:03:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

text-splitters: Ruff autofixes (#31858)

Browse Source 
Auto-fixes from ruff with rule `ALL`
This commit is contained in:
Christophe Bornet
2025-07-07 16:06:08 +02:00
committed by GitHub
parent 8aed3b61a9
commit 451c90fefa
16 changed files with 121 additions and 123 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
libs/text-splitters/tests/unit_tests/conftest.py
View File

@@ -45,7 +45,8 @@ def pytest_collection_modifyitems(config: Config, items: Sequence[Function]) ->
only_core = config.getoption("--only-core") or False
if only_extended and only_core:
raise ValueError("Cannot specify both `--only-extended` and `--only-core`.")
msg = "Cannot specify both `--only-extended` and `--only-core`."
raise ValueError(msg)
for item in items:
requires_marker = item.get_closest_marker("requires")
@@ -81,8 +82,5 @@ def pytest_collection_modifyitems(config: Config, items: Sequence[Function]) ->
pytest.mark.skip(reason=f"Requires pkg: `{pkg}`")
)
break
else:
if only_extended:
item.add_marker(
pytest.mark.skip(reason="Skipping not an extended test.")
)
elif only_extended:
item.add_marker(pytest.mark.skip(reason="Skipping not an extended test."))

20
libs/text-splitters/tests/unit_tests/test_text_splitters.py
View File

@@ -98,7 +98,7 @@ def test_character_text_splitter_longer_words() -> None:
@pytest.mark.parametrize(
"separator, is_separator_regex", [(re.escape("."), True), (".", False)]
("separator", "is_separator_regex"), [(re.escape("."), True), (".", False)]
)
def test_character_text_splitter_keep_separator_regex(
separator: str, is_separator_regex: bool
@@ -120,7 +120,7 @@ def test_character_text_splitter_keep_separator_regex(
@pytest.mark.parametrize(
"separator, is_separator_regex", [(re.escape("."), True), (".", False)]
("separator", "is_separator_regex"), [(re.escape("."), True), (".", False)]
)
def test_character_text_splitter_keep_separator_regex_start(
separator: str, is_separator_regex: bool
@@ -142,7 +142,7 @@ def test_character_text_splitter_keep_separator_regex_start(
@pytest.mark.parametrize(
"separator, is_separator_regex", [(re.escape("."), True), (".", False)]
("separator", "is_separator_regex"), [(re.escape("."), True), (".", False)]
)
def test_character_text_splitter_keep_separator_regex_end(
separator: str, is_separator_regex: bool
@@ -164,7 +164,7 @@ def test_character_text_splitter_keep_separator_regex_end(
@pytest.mark.parametrize(
"separator, is_separator_regex", [(re.escape("."), True), (".", False)]
("separator", "is_separator_regex"), [(re.escape("."), True), (".", False)]
)
def test_character_text_splitter_discard_separator_regex(
separator: str, is_separator_regex: bool
@@ -250,7 +250,7 @@ def test_create_documents_with_metadata() -> None:
@pytest.mark.parametrize(
"splitter, text, expected_docs",
("splitter", "text", "expected_docs"),
[
(
CharacterTextSplitter(
@@ -1390,7 +1390,7 @@ def test_md_header_text_splitter_fenced_code_block(fence: str) -> None:
assert output == expected_output
@pytest.mark.parametrize(["fence", "other_fence"], [("```", "~~~"), ("~~~", "```")])
@pytest.mark.parametrize(("fence", "other_fence"), [("```", "~~~"), ("~~~", "```")])
def test_md_header_text_splitter_fenced_code_block_interleaved(
fence: str, other_fence: str
) -> None:
@@ -2240,7 +2240,7 @@ def html_header_splitter_splitter_factory() -> Callable[
@pytest.mark.parametrize(
"headers_to_split_on, html_input, expected_documents, test_case",
("headers_to_split_on", "html_input", "expected_documents", "test_case"),
[
(
# Test Case 1: Split on h1 and h2
@@ -2469,7 +2469,7 @@ def test_html_header_text_splitter(
@pytest.mark.parametrize(
"headers_to_split_on, html_content, expected_output, test_case",
("headers_to_split_on", "html_content", "expected_output", "test_case"),
[
(
# Test Case A: Split on h1 and h2 with h3 in content
@@ -2624,7 +2624,7 @@ def test_additional_html_header_text_splitter(
@pytest.mark.parametrize(
"headers_to_split_on, html_content, expected_output, test_case",
("headers_to_split_on", "html_content", "expected_output", "test_case"),
[
(
# Test Case C: Split on h1, h2, and h3 with no headers present
@@ -3551,7 +3551,7 @@ def test_character_text_splitter_discard_regex_separator_on_merge() -> None:
@pytest.mark.parametrize(
"separator,is_regex,text,chunk_size,expected",
("separator", "is_regex", "text", "chunk_size", "expected"),
[
# 1) regex lookaround & split happens
# "abcmiddef" split by "(?<=mid)" → ["abcmid","def"], chunk_size=5 keeps both