forked from mrlan/EnglishPal
Compare commits
No commits in common. "Bug476-Yuhuangtao" and "master" have entirely different histories.
Bug476-Yuh
...
master
|
|
@ -6,14 +6,10 @@
|
|||
# Purpose: compute difficulty level of a English text
|
||||
|
||||
import pickle
|
||||
import time
|
||||
|
||||
import math
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
|
||||
import snowballstemmer
|
||||
|
||||
from wordfreqCMD import remove_punctuation, freq, sort_in_descending_order, sort_in_ascending_order
|
||||
|
||||
# 定义一个全局的res_d， 记录数据库单词评级之后的单词及其等级
|
||||
res_d = {}
|
||||
|
||||
def load_record(pickle_fname):
|
||||
f = open(pickle_fname, 'rb')
|
||||
|
|
@ -28,7 +24,6 @@ def convert_test_type_to_difficulty_level(d):
|
|||
:param d: 存储了单词库pickle文件中的单词的字典
|
||||
:return:
|
||||
"""
|
||||
time_start = time.time()
|
||||
result = {}
|
||||
L = list(d.keys()) # in d, we have test types (e.g., CET4,CET6,BBC) for each word
|
||||
|
||||
|
|
@ -43,10 +38,7 @@ def convert_test_type_to_difficulty_level(d):
|
|||
result[k] = 7
|
||||
elif 'BBC' in d[k]:
|
||||
result[k] = 8
|
||||
time_end = time.time()
|
||||
print('convert_test_type_to_difficulty_level totally cost', time_end - time_start)
|
||||
global res_d
|
||||
res_d = result
|
||||
|
||||
return result # {'apple': 4, ...}
|
||||
|
||||
|
||||
|
|
@ -56,12 +48,8 @@ def get_difficulty_level_for_user(d1, d2):
|
|||
d1 用户不会的词
|
||||
在d2的后面添加单词，没有新建一个新的字典
|
||||
"""
|
||||
time_start = time.time()
|
||||
# TODO: convert_test_type_to_difficulty_level() should not be called every time. Each word's difficulty level should be pre-computed.
|
||||
if res_d == {}:
|
||||
d2 = convert_test_type_to_difficulty_level(d2) # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
|
||||
else:
|
||||
d2 = res_d
|
||||
d2 = convert_test_type_to_difficulty_level(d2) # 根据d2的标记评级{'apple': 4, 'abandon': 4, ...}
|
||||
stemmer = snowballstemmer.stemmer('english')
|
||||
|
||||
for k in d1: # 用户的词
|
||||
|
|
@ -73,8 +61,6 @@ def get_difficulty_level_for_user(d1, d2):
|
|||
d2[k] = d2[stem] # 按照词根进行评级
|
||||
else:
|
||||
d2[k] = 3 # 如果k的词根都不在，那么就当认为是3级
|
||||
time_end = time.time()
|
||||
print('get_difficulty_level_for_user totally cost', time_end - time_start)
|
||||
return d2
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -29,8 +29,3 @@ function onReadClick() {
|
|||
function onChooseClick() {
|
||||
isChoose = !isChoose;
|
||||
}
|
||||
|
||||
// 如果网页刷新，停止播放声音
|
||||
if (performance.getEntriesByType("navigation")[0].type == "reload") {
|
||||
Reader.stopRead();
|
||||
}
|
||||
|
|
@ -22,38 +22,62 @@ function getWord() {
|
|||
|
||||
function highLight() {
|
||||
if (!isHighlight) return;
|
||||
let articleContent = document.getElementById("article").innerHTML; // innerHTML保留HTML标签来保持部分格式，且适配不同的浏览器
|
||||
let articleContent = document.getElementById("article").innerText; //将原来的.innerText改为.innerHtml，使用innerText会把原文章中所包含的<br>标签去除，导致处理后的文章内容失去了原来的格式
|
||||
let pickedWords = document.getElementById("selected-words"); // words picked to the text area
|
||||
let dictionaryWords = document.getElementById("selected-words2"); // words appearing in the user's new words list
|
||||
let allWords = dictionaryWords === null ? pickedWords.value + " " : pickedWords.value + " " + dictionaryWords.value;
|
||||
