Fix bug 511

app/WordFreq.py

@@ -2,17 +2,18 @@
 # Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
 # Written permission must be obtained from the author for commercial uses.
 ###########################################################################
-
 from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
 import string
 
+
 class WordFreq:
-    def __init__(self, s):
+    def __init__(self, s, max_word_length=30):
         self.s = remove_punctuation(s)
+        self.max_word_length = max_word_length
 
     def get_freq(self):
         lst = []
-        for t in freq(self.s):
+        for t in freq(self.s, self.max_word_length):
             word = t[0]
             if len(word) > 0 and word[0] in string.ascii_letters:
                 lst.append(t)
@@ -20,6 +21,5 @@ class WordFreq:
 
 
 if __name__ == '__main__':
-    f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.')
+    f = WordFreq('BANANA; Banana, apple ORANGE Banana banana.', max_word_length=30)
     print(f.get_freq())
-

app/test_bug511_Bosh.py

@@ -0,0 +1,56 @@
+###########################################################################
+# Copyright 2019 (C) Hui Lan <hui.lan@cantab.net>
+# Written permission must be obtained from the author for commercial uses.
+###########################################################################
+import unittest
+from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order
+from WordFreq import WordFreq
+
+
+class TestWordFrequency(unittest.TestCase):
+
+    def test_word_frequency_normal_case(self):
+        text = "BANANA; Banana, apple ORANGE Banana banana."
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = [('banana', 4), ('orange', 1), ('apple', 1)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_long_word(self):
+        text = "apple banana " + "a" * 31 + " orange banana apple"
+        wf = WordFreq(text, max_word_length=30)
+        result = wf.get_freq()
+        expected = [('banana', 2), ('apple', 2), ('orange', 1)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_all_long_words(self):
+        text = "a" * 31 + " " + "b" * 32 + " " + "c" * 33
+        wf = WordFreq(text, max_word_length=30)
+        result = wf.get_freq()
+        expected = []
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_punctuation(self):
+        text = "Hello, world! Hello... hello; 'hello' --world--"
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = [('hello', 4), ('world', 2)]
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_empty_string(self):
+        text = ""
+        wf = WordFreq(text)
+        result = wf.get_freq()
+        expected = []
+        self.assertEqual(result, expected)
+
+    def test_word_frequency_with_max_length_parameter(self):
+        text = "apple banana apple"
+        wf = WordFreq(text, max_word_length=5)
+        result = wf.get_freq()
+        expected = [('apple', 2)]
+        self.assertEqual(result, expected)
+
+
+if __name__ == '__main__':
+    unittest.main()

app/wordfreqCMD.py

@@ -2,56 +2,56 @@
 # 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 os
+import sys
 import pickle_idea
 
-def freq(fruit):
+
+def freq(fruit, max_word_length=30):
     '''
     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。。。
+    注意事项： 首先要把字符串转小写。
     '''
 
     result = []
 
-    fruit = fruit.lower() # 字母转小写
+    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()
+    for word, count in c.most_common():
+        if len(word) <= max_word_length:
+            result.append((word, count))
     return result
 
-
-def youdao_link(s): # 有道链接
-    link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'# 网址
+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
+def file2str(fname):  # 文件转字符
+    with open(fname) as f:  # 使用with打开文件
+        s = f.read()  # 读取
     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 = '\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|' # 把里面的字符都去掉
+def remove_punctuation(s):  # 这里是s是形参(parameter)。函数被调用时才给s赋值。
+    special_characters = r'\_©~<=>+/[]*&$%^@.,?!:;#()"“”—‘’{}|'  # 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(c, ' ')  # 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
+    s = s.strip()  # 去除前后的空格
 
     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
+        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:
+                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]
@@ -60,12 +60,12 @@ def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用
         return s
 
 
-def sort_in_descending_order(lst):# 单词按频率降序排列
+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
+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
 
@@ -80,28 +80,27 @@ def make_html_page(lst, fname):  # 只是在wordfreqCMD.py中的main函数中调
         # <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()
+    with open(fname, 'w') as f:
+        f.write(s)
 
 
 ## main（程序入口）
 if __name__ == '__main__':
     num = len(sys.argv)
 
-    if num == 1: # 从键盘读入字符串
+    if num == 1:  # 从键盘读入字符串
         s = input()
-    elif num == 2: # 从文件读入字符串
+    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。
+        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
+    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
+        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')
@@ -120,4 +119,3 @@ if __name__ == '__main__':
     pickle_idea.save_frequency_to_pickle(d, 'frequency.p')
 
 
-

build.sh

@@ -1,6 +1,6 @@
 #!/bin/sh
 
-DEPLOYMENT_DIR=/home/lanhui/englishpal2/EnglishPal
+DEPLOYMENT_DIR=/home/main/EnglishPal
 cd $DEPLOYMENT_DIR
 pwd
 

requirements.txt

@@ -8,4 +8,7 @@ Werkzeug==2.2.2
 =======
 
 pytest~=8.1.1
+<<<<<<< HEAD
 >>>>>>> 8cbc7c9 (修复快速点击下一页按钮点击频率过快时页面跳转到未知名页面)
+=======
+>>>>>>> fa65055 (Fix bug 511)