forked from mrlan/EnglishPal
172 lines
5.5 KiB
Python
172 lines
5.5 KiB
Python
###########################################################################
|
||
# 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
|
||
|
||
|
||
def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用时才给s赋值。
|
||
special_characters = '_©~=+[]*&$%^@.,?!:;#()"“”—' # 把里面的字符都去掉
|
||
|
||
for c in special_characters:
|
||
s = s.replace(c, ' ') # 把所有符号都替换成空格，防止出现把 apple,apple 移掉逗号后变成 appleapple 情况
|
||
s = s.replace('--', ' ')
|
||
s = s.strip() # 去除前后的空格
|
||
|
||
single_quote = '‘’\'' # 各种单引号单独处理
|
||
n, i = len(s), 0
|
||
t = '' # 用来收集我需要保留的字符
|
||
while i < n: # 只有单引号前后都有英文字符，才保留
|
||
if s[i] in single_quote:
|
||
if i == 0 or i == n - 1 or s[i - 1] == ' ' or s[i + 1] == ' ':
|
||
i = i + 1
|
||
continue # condition 1+2
|
||
if s[i + 1] == 's' and (i + 2 == n or s[i + 2] == ' '):
|
||
i = i + 2
|
||
continue # condition 2
|
||
t += '\'' # condition 3, standardize quote
|
||
else:
|
||
t += s[i]
|
||
i = i + 1
|
||
return t
|
||
|
||
'''
|
||
单引号出现在文章中的情况：
|
||
1、某些情况下作为双引号使用，引用段落
|
||
这种情况一般出现在词首或词尾
|
||
处理方式：直接去除
|
||
2、表示名词所有格
|
||
对于单数名词以's为后缀，对于复数名词以s'或'为后缀
|
||
处理方式：将'其后的部分去除
|
||
3、单词元音位置的缩写
|
||
最常见的有not->n't/is->'s/have->'ve这类
|
||
处理方式：保留
|
||
|
||
上述处理方式2/3两点可能产生一种冲突：
|
||
某些单词元音缩写后恰好以's结尾
|
||
但考虑到用于学习英语的文章一般不会出现过于口语化的缩写单词
|
||
因此要么还是表所有格，要么就是is的缩写
|
||
故不考虑这种冲突情况
|
||
'''
|
||
|
||
'''
|
||
以下是原本的代码
|
||
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
|
||
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:
|
||
t += s[i]
|
||
else:
|
||
t += s[i]
|
||
return t
|
||
else:
|
||
return s
|
||
'''
|
||
|
||
|
||
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):
|
||
'''
|
||
功能：把lst的信息存到fname中，以html格式。
|
||
'''
|
||
result = ''
|
||
id = 1
|
||
|
||
for word in lst:
|
||
result += '<p>'
|
||
result += '%d ' % id
|
||
result += get_html_hyperlink(word[0])
|
||
result += ' (%d)' % word[1]
|
||
result += '</p>'
|
||
# result += '<p>%d <a href="%s">%s</a> (%d)</p>' % (count, youdao_link(x[0]), x[0], x[1])
|
||
id += 1
|
||
|
||
f = open(fname, 'w')
|
||
f.write(result)
|
||
f.close()
|
||
|
||
def get_html_hyperlink(word):
|
||
s = '<a href="' + youdao_link(word) + '">' + word + '</a>'
|
||
return s
|
||
|
||
## 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')
|
||
|
||
|
||
|