Python jieba 模块，tokenize() 实例源码

def getChList(docStrByte):
    ## ??????????????????????????????????

    inputStr = str(docStrByte, encoding = 'gbk', errors = 'ignore').lower()#?????????????????
    strList = ''.join(inputStr.split('\n'))#????????????????
    rawTokens = list(jieba.tokenize(strList))#????

    #stopWord ? ???????key ???????value??None
    fSW = open('stopwords.txt', 'r', encoding = 'utf-8', errors = 'ignore').read()
    stopWord = {}.fromkeys(fSW.split('\n'))
    stopWord[''] = None

    final = []
    s = nltk.stem.SnowballStemmer('english')
    for seg in rawTokens:
        # print(seg[0].strip())
        rawWord = seg[0].strip()#strip()?????????????
        if (rawWord.isalpha()):#?????????????
            word = s.stem(rawWord)
        else:
            word = rawWord

        if  word not in stopWord:#?????
            final.append(word)#????list
    return final

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def testTokenize(self):
        for content in test_contents:
            result = jieba.tokenize(content)
            assert isinstance(result, types.GeneratorType), "Test Tokenize Generator error"
            result = list(result)
            assert isinstance(result, list), "Test Tokenize error on content: %s" % content
            for tk in result:
                print("word %s\t\t start: %d \t\t end:%d" % (tk[0],tk[1],tk[2]), file=sys.stderr)
        print("testTokenize", file=sys.stderr)

def testTokenize_NOHMM(self):
        for content in test_contents:
            result = jieba.tokenize(content,HMM=False)
            assert isinstance(result, types.GeneratorType), "Test Tokenize Generator error"
            result = list(result)
            assert isinstance(result, list), "Test Tokenize error on content: %s" % content
            for tk in result:
                print("word %s\t\t start: %d \t\t end:%d" % (tk[0],tk[1],tk[2]), file=sys.stderr)
        print("testTokenize_NOHMM", file=sys.stderr)

def cuttest(test_sent):
    global g_mode
    result = jieba.tokenize(test_sent,mode=g_mode,HMM=False)
    for tk in result:
        print("word %s\t\t start: %d \t\t end:%d" % (tk[0],tk[1],tk[2]))

def cuttest(test_sent):
    global g_mode
    result = jieba.tokenize(test_sent,mode=g_mode)
    for tk in result:
        print("word %s\t\t start: %d \t\t end:%d" % (tk[0],tk[1],tk[2]))

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def train(self, training_data, config, **kwargs):
        # type: (TrainingData, RasaNLUConfig, **Any) -> None
        if config['language'] != 'zh':
            raise Exception("tokenizer_jieba is only used for Chinese. Check your configure json file.")

        for example in training_data.training_examples:
            example.set("tokens", self.tokenize(example.text))

def process(self, message, **kwargs):
        # type: (Message, **Any) -> None

        message.set("tokens", self.tokenize(message.text))

def tokenize(self, text):
        # type: (Text) -> List[Token]
        tokenized = jieba.tokenize(text)
        tokens = [Token(word, start) for (word, start, end) in tokenized]

        return tokens

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token

def __call__(self, text, **kargs):
        words = jieba.tokenize(text, mode="search")
        token = Token()
        for (w, start_pos, stop_pos) in words:
            if not accepted_chars.match(w) and len(w) <= 1:
                continue
            token.original = token.text = w
            token.pos = start_pos
            token.startchar = start_pos
            token.endchar = stop_pos
            yield token