mirror of
https://github.com/CoderSherlock/CoderSherlock.github.io.git
synced 2026-06-13 08:08:10 -07:00
haopengzhan
4859927856
- Added temp logo
- Added favicon
- Enabled Disqus (jekyll.env)
- Changed Home layout
1275 lines
62 KiB
HTML
1275 lines
62 KiB
HTML
<!DOCTYPE html><html lang="en">
|
||
<head><!-- Global site tag (gtag.js) - Google Analytics -->
|
||
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-82637164-1"></script>
|
||
<script>
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
|
||
gtag('config', 'UA-82637164-1');
|
||
|
||
</script><meta charset="utf-8">
|
||
<meta http-equiv="X-UA-Compatible" content="IE=edge">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1, user-scalable=no"><title>Generate Word Cloud Figures with Chinese-Tokenization and WordCloud python libraries - Stop Talking, Start Doing</title>
|
||
|
||
<meta name="description" content="Let’s generate a word cloud like this. Don’t understand the language is not a big deal.If your written language is based on latin alphabet(or other language ...">
|
||
<link rel="canonical" href="https://codersherlock.github.com//posts/generate-word-cloud-with-chinese-fenci"><link rel="alternate" type="application/rss+xml" title="Stop Talking, Start Doing" href="/feed.xml"><link rel="apple-touch-icon" sizes="180x180" href="/assets/apple-touch-icon.png">
|
||
<link rel="icon" type="image/png" sizes="32x32" href="/assets/favicon-32x32.png">
|
||
<link rel="icon" type="image/png" sizes="16x16" href="/assets/favicon-16x16.png">
|
||
<link rel="manifest" href="/assets/site.webmanifest">
|
||
<link rel="mask-icon" href="/assets/safari-pinned-tab.svg" color="#5bbad5">
|
||
<link rel="shortcut icon" href="/assets/favicon.ico">
|
||
<meta name="msapplication-TileColor" content="#da532c">
|
||
<meta name="msapplication-config" content="/assets/browserconfig.xml">
|
||
<meta name="theme-color" content="#ffffff">
|
||
<link rel="stylesheet" href="/assets/css/main.css"><link rel="stylesheet" href="https://cdn.bootcdn.net/ajax/libs/font-awesome/5.15.1/css/all.css" ><!-- start custom head snippets -->
|
||
|
||
<!-- end custom head snippets -->
|
||
<script>(function() {
|
||
window.isArray = function(val) {
|
||
return Object.prototype.toString.call(val) === '[object Array]';
|
||
};
|
||
window.isString = function(val) {
|
||
return typeof val === 'string';
|
||
};
|
||
|
||
window.hasEvent = function(event) {
|
||
return 'on'.concat(event) in window.document;
|
||
};
|
||
|
||
window.isOverallScroller = function(node) {
|
||
return node === document.documentElement || node === document.body || node === window;
|
||
};
|
||
|
||
window.isFormElement = function(node) {
|
||
var tagName = node.tagName;
|
||
return tagName === 'INPUT' || tagName === 'SELECT' || tagName === 'TEXTAREA';
|
||
};
|
||
|
||
window.pageLoad = (function () {
|
||
var loaded = false, cbs = [];
|
||
window.addEventListener('load', function () {
|
||
var i;
|
||
loaded = true;
|
||
if (cbs.length > 0) {
|
||
for (i = 0; i < cbs.length; i++) {
|
||
cbs[i]();
|
||
}
|
||
}
|
||
});
|
||
return {
|
||
then: function(cb) {
|
||
cb && (loaded ? cb() : (cbs.push(cb)));
|
||
}
|
||
};
|
||
})();
|
||
})();
|
||
(function() {
|
||
window.throttle = function(func, wait) {
|
||
var args, result, thisArg, timeoutId, lastCalled = 0;
|
||
|
||
function trailingCall() {
|
||
lastCalled = new Date;
|
||
timeoutId = null;
|
||
result = func.apply(thisArg, args);
|
||
}
|
||
return function() {
|
||
var now = new Date,
|
||
remaining = wait - (now - lastCalled);
|
||
|
||
args = arguments;
|
||
thisArg = this;
|
||
|
||
if (remaining <= 0) {
|
||
clearTimeout(timeoutId);
|
||
timeoutId = null;
|
||
lastCalled = now;
|
||
result = func.apply(thisArg, args);
|
||
} else if (!timeoutId) {
|
||
timeoutId = setTimeout(trailingCall, remaining);
|
||
}
|
||
return result;
|
||
};
|
||
};
|
||
})();
|
||
(function() {
|
||
var Set = (function() {
|
||
var add = function(item) {
|
||
var i, data = this._data;
|
||
for (i = 0; i < data.length; i++) {
|
||
if (data[i] === item) {
|
||
return;
|
||
}
|
||
}
|
||
this.size ++;
|
||
data.push(item);
|
||
return data;
|
||
};
|
||
|
||
var Set = function(data) {
|
||
this.size = 0;
|
||
this._data = [];
|
||
var i;
|
||
if (data.length > 0) {
|
||
for (i = 0; i < data.length; i++) {
|
||
add.call(this, data[i]);
|
||
}
|
||
}
|
||
};
|
||
Set.prototype.add = add;
|
||
Set.prototype.get = function(index) { return this._data[index]; };
|
||
Set.prototype.has = function(item) {
|
||
var i, data = this._data;
|
||
for (i = 0; i < data.length; i++) {
|
||
if (this.get(i) === item) {
|
||
return true;
|
||
}
|
||
}
|
||
return false;
|
||
};
|
||
Set.prototype.is = function(map) {
|
||
if (map._data.length !== this._data.length) { return false; }
|
||
var i, j, flag, tData = this._data, mData = map._data;
|
||
for (i = 0; i < tData.length; i++) {
|
||
for (flag = false, j = 0; j < mData.length; j++) {