const list = allWords.split(" "); // 将所有的生词放入一个list中
|
||||
let totalSet = new Set();
|
||||
let allWords = ""; //初始化allWords的值，避免进入判断后编译器认为allWords未初始化的问题
|
||||
if(dictionaryWords != null){//增加一个判断，检查生词本里面是否为空，如果为空，allWords只添加选中的单词
|
||||
allWords = pickedWords.value + " " + dictionaryWords.value;
|
||||
}
|
||||
else{
|
||||
allWords = pickedWords.value + " ";
|
||||
}
|
||||
const list = allWords.split(" ");//将所有的生词放入一个list中，用于后续处理
|
||||
for (let i = 0; i < list.length; ++i) {
|
||||
list[i] = list[i].replace(/(^\W*)|(\W*$)/g, ""); // 消除单词两边的非单词字符
|
||||
if (list[i] != "" && !totalSet.has(list[i])) {
|
||||
// 返回所有匹配单词的集合, 正则表达式RegExp()中, "\b"匹配一个单词的边界, g 表示全局匹配, i 表示对大小写不敏感。
|
||||
let matches = new Set(articleContent.match(new RegExp("\\b" + list[i] + "\\b", "gi")));
|
||||
if (matches.has("mark")) {
|
||||
// 优先处理单词为 "mark" 的情况
|
||||
totalSet = new Set(["mark", ...totalSet]);
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/g, ""); //消除单词两边的空字符
|
||||
list[i] = list[i].replace('|', "");
|
||||
list[i] = list[i].replace('?', "");
|
||||
if (list[i] !== "" && "<mark>".indexOf(list[i]) === -1 && "</mark>".indexOf(list[i]) === -1) {
|
||||
//将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。 正则表达式RegExp()中，"\\b"代表单词边界匹配。
|
||||
|
||||
//修改代码
|
||||
let articleContent_fb = articleContent; //文章副本
|
||||
while(articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase()) !== -1 && list[i]!=""){
|
||||
//找到副本中和list[i]匹配的第一个单词(第一种匹配情况),并赋值给list[i]。
|
||||
const index = articleContent_fb.toLowerCase().indexOf(list[i].toLowerCase());
|
||||
list[i] = articleContent_fb.substring(index, index + list[i].length);
|
||||
|
||||
articleContent_fb = articleContent_fb.substring(index + list[i].length); // 使用副本中list[i]之后的子串替换掉副本
|
||||
articleContent = articleContent.replace(new RegExp("\\b"+list[i]+"\\b","g"),"<mark>" + list[i] + "</mark>");
|
||||
}
|
||||
totalSet = new Set([...totalSet, ...matches]);
|
||||
}
|
||||
}
|
||||
// 删除所有的mark标签,防止标签发生嵌套
|
||||
articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
|
||||
articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
|
||||
// 将文章中所有出现该单词word的地方改为："<mark>" + word + "<mark>"。
|
||||
for (let word of totalSet) {
|
||||
articleContent = articleContent.replace(new RegExp("\\b" + word + "\\b", "g"), "<mark>" + word + "</mark>");
|
||||
}
|
||||
document.getElementById("article").innerHTML = articleContent;
|
||||
}
|
||||
|
||||
function cancelHighlighting() {
|
||||
let articleContent = document.getElementById("article").innerHTML;
|
||||
articleContent = articleContent.replace(/<(mark)[^>]*>/gi, "");
|
||||
articleContent = articleContent.replace(/<(\/mark)[^>]*>/gi, "");
|
||||
let articleContent = document.getElementById("article").innerText;//将原来的.innerText改为.innerHtml，原因同上
|
||||
let pickedWords = document.getElementById("selected-words");
|
||||
const dictionaryWords = document.getElementById("selected-words2");
|
||||
const list = pickedWords.value.split(" ");
|
||||
if (pickedWords != null) {
|
||||
for (let i = 0; i < list.length; ++i) {
|
||||
list[i] = list[i].replace(/(^\s*)|(\s*$)/g, "");
|
||||
if (list[i] !== "") { //原来判断的代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
|
||||
articleContent = articleContent.replace(new RegExp("<mark>"+list[i]+"</mark>", "g"), list[i]);
|
||||
}
|
||||
}
|
||||
}
|
||||
if (dictionaryWords != null) {
|
||||
let list2 = pickedWords.value.split(" ");
|
||||
for (let i = 0; i < list2.length; ++i) {
|
||||
list2 = dictionaryWords.value.split(" ");
|
||||
list2[i] = list2[i].replace(/(^\s*)|(\s*$)/g, "");
|
||||
if (list2[i] !== "") { //原来代码中，替换的内容为“list[i]”这个字符串，这明显是错误的，我们需要替换的是list[i]里的内容
|
||||
articleContent = articleContent.replace(new RegExp("<mark>"+list2[i]+"</mark>", "g"), list2[i]);
|
||||
}
|
||||
}
|
||||
}
|
||||
document.getElementById("article").innerHTML = articleContent;
|
||||
}
|
||||
|
||||
|
|
@ -75,4 +99,4 @@ function toggleHighlighting() {
|
|||
}
|
||||
}
|
||||
|
||||
showBtnHandler();
|
||||
showBtnHandler();
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@ var Reader = (function() {
|
|||
msg.rate = rate;
|
||||
msg.lang = "en-US";
|
||||
msg.onboundary = ev => {
|
||||
if (ev.name === "word") {
|
||||
if (ev.name == "word") {
|
||||
current_position = ev.charIndex;
|
||||
}
|
||||
}
|
||||
|
|
@ -32,4 +32,4 @@ var Reader = (function() {
|
|||
read: read,
|
||||
stopRead: stopRead
|
||||
};
|
||||
}) ();
|
||||
})();
|
||||
|
|
|
|||
|
|
@ -5,14 +5,15 @@ function familiar(theWord) {
|
|||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/familiar",
|
||||
success:function(response) {
|
||||
success:function(response){
|
||||
let new_freq = freq - 1;
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
if (allow_move) {
|
||||
|
||||
if (new_freq <= 0) {
|
||||
removeWord(theWord);
|
||||
} else {
|
||||
renderWord({word: theWord, freq: new_freq});
|
||||
renderWord({ word: theWord, freq: new_freq });
|
||||
}
|
||||
} else {
|
||||
if(new_freq <1) {
|
||||
|
|
@ -32,11 +33,11 @@ function unfamiliar(theWord) {
|
|||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/unfamiliar",
|
||||
success:function(response) {
|
||||
success:function(response){
|
||||
let new_freq = parseInt(freq) + 1;
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
if (allow_move) {
|
||||
renderWord({word: theWord, freq: new_freq});
|
||||
renderWord({ word: theWord, freq: new_freq });
|
||||
} else {
|
||||
$("#freq_" + theWord).text(new_freq);
|
||||
}
|
||||
|
|
@ -50,7 +51,7 @@ function delete_word(theWord) {
|
|||
$.ajax({
|
||||
type:"GET",
|
||||
url:"/" + username + "/" + word + "/del",
|
||||
success:function(response) {
|
||||
success:function(response){
|
||||
const allow_move = document.getElementById("move_dynamiclly").checked;
|
||||
if (allow_move) {
|
||||
removeWord(theWord);
|
||||
|
|
@ -113,7 +114,7 @@ function removeWord(word) {
|
|||
// 根据词频信息删除元素
|
||||
word = word.replace('&', '&');
|
||||
const element_to_remove = document.getElementById(`p_${word}`);
|
||||
if (element_to_remove !== null) {
|
||||
if (element_to_remove != null) {
|
||||
element_to_remove.remove();
|
||||
}
|
||||
}
|
||||
|
|
@ -128,7 +129,7 @@ function renderWord(word) {
|
|||
for (const current of container.children) {
|
||||
const cur_word = parseWord(current);
|
||||
// 找到第一个词频比它小的元素，插入到这个元素前面
|
||||
if (compareWord(cur_word, word) === -1) {
|
||||
if (compareWord(cur_word, word) == -1) {
|
||||
container.insertBefore(new_element, current);
|
||||
inserted = true;
|
||||
break;
|
||||
|
|
@ -164,11 +165,17 @@ function elementFromString(string) {
|
|||
* 当first大于second时返回1
|
||||
*/
|
||||
