explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-10-31 16:07:41 +03:00
Code Issues Packages Projects Releases Wiki Activity

Rename and update ru pymorphy2 lookup lemmatize

Browse Source 
* To allow default lookup lemmatization with a blank Russian model,
rename pymorphy2 lookup mode to `pymorphy2_lookup`

* Bug fix: update pymorphy2 lookup lemmatize to return list rather than
string
This commit is contained in:
Adriane Boyd 2021-03-15 11:11:06 +01:00
parent 508cb3bef7
commit 3bcf74aca7
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/lang/ru/lemmatizer.py
View File

@ -90,12 +90,12 @@ class RussianLemmatizer(Lemmatizer):
return [string.lower()] return [string.lower()]
return list(set([analysis.normal_form for analysis in filtered_analyses])) return list(set([analysis.normal_form for analysis in filtered_analyses]))
def lookup_lemmatize(self, token: Token) -> List[str]: def pymorphy2_lookup_lemmatize(self, token: Token) -> List[str]:
string = token.text string = token.text
analyses = self._morph.parse(string) analyses = self._morph.parse(string)
if len(analyses) == 1: if len(analyses) == 1:
return analyses[0].normal_form return [analyses[0].normal_form]
return string return [string]
def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: def oc2ud(oc_tag: str) -> Tuple[str, Dict[str, str]]: