explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-06 05:10:21 +03:00
Code Issues Packages Projects Releases Wiki Activity

Refactor to private generic-looking pymorphy methods

Browse Source
This commit is contained in:
Adriane Boyd 2022-11-18 08:37:37 +01:00
parent d2045fa145
commit df127bfe33
1 changed files with 10 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
spacy/lang/ru/lemmatizer.py
View File

@ -53,7 +53,7 @@ class RussianLemmatizer(Lemmatizer):
vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer vocab, model, name, mode=mode, overwrite=overwrite, scorer=scorer
) )
def pymorphy2_lemmatize(self, token: Token) -> List[str]: def _pymorphy_lemmatize(self, token: Token) -> List[str]:
string = token.text string = token.text
univ_pos = token.pos_ univ_pos = token.pos_
morphology = token.morph.to_dict() morphology = token.morph.to_dict()
@ -114,7 +114,7 @@ class RussianLemmatizer(Lemmatizer):
dict.fromkeys([analysis.normal_form for analysis in filtered_analyses]) dict.fromkeys([analysis.normal_form for analysis in filtered_analyses])
) )
def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]: def _pymorphy_lookup_lemmatize(self, token: Token) -> List[str]:
string = token.text string = token.text
analyses = self._morph.parse(string) analyses = self._morph.parse(string)
# often multiple forms would derive from the same normal form # often multiple forms would derive from the same normal form
@ -124,11 +124,17 @@ class RussianLemmatizer(Lemmatizer):
return [next(iter(normal_forms))] return [next(iter(normal_forms))]
return [string] return [string]
def pymorphy2_lemmatize(self, token: Token) -> List[str]:
return self._pymorphy_lemmatize(token)
def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]:
return self._pymorphy_lookup_lemmatize(token)
def pymorphy3_lemmatize(self, token: Token) -> List[str]: def pymorphy3_lemmatize(self, token: Token) -> List[str]:
return self.pymorphy2_lemmatize(token) return self._pymorphy_lemmatize(token)
def pymorphy3_lookup_lemmatize(self, token: Token) -> List[str]: def pymorphy3_lookup_lemmatize(self, token: Token) -> List[str]:
return self.pymorphy2_lookup_lemmatize(token) return self._pymorphy_lookup_lemmatize(token)
def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: