Python自然语言处理之切分算法详解

from pyhanlp import *


def load_dictionary():
    IOUtil = JClass('com.hankcs.hanlp.corpus.io.IOUtil')
    path = HanLP.Config.CoreDictionaryPath.replace('.txt', '.mini.txt')
    dic = IOUtil.loadDictionary([path])
    return set(dic.keySet())


def fully_segment(text, dic):
    list = []
    for i in range(len(text)):
        for j in range(i + 1, len(text) + 1):
            temp = text[i:j]
            if temp in dic:
                list.append(temp)
    return list


if __name__ == "__main__":
    dic = load_dictionary()
    print(fully_segment("在绝对实力面前，一切的说辞都是枉然", dic))

def forward_segment(text, dic):
    list = []
    i = 0
    while i < len(text):
        long_word = text[i]
        for j in range(i + 1, len(text) + 1):
            word = text[i:j]
            if word in dic:
                if len(word) > len(long_word):
                    long_word = word
        list.append(long_word)
        i += len(long_word)
    return list

def backward_segment(text, dic):
    list = []
    i = len(text) - 1
    while i >= 0:
        long_word = text[i]
        for j in range(0, i):
            word = text[j:i + 1]
            if word in dic:
                if len(word) > len(long_word):
                    long_word = word
                    break
        list.append(long_word)
        i -= len(long_word)
    return list

#统计单字个数
def count_single_char(list):
    return sum(1 for word in list if len(word) == 1)

#双向匹配算法
def bidirectional_segment():
    f = forward_segment("在绝对实力面前，一切的说辞都是枉然", dic)
    b = backward_segment("在绝对实力面前，一切的说辞都是枉然", dic)
    if len(f) < len(b):
        return f
    elif len(f) > len(b):
        return b
    else:
        if count_single_char(f)<count_single_char(b):
            return f
        else:
            return b