1
0
Fork 0
EnglishPal/app/wordfreqCMD.py

151 lines
4.7 KiB
Python
Raw Normal View History

2021-04-06 16:22:03 +08:00
###########################################################################
# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
# Written permission must be obtained from the author for commercial uses.
###########################################################################
import collections
import string
import operator
import os, sys # 引入模块sys因为我要用里面的sys.argv列表中的信息来读取命令行参数。
import pickle_idea
def freq(fruit):
'''
功能 把字符串转成列表 目的是得到每个单词的频率
输入 字符串
输出 列表 列表里包含一组元组每个元组包含单词与单词的频率 比如 [('apple', 2), ('banana', 1)]
注意事项 首先要把字符串转成小写原因是
'''
result = []
fruit = fruit.lower() # 字母转小写
flst = fruit.split() # 字符串转成list
c = collections.Counter(flst)
result = c.most_common()
return result
def youdao_link(s): # 有道链接
link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'# 网址
return link
def file2str(fname):#文件转字符
f = open(fname) #打开
s = f.read() #读取
f.close() #关闭
return s
2023-05-14 21:20:16 +08:00
def str2chararray(str): # 字符串转字符数组
chararray = []
for i in range(len(str)):
chararray.append(str[i])
return chararray
2021-04-06 16:22:03 +08:00
def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
2023-05-14 14:43:16 +08:00
# carr = str2chararray(s) # 字符串转字符数组
# print(carr)
special_characters = '&_~=+[]%^@.,?!:;#()"“”—‘’|/\\<>{}' # 把里面的字符都去掉
special_words = ('$lt', '$gt', '$') # 特殊词汇
2023-05-14 14:43:16 +08:00
2023-05-14 21:20:16 +08:00
special_characters = '\_©~<=>+-/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
2021-04-06 16:22:03 +08:00
for c in special_characters:
s = s.replace(c, ' ') # 防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
2023-05-14 21:20:16 +08:00
carr = str2chararray(s) # 字符串转字符数组
for i, value in enumerate(carr):
if value == '&': # 遍历替换
carr[i] = '\''
print('sss' + s)
for j in range(1,5):
if carr[i+j] in [' ','3','9']:
carr[i + j]=''
s = ''.join(carr) # 字符数组转字符串
print('sss'+s)
for w in special_words: # 替换字符串中的剩余特殊字符
s = s.replace(w, ' ')
2021-04-06 16:22:03 +08:00
s = s.replace('--', ' ')
s = s.strip() # 去除前后的空格
2021-04-06 16:22:03 +08:00
if '\'' in s:
n = len(s)
t = '' # 用来收集我需要保留的字符
for i in range(n): # 只有单引号前后都有英文字符,才保留
2021-04-06 16:22:03 +08:00
if s[i] == '\'':
i_is_ok = i - 1 >= 0 and i + 1 < n
if i_is_ok and s[i - 1] in string.ascii_letters and s[i + 1] in string.ascii_letters:
2021-04-06 16:22:03 +08:00
t += s[i]
else:
t += s[i]
return t
else:
return s
2021-04-06 16:22:03 +08:00
def sort_in_descending_order(lst):# 单词按频率降序排列
lst2 = sorted(lst, reverse=True, key=lambda x: (x[1], x[0]))
return lst2
def sort_in_ascending_order(lst):# 单词按频率降序排列
lst2 = sorted(lst, reverse=False, key=lambda x: (x[1], x[0]))
return lst2
def make_html_page(lst, fname): # 只是在wordfreqCMD.py中的main函数中调用所以不做修改
2021-04-06 16:22:03 +08:00
'''
功能把lst的信息存到fname中以html格式
'''
s = ''
count = 1
for x in lst:
# <a href="">word</a>
s += '<p>%d <a href="%s">%s</a> (%d)</p>' % (count, youdao_link(x[0]), x[0], x[1])
count += 1
f = open(fname, 'w')
f.write(s)
f.close()
## main程序入口
if __name__ == '__main__':
num = len(sys.argv)
if num == 1: # 从键盘读入字符串
s = input()
elif num == 2: # 从文件读入字符串
fname = sys.argv[1]
s = file2str(fname)
else:
print('I can accept at most 2 arguments.')
sys.exit()# 结束程序运行, 下面的代码不会被执行了。
s = remove_punctuation(s) # 这里是s是实参(argument),里面有值
L = freq(s)
for x in sort_in_descending_order(L):
print('%s\t%d\t%s' % (x[0], x[1], youdao_link(x[0])))#函数导出
# 把频率的结果放result.html中
make_html_page(sort_in_descending_order(L), 'result.html')
print('\nHistory:\n')
if os.path.exists('frequency.p'):
d = pickle_idea.load_record('frequency.p')
else:
d = {}
print(sort_in_descending_order(pickle_idea.dict2lst(d)))
# 合并频率
lst_history = pickle_idea.dict2lst(d)
d = pickle_idea.merge_frequency(L, lst_history)
pickle_idea.save_frequency_to_pickle(d, 'frequency.p')