2024-04-25 15:12:55 +08:00
3 changed files with 63 additions and 3 deletions
--- a/app/templates/mainpage_post.html
+++ b/app/templates/mainpage_post.html
@ -2,7 +2,7 @@
 <html lang="en">
 <head>
    <meta charset="UTF-8">
-    <title>Title</title>
+    <title>单词词频</title>

    {{ yml['header'] | safe }}
    {% if yml['css']['item'] %}
--- a/app/test/test_bug553_LinShan.py
+++ b/app/test/test_bug553_LinShan.py
@ -0,0 +1,58 @@
+from selenium import webdriver
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+from selenium.webdriver.support import expected_conditions as EC
+from selenium import webdriver
+from selenium.webdriver.support.wait import WebDriverWait
+from selenium.webdriver.common.by import By
+from selenium.webdriver.common.keys import Keys
+import logging
+import time
+import pytest
+
+@pytest.mark.parametrize("test_input,expected",
+                         [("‘test1’", "test1"),
+                          ("'test2'", "test2"),
+                          ("“test3”", "test3"),
+                          ("it's", "it's"),
+                          ("hello,I'm linshan", ["hello","i'm","linshan"]),
+                          ("Happy New Year！？", ["happy","new","year"]),
+                          ("My favorite book is 《Harry Potter》。", ["potter","harry","my","favorite","book","is"])])
+def test_bug553_LinShan(test_input,expected, driver, URL):
+    try:
+        # 打开对应地址的网页
+        driver.get(URL)
+
+        # 浏览器最大窗口化
+        driver.maximize_window()
+
+        # 判断网页源代码中是否有English Pal -文字
+        assert 'English Pal -' in driver.page_source
+
+        # 将测试的数据输入到主页的textarea里
+        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(Keys.CONTROL, "a")
+        driver.find_element_by_xpath("//textarea[@name='content']").send_keys(test_input)
+        time.sleep(1)
+
+        # 点击按钮获取单词
+        driver.find_element_by_xpath("//input[@value='get文章中的词频']").click()
+        time.sleep(1)
+
+        # 获取筛选后的单词
+        words = driver.find_elements_by_xpath("//p/a")
+
+        # 遍历获取到的单词，并判断单词与预期的相同
+        for word in words:
+            # 判断单词是否在预期结果中
+            assert word.text in expected
+            
+        # 返回上一页网页
+        driver.find_element_by_xpath("//input[@value='确定并返回']").click()
+        time.sleep(0.1)
+
+    except Exception as e:
+        # 输出异常信息
+        logging.error(e)
+        # 关闭浏览器
+        driver.quit()
+    finally:
+        driver.quit()
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@ -4,6 +4,7 @@
 ###########################################################################

 import collections
+import html
 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。
@ -39,7 +40,8 @@ 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
+    s = html.unescape(s) # 将HTML实体转换为对应的字符，比如<会被识别为小于号
    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('--', ' ')