From 3654776aec7d2ee69d26731b34b96bdce9eec2e8 Mon Sep 17 00:00:00 2001
From: Stela <1710738188@qq.com>
Date: Mon, 6 Jun 2022 19:42:26 +0800
Subject: [PATCH] BugFix358 + Improve + Refactor

---
 app/templates/analyse_word.html  | 27 +++++++++++
 app/templates/userpage_get.html  |  9 +++-
 app/templates/userpage_post.html |  3 ++
 app/user_service.py              | 39 +++++++++++----
 app/wordfreqCMD.py               | 82 +++++++++++++++++++++++++-------
 requirements.txt                 |  4 +-
 6 files changed, 136 insertions(+), 28 deletions(-)
 create mode 100644 app/templates/analyse_word.html
diff --git a/app/templates/analyse_word.html b/app/templates/analyse_word.html
new file mode 100644
index 0000000..6736f57
--- /dev/null
+++ b/app/templates/analyse_word.html
@@ -0,0 +1,27 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0, minimum-scale=0.5, maximum-scale=3.0, user-scalable=yes" />
+    <title>EnglishPal - Analyse Result</title>
+</head>
+<body>
+    <div>
+        <br/>
+        <h3>单词 {{ word }} 的统计信息</h3>
+        <hr/>
+        <ul>
+            <li>在总 {{ resultlen }} 篇文章中，总共出现了 {{ totcount }} 次</li>
+            <li>总占比为 {{ '%.5f' % (100 * totcount / totcnt) }}%</li>
+        </ul>
+        <ul>
+            <li>在一篇文章中：</li>
+            <li>最多出现了 {{ maxcount }} 次</li>
+            <li>最高占比为 {{ '%.5f' % maxrate }}%</li>
+            <li>最少出现了 {{ mincount }} 次</li>
+            <li>最低占比为 {{ '%.5f' % minrate }}%</li>
+        </ul>
+        <input type="button" value="返回" onclick="location.href='{{ username }}'"/>
+    </div>
+</body>
+</html>
\ No newline at end of file
diff --git a/app/templates/userpage_get.html b/app/templates/userpage_get.html
index 19542c1..9dee463 100644
--- a/app/templates/userpage_get.html
+++ b/app/templates/userpage_get.html
@@ -38,10 +38,17 @@
 
     <p><b>收集生词吧</b> （可以在正文中划词，也可以复制黏贴）</p>
     <form method="post" action="/{{ username }}">
+        <input type="hidden" name="methodtype" value="multiple"/>
         <textarea name="content" id="selected-words" rows="10" cols="120"></textarea><br/>
         <input type="submit" value="把生词加入我的生词库"/>
         <input type="reset" value="清除"/>
-    </form>
+    </form><br/>
+    <form method="post" action="/{{ username }}">
+        <input type="hidden" name="methodtype" value="single"/>
+        <input type="text" name="content"/><br/>
+        <input type="submit" value="分析此单词" style="margin-top:5px"/>
+        <input type="reset" value="清除"/>
+    </form><br/>
     {% if session.get['thisWord'] %}
         <script type="text/javascript">
             //point to the anchor in the page whose id is aaa if it exists
diff --git a/app/templates/userpage_post.html b/app/templates/userpage_post.html
index ba3b38d..fb4e14a 100644
--- a/app/templates/userpage_post.html
+++ b/app/templates/userpage_post.html
@@ -31,6 +31,9 @@
             <a href='http://youdao.com/w/eng/{{word}}/#keyfrom=dict2.index' title={{word}}>{{word}}</a>
             ({{x[1]}})
             <input type="checkbox" name="marked" value={{word}}>
+            {% if x[0] in userwordlist %}
+                &nbsp; <font color="red"><b>已在生词簿内</b></font>
+            {% endif %}
         </p>
 
