forked from mrlan/EnglishPal
BugFix358 + Improve + Refactor
Stela
parent
b9cf94da74
commit
3654776aec
|
|
@ -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>
|
||||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -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 %}
|
||||
<font color="red"><b>已在生词簿内</b></font>
|
||||
{% endif %}
|
||||
</p>
|
||||
|
||||
{% endfor %}
|
||||
|
|
|
|||
|
|
@ -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):
|
||||
'''
|
||||
|
|
|
|||
|
|
@ -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')
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
Flask==1.1.2
|
||||
selenium==3.141.0
|
||||
Flask==2.1.2
|
||||
selenium==4.2.0
|
||||
PyYAML~=6.0
|
||||
|
|
|
|||
Loading…
Reference in New Issue