github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-24 23:54:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

text-splitters: Bump ruff version to 0.9 (#29231)

Browse Source 
Co-authored-by: Erick Friis <erick@langchain.dev>
This commit is contained in:
Christophe Bornet 2025-01-22 01:27:58 +01:00 committed by GitHub
parent a004dec119
commit 836c791829
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 40 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
libs/text-splitters/langchain_text_splitters/markdown.py
View File

@ -197,7 +197,10 @@ class MarkdownHeaderTextSplitter:
if current_content:
lines_with_metadata.append(
{"content": "\n".join(current_content), "metadata": current_metadata}
{
"content": "\n".join(current_content),
"metadata": current_metadata,
}
)
# lines_with_metadata has each line with associated header metadata

40
libs/text-splitters/poetry.lock generated
View File

@ -3471,29 +3471,29 @@ files = [
[[package]]
name = "ruff"
version = "0.5.7"
version = "0.9.2"
description = "An extremely fast Python linter and code formatter, written in Rust."
optional = false
python-versions = ">=3.7"
files = [
{file = "ruff-0.5.7-py3-none-linux_armv6l.whl", hash = "sha256:548992d342fc404ee2e15a242cdbea4f8e39a52f2e7752d0e4cbe88d2d2f416a"},
{file = "ruff-0.5.7-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:00cc8872331055ee017c4f1071a8a31ca0809ccc0657da1d154a1d2abac5c0be"},
{file = "ruff-0.5.7-py3-none-macosx_11_0_arm64.whl", hash = "sha256:eaf3d86a1fdac1aec8a3417a63587d93f906c678bb9ed0b796da7b59c1114a1e"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a01c34400097b06cf8a6e61b35d6d456d5bd1ae6961542de18ec81eaf33b4cb8"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:fcc8054f1a717e2213500edaddcf1dbb0abad40d98e1bd9d0ad364f75c763eea"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7f70284e73f36558ef51602254451e50dd6cc479f8b6f8413a95fcb5db4a55fc"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:a78ad870ae3c460394fc95437d43deb5c04b5c29297815a2a1de028903f19692"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9ccd078c66a8e419475174bfe60a69adb36ce04f8d4e91b006f1329d5cd44bcf"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7e31c9bad4ebf8fdb77b59cae75814440731060a09a0e0077d559a556453acbb"},
{file = "ruff-0.5.7-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d796327eed8e168164346b769dd9a27a70e0298d667b4ecee6877ce8095ec8e"},
{file = "ruff-0.5.7-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:4a09ea2c3f7778cc635e7f6edf57d566a8ee8f485f3c4454db7771efb692c499"},
{file = "ruff-0.5.7-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:a36d8dcf55b3a3bc353270d544fb170d75d2dff41eba5df57b4e0b67a95bb64e"},
{file = "ruff-0.5.7-py3-none-musllinux_1_2_i686.whl", hash = "sha256:9369c218f789eefbd1b8d82a8cf25017b523ac47d96b2f531eba73770971c9e5"},
{file = "ruff-0.5.7-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:b88ca3db7eb377eb24fb7c82840546fb7acef75af4a74bd36e9ceb37a890257e"},
{file = "ruff-0.5.7-py3-none-win32.whl", hash = "sha256:33d61fc0e902198a3e55719f4be6b375b28f860b09c281e4bdbf783c0566576a"},
{file = "ruff-0.5.7-py3-none-win_amd64.whl", hash = "sha256:083bbcbe6fadb93cd86709037acc510f86eed5a314203079df174c40bbbca6b3"},
{file = "ruff-0.5.7-py3-none-win_arm64.whl", hash = "sha256:2dca26154ff9571995107221d0aeaad0e75a77b5a682d6236cf89a58c70b76f4"},
{file = "ruff-0.5.7.tar.gz", hash = "sha256:8dfc0a458797f5d9fb622dd0efc52d796f23f0a1493a9527f4e49a550ae9a7e5"},
{file = "ruff-0.9.2-py3-none-linux_armv6l.whl", hash = "sha256:80605a039ba1454d002b32139e4970becf84b5fee3a3c3bf1c2af6f61a784347"},
{file = "ruff-0.9.2-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:b9aab82bb20afd5f596527045c01e6ae25a718ff1784cb92947bff1f83068b00"},
{file = "ruff-0.9.2-py3-none-macosx_11_0_arm64.whl", hash = "sha256:fbd337bac1cfa96be615f6efcd4bc4d077edbc127ef30e2b8ba2a27e18c054d4"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82b35259b0cbf8daa22a498018e300b9bb0174c2bbb7bcba593935158a78054d"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8b6a9701d1e371bf41dca22015c3f89769da7576884d2add7317ec1ec8cb9c3c"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9cc53e68b3c5ae41e8faf83a3b89f4a5d7b2cb666dff4b366bb86ed2a85b481f"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:8efd9da7a1ee314b910da155ca7e8953094a7c10d0c0a39bfde3fcfd2a015684"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3292c5a22ea9a5f9a185e2d131dc7f98f8534a32fb6d2ee7b9944569239c648d"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1a605fdcf6e8b2d39f9436d343d1f0ff70c365a1e681546de0104bef81ce88df"},
{file = "ruff-0.9.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c547f7f256aa366834829a08375c297fa63386cbe5f1459efaf174086b564247"},
{file = "ruff-0.9.2-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:d18bba3d3353ed916e882521bc3e0af403949dbada344c20c16ea78f47af965e"},
{file = "ruff-0.9.2-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:b338edc4610142355ccf6b87bd356729b62bf1bc152a2fad5b0c7dc04af77bfe"},
{file = "ruff-0.9.2-py3-none-musllinux_1_2_i686.whl", hash = "sha256:492a5e44ad9b22a0ea98cf72e40305cbdaf27fac0d927f8bc9e1df316dcc96eb"},
{file = "ruff-0.9.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:af1e9e9fe7b1f767264d26b1075ac4ad831c7db976911fa362d09b2d0356426a"},
{file = "ruff-0.9.2-py3-none-win32.whl", hash = "sha256:71cbe22e178c5da20e1514e1e01029c73dc09288a8028a5d3446e6bba87a5145"},
{file = "ruff-0.9.2-py3-none-win_amd64.whl", hash = "sha256:c5e1d6abc798419cf46eed03f54f2e0c3adb1ad4b801119dedf23fcaf69b55b5"},
{file = "ruff-0.9.2-py3-none-win_arm64.whl", hash = "sha256:a1b63fa24149918f8b37cef2ee6fff81f24f0d74b6f0bdc37bc3e1f2143e41c6"},
{file = "ruff-0.9.2.tar.gz", hash = "sha256:b5eceb334d55fae5f316f783437392642ae18e16dcf4f1858d55d3c2a0f8f5d0"},
]
[[package]]
@ -4802,4 +4802,4 @@ type = ["pytest-mypy"]
[metadata]
lock-version = "2.0"
python-versions = ">=3.9,<4.0"
content-hash = "cdc4edb327b2a72ce35cda46d12dcd77403aa32ddf210e6ae96b32d98deba9b3"
content-hash = "f3bd10c1b313f727c1b43f53627c6afd9416b2a555f01ea84a3c789d86caffcd"

12
libs/text-splitters/pyproject.toml
View File

@ -38,6 +38,9 @@ ignore_missing_imports = "True"
python = ">=3.9,<4.0"
langchain-core = "^0.3.29"
[tool.ruff]
target-version = "py39"
[tool.ruff.lint]
select = ["E", "F", "I", "T201", "D"]
ignore = ["D100"]
@ -72,7 +75,8 @@ convention = "google"
"tests/**" = ["D"]
[tool.poetry.group.lint.dependencies]
ruff = "^0.5"
ruff = "^0.9.2"
@ -84,12 +88,14 @@ tiktoken = "^0.8.0"
[tool.poetry.group.dev.dependencies]
jupyter = "^1.0.0"
[tool.poetry.group.test.dependencies]
pytest = "^8"
freezegun = "^1.2.2"
@ -101,6 +107,7 @@ pytest-xdist = "^3.6.1"
[tool.poetry.group.test_integration]
optional = true
@ -112,18 +119,21 @@ sentence-transformers = { version = ">=2.6.0", python = "<3.13" }
[tool.poetry.group.lint.dependencies.langchain-core]
path = "../core"
develop = true
[tool.poetry.group.dev.dependencies.langchain-core]
path = "../core"
develop = true
[tool.poetry.group.test.dependencies.langchain-core]
path = "../core"
develop = true

17
libs/text-splitters/tests/unit_tests/test_text_splitters.py
View File

@ -1229,12 +1229,7 @@ def test_md_header_text_splitter_fenced_code_block(fence: str) -> None:
"""Test markdown splitter by header: Fenced code block."""
markdown_document = (
"# This is a Header\n\n"
f"{fence}\n"
"foo()\n"
"# Not a header\n"
"bar()\n"
f"{fence}"
f"# This is a Header\n\n{fence}\nfoo()\n# Not a header\nbar()\n{fence}"
)
headers_to_split_on = [
@ -1299,9 +1294,7 @@ def test_md_header_text_splitter_fenced_code_block_interleaved(
def test_md_header_text_splitter_with_invisible_characters(characters: str) -> None:
"""Test markdown splitter by header: Fenced code block."""
markdown_document = (
f"{characters}# Foo\n\n" "foo()\n" f"{characters}## Bar\n\n" "bar()"
)
markdown_document = f"{characters}# Foo\n\nfoo()\n{characters}## Bar\n\nbar()"
headers_to_split_on = [
("#", "Header 1"),
@ -2041,9 +2034,9 @@ def test_haskell_code_splitter() -> None:
@pytest.fixture
@pytest.mark.requires("bs4")
def html_header_splitter_splitter_factory() -> (
Callable[[List[Tuple[str, str]]], HTMLHeaderTextSplitter]
):
def html_header_splitter_splitter_factory() -> Callable[
[List[Tuple[str, str]]], HTMLHeaderTextSplitter
]:
"""
Fixture to create an HTMLHeaderTextSplitter instance with given headers.
This factory allows dynamic creation of splitters with different headers.