        {% endfor %}
diff --git a/app/user_service.py b/app/user_service.py
index 139c140..30c3027 100644
--- a/app/user_service.py
+++ b/app/user_service.py
@@ -11,6 +11,7 @@ import Yaml
 from Article import get_today_article, load_freq_history
 from WordFreq import WordFreq
 from wordfreqCMD import sort_in_descending_order
+from UseSqlite import RecordQuery
 
 import pickle_idea
 import pickle_idea2
@@ -102,10 +103,36 @@ def userpage(username):
     user_freq_record = path_prefix + 'static/frequency/' + 'frequency_%s.pickle' % (username)
 
     if request.method == 'POST':  # when we submit a form
-        content = request.form['content']
-        f = WordFreq(content)
-        lst = f.get_freq()
-        return render_template('userpage_post.html',username=username,lst = lst, yml=Yaml.yml)
+        if request.form['methodtype'] == 'multiple':
+            content = request.form['content']
+            f = WordFreq(content)
+            lst = f.get_freq()
+            userwordlist = pickle_idea2.dict2lst(load_freq_history(user_freq_record))
+            userwordlist2 = []
+            for t in userwordlist:
+                userwordlist2.append(t[0])
+            return render_template('userpage_post.html', username=username, lst = lst, yml=Yaml.yml, userwordlist=userwordlist2)
+        else:
+            word = request.form['content'].lower()  # 指定单词
+            rq = RecordQuery(path_prefix + 'static/wordfreqapp.db')
+            rq.instructions("SELECT * FROM article")  # 获取所有文章
+            rq.do()
+            result = rq.get_results()
+            mincount, maxcount, totcount, totcnt = 1e9, 0, 0, 0
+            maxrate, minrate = 0.0, 100.0
+            for d in result:  # 查找数据库内的所有文章
+                str = d['text'].lower().split()
+                cnt = str.count(word)
+                tot = len(str)
+                totcnt += tot
+                mincount = min(mincount, cnt)
+                maxcount = max(maxcount, cnt)
+                totcount += cnt
+                maxrate = max(maxrate, 100 * cnt / tot)
+                minrate = min(minrate, 100 * cnt / tot)
+            return render_template('analyse_word.html', mincount=mincount, maxcount=maxcount, totcount=totcount, totcnt=totcnt,
+                                   maxrate=maxrate, minrate=minrate, resultlen=len(result),
+                                   word=word, username=session.get('username'))
 
     elif request.method == 'GET':  # when we load a html page
         d = load_freq_history(user_freq_record)
@@ -127,10 +154,6 @@ def userpage(username):
                                yml=Yaml.yml,
                                words=words)
 
-
-
-
-
 @userService.route("/<username>/mark", methods=['GET', 'POST'])
 def user_mark_word(username):
     '''
diff --git a/app/wordfreqCMD.py b/app/wordfreqCMD.py
index 9ee7e56..b890805 100644
--- a/app/wordfreqCMD.py
+++ b/app/wordfreqCMD.py
@@ -18,7 +18,6 @@ def freq(fruit):
     '''
 
     result = []
-    
     fruit = fruit.lower() # 字母转小写
     flst = fruit.split()  # 字符串转成list
     c = collections.Counter(flst)
@@ -27,24 +26,63 @@ def freq(fruit):
 
 
 def youdao_link(s): # 有道链接
-    link = 'http://youdao.com/w/eng/' + s + '/#keyfrom=dict2.index'# 网址
+    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
+    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 = '_©~=+[]*&$%^@.,?!:;#()"“”—‘’' # 把里面的字符都去掉
+    special_characters = '_©~=+[]*&$%^@.,?!:;#()"“”—' # 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(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
@@ -58,6 +96,7 @@ def remove_punctuation(s): # 这里是s是形参 (parameter)。函数被调用
         return t
     else:
         return s
+    '''
 
 
 def sort_in_descending_order(lst):# 单词按频率降序排列
@@ -74,16 +113,25 @@ def make_html_page(lst, fname):
     '''
     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
+    result = ''
+    id = 1
+
+    for word in lst:
+        result += '<p>'
+        result += '%d ' % id
+        result += getHyperlinkHTML(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(s)
+    f.write(result)
     f.close()
 
+def getHyperlinkHTML(word):
+    s = '<a href="' + youdao_link(word) + '">' + word + '</a>'
+    return s
 
 ## main（程序入口）
 if __name__ == '__main__':
@@ -96,12 +144,12 @@ if __name__ == '__main__':
         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
     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') 
diff --git a/requirements.txt b/requirements.txt
index 2746a3b..ce2da4f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,3 @@
-Flask==1.1.2
-selenium==3.141.0
+Flask==2.1.2
+selenium==4.2.0
 PyYAML~=6.0
