explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-29 11:26:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Revert "Fix apparent bug in Spanish lemmatizer. Not sure why this emerges in v4 not in v3"

Browse Source 
This reverts commit 64b22be76e.
This commit is contained in:
Matthew Honnibal 2024-09-04 14:26:39 +02:00
parent 64b22be76e
commit 6f7590bbf1
1 changed files with 6 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
spacy/lang/es/lemmatizer.py
View File

@ -53,15 +53,12 @@ class SpanishLemmatizer(Lemmatizer):
else: else:
rule_pos = pos rule_pos = pos
rule = self.select_rule(rule_pos, list(features)) rule = self.select_rule(rule_pos, list(features))
if rule is None: index = self.lookups.get_table("lemma_index").get(rule_pos, [])
lemmas = [string] lemmas = getattr(self, "lemmatize_" + rule_pos)(
else: string, features, rule, index
index = self.lookups.get_table("lemma_index").get(rule_pos, []) )
lemmas = getattr(self, "lemmatize_" + rule_pos)( # Remove duplicates but preserve the ordering
string, features, rule, index lemmas = list(dict.fromkeys(lemmas))
)
# Remove duplicates but preserve the ordering
lemmas = list(dict.fromkeys(lemmas))
self.cache[cache_key] = lemmas self.cache[cache_key] = lemmas
return lemmas return lemmas
@ -206,7 +203,6 @@ class SpanishLemmatizer(Lemmatizer):
word (str): The word to lemmatize. word (str): The word to lemmatize.
features (List[str]): The morphological features as a list of Feat=Val features (List[str]): The morphological features as a list of Feat=Val
pairs. pairs.
rule (str): The rule ID to use
index (List[str]): The POS-specific lookup list. index (List[str]): The POS-specific lookup list.
RETURNS (List[str]): The list of lemmas. RETURNS (List[str]): The list of lemmas.