更新 'app/wordfreqCMD.py'

app/WordFreq.py

@@ -20,6 +20,6 @@ class WordFreq:
     
 
 if __name__ == '__main__':
-    f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.')
+    f = WordFreq('i\'m BANANA; Banana, apple ORANGE Bana-na/////,./;\'[]-=---\'/-banana.')
     print(f.get_freq())
 

app/wordfreqCMD.py

@@ -8,6 +8,7 @@ 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
+import re
 
 def freq(fruit):
     '''
@@ -39,19 +40,26 @@ def file2str(fname):#文件转字符
 
 
 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 = '_©~=+[]*&$%^@.,?!:;#()"“”—‘’' # 把里面的字符都去掉
+    '''special_characters = '_©~=+[]*&$%^@.,?!:;#()"“”—‘’'  #把里面的字符都去掉
     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
-    s = s.replace('--', ' ')
+    s = s.replace('--', ' ')'''
+    cop = re.compile("[^a-z^A-Z^\\']")#通过正则表达式保留英文字符和'特殊字符
+    s=cop.sub(' ' , s)
     s = s.strip() # 去除前后的空格
+    #s=keep_need_punctuation(s,'-')
+    s=keep_need_punctuation(s,'\'')
+    return s
 
-    if '\'' in s:
+
+def keep_need_punctuation(s,need):#用于保留特定的字符
+    if need 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] == '\'':
+            if s[i] == need:
                 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:
+                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]
@@ -59,7 +67,6 @@ def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用
     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