|
|
|
|
@ -85,6 +85,7 @@ class TOKENIZER():
|
|
|
|
|
self.UNKNOWN_CHAR = self.stoi[UNKNOWN_CHAR]
|
|
|
|
|
|
|
|
|
|
def refine_context(self, context):
|
|
|
|
|
if self.charMode:
|
|
|
|
|
context = context.strip().split('\n')
|
|
|
|
|
for c in range(len(context)):
|
|
|
|
|
context[c] = context[c].strip().strip('\u3000').strip('\r')
|
|
|
|
|
|