【snownlp相关文件】上传自己的模型,调用utils/mynlp

This commit is contained in:
redhongx
2024-07-04 11:54:06 +08:00
parent f09fcb3000
commit 93b72ea2e0
33 changed files with 135956 additions and 0 deletions
+26
View File
@@ -0,0 +1,26 @@
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
from ..utils.trie import Trie
class PinYin(object):
def __init__(self, fname):
self.handle = Trie()
fr = codecs.open(fname, 'r', 'utf-8')
for line in fr:
words = line.split()
self.handle.insert(words[0], words[1:])
fr.close()
def get(self, text):
ret = []
for i in self.handle.translate(text):
if isinstance(i, list) or isinstance(i, tuple):
ret = ret + i
else:
ret.append(i)
return ret