mirror of
https://github.com/mii443/tokenizers.git
synced 2025-08-22 16:25:30 +00:00
0ff2ab0f64
* Fixing the stream by removing the read_index altogether. * Moving the test location because.. Windows. * Ok whatever. * Rust 1.84 * Fmt.
38 lines
908 B
Makefile
38 lines
908 B
Makefile
.PHONY: style check-style test
|
|
|
|
DATA_DIR = data
|
|
|
|
dir_guard=@mkdir -p $(@D)
|
|
check_dirs := examples py_src/tokenizers tests
|
|
|
|
# Format source code automatically
|
|
style:
|
|
python stub.py
|
|
ruff check $(check_dirs) --fix
|
|
ruff format $(check_dirs)
|
|
|
|
# Check the source code is formatted correctly
|
|
check-style:
|
|
python stub.py --check
|
|
ruff check $(check_dirs)
|
|
ruff format --check $(check_dirs)
|
|
|
|
TESTS_RESOURCES = $(DATA_DIR)/small.txt $(DATA_DIR)/roberta.json
|
|
|
|
# Launch the test suite
|
|
test: $(TESTS_RESOURCES)
|
|
pip install pytest requests setuptools_rust numpy pyarrow datasets
|
|
python -m pytest -s -v tests
|
|
cargo test --no-default-features
|
|
|
|
$(DATA_DIR)/big.txt :
|
|
$(dir_guard)
|
|
wget https://norvig.com/big.txt -O $@
|
|
|
|
$(DATA_DIR)/small.txt : $(DATA_DIR)/big.txt
|
|
head -100 $(DATA_DIR)/big.txt > $@
|
|
|
|
$(DATA_DIR)/roberta.json :
|
|
$(dir_guard)
|
|
wget https://huggingface.co/roberta-large/raw/main/tokenizer.json -O $@
|