Lemmatization of Nouns - French : adding rules and vocabulary (#2992)

* modifying FR lemmatization for nouns

* modifying FR lemmatization for nouns

* adding contributor agreement for amperinet

* adding rules for words with inclusive parentheses wrongly tokenized

* adding contributor agreement for amperinet

* adding a missing comma

spacy/lang/fr/lemmatizer/_lemma_rules.py

@@ -10,7 +10,89 @@ ADJECTIVE_RULES = [
     
     
 NOUN_RULES = [
-    ["s", ""]
+    ["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"],
+
+    ["as", "a"],
+    ["aux", "au"],
+    ["cs", "c"],
+    ["chs", "ch"],
+    ["ds", "d"],
+    ["és", "é"],
+    ["es", "e"],
+    ["eux", "eu"],
+    ["fs", "f"],
+    ["gs", "g"],
+    ["hs", "h"],
+    ["is", "i"],
+    ["ïs", "ï"],
+    ["js", "j"],
+    ["ks", "k"],
+    ["ls", "l"],
+    ["ms", "m"],
+    ["ns", "n"],
+    ["oux", "ou"],
+    ["os", "o"],
+    ["ps", "p"],
+    ["qs", "q"],
+    ["rs", "r"],
+    ["ses", "se"],
+    ["se", "se"],
+    ["ts", "t"],
+    ["us", "u"],
+    ["vs", "v"],
+    ["ws", "w"],
+    ["ys", "y"],
+
+    ["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"]
 ]
 
 
@@ -60,5 +142,5 @@ VERB_RULES = [
     ["u(er", "u"],
     ["és(ées", "er"],
     ["é()e", "er"],
-    ["é()", "er"],
+    ["é()", "er"]
 ]