|
||
if (tData[i] === mData[j]) {
|
||
flag = true;
|
||
break;
|
||
}
|
||
}
|
||
if (!flag) { return false; }
|
||
}
|
||
return true;
|
||
};
|
||
Set.prototype.values = function() {
|
||
return this._data;
|
||
};
|
||
return Set;
|
||
})();
|
||
|
||
window.Lazyload = (function(doc) {
|
||
var queue = {js: [], css: []}, sources = {js: {}, css: {}}, context = this;
|
||
var createNode = function(name, attrs) {
|
||
var node = doc.createElement(name), attr;
|
||
for (attr in attrs) {
|
||
if (attrs.hasOwnProperty(attr)) {
|
||
node.setAttribute(attr, attrs[attr]);
|
||
}
|
||
}
|
||
return node;
|
||
};
|
||
var end = function(type, url) {
|
||
var s, q, qi, cbs, i, j, cur, val, flag;
|
||
if (type === 'js' || type ==='css') {
|
||
s = sources[type], q = queue[type];
|
||
s[url] = true;
|
||
for (i = 0; i < q.length; i++) {
|
||
cur = q[i];
|
||
if (cur.urls.has(url)) {
|
||
qi = cur, val = qi.urls.values();
|
||
qi && (cbs = qi.callbacks);
|
||
for (flag = true, j = 0; j < val.length; j++) {
|
||
cur = val[j];
|
||
if (!s[cur]) {
|
||
flag = false;
|
||
}
|
||
}
|
||
if (flag && cbs && cbs.length > 0) {
|
||
for (j = 0; j < cbs.length; j++) {
|
||
cbs[j].call(context);
|
||
}
|
||
qi.load = true;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
};
|
||
var load = function(type, urls, callback) {
|
||
var s, q, qi, node, i, cur,
|
||
_urls = typeof urls === 'string' ? new Set([urls]) : new Set(urls), val, url;
|
||
if (type === 'js' || type ==='css') {
|
||
s = sources[type], q = queue[type];
|
||
for (i = 0; i < q.length; i++) {
|
||
cur = q[i];
|
||
if (_urls.is(cur.urls)) {
|
||
qi = cur;
|
||
break;
|
||
}
|
||
}
|
||
val = _urls.values();
|
||
if (qi) {
|
||
callback && (qi.load || qi.callbacks.push(callback));
|
||
callback && (qi.load && callback());
|
||
} else {
|
||
q.push({
|
||
urls: _urls,
|
||
callbacks: callback ? [callback] : [],
|
||
load: false
|
||
});
|
||
for (i = 0; i < val.length; i++) {
|
||
node = null, url = val[i];
|
||
if (s[url] === undefined) {
|
||
(type === 'js' ) && (node = createNode('script', { src: url }));
|
||
(type === 'css') && (node = createNode('link', { rel: 'stylesheet', href: url }));
|
||
if (node) {
|
||
node.onload = (function(type, url) {
|
||
return function() {
|
||
end(type, url);
|
||
};
|
||
})(type, url);
|
||
(doc.head || doc.body).appendChild(node);
|
||
s[url] = false;
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
};
|
||
return {
|
||
js: function(url, callback) {
|
||
load('js', url, callback);
|
||
},
|
||
css: function(url, callback) {
|
||
load('css', url, callback);
|
||
}
|
||
};
|
||
})(this.document);
|
||
})();
|
||
</script><script>
|
||
(function() {
|
||
var TEXT_VARIABLES = {
|
||
version: '2.2.6',
|
||
sources: {
|
||
font_awesome: 'https://cdn.bootcdn.net/ajax/libs/font-awesome/5.15.1/css/all.css',
|
||
jquery: 'https://cdn.bootcss.com/jquery/3.1.1/jquery.min.js',
|
||
leancloud_js_sdk: '//cdn.jsdelivr.net/npm/leancloud-storage@3.13.2/dist/av-min.js',
|
||
chart: 'https://cdn.bootcss.com/Chart.js/2.7.2/Chart.bundle.min.js',
|
||
gitalk: {
|
||
js: 'https://cdn.bootcss.com/gitalk/1.2.2/gitalk.min.js',
|
||
css: 'https://cdn.bootcss.com/gitalk/1.2.2/gitalk.min.css'
|
||
},
|
||
valine: 'https://unpkg.com/valine/dist/Valine.min.js',
|
||
mathjax: 'https://cdn.bootcss.com/mathjax/2.7.4/MathJax.js?config=TeX-MML-AM_CHTML',
|
||
mermaid: 'https://cdn.bootcss.com/mermaid/8.0.0-rc.8/mermaid.min.js'
|
||
},
|
||
site: {
|
||
toc: {
|
||
selectors: 'h1,h2,h3'
|
||
}
|
||
},
|
||
paths: {
|
||
search_js: '/assets/search.js'
|
||
}
|
||
};
|
||
window.TEXT_VARIABLES = TEXT_VARIABLES;
|
||
})();
|
||
</script>
|
||
</head>
|
||
<body>
|
||
<div class="root" data-is-touch="false">
|
||
<div class="layout--page js-page-root"><div class="page__main js-page-main page__viewport has-aside cell cell--auto">
|
||
|
||
<div class="page__main-inner"><div class="page__header d-print-none"><header class="header"><div class="main">
|
||
<div class="header__title">
|
||
<div class="header__brand"><?xml version="1.0" standalone="no"?>
|
||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 20010904//EN"
|
||
"http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
|
||
<svg version="1.0" xmlns="http://www.w3.org/2000/svg"
|
||
width="231.000000pt" height="218.000000pt" viewBox="0 0 231.000000 218.000000"
|
||
preserveAspectRatio="xMidYMid meet">
|
||
<metadata>
|
||
Created by potrace 1.16, written by Peter Selinger 2001-2019
|
||
</metadata>
|
||
<g transform="translate(0.000000,218.000000) scale(0.100000,-0.100000)"
|
||
fill="#000000" stroke="none">
|
||
<path d="M1754 2168 c-3 -4 -2 -8 3 -8 4 0 3 -4 -4 -8 -6 -4 -13 -23 -16 -42
|
||
-4 -19 -14 -41 -24 -49 -17 -12 -16 -13 6 -8 l25 6 -27 -25 c-31 -29 -33 -34
|
||
-11 -34 8 0 12 5 9 10 -3 6 -2 10 4 10 5 0 13 -5 16 -10 4 -6 12 -7 18 -4 8 5
|
||
8 3 0 -7 -7 -7 -13 -21 -13 -32 0 -10 -4 -16 -9 -13 -14 9 -7 -18 11 -45 l16
