├── .github ├── stale.yml └── workflows │ └── python-publish.yml ├── .gitignore ├── .gitmodules ├── LICENSE ├── MANIFEST.in ├── README.md ├── conda_build ├── bifixer │ ├── build.sh │ └── meta.yaml └── make_build.sh ├── pyproject.toml └── src ├── bifixer ├── __init__.py ├── bifixer.py ├── detok │ └── detok.mt ├── monofixer.py ├── replacements │ ├── replacements.da │ ├── replacements.de │ ├── replacements.en │ ├── replacements.es │ ├── replacements.fr │ ├── replacements.nb │ ├── replacements.nl │ ├── replacements.pt │ └── replacements.tr ├── restorative_cleaning.py ├── segmenter.py └── util.py └── tests ├── input_test_1.txt ├── input_test_2.txt ├── output_expected_1.txt ├── output_test_1.txt └── test_bifixer.py /.github/stale.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/.github/stale.yml -------------------------------------------------------------------------------- /.github/workflows/python-publish.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/.github/workflows/python-publish.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitmodules: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/LICENSE -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/MANIFEST.in -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/README.md -------------------------------------------------------------------------------- /conda_build/bifixer/build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/conda_build/bifixer/build.sh -------------------------------------------------------------------------------- /conda_build/bifixer/meta.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/conda_build/bifixer/meta.yaml -------------------------------------------------------------------------------- /conda_build/make_build.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/conda_build/make_build.sh -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/pyproject.toml -------------------------------------------------------------------------------- /src/bifixer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/__init__.py -------------------------------------------------------------------------------- /src/bifixer/bifixer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/bifixer.py -------------------------------------------------------------------------------- /src/bifixer/detok/detok.mt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/detok/detok.mt -------------------------------------------------------------------------------- /src/bifixer/monofixer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/monofixer.py -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.da: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.da -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.de: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.de -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.en: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.en -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.es: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.es -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.fr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.fr -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.nb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.nb -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.nl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.nl -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.pt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.pt -------------------------------------------------------------------------------- /src/bifixer/replacements/replacements.tr: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/replacements/replacements.tr -------------------------------------------------------------------------------- /src/bifixer/restorative_cleaning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/restorative_cleaning.py -------------------------------------------------------------------------------- /src/bifixer/segmenter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/segmenter.py -------------------------------------------------------------------------------- /src/bifixer/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/bifixer/util.py -------------------------------------------------------------------------------- /src/tests/input_test_1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/tests/input_test_1.txt -------------------------------------------------------------------------------- /src/tests/input_test_2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/tests/input_test_2.txt -------------------------------------------------------------------------------- /src/tests/output_expected_1.txt: -------------------------------------------------------------------------------- 1 | URL1 URL2 Source Target 2 | -------------------------------------------------------------------------------- /src/tests/output_test_1.txt: -------------------------------------------------------------------------------- 1 | URL1 URL2 Source Target 2 | -------------------------------------------------------------------------------- /src/tests/test_bifixer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/bitextor/bifixer/HEAD/src/tests/test_bifixer.py --------------------------------------------------------------------------------