explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Lemmatizer honors exceptions: Fix #1387

Browse Source
This commit is contained in:
Orion Montoya 2017-10-05 10:49:02 -04:00
parent e81a608173
commit ffb50d21a0
1 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
spacy/lemmatizer.py
View File

@ -78,15 +78,16 @@ def lemmatize(string, index, exceptions, rules):
# forms.append(string)
forms.extend(exceptions.get(string, []))
oov_forms = []
for old, new in rules:
if string.endswith(old):
form = string[:len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
for old, new in rules:
if string.endswith(old):
form = string[:len(string) - len(old)] + new
if not form:
pass
elif form in index or not form.isalpha():
forms.append(form)
else:
oov_forms.append(form)
if not forms:
forms.extend(oov_forms)
if not forms: