explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-26 01:04:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

apply patch

Browse Source
This commit is contained in:
Juan Miguel Cejuela 2017-03-01 21:44:17 +01:00
parent a8cfde46d3
commit 25c29f072d
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/lemmatizer.py
View File

@ -86,13 +86,16 @@ def lemmatize(string, index, exceptions, rules):
#if string in index: #if string in index:
# forms.append(string) # forms.append(string)
forms.extend(exceptions.get(string, [])) forms.extend(exceptions.get(string, []))
oov_forms = []
for old, new in rules: for old, new in rules:
if string.endswith(old): if string.endswith(old):
form = string[:len(string) - len(old)] + new form = string[:len(string) - len(old)] + new
if form in index or not form.isalpha(): if form in index or not form.isalpha():
forms.append(form) forms.append(form)
else:
oov_forms.append(form)
if not forms: if not forms:
forms.append(string) forms.extend(oov_forms)
return set(forms) return set(forms)