初始python 之 自动拆分转换文本内容
2021-07-12 01:06
标签:word closed env def odi load close nbsp lse 上一篇升级版,转换文件内容。 字典库: 要转换的文件内容: 转换结果: 初始python 之 自动拆分转换文本内容 标签:word closed env def odi load close nbsp lse 原文地址:https://www.cnblogs.com/simple-li/p/14988777.html#!/user/bin env python
# author:Simple-Sir
# time:2021/7/9 23:32
def txt_2_list(filename):
dic = {}
dic_k = []
dic_v = []
with open(filename,‘r‘,encoding=‘utf-8‘) as f:
for i in f.readlines():
j = i.strip(‘\n‘) # 删除换行符
li_k = j.split(‘,‘) # 以逗号分隔为列表
if len(li_k) == 2:
dic[li_k[0]] = li_k[1]
dic_k.append(li_k[0])
dic_v.append(li_k[1])
else:
dic_k.append(li_k[0])
return dic,dic_k,dic_v
def get_word_in_list(info,dic_k):
word_li = []
while len(info) > 0:
m = 0
n = 0
for i in range(len(info)+1):
if info[:i] in dic_k:
word_li.append(info[:i])
info = info[i:]
n = 1
m = i
if n == 0:
word_li.append(info[0:1])
info = info[m+1:]
return word_li
def translat_word(word_li,dic,dic_k):
get_v = []
for i in word_li:
if i in dic_k:
get_v.append(dic[i])
else:
get_v.append(i)
re_w = (‘_‘).join(get_v)
return re_w
if __name__ == ‘__main__‘:
dict_file = ‘dir‘
info_file = ‘infofile‘
info_k=txt_2_list(info_file)[1]
print(‘----------- 要转换的内容 ----------\n ‘,(‘\n ‘).join(info_k))
print(‘----------- 转换结果 ------------‘)
for info in info_k:
dic,dic_k,dic_v = txt_2_list(dict_file)
word_li = get_word_in_list(info, dic_k)
tw = translat_word(word_li,dic,dic_k)
print(‘%s -->> %s‘%(info,tw))
剪刀,jiandao
被子,beizi
笔,bi
我,wo
要,yao
我要剪刀
我不要剪刀
我要剪刀和笔
我要被子和剪刀
上一篇:JavaScript