spaCy/spacy/lang/lb/norm_exceptions.py

14 lines
403 B
Python
Raw Normal View History

# TODO
2019-10-18 12:27:38 +03:00
# norm execptions: find a possibility to deal with the zillions of spelling
# variants (vläicht = vlaicht, vleicht, viläicht, viläischt, etc. etc.)
# here one could include the most common spelling mistakes
_exc = {"dass": "datt", "viläicht": "vläicht"}
NORM_EXCEPTIONS = {}
for string, norm in _exc.items():
NORM_EXCEPTIONS[string] = norm
2019-10-18 12:27:38 +03:00
NORM_EXCEPTIONS[string.title()] = norm