langchain/libs/text-splitters/Makefile

72 lines
2.2 KiB
Makefile
Raw Normal View History

.PHONY: all format lint test tests test_watch integration_tests docker_tests help extended_tests
# Default target executed when no arguments are given to make.
all: help
# Define a variable for the test file path.
TEST_FILE ?= tests/unit_tests/
test:
poetry run pytest $(TEST_FILE)
tests:
poetry run pytest $(TEST_FILE)
test_watch:
poetry run ptw --snapshot-update --now . -- -vv -x tests/unit_tests
test_profile:
poetry run pytest -vv tests/unit_tests/ --profile-svg
check_imports: $(shell find langchain_text_splitters -name '*.py')
poetry run python ./scripts/check_imports.py $^
extended_tests:
poetry run pytest --only-extended $(TEST_FILE)
######################
# LINTING AND FORMATTING
######################
# Define a variable for Python and notebook files.
PYTHON_FILES=.
MYPY_CACHE=.mypy_cache
lint format: PYTHON_FILES=.
lint_diff format_diff: PYTHON_FILES=$(shell git diff --relative=libs/core --name-only --diff-filter=d master | grep -E '\.py$$|\.ipynb$$')
lint_package: PYTHON_FILES=langchain_text_splitters
lint_tests: PYTHON_FILES=tests
lint_tests: MYPY_CACHE=.mypy_cache_test
lint lint_diff lint_package lint_tests:
./scripts/check_pydantic.sh .
./scripts/lint_imports.sh
infra: update mypy 1.10, ruff 0.5 (#23721) ```python """python scripts/update_mypy_ruff.py""" import glob import tomllib from pathlib import Path import toml import subprocess import re ROOT_DIR = Path(__file__).parents[1] def main(): for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True): print(path) with open(path, "rb") as f: pyproject = tomllib.load(f) try: pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = ( "^1.10" ) pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = ( "^0.5" ) except KeyError: continue with open(path, "w") as f: toml.dump(pyproject, f) cwd = "/".join(path.split("/")[:-1]) completed = subprocess.run( "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color", cwd=cwd, shell=True, capture_output=True, text=True, ) logs = completed.stdout.split("\n") to_ignore = {} for l in logs: if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l): path, line_no, error_type = re.match( "^(.*)\:(\d+)\: error:.*\[(.*)\]", l ).groups() if (path, line_no) in to_ignore: to_ignore[(path, line_no)].append(error_type) else: to_ignore[(path, line_no)] = [error_type] print(len(to_ignore)) for (error_path, line_no), error_types in to_ignore.items(): all_errors = ", ".join(error_types) full_path = f"{cwd}/{error_path}" try: with open(full_path, "r") as f: file_lines = f.readlines() except FileNotFoundError: continue file_lines[int(line_no) - 1] = ( file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n" ) with open(full_path, "w") as f: f.write("".join(file_lines)) subprocess.run( "poetry run ruff format .; poetry run ruff --select I --fix .", cwd=cwd, shell=True, capture_output=True, text=True, ) if __name__ == "__main__": main() ```
2024-07-03 17:33:27 +00:00
poetry run ruff check .
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff format $(PYTHON_FILES) --diff
infra: update mypy 1.10, ruff 0.5 (#23721) ```python """python scripts/update_mypy_ruff.py""" import glob import tomllib from pathlib import Path import toml import subprocess import re ROOT_DIR = Path(__file__).parents[1] def main(): for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True): print(path) with open(path, "rb") as f: pyproject = tomllib.load(f) try: pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = ( "^1.10" ) pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = ( "^0.5" ) except KeyError: continue with open(path, "w") as f: toml.dump(pyproject, f) cwd = "/".join(path.split("/")[:-1]) completed = subprocess.run( "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color", cwd=cwd, shell=True, capture_output=True, text=True, ) logs = completed.stdout.split("\n") to_ignore = {} for l in logs: if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l): path, line_no, error_type = re.match( "^(.*)\:(\d+)\: error:.*\[(.*)\]", l ).groups() if (path, line_no) in to_ignore: to_ignore[(path, line_no)].append(error_type) else: to_ignore[(path, line_no)] = [error_type] print(len(to_ignore)) for (error_path, line_no), error_types in to_ignore.items(): all_errors = ", ".join(error_types) full_path = f"{cwd}/{error_path}" try: with open(full_path, "r") as f: file_lines = f.readlines() except FileNotFoundError: continue file_lines[int(line_no) - 1] = ( file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n" ) with open(full_path, "w") as f: f.write("".join(file_lines)) subprocess.run( "poetry run ruff format .; poetry run ruff --select I --fix .", cwd=cwd, shell=True, capture_output=True, text=True, ) if __name__ == "__main__": main() ```
2024-07-03 17:33:27 +00:00
[ "$(PYTHON_FILES)" = "" ] || poetry run ruff check --select I $(PYTHON_FILES)
[ "$(PYTHON_FILES)" = "" ] || poetry run mypy $(PYTHON_FILES)
[ "$(PYTHON_FILES)" = "" ] || mkdir -p $(MYPY_CACHE) && poetry run mypy $(PYTHON_FILES) --cache-dir $(MYPY_CACHE)
format format_diff:
poetry run ruff format $(PYTHON_FILES)
infra: update mypy 1.10, ruff 0.5 (#23721) ```python """python scripts/update_mypy_ruff.py""" import glob import tomllib from pathlib import Path import toml import subprocess import re ROOT_DIR = Path(__file__).parents[1] def main(): for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True): print(path) with open(path, "rb") as f: pyproject = tomllib.load(f) try: pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = ( "^1.10" ) pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = ( "^0.5" ) except KeyError: continue with open(path, "w") as f: toml.dump(pyproject, f) cwd = "/".join(path.split("/")[:-1]) completed = subprocess.run( "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color", cwd=cwd, shell=True, capture_output=True, text=True, ) logs = completed.stdout.split("\n") to_ignore = {} for l in logs: if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l): path, line_no, error_type = re.match( "^(.*)\:(\d+)\: error:.*\[(.*)\]", l ).groups() if (path, line_no) in to_ignore: to_ignore[(path, line_no)].append(error_type) else: to_ignore[(path, line_no)] = [error_type] print(len(to_ignore)) for (error_path, line_no), error_types in to_ignore.items(): all_errors = ", ".join(error_types) full_path = f"{cwd}/{error_path}" try: with open(full_path, "r") as f: file_lines = f.readlines() except FileNotFoundError: continue file_lines[int(line_no) - 1] = ( file_lines[int(line_no) - 1][:-1] + f" # type: ignore[{all_errors}]\n" ) with open(full_path, "w") as f: f.write("".join(file_lines)) subprocess.run( "poetry run ruff format .; poetry run ruff --select I --fix .", cwd=cwd, shell=True, capture_output=True, text=True, ) if __name__ == "__main__": main() ```
2024-07-03 17:33:27 +00:00
poetry run ruff check --select I --fix $(PYTHON_FILES)
spell_check:
poetry run codespell --toml pyproject.toml
spell_fix:
poetry run codespell --toml pyproject.toml -w
######################
# HELP
######################
help:
@echo '----'
@echo 'format - run code formatters'
@echo 'lint - run linters'
@echo 'test - run unit tests'
@echo 'tests - run unit tests'
@echo 'test TEST_FILE=<test_file> - run all tests in file'
@echo 'test_watch - run unit tests in watch mode'