|
||
-24 16 39 c9 21 16 44 16 51 0 6 3 15 8 19 4 4 7 11 8 14 0 4 4 23 9 42 9 36
|
||
11 46 13 68 1 7 6 11 11 8 4 -3 6 5 4 18 -4 17 0 26 14 29 10 3 -8 5 -40 4
|
||
-32 0 -60 -4 -63 -9z"/>
|
||
<path d="M1936 2163 c-4 -9 -2 -20 5 -23 14 -9 14 -21 -1 -30 -8 -5 -2 -10 14
|
||
-14 15 -4 24 -11 21 -17 -4 -5 -15 -7 -26 -4 -13 5 -19 2 -19 -10 0 -9 7 -15
|
||
17 -13 14 3 17 -6 18 -52 1 -30 3 -60 7 -65 3 -6 4 -23 2 -40 -1 -16 -5 -62
|
||
-8 -102 -2 -39 -7 -80 -10 -90 -4 -12 3 -28 19 -45 14 -15 21 -30 15 -33 -6
|
||
-4 -4 -17 5 -36 9 -16 13 -34 10 -39 -3 -6 1 -10 9 -10 22 0 20 -30 -1 -31
|
||
-14 0 -15 -2 -3 -6 22 -9 42 -32 36 -42 -3 -5 -17 -11 -31 -13 -14 -3 -22 -1
|
||
-18 5 7 12 -16 27 -42 27 -19 -1 -19 -1 -2 -14 16 -12 16 -15 3 -29 -14 -13
|
||
-14 -16 0 -21 13 -5 14 -9 4 -21 -8 -10 -9 -15 -2 -15 6 0 9 -6 6 -13 -2 -7 2
|
||
-26 10 -42 8 -16 13 -32 10 -37 -3 -4 0 -8 5 -8 6 0 11 -7 11 -15 0 -8 5 -15
|
||
12 -15 6 0 3 -10 -8 -21 -19 -22 -19 -22 5 -14 16 5 21 4 17 -4 -5 -7 -1 -8
|
||
10 -4 12 5 15 3 9 -6 -6 -10 -2 -11 16 -7 19 6 21 5 8 -3 -20 -13 -66 -9 -98
|
||
8 -15 9 -21 9 -16 2 3 -6 -4 -20 -17 -31 -16 -14 -18 -18 -5 -14 12 4 17 1 17
|
||
-11 0 -14 -6 -16 -30 -11 -38 7 -39 -1 -2 -15 24 -9 25 -11 9 -20 -9 -6 -15
|
||
-14 -12 -20 4 -5 -2 -9 -12 -9 -10 0 -25 -5 -33 -11 -13 -10 -13 -10 1 -6 9 3
|
||
16 -1 16 -9 0 -12 -3 -12 -21 0 -17 10 -21 25 -22 65 -1 29 -7 58 -14 64 -10
|
||
9 -11 9 -5 -3 6 -10 1 -8 -13 4 -12 10 -19 22 -17 26 3 4 -2 11 -11 14 -8 3
|
||
-12 10 -9 16 3 6 -1 13 -10 16 -10 4 -15 14 -12 25 3 10 -2 19 -12 22 -26 6
|
||
-39 -3 -34 -24 6 -23 -13 -49 -37 -49 -10 0 -27 11 -38 25 -24 30 -32 31 -32
|
||
4 0 -16 -4 -19 -21 -14 -15 5 -19 4 -14 -5 5 -8 0 -7 -14 2 -14 9 -20 22 -19
|
||
40 1 16 6 28 11 28 5 0 3 7 -4 16 -8 9 -12 27 -11 40 7 52 -18 131 -54 168
|
||
-40 42 -76 50 -182 44 -86 -5 -133 -24 -174 -72 -23 -26 -27 -40 -28 -94 0
|
||
-66 17 -113 47 -132 17 -10 17 -10 -1 -8 -10 2 -21 -3 -24 -11 -3 -10 0 -12
|
||
13 -7 15 5 16 4 5 -9 -10 -12 -10 -15 3 -15 8 0 17 9 20 21 3 12 10 18 16 14
|
||
8 -4 6 -11 -4 -21 -8 -9 -13 -19 -10 -24 3 -4 -5 -6 -17 -4 -21 4 -21 4 -3 -5
|
||
15 -7 24 -4 37 13 21 25 22 20 7 -22 -6 -18 -14 -30 -19 -27 -4 2 -15 -4 -24
|
||
-14 -17 -18 -16 -19 18 -18 20 1 36 4 36 8 0 4 7 9 15 13 13 5 13 2 -1 -19
|
||
-13 -20 -20 -23 -34 -15 -15 8 -22 5 -33 -10 -12 -17 -16 -18 -20 -6 -4 9 -14
|
||
12 -26 9 -13 -3 -21 -1 -21 8 0 7 -3 10 -6 7 -3 -4 -1 -15 4 -25 6 -11 7 -25
|
||
3 -32 -6 -8 -10 -2 -14 18 -8 36 -22 40 -38 9 -10 -18 -9 -20 5 -15 9 4 16 1
|
||
16 -4 0 -7 -11 -9 -25 -7 -13 3 -26 0 -29 -6 -3 -7 -5 -6 -5 2 -1 7 -7 10 -13
|
||
7 -7 -4 -4 2 8 12 19 16 39 53 29 53 -2 0 -17 -14 -33 -31 l-30 -32 5 27 c4
|
||
20 1 26 -11 26 -11 0 -15 -5 -10 -12 4 -7 -2 -5 -13 4 -11 10 -27 18 -36 18
|
||
-9 0 -21 8 -27 18 -9 14 -10 11 -5 -15 5 -24 2 -34 -12 -43 -16 -10 -15 -10 5
|
||
-4 23 6 24 6 5 -14 -18 -19 -18 -19 -52 0 -33 19 -34 19 -28 -1 5 -19 3 -19
|
||
-18 -5 -26 17 -39 51 -21 57 6 2 4 3 -4 2 -8 0 -14 -6 -13 -12 1 -6 -5 -17
|
||
-14 -25 -10 -8 -14 -8 -10 -1 4 6 2 15 -4 19 -7 4 -9 3 -5 -4 3 -6 -2 -15 -11
|
||
-21 -14 -8 -14 -10 -3 -11 9 0 5 -6 -10 -17 -14 -10 -28 -17 -32 -15 -5 1 -8
|
||
-6 -8 -16 0 -10 -5 -23 -11 -29 -7 -7 -7 -13 0 -17 7 -4 6 -16 -1 -36 -7 -23
|
||
-7 -34 2 -45 11 -14 7 -19 -12 -16 -5 0 -8 -3 -8 -9 0 -13 6 -13 31 1 19 10
|
||
20 9 9 -12 -11 -19 -10 -21 4 -16 10 4 14 3 11 -2 -3 -5 -1 -12 5 -16 13 -8
|
||
13 -25 -1 -25 -5 0 -7 6 -3 13 4 7 3 9 -2 4 -5 -5 -9 -14 -9 -20 -1 -7 -7 -11
|
||
-14 -9 -7 1 -19 -5 -27 -15 -13 -17 -13 -17 -14 4 0 12 5 25 10 28 6 4 7 11 4
|
||
17 -4 7 -2 8 4 4 7 -4 12 -1 12 9 0 11 -5 15 -16 11 -8 -3 -12 -2 -9 4 3 6 1
|
||
10 -6 10 -7 0 -5 8 6 20 10 11 13 20 7 20 -6 0 -14 -5 -17 -10 -5 -8 -11 -7
|
||
-21 1 -7 6 -11 15 -8 20 3 5 -3 6 -12 2 -10 -4 -13 -8 -7 -10 6 -2 9 -16 7
|
||
-29 -3 -15 -1 -23 5 -20 5 4 12 3 14 -1 3 -5 -14 -9 -36 -10 -31 -2 -38 0 -27
|
||
7 13 9 12 13 -8 30 -13 10 -29 17 -37 14 -17 -7 -28 -34 -14 -34 6 0 9 -9 6
|
||
-20 -3 -11 -1 -20 5 -20 5 0 7 -4 3 -9 -3 -5 -1 -12 5 -16 6 -4 7 -11 4 -17
|
||
-4 -6 1 -17 11 -25 11 -7 13 -13 6 -13 -7 0 -9 -4 -6 -10 8 -13 -1 -13 -26 0
|
||
-13 7 -19 7 -19 0 0 -5 7 -10 16 -10 8 0 13 -4 9 -9 -3 -5 7 -11 22 -13 20 -2
|
||
27 -8 25 -20 -2 -10 3 -18 9 -18 7 0 3 -9 -9 -20 -22 -21 -67 -27 -77 -10 -6
|
||
10 13 14 45 11 13 -2 13 -1 0 8 -12 9 -13 11 -1 11 8 0 11 3 8 7 -4 3 -22 -2
|
||
-41 -12 l-34 -18 26 -24 c14 -12 19 -23 12 -23 -7 0 -10 -7 -6 -16 3 -9 2 -12
|
||
-4 -9 -6 4 -9 14 -8 23 2 9 -5 18 -15 20 -16 3 -17 1 -8 -16 8 -15 8 -22 -2
|
||
-25 -7 -3 -5 -6 6 -6 9 -1 16 -6 15 -13 -2 -7 8 -12 24 -12 23 1 25 -1 18 -21
|
||
-10 -26 -2 -104 13 -122 6 -9 6 -13 -2 -13 -7 0 -9 -4 -6 -10 3 -5 0 -10 -7
|
||
-10 -11 0 -11 -2 0 -9 10 -6 11 -13 1 -34 -9 -21 -9 -33 -1 -53 8 -16 9 -31 3
|
||
-43 -7 -13 -4 -24 15 -46 13 -15 24 -39 24 -53 0 -17 4 -22 14 -19 10 4 17 -4
|
||
21 -24 4 -17 13 -33 20 -35 7 -3 16 -16 19 -30 l6 -24 600 0 c368 0 600 4 600
|
||
