spaCy/spacy/lang/fr/lemmatizer/_lemma_rules.py
Amandine Périnet eef11a7a2c French lemmatization: correcting wrong lemmas in the lookup dictionnary (#3104)
* modifying French lookup that contained wrong lemmas

* correcting wrong line breaks on hyphen

* adding contributor agreement for amperinet@

* correcting a typo
2019-01-07 14:15:19 +01:00

136 lines
2.3 KiB
Python

# coding: utf8
from __future__ import unicode_literals
ADJECTIVE_RULES = [
["a", "a"],
["aux", "al"],
["c", "c"],
["d", "d"],
["e", ""],
["é", "é"],
["eux", "eux"],
["f", "f"],
["i", "i"],
["ï", "ï"],
["l", "l"],
["m", "m"],
["n", "n"],
["o", "o"],
["p", "p"],
["r", "r"],
["s", ""],
["t", "t"],
["u", "u"],
["y", "y"]
]
NOUN_RULES = [
["a", "a"],
["à", "à"],
["â", "â"],
["b", "b"],
["c", "c"],
["ç", "ç"],
["d", "d"],
["e", "e"],
["é", "é"],
["è", "è"],
["ê", "ê"],
["ë", "ë"],
["f", "f"],
["g", "g"],
["h", "h"],
["i", "i"],
["î", "î"],
["ï", "ï"],
["j", "j"],
["k", "k"],
["l", "l"],
["m", "m"],
["n", "n"],
["o", "o"],
["ô", "ö"],
["ö", "ö"],
["p", "p"],
["q", "q"],
["r", "r"],
["t", "t"],
["u", "u"],
["û", "û"],
["v", "v"],
["w", "w"],
["y", "y"],
["z", "z"],
["s", ""],
["x", ""],
["nt(e", "nt"],
["nt(e)", "nt"],
["al(e", "ale"],
["é(", "é"],
["é(e", "é"],
["é.e", "é"],
["el(le", "el"],
["eurs(rices", "eur"],
["eur(rice", "eur"],
["eux(se", "eux"],
["ial(e","ial"],
["er(ère", "er"],
["eur(se", "eur"],
["teur(trice", "teur"],
["teurs(trices", "teur"]
]
VERB_RULES = [
["é", "er"],
["és", "er"],
["ée", "er"],
["ées", "er"],
["é", "er"],
["es", "er"],
["ons", "er"],
["ez", "er"],
["ent", "er"],
["ais", "er"],
["ait", "er"],
["ions", "er"],
["iez", "er"],
["aient", "er"],
["ai", "er"],
["as", "er"],
["a", "er"],
["âmes", "er"],
["âtes", "er"],
["èrent", "er"],
["erai", "er"],
["eras", "er"],
["era", "er"],
["erons", "er"],
["erez", "er"],
["eront", "er"],
["erais", "er"],
["erait", "er"],
["erions", "er"],
["eriez", "er"],
["eraient", "er"],
["asse", "er"],
["asses", "er"],
["ât", "er"],
["assions", "er"],
["assiez", "er"],
["assent", "er"],
["ant", "er"],
["ante", "er"],
["ants", "er"],
["antes", "er"],
["u(er", "u"],
["és(ées", "er"],
["é()e", "er"],
["é()", "er"]
]