explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-04 21:50:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix Spanish lemmatizer

Browse Source
This commit is contained in:
Matthew Honnibal 2024-09-04 14:29:34 +02:00
parent 6f7590bbf1
commit 3ee1b2bd1f
1 changed files with 5 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/lang/es/lemmatizer.py
View File

@ -63,13 +63,16 @@ class SpanishLemmatizer(Lemmatizer):
self.cache[cache_key] = lemmas self.cache[cache_key] = lemmas
return lemmas return lemmas
def select_rule(self, pos: str, features: List[str]) -> Optional[str]: def select_rule(self, pos: str, features: List[str]) -> str:
groups = self.lookups.get_table("lemma_rules_groups") groups = self.lookups.get_table("lemma_rules_groups")
if pos in groups: if pos in groups:
for group in groups[pos]: for group in groups[pos]:
if set(group[1]).issubset(features): if set(group[1]).issubset(features):
return group[0] return group[0]
return None # In v3, returning None here apparently took advantage of a bug in the string store
# that didn't raise an error on None as a value to decode. We emulate the previous
# behaviour by returning "" here, which should not match any lookups as before.
return ""
def lemmatize_adj( def lemmatize_adj(
self, word: str, features: List[str], rule: str, index: List[str] self, word: str, features: List[str], rule: str, index: List[str]