9 0 6 -4 13 -10 16 -5 3 -10 12 -9 18 0 9 2 9 5 1 7 -16 44 -5 44 12 0 17 21
|
||
18 44 1 22 -16 12 -44 -17 -50 -12 -2 28 -5 90 -6 98 -1 112 1 117 17 3 9 20
|
||
23 37 31 20 9 28 18 24 29 -4 12 -3 13 9 3 17 -14 36 -7 36 14 0 8 -6 12 -14
|
||
9 -10 -4 -13 0 -9 14 5 20 -23 84 -59 134 -12 18 -29 29 -46 29 -24 2 -24 2
|
||
-4 6 12 2 22 7 22 10 0 2 -17 29 -37 58 -35 50 -114 115 -141 115 -6 0 -12 4
|
||
-12 8 0 5 -16 27 -36 50 -19 23 -31 42 -25 42 6 0 16 -9 23 -20 16 -24 30 -26
|
||
21 -3 -5 13 0 12 28 -7 43 -30 80 -70 115 -125 15 -24 31 -42 36 -39 5 3 7 2
|
||
6 -3 -5 -15 39 -63 57 -63 13 0 15 -3 7 -13 -9 -10 -1 -34 29 -95 23 -45 46
|
||
-82 51 -82 5 0 6 -5 3 -10 -3 -6 0 -13 8 -16 9 -3 13 -13 10 -25 -3 -10 -1
|
||
-19 5 -19 6 0 12 -10 14 -22 3 -21 8 -23 63 -23 l60 0 3 62 c3 59 2 63 -19 63
|
||
-22 0 -22 -1 -4 -13 11 -9 14 -16 7 -21 -6 -3 -18 2 -28 11 -12 13 -19 14 -22
|
||
5 -9 -28 -32 -12 -32 23 0 24 5 35 15 35 8 0 15 -5 15 -11 0 -5 5 -7 11 -3 8
|
||
5 8 9 -1 14 -8 5 -9 9 -1 11 12 5 3 49 -10 49 -5 0 -8 -3 -7 -7 2 -5 -1 -8 -7
|
||
-8 -5 0 -9 11 -7 25 l2 25 -17 -27 c-21 -33 -34 -35 -58 -8 -10 11 -26 22 -36
|
||
25 -23 8 -25 25 -4 25 8 0 15 -5 15 -11 0 -8 4 -8 13 -1 7 6 25 9 40 6 22 -3
|
||
27 -1 27 16 0 11 4 20 10 20 5 0 7 -6 4 -14 -7 -17 25 -36 52 -32 10 2 13 1 7
|
||
-1 -9 -3 -10 -10 -3 -23 6 -11 9 -23 8 -27 -4 -14 13 -53 23 -53 5 0 7 50 5
|
||
123 -6 156 -6 68 0 1050 l5 848 -28 -3 c-20 -2 -29 -9 -31 -24 -2 -16 -8 -20
|
||
-21 -17 -13 3 -17 11 -14 24 4 14 0 19 -16 19 -11 0 -21 -3 -20 -7 1 -5 -2
|
||
-18 -6 -31 -6 -19 -12 -22 -35 -17 -16 3 -31 2 -34 -3 -7 -11 -106 -3 -123 10
|
||
-8 6 -13 3 -16 -9 -3 -10 -5 -1 -6 20 -1 38 -14 49 -25 20z m-1276 -1513 c-12
|
||
-7 -12 -10 -1 -10 8 0 11 -6 7 -17 -3 -10 3 -6 15 10 23 30 41 34 59 12 11
|
||
-13 10 -14 -5 -9 -13 5 -16 4 -11 -4 4 -7 19 -12 34 -13 l27 -1 -29 -8 c-16
|
||
-5 -32 -7 -36 -5 -3 2 -6 -8 -6 -21 0 -21 4 -24 23 -19 21 5 22 4 11 -15 -7
|
||
-11 -19 -20 -26 -20 -8 0 -10 5 -6 12 5 8 2 9 -12 3 -39 -16 -67 -19 -59 -5 5
|
||
9 4 11 -4 6 -6 -4 -9 -12 -6 -17 3 -5 -1 -6 -10 -3 -9 4 -14 13 -11 20 4 10
|
||
-4 9 -29 -4 -18 -9 -32 -21 -32 -26 1 -5 -4 -11 -12 -14 -10 -3 -12 0 -8 11 3
|
||
9 1 17 -6 20 -7 2 -4 16 11 40 l22 38 -23 -13 c-12 -6 -32 -12 -45 -13 -20 -1
|
||
-21 1 -7 11 12 9 13 13 3 17 -10 3 -10 7 -1 17 10 11 15 11 28 0 11 -9 15 -9
|
||
15 -1 0 7 4 10 10 6 5 -3 18 0 29 7 15 9 25 9 46 0 14 -7 24 -8 21 -3 -6 9 8
|
||
19 29 20 6 0 3 -4 -5 -9z m914 -29 c34 -29 46 -76 46 -179 0 -87 -3 -105 -26
|
||
-148 -50 -95 -82 -115 -187 -115 -60 0 -82 4 -122 26 -44 23 -104 79 -105 97
|
||
0 10 -46 110 -82 181 -31 61 -31 78 3 121 27 34 75 34 164 2 61 -22 70 -23
|
||
101 -10 18 8 42 14 53 14 10 0 38 9 61 19 45 20 62 19 94 -8z"/>
|
||
<path d="M164 1993 c36 -55 77 -136 71 -141 -3 -3 -57 -6 -120 -6 l-115 -1 4
|
||
-755 c2 -415 4 -769 5 -786 2 -46 27 -52 35 -9 7 38 29 55 57 48 11 -3 19 0
|
||
19 6 0 6 -7 11 -15 11 -20 0 -19 27 2 38 10 6 14 16 10 26 -4 9 -3 16 2 16 7
|
||
0 17 38 25 92 1 3 4 10 8 14 4 4 3 13 -3 21 -9 10 -8 13 5 13 9 0 17 9 17 20
|
||
2 28 3 33 12 48 5 7 6 21 2 31 -4 13 2 26 15 39 12 11 24 38 27 61 3 23 10 41
|
||
16 41 7 0 7 4 -1 12 -14 14 -16 32 -3 23 6 -3 15 4 21 15 8 15 8 20 -2 20 -7
|
||
1 -4 6 7 13 11 7 21 23 22 37 1 14 4 37 7 52 6 25 3 28 -29 34 l-36 6 23 16
|
||
c13 9 26 20 30 26 7 11 -9 26 -27 26 -5 0 -3 -5 5 -10 9 -6 10 -10 3 -10 -24
|
||
0 -24 20 1 29 23 9 29 31 13 47 -4 4 1 12 10 19 11 8 13 14 5 19 -7 4 -12 2
|
||
-12 -3 0 -6 -10 -11 -22 -11 -21 0 -21 0 -2 16 13 11 14 14 3 11 -9 -3 -16 1
|
||
-16 9 0 9 6 13 14 10 8 -3 11 -1 8 4 -3 5 -2 26 4 45 6 21 6 37 0 41 -5 3 -9
|
||
14 -9 25 0 10 -6 19 -12 19 -9 0 -9 3 1 9 8 5 14 22 15 37 1 16 5 35 9 42 5 6
|
||
5 12 2 12 -4 0 1 7 10 16 9 10 15 24 12 33 -2 9 2 22 10 29 7 7 13 23 13 35 0
|
||
28 15 51 28 43 5 -3 13 2 16 11 6 15 -8 32 -26 33 -5 0 -8 7 -8 15 0 8 -6 15
|
||
-12 15 -8 0 -5 7 6 15 12 9 15 15 7 15 -9 0 -12 9 -9 24 3 17 1 23 -8 19 -25
|
||
-9 -36 8 -18 28 16 17 16 19 1 19 -10 0 -17 5 -17 10 0 6 5 10 11 10 6 0 9 6
|
||
6 13 -2 6 3 17 11 23 13 10 13 14 -1 35 -10 13 -17 18 -17 11 0 -18 -24 -15
|
||
-43 6 -59 64 -60 64 -46 74 11 8 10 9 -3 4 -11 -3 -18 0 -18 8 0 12 -20 26
|
||
-36 26 -2 0 7 -17 20 -37z"/>
|
||
<path d="M1443 1727 c-3 -6 -1 -7 5 -3 23 14 12 -12 -13 -30 -25 -19 -34 -58
|
||
-15 -69 6 -4 26 5 45 19 35 27 73 33 104 16 10 -5 42 -12 72 -15 29 -4 59 -11
|
||
66 -17 17 -14 17 3 0 27 -9 12 -16 14 -21 7 -7 -12 -64 15 -101 48 -22 20
|
||
-132 33 -142 17z"/>
|
||
<path d="M726 1647 c-31 -20 -50 -40 -76 -82 l-24 -40 27 26 c18 17 43 28 73
|
||
33 77 10 102 7 155 -19 27 -14 54 -23 59 -20 16 10 12 55 -5 55 -8 0 -15 5
|
||
-15 10 0 6 -11 10 -24 10 -16 0 -27 7 -31 20 -3 11 -11 20 -16 20 -6 0 -7 -5
|
||
-3 -12 5 -8 2 -9 -12 -3 -33 13 -88 15 -108 2z"/>
|
||
</g>
|
||
</svg>
|
||
<a title="My personal blog, with some boring research staff and some tricks I was fancy to. I'll try my best to make this blog fun and useful. Not just a place I complain about all happens in my Lab.
|
||
" href="/">Stop Talking, Start Doing</a></div><button class="button button--secondary button--circle search-button js-search-toggle"><i class="fas fa-search"></i></button></div><nav class="navigation">
|
||
<ul><li class="navigation__item"><a href="/archive.html">Archive</a></li><li class="navigation__item"><a href="/about.html">About</a></li><li><button class="button button--secondary button--circle search-button js-search-toggle"><i class="fas fa-search"></i></button></li></ul>
|
||
</nav></div>
|
||
</header>
|
||
</div><div class="page__content"><div class ="main"><div class="grid grid--reverse">
|
||
|
||
<div class="col-aside d-print-none js-col-aside"><aside class="page__aside js-page-aside"><div class="toc-aside js-toc-root"></div>
|
||
</aside></div>
|
||
|
||
<div class="col-main cell cell--auto"><!-- start custom main top snippet -->
|
||
|
||
<!-- end custom main top snippet -->
|
||
<article itemscope itemtype="http://schema.org/Article"><div class="article__header"><header><h1>Generate Word Cloud Figures with Chinese-Tokenization and WordCloud python libraries</h1></header></div><meta itemprop="headline" content="Generate Word Cloud Figures with Chinese-Tokenization and WordCloud python libraries"><div class="article__info clearfix"><ul class="left-col menu"><li>
|
||
<a class="button button--secondary button--pill button--sm"
|
||
href="/archive.html?tag=visualization">visualization</a>
|
||
</li></ul><ul class="right-col menu"><li><i class="fas fa-user"></i> <span>Pengzhan Hao</span></li><li><i class="far fa-calendar-alt"></i> <span>Sep 15, 2020</span>
|
||
</li></ul></div><meta itemprop="author" content="Pengzhan Hao"/><meta itemprop="datePublished" content="2020-09-15T22:00:14-04:00">
|
||
<meta itemprop="keywords" content="visualization"><div class="js-article-content"><div class="layout--article"><!-- start custom article top snippet -->
|
||
|
||
<!-- end custom article top snippet -->
|
||
<div class="article__content" itemprop="articleBody"><p>Let’s generate a word cloud like this.
|
||
Don’t understand the language is not a big deal.
|
||
If your written language is based on latin alphabet(or other language has space between words), skip tokenization.</p>
|
||
|
||
<p><img src="/static/2020-09/2020-06-28.png" height="250" />
|
||
<!--more--></p>
|
||
|
||
<h2 id="background">Background</h2>
|
||
|
||
<p>Recently, I set up a web-based RSS client for retrieving and organizing everyday news. I used <a href="https://tt-rss.org/">TinyTinyRSS</a>, or as ttrss, a popular RSS client which friendly to docker. Thanks to developer <a href="https://ttrss.henry.wang/#about">HenryQW</a>, a well-written Nginx-based docker configuration is already available in docker hub. With more feeds were added, I found some feeds does not need to be checked everyday. Thus I was thinking to create a script to automatically list all keywords appears in a last period and generate a heat map kind figure of it.</p>
|
||
|
||
<p>Before you go further, I’ll tell you all my settings to give readers a general overview.</p>
|
||
|
||
<p>My first step is to read all text-based information from TTRSS’s PostgreSQL database. With information, I used a Chinese-NLP library, <a href="https://github.com/fxsjy/jieba">jieba</a>, to extract all keyword with their occurrences frequency. By using <a href="https://github.com/amueller/word_cloud">WordCloud</a>, a python library, word cloud figure is generated and present. More details will be discussed in later sections.</p>
|
||
|
||
<h2 id="get-rss-feeds-text">Get RSS feeds’ text</h2>
|
||
|
||
<p>My first thought is generating a keyword heat map for economy news of a last week. Since this blog post are more skewed to Chinese tokenization and draw the word cloud figure. I’ll leave my code here just in case. The SQL connector I used is <a href="https://pypi.org/project/psycopg2/">psycopg2</a>, an easy-use PostgreSQL library.</p>
|
||
|
||
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||
<span class="bp">self</span><span class="p">.</span><span class="n">dbe</span> <span class="o">=</span> <span class="n">psycopg2</span><span class="p">.</span><span class="n">connect</span><span class="p">(</span>
|
||
<span class="n">host</span><span class="o">=</span><span class="n">DB_HOST</span><span class="p">,</span> <span class="n">port</span><span class="o">=</span><span class="n">DB_PORT</span><span class="p">,</span> <span class="n">database</span><span class="o">=</span><span class="n">DB_NAME</span><span class="p">,</span> <span class="n">user</span><span class="o">=</span><span class="n">DB_USER</span><span class="p">,</span> <span class="n">password</span><span class="o">=</span><span class="n">DB_PASS</span><span class="p">)</span>
|
||
|
||
<span class="k">def</span> <span class="nf">get_1w_of_feed_byid</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="nb">id</span><span class="o">=</span><span class="mi">1</span><span class="p">)</span> <span class="o">-></span> <span class="nb">list</span><span class="p">:</span>
|
||
<span class="n">cur</span> <span class="o">=</span> <span class="bp">self</span><span class="p">.</span><span class="n">dbe</span><span class="p">.</span><span class="n">cursor</span><span class="p">()</span>
|
||
<span class="n">cur</span><span class="p">.</span><span class="n">execute</span><span class="p">(</span><span class="s">'SELECT content FROM public.ttrss_entries </span><span class="se">\
|
||
</span><span class="s"> where date_updated > now() - interval </span><span class="se">\'</span><span class="s">1 week</span><span class="se">\'</span><span class="s"> AND id in ( </span><span class="se">\
|
||
</span><span class="s"> select int_id from DB_TABLE_NAME </span><span class="se">\
|
||
</span><span class="s"> where feed_id='</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="nb">id</span><span class="p">)</span> <span class="o">+</span> <span class="s">' </span><span class="se">\
|
||
</span><span class="s"> ) </span><span class="se">\
|
||
</span><span class="s"> ORDER BY id ASC '</span>
|
||
<span class="p">)</span>
|
||
<span class="n">rows</span> <span class="o">=</span> <span class="n">cur</span><span class="p">.</span><span class="n">fetchall</span><span class="p">()</span>
|
||
<span class="k">return</span> <span class="n">rows</span>
|
||
</code></pre></div></div>
|
||
|
||
<p>Most arguments are intuitive and easy to understand. The only exception is argument of function <em>get_1w_of_feed_byid</em>. This <strong>id</strong> is the feed index of my subscriptions.</p>
|
||
|
||
<h2 id="tokenize-with-frequency">Tokenize with frequency</h2>
|
||
|
||
<p>Two popular tokenization library were used, and I chose <a href="https://github.com/fxsjy/jieba">jieba</a> after a few comparison. Before cutting the sentence, we first need to remove all punctuation marks.</p>
|
||
|
||
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="k">def</span> <span class="nf">remove_biaodian</span><span class="p">(</span><span class="n">text</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span>
|
||
<span class="n">punct</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span><span class="sa">u</span><span class="s">''':!),.:;?]}¢'"、。〉》」』】〕〗〞︰︱︳﹐､﹒
|
||
﹔﹕﹖﹗﹚﹜﹞！），．：；？｜｝︴︶︸︺︼︾﹀﹂﹄﹏､～￠
|
||
々‖•·ˇˉ―--′’”([{£¥'"‵〈《「『【〔〖（［｛￡￥〝︵︷︹︻
|
||
︽︿﹁﹃﹙﹛﹝（｛“‘-—_…'''</span><span class="p">)</span>
|
||
<span class="n">ret</span> <span class="o">=</span> <span class="s">""</span>
|
||
<span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">text</span><span class="p">:</span>
|
||
<span class="k">if</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">punct</span><span class="p">:</span>
|
||
<span class="n">ret</span> <span class="o">+=</span> <span class="s">''</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">ret</span> <span class="o">+=</span> <span class="n">x</span>
|
||
<span class="k">return</span> <span class="n">ret</span>
|
||
</code></pre></div></div>
|
||
|
||
<p>After we have an all characters string, we can call jieba. By using the function <em>jieba.posseg.cut</em> with or without paddle, we can have a word list and their “part of speech”. As you can see in the following code, I also did two more works.</p>
|
||
|
||
<p>First, in the if statement, I only kept all nouns with some categories. Category abbreviation such as “nr” and “ns” represent different “part of speech”, I attached with categories I used in the following table. For more details you can find in this <a href="https://github.com/fxsjy/jieba">link</a>.</p>
|
||
|
||
<p>The second work is only keeping words with length longer than 2 characters. In Chinese, there’s no space between words such as Latin writing systems. Since then, some single-character-words such as conjunction words are easy to be misrecognized as specialty-noun. And this misrecognition will cause more single-character being regarded as specialty-noun. I am not able to improve NLP method, so I used a easy way to fix this by removing any words less than 2 characters.</p>
|
||
|
||
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">import</span> <span class="nn">jieba.posseg</span> <span class="k">as</span> <span class="n">pseg</span>
|
||
|
||
<span class="k">def</span> <span class="nf">get_noun_jieba</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">content</span><span class="p">:</span> <span class="nb">str</span><span class="p">)</span> <span class="o">-></span> <span class="nb">list</span><span class="p">:</span>
|
||
<span class="n">content</span> <span class="o">=</span> <span class="n">remove_biaodian</span><span class="p">(</span><span class="n">content</span><span class="p">)</span>
|
||
<span class="n">words</span> <span class="o">=</span> <span class="n">pseg</span><span class="p">.</span><span class="n">cut</span><span class="p">(</span><span class="n">content</span><span class="p">)</span> <span class="c1"># Invoking jieba.posseg.cut function
|
||
</span>
|
||
<span class="n">ret</span> <span class="o">=</span> <span class="p">[]</span>
|
||
<span class="k">for</span> <span class="n">word</span><span class="p">,</span> <span class="n">flag</span> <span class="ow">in</span> <span class="n">words</span><span class="p">:</span>
|
||
<span class="c1"># print(word, flag)
|
||
</span> <span class="k">if</span> <span class="n">flag</span> <span class="ow">in</span> <span class="p">[</span><span class="s">'nr'</span><span class="p">,</span> <span class="s">'ns'</span><span class="p">,</span> <span class="s">'nt'</span><span class="p">,</span> <span class="s">'nw'</span><span class="p">,</span> <span class="s">'nz'</span><span class="p">,</span> <span class="s">'PER'</span><span class="p">,</span> <span class="s">'ORG'</span><span class="p">,</span> <span class="s">'x'</span><span class="p">]:</span> <span class="c1"># LOC
|
||
</span> <span class="n">ret</span><span class="p">.</span><span class="n">append</span><span class="p">(</span><span class="n">word</span><span class="p">)</span>
|
||
<span class="k">return</span> <span class="p">[</span><span class="n">remove_biaodian</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">ret</span> <span class="k">if</span> <span class="n">i</span><span class="p">.</span><span class="n">strip</span><span class="p">()</span> <span class="o">!=</span> <span class="s">""</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">remove_biaodian</span><span class="p">(</span><span class="n">i</span><span class="p">.</span><span class="n">strip</span><span class="p">()))</span> <span class="o">>=</span> <span class="mi">2</span><span class="p">]</span>
|
||
</code></pre></div></div>
|
||
|
||
<ul>
|
||
<li>Word category names and abbreviations</li>
|
||
</ul>
|
||
|
||
<table>
|
||
<thead>
|
||
<tr>
|
||
<th>Abbreviation</th>
|
||
<th>Category name/ Part of speech</th>
|
||
</tr>
|
||
</thead>
|
||
<tbody>
|
||
<tr>
|
||
<td>nr</td>
|
||
<td>People name noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>ns</td>
|
||
<td>Location name noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>nt</td>
|
||
<td>Organization name noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>nw</td>
|
||
<td>Arts work noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>nz</td>
|
||
<td>Other noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>PER</td>
|
||
<td>People name noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>ORG</td>
|
||
<td>Location name noun</td>
|
||
</tr>
|
||
<tr>
|
||
<td>x</td>
|
||
<td>Non-morpheme word</td>
|
||
</tr>
|
||
</tbody>
|
||
</table>
|
||
|
||
<p>With all words extracted, we can easily calculate their frequencies. After this, we can using the following line of code to print a sorted result to verify correctness.</p>
|
||
|
||
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="n">noun</span> <span class="o">=</span> <span class="n">seg</span><span class="p">.</span><span class="n">get_noun_jieba</span><span class="p">(</span><span class="n">test_content</span><span class="p">)</span>
|
||
<span class="c1"># ... Calculate frequency of above word list ...
|
||
</span><span class="k">print</span><span class="p">(</span><span class="nb">sorted</span><span class="p">(</span><span class="n">a_dict</span><span class="p">.</span><span class="n">items</span><span class="p">(),</span> <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="n">x</span><span class="p">[</span><span class="mi">1</span><span class="p">]))</span>
|
||
</code></pre></div></div>
|
||
|
||
<h2 id="draw-word-cloud">Draw word cloud</h2>
|
||
|
||
<p>With a keyword and frequency dictionary(data structure), we can just call built-in functions from wordcloud library to generate the figure.</p>
|
||
|
||
<p>First we need to initialize an instance of wordcloud class. As you can see in my code, I set it with 6 parameters. Width and Height of the canvas, maximum amount of words used to generate the figure, the font of words, background color and margin between any two words.</p>
|
||
|
||
<p>After having the instance, we call function <em>generate_from_frequencies</em> and pass keyword dictionary to it. The return value of this function is an bitmap image, which we can use <a href="https://matplotlib.org/">matplotlib</a> to plot it to your screen.</p>
|
||
|
||
<p>I tested my plot on ubuntu-subsystem on Windows 10, unfortunately matplotlib under subsystem depends on x11 window manager and its not default available on windows. We need to install an x11 manager to support. <a href="https://sourceforge.net/projects/xming/">Xming</a> is the one I used.</p>
|
||
|
||
<div class="language-python highlighter-rouge"><div class="highlight"><pre class="highlight"><code><span class="kn">from</span> <span class="nn">wordcloud</span> <span class="kn">import</span> <span class="n">WordCloud</span>
|
||
<span class="kn">import</span> <span class="nn">matplotlib.pyplot</span> <span class="k">as</span> <span class="n">plt</span>
|
||
|
||
<span class="n">font_path</span> <span class="o">=</span> <span class="s">"./font/haipai.ttf"</span>
|
||
<span class="n">output_path</span> <span class="o">=</span> <span class="s">"./font/out.png"</span>
|
||
|
||
|
||
<span class="k">def</span> <span class="nf">show_figure_with_frequency</span><span class="p">(</span><span class="n">keywords</span><span class="p">:</span> <span class="nb">dict</span><span class="p">):</span>
|
||
<span class="n">wc</span> <span class="o">=</span> <span class="n">WordCloud</span><span class="p">(</span><span class="n">width</span><span class="o">=</span><span class="mi">828</span><span class="p">,</span> <span class="n">height</span><span class="o">=</span><span class="mi">1792</span><span class="p">,</span> <span class="n">max_words</span><span class="o">=</span><span class="mi">200</span><span class="p">,</span> <span class="n">font_path</span><span class="o">=</span><span class="n">font_path</span><span class="p">,</span>
|
||
<span class="n">background_color</span><span class="o">=</span><span class="s">"white"</span><span class="p">,</span> <span class="n">margin</span><span class="o">=</span><span class="mi">1</span><span class="p">).</span><span class="n">generate_from_frequencies</span><span class="p">(</span><span class="n">keywords</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="p">.</span><span class="n">imshow</span><span class="p">(</span><span class="n">wc</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="p">.</span><span class="n">axis</span><span class="p">(</span><span class="s">'off'</span><span class="p">)</span>
|
||
<span class="n">plt</span><span class="p">.</span><span class="n">show</span><span class="p">()</span>
|
||
</code></pre></div></div>
|
||
|
||
<p>If everything work fine, a word cloud figure will show up in a new window. My version looks like this.</p>
|
||
|
||
<p><img src="/static/2020-09/2020-06-28.png" height="150" /></p>
|
||
|
||
<p>This generated word cloud figure reflects the most popular economy news’ keyword in the week started 06-28-2020. Two largest words in the figure are “新冠” and “新冠病毒”, both means “Covid-19” (This figure was in the week of the second covid spur in Beijing, China). The size of the image fits my phone screen and I can use an app to automatic sync it to my phone’s wallpaper. However, in this image, too many location nouns are presented. This will be something I can make progress on in the future.</p>
|
||
|
||
</div><section class="article__sharing d-print-none"></section><div class="d-print-none"><footer class="article__footer"><meta itemprop="dateModified" content="2020-09-15T22:00:14-04:00"><!-- start custom article footer snippet -->
|
||
|
||
<!-- end custom article footer snippet -->
|
||
<div class="article__subscribe"><div class="subscribe"><i class="fas fa-rss"></i> <a type="application/rss+xml" href="/feed.xml">Subscribe</a></div>
|
||
</div><div class="article__license"></div></footer>
|
||
<div class="article__section-navigator clearfix"><div class="previous"><span>PREVIOUS</span><a href="/posts/intro-xv6">Xv6 introduction</a></div><div class="next"><span>NEXT</span><a href="/posts/eddl-how-do-we-train-on-limited-edge-devices">EDDL: How do we train neural networks on limited edge devices - PART 1</a></div></div></div>
|
||
|
||
</div>
|
||
|
||
<script>(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
$(function() {
|
||
var $this ,$scroll;
|
||
var $articleContent = $('.js-article-content');
|
||
var hasSidebar = $('.js-page-root').hasClass('layout--page--sidebar');
|
||
var scroll = hasSidebar ? '.js-page-main' : 'html, body';
|
||
$scroll = $(scroll);
|
||
|
||
$articleContent.find('.highlight').each(function() {
|
||
$this = $(this);
|
||
$this.attr('data-lang', $this.find('code').attr('data-lang'));
|
||
});
|
||
$articleContent.find('h1[id], h2[id], h3[id], h4[id], h5[id], h6[id]').each(function() {
|
||
$this = $(this);
|
||
$this.append($('<a class="anchor d-print-none" aria-hidden="true"></a>').html('<i class="fas fa-anchor"></i>'));
|
||
});
|
||
$articleContent.on('click', '.anchor', function() {
|
||
$scroll.scrollToAnchor('#' + $(this).parent().attr('id'), 400);
|
||
});
|
||
});
|
||
});
|
||
})();
|
||
</script>
|
||
</div><section class="page__comments d-print-none"><div id="disqus_thread"></div>
|
||
<script>
|
||
/**
|
||
* RECOMMENDED CONFIGURATION VARIABLES: EDIT AND UNCOMMENT THE SECTION BELOW TO INSERT DYNAMIC VALUES FROM YOUR PLATFORM OR CMS.
|
||
* LEARN WHY DEFINING THESE VARIABLES IS IMPORTANT: https://disqus.com/admin/universalcode/#configuration-variables*/
|
||
var disqus_config = function () {
|
||
this.page.url = 'https://codersherlock.github.com//posts/generate-word-cloud-with-chinese-fenci';
|
||
this.page.identifier = '/posts/generate-word-cloud-with-chinese-fenci';
|
||
};
|
||
(function() { // DON'T EDIT BELOW THIS LINE
|
||
var d = document, s = d.createElement('script');
|
||
s.src = 'https://codersherlockblog.disqus.com/embed.js';
|
||
s.setAttribute('data-timestamp', +new Date());
|
||
(d.head || d.body).appendChild(s);
|
||
})();
|
||
</script>
|
||
<noscript>Please enable JavaScript to view the <a href="https://disqus.com/?ref_noscript">comments powered by Disqus.</a></noscript></section></article><!-- start custom main bottom snippet -->
|
||
|
||
<!-- end custom main bottom snippet -->
|
||
</div>
|
||
</div></div></div><div class="page__footer d-print-none">
|
||
<footer class="footer py-4 js-page-footer">
|
||
<div class="main"><div itemscope itemtype="http://schema.org/Person">
|
||
<meta itemprop="name" content="Pengzhan Hao"><meta itemprop="url" content="/"><div class="footer__author-links"><div class="author-links">
|
||
<ul class="menu menu--nowrap menu--inline"><li title="Send me an Email.">
|
||
<a class="button button--circle mail-button" itemprop="email" href="mailto:haopengzhan@gmail.com" target="_blank">
|
||
<i class="fas fa-envelope"></i>
|
||
</a><li title="Follow me on Linkedin.">
|
||
<a class="button button--circle linkedin-button" itemprop="sameAs" href="https://www.linkedin.com/in/pengzhanhao" target="_blank">
|
||
<div class="icon"><svg fill="#000000" width="24px" height="24px" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg">
|
||
<path d="M260.096 155.648c0 27.307008-9.899008 50.516992-29.696 69.632-19.796992 19.115008-45.396992 28.672-76.8 28.672-30.036992 0-54.612992-9.556992-73.728-28.672-19.115008-19.115008-28.672-42.324992-28.672-69.632 0-28.672 9.556992-52.224 28.672-70.656 19.115008-18.432 44.372992-27.648 75.776-27.648 31.403008 0 56.32 9.216 74.752 27.648 18.432 18.432 28.331008 41.984 29.696 70.656 0 0 0 0 0 0m-202.752 808.96c0 0 0-632.832 0-632.832 0 0 196.608 0 196.608 0 0 0 0 632.832 0 632.832 0 0-196.608 0-196.608 0 0 0 0 0 0 0m313.344-430.08c0-58.708992-1.364992-126.292992-4.096-202.752 0 0 169.984 0 169.984 0 0 0 10.24 88.064 10.24 88.064 0 0 4.096 0 4.096 0 40.96-68.267008 105.812992-102.4 194.56-102.4 68.267008 0 123.220992 22.868992 164.864 68.608 41.643008 45.739008 62.464 113.664 62.464 203.776 0 0 0 374.784 0 374.784 0 0-196.608 0-196.608 0 0 0 0-350.208 0-350.208 0-91.476992-33.451008-137.216-100.352-137.216-47.787008 0-81.236992 24.576-100.352 73.728-4.096 8.192-6.144 24.576-6.144 49.152 0 0 0 364.544 0 364.544 0 0-198.656 0-198.656 0 0 0 0-430.08 0-430.08 0 0 0 0 0 0" />
|
||
</svg>
|
||
</div>
|
||
</a>
|
||
</li><li title="Follow me on Github.">
|
||
<a class="button button--circle github-button" itemprop="sameAs" href="https://github.com/codersherlock" target="_blank">
|
||
<div class="icon"><svg fill="#000000" width="24px" height="24px" viewBox="0 0 1024 1024" version="1.1" xmlns="http://www.w3.org/2000/svg">
|
||
<path class="svgpath" data-index="path_0" fill="#272636" d="M0 525.2c0 223.6 143.3 413.7 343 483.5 26.9 6.8 22.8-12.4 22.8-25.4l0-88.7c-155.3 18.2-161.5-84.6-172-101.7-21.1-36-70.8-45.2-56-62.3 35.4-18.2 71.4 4.6 113.1 66.3 30.2 44.7 89.1 37.2 119 29.7 6.5-26.9 20.5-50.9 39.7-69.6C248.8 728.2 181.7 630 181.7 513.2c0-56.6 18.7-108.7 55.3-150.7-23.3-69.3 2.2-128.5 5.6-137.3 66.5-6 135.5 47.6 140.9 51.8 37.8-10.2 80.9-15.6 129.1-15.6 48.5 0 91.8 5.6 129.8 15.9 12.9-9.8 77-55.8 138.8-50.2 3.3 8.8 28.2 66.7 6.3 135 37.1 42.1 56 94.6 56 151.4 0 117-67.5 215.3-228.8 243.7 26.9 26.6 43.6 63.4 43.6 104.2l0 128.8c0.9 10.3 0 20.5 17.2 20.5C878.1 942.4 1024 750.9 1024 525.3c0-282.9-229.3-512-512-512C229.1 13.2 0 242.3 0 525.2L0 525.2z" />
|
||
</svg>
|
||
</div>
|
||
</a>
|
||
</li></ul>
|
||
</div>
|
||
</div>
|
||
</div><div class="site-info mt-2">
|
||
<div>© Stop Talking, Start Doing 2021,
|
||
Powered by <a title="Jekyll is a simple, blog-aware, static site generator." href="http://jekyllrb.com/">Jekyll</a> & <a
|
||
title="TeXt is a super customizable Jekyll theme." href="https://github.com/kitian616/jekyll-TeXt-theme">TeXt Theme</a>.
