PCQRSCANER/venv/Lib/site-packages/nltk/stem/wordnet.py

53 lines
1.4 KiB
Python
Raw Normal View History

2019-12-22 21:51:47 +01:00
# Natural Language Toolkit: WordNet stemmer interface
#
# Copyright (C) 2001-2019 NLTK Project
# Author: Steven Bird <stevenbird1@gmail.com>
# Edward Loper <edloper@gmail.com>
# URL: <http://nltk.org/>
# For license information, see LICENSE.TXT
from __future__ import unicode_literals
from nltk.corpus.reader.wordnet import NOUN
from nltk.corpus import wordnet
from nltk.compat import python_2_unicode_compatible
@python_2_unicode_compatible
class WordNetLemmatizer(object):
"""
WordNet Lemmatizer
Lemmatize using WordNet's built-in morphy function.
Returns the input word unchanged if it cannot be found in WordNet.
>>> from nltk.stem import WordNetLemmatizer
>>> wnl = WordNetLemmatizer()
>>> print(wnl.lemmatize('dogs'))
dog
>>> print(wnl.lemmatize('churches'))
church
>>> print(wnl.lemmatize('aardwolves'))
aardwolf
>>> print(wnl.lemmatize('abaci'))
abacus
>>> print(wnl.lemmatize('hardrock'))
hardrock
"""
def __init__(self):
pass
def lemmatize(self, word, pos=NOUN):
lemmas = wordnet._morphy(word, pos)
return min(lemmas, key=len) if lemmas else word
def __repr__(self):
return '<WordNetLemmatizer>'
# unload wordnet
def teardown_module(module=None):
from nltk.corpus import wordnet
wordnet._unload()