function compareWord(first, second) {
|
||||
if (first.freq !== second.freq) {
|
||||
return first.freq < second.freq ? -1 : 1;
|
||||
if (first.freq < second.freq) {
|
||||
return -1;
|
||||
}
|
||||
if (first.word !== second.word) {
|
||||
return first.word < second.word ? -1 : 1;
|
||||
if (first.freq > second.freq) {
|
||||
return 1;
|
||||
}
|
||||
if (first.word < second.word) {
|
||||
return -1;
|
||||
}
|
||||
if (first.word > second.word) {
|
||||
return 1;
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -32,17 +32,6 @@
|
|||
40%, 60% { transform: translate3d(+4px, 0, 0); }
|
||||
50% { transform: translate3d(-4px, 0, 0); }
|
||||
}
|
||||
|
||||
.lead{
|
||||
font-size: 17px;
|
||||
font-family: Arial, Helvetica, sans-serif;
|
||||
}
|
||||
|
||||
.display-5{
|
||||
font-size: 30px;
|
||||
}
|
||||
|
||||
|
||||
</style>
|
||||
</head>
|
||||
<body>
|
||||
|
|
@ -60,22 +49,18 @@
|
|||
{# <div class="alert alert-warning" role="alert">Congratulations! {{ message }}</div>#}
|
||||
{# {% endfor %}#}
|
||||
|
||||
<button class="btn btn-success" id="load_next_article" onclick="load_next_article();Reader.stopRead()"> 下一篇 Next Article </button>
|
||||
<button class="btn btn-success" id="load_pre_article" onclick="load_pre_article();Reader.stopRead()" > 上一篇 Previous Article </button>
|
||||
<button class="btn btn-success" id="load_next_article" onclick="load_next_article()"> 下一篇 Next Article </button>
|
||||
<button class="btn btn-success" id="load_pre_article" onclick="load_pre_article()" > 上一篇 Previous Article </button>
|
||||
|
||||
<p><b>阅读文章并回答问题</b></p>
|
||||
<div id="text-content">
|
||||
<div id="found">
|
||||
<div class="alert alert-success" role="alert">According to your word list, your level is <span class="badge bg-success" id="user-level">{{ today_article["user_level"] }}</span> and we have chosen an article with a difficulty level of <span class="badge bg-success" id="text_level">{{ today_article["text_level"] }}</span> for you.</div>
|
||||
<p class="text-muted" id="date">Article added on: {{ today_article["date"] }}</p><br/>
|
||||
<div class="p-3 mb-2 bg-light text-dark" style="margin: 0 0.5%;"><br/>
|
||||
<div class="p-3 mb-2 bg-light text-dark"><br/>
|
||||
<p class="display-5" id="article_title">{{ today_article["article_title"] }}</p><br/>
|
||||
<p class="lead"><font id="article">{{ today_article["article_body"] }}</font></p><br/>
|
||||
<div>
|
||||
<h6>source: </h6>
|
||||
<p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
|
||||
</div>
|
||||
|
||||
<p class="lead"><font id="article" size=2>{{ today_article["article_body"] }}</font></p><br/>
|
||||
<p><small class="text-muted" id="source">{{ today_article['source'] }}</small></p><br/>
|
||||
<p><b id="question">{{ today_article['question'] }}</b></p><br/>
|
||||
<script type="text/javascript">
|
||||
function toggle_visibility(id) { {# https://css-tricks.com/snippets/javascript/showhide-element/#}
|
||||
|
|
@ -112,7 +97,7 @@
|
|||
<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 }}/userpage">
|
||||
<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" onclick="Reader.stopRead()"/>
|
||||
<input type="submit" value="把生词加入我的生词库"/>
|
||||
<input type="reset" value="清除"/>
|
||||
</form>
|
||||
{% if session.get['thisWord'] %}
|
||||
|
|
|
|||
Loading…
Reference in New Issue