更多代码阅读及测试（词典操作）_user_dict.txt

import sys
sys.path.append("../")
import jieba
jieba.load_userdict("userdict.txt")
test_sent = (
"李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿\n"
"例如我输入一个带“韩玉赏鉴”的标题，在自定义词库中也增加了此词为N类\n"
"「台中」正確應該不會被切開。mac上可分出「石墨烯」；此時又可以分出來凱特琳了。"
)
words = jieba.cut(test_sent)
print('/'.join(words))

​

​

​

import sys
sys.path.append("../")
import jieba
# jieba.load_userdict("userdict.txt")
 
jieba.add_word('石墨烯')
jieba.add_word('凱特琳')
jieba.del_word('自定义词')
test_sent = (
"李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿\n"
"例如我输入一个带“韩玉赏鉴”的标题，在自定义词库中也增加了此词为N类\n"
"「台中」正確應該不會被切開。mac上可分出「石墨烯」；此時又可以分出來凱特琳了。"
)
words = jieba.cut(test_sent)
print('/'.join(words))

import sys
sys.path.append("../")
import jieba
jieba.suggest_freq('台中',tune=True)#使得“台中”可以被识别
jieba.suggest_freq(('增','加'),tune=True)#使得“增加”不可被识别，分成增/加
test_sent = (
"李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿\n"
"例如我输入一个带“韩玉赏鉴”的标题，在自定义词库中也增加了此词为N类\n"
"「台中」正確應該不會被切開。mac上可分出「石墨烯」；此時又可以分出來凱特琳了。"
)
words = jieba.cut(test_sent)
print('/'.join(words))

    def add_word(self, word, freq=None, tag=None):
        """
        Add a word to dictionary.
        freq and tag can be omitted, freq defaults to be a calculated value
        that ensures the word can be cut out.
        """
        self.check_initialized()
        word = strdecode(word)
        freq = int(freq) if freq is not None else self.suggest_freq(word, False)
        self.FREQ[word] = freq
        self.total += freq
        if tag:
            self.user_word_tag_tab[word] = tag
        for ch in xrange(len(word)):
            wfrag = word[:ch + 1]
            if wfrag not in self.FREQ:
                self.FREQ[wfrag] = 0
        if freq == 0:
            finalseg.add_force_split(word)