default.py 文件源码

def tokenizer():
    if len(request.vars)!=0:
        user_input=request.vars
        import sys
        reload(sys)
        sys.setdefaultencoding('utf-8')
        if user_input.parameter=="sentence":

            our_output=nltk.sent_tokenize(user_input.input,"english")
            print user_input
            if request.vars.filename!='' and len(request.vars.filename.value)!="":
                file_input=user_input.filename.value
                file_output=nltk.word_tokenize(file_input,"english")
            print our_output
        else:
            our_output=nltk.word_tokenize(user_input.input,"english")
            if request.vars.filename!='' and len(request.vars.filename.value)!=None:
                file_input=user_input.filename.value
                file_output=nltk.word_tokenize(file_input,"english")


        user_input.output=our_output


    return locals()