|
||
</div>
|
||
</div>
|
||
</div>
|
||
</footer>
|
||
</div></div>
|
||
</div><script>(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
var $body = $('body'), $window = $(window);
|
||
var $pageRoot = $('.js-page-root'), $pageMain = $('.js-page-main');
|
||
var activeCount = 0;
|
||
function modal(options) {
|
||
var $root = this, visible, onChange, hideWhenWindowScroll = false;
|
||
var scrollTop;
|
||
function setOptions(options) {
|
||
var _options = options || {};
|
||
visible = _options.initialVisible === undefined ? false : show;
|
||
onChange = _options.onChange;
|
||
hideWhenWindowScroll = _options.hideWhenWindowScroll;
|
||
}
|
||
function init() {
|
||
setState(visible);
|
||
}
|
||
function setState(isShow) {
|
||
if (isShow === visible) {
|
||
return;
|
||
}
|
||
visible = isShow;
|
||
if (visible) {
|
||
activeCount++;
|
||
scrollTop = $(window).scrollTop() || $pageMain.scrollTop();
|
||
$root.addClass('modal--show');
|
||
$pageMain.scrollTop(scrollTop);
|
||
activeCount === 1 && ($pageRoot.addClass('show-modal'), $body.addClass('of-hidden'));
|
||
hideWhenWindowScroll && window.hasEvent('touchstart') && $window.on('scroll', hide);
|
||
$window.on('keyup', handleKeyup);
|
||
} else {
|
||
activeCount > 0 && activeCount--;
|
||
$root.removeClass('modal--show');
|
||
$window.scrollTop(scrollTop);
|
||
activeCount === 0 && ($pageRoot.removeClass('show-modal'), $body.removeClass('of-hidden'));
|
||
hideWhenWindowScroll && window.hasEvent('touchstart') && $window.off('scroll', hide);
|
||
$window.off('keyup', handleKeyup);
|
||
}
|
||
onChange && onChange(visible);
|
||
}
|
||
function show() {
|
||
setState(true);
|
||
}
|
||
function hide() {
|
||
setState(false);
|
||
}
|
||
function handleKeyup(e) {
|
||
// Char Code: 27 ESC
|
||
if (e.which === 27) {
|
||
hide();
|
||
}
|
||
}
|
||
setOptions(options);
|
||
init();
|
||
return {
|
||
show: show,
|
||
hide: hide,
|
||
$el: $root
|
||
};
|
||
}
|
||
$.fn.modal = modal;
|
||
});
|
||
})();
|
||
</script><div class="modal modal--overflow page__search-modal d-print-none js-page-search-modal"><script>
|
||
(function () {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
// search panel
|
||
var search = (window.search || (window.search = {}));
|
||
var useDefaultSearchBox = window.useDefaultSearchBox === undefined ?
|
||
true : window.useDefaultSearchBox ;
|
||
|
||
var $searchModal = $('.js-page-search-modal');
|
||
var $searchToggle = $('.js-search-toggle');
|
||
var searchModal = $searchModal.modal({ onChange: handleModalChange, hideWhenWindowScroll: true });
|
||
var modalVisible = false;
|
||
search.searchModal = searchModal;
|
||
|
||
var $searchBox = null;
|
||
var $searchInput = null;
|
||
var $searchClear = null;
|
||
|
||
function getModalVisible() {
|
||
return modalVisible;
|
||
}
|
||
search.getModalVisible = getModalVisible;
|
||
|
||
function handleModalChange(visible) {
|
||
modalVisible = visible;
|
||
if (visible) {
|
||
search.onShow && search.onShow();
|
||
useDefaultSearchBox && $searchInput[0] && $searchInput[0].focus();
|
||
} else {
|
||
search.onShow && search.onHide();
|
||
useDefaultSearchBox && $searchInput[0] && $searchInput[0].blur();
|
||
setTimeout(function() {
|
||
useDefaultSearchBox && ($searchInput.val(''), $searchBox.removeClass('not-empty'));
|
||
search.clear && search.clear();
|
||
window.pageAsideAffix && window.pageAsideAffix.refresh();
|
||
}, 400);
|
||
}
|
||
}
|
||
|
||
$searchToggle.on('click', function() {
|
||
modalVisible ? searchModal.hide() : searchModal.show();
|
||
});
|
||
// Char Code: 83 S, 191 /
|
||
$(window).on('keyup', function(e) {
|
||
if (!modalVisible && !window.isFormElement(e.target || e.srcElement) && (e.which === 83 || e.which === 191)) {
|
||
modalVisible || searchModal.show();
|
||
}
|
||
});
|
||
|
||
if (useDefaultSearchBox) {
|
||
$searchBox = $('.js-search-box');
|
||
$searchInput = $searchBox.children('input');
|
||
$searchClear = $searchBox.children('.js-icon-clear');
|
||
search.getSearchInput = function() {
|
||
return $searchInput.get(0);
|
||
};
|
||
search.getVal = function() {
|
||
return $searchInput.val();
|
||
};
|
||
search.setVal = function(val) {
|
||
$searchInput.val(val);
|
||
};
|
||
|
||
$searchInput.on('focus', function() {
|
||
$(this).addClass('focus');
|
||
});
|
||
$searchInput.on('blur', function() {
|
||
$(this).removeClass('focus');
|
||
});
|
||
$searchInput.on('input', window.throttle(function() {
|
||
var val = $(this).val();
|
||
if (val === '' || typeof val !== 'string') {
|
||
search.clear && search.clear();
|
||
} else {
|
||
$searchBox.addClass('not-empty');
|
||
search.onInputNotEmpty && search.onInputNotEmpty(val);
|
||
}
|
||
}, 400));
|
||
$searchClear.on('click', function() {
|
||
$searchInput.val(''); $searchBox.removeClass('not-empty');
|
||
search.clear && search.clear();
|
||
});
|
||
}
|
||
});
|
||
})();
|
||
</script><div class="search search--dark">
|
||
<div class="main">
|
||
<div class="search__header">Search</div>
|
||
<div class="search-bar">
|
||
<div class="search-box js-search-box">
|
||
<div class="search-box__icon-search"><i class="fas fa-search"></i></div>
|
||
<input type="text" />
|
||
<div class="search-box__icon-clear js-icon-clear">
|
||
<a><i class="fas fa-times"></i></a>
|
||
</div>
|
||
</div>
|
||
<button class="button button--theme-dark button--pill search__cancel js-search-toggle">
|
||
Cancel</button>
|
||
</div>
|
||
<div class="search-result js-search-result"></div>
|
||
</div>
|
||
</div>
|
||
<script>var SOURCES = window.TEXT_VARIABLES.sources;
|
||
var PAHTS = window.TEXT_VARIABLES.paths;
|
||
window.Lazyload.js([SOURCES.jquery, PAHTS.search_js], function() {
|
||
var search = (window.search || (window.search = {}));
|
||
var searchData = window.TEXT_SEARCH_DATA || {};
|
||
|
||
function memorize(f) {
|
||
var cache = {};
|
||
return function () {
|
||
var key = Array.prototype.join.call(arguments, ',');
|
||
if (key in cache) return cache[key];
|
||
else return cache[key] = f.apply(this, arguments);
|
||
};
|
||
}
|
||
|
||
/// search
|
||
function searchByQuery(query) {
|
||
var i, j, key, keys, cur, _title, result = {};
|
||
keys = Object.keys(searchData);
|
||
for (i = 0; i < keys.length; i++) {
|
||
key = keys[i];
|
||
for (j = 0; j < searchData[key].length; j++) {
|
||
cur = searchData[key][j], _title = cur.title;
|
||
if ((result[key] === undefined || result[key] && result[key].length < 4 )
|
||
&& _title.toLowerCase().indexOf(query.toLowerCase()) >= 0) {
|
||
if (result[key] === undefined) {
|
||
result[key] = [];
|
||
}
|
||
result[key].push(cur);
|
||
}
|
||
}
|
||
}
|
||
return result;
|
||
}
|
||
|
||
var renderHeader = memorize(function(header) {
|
||
return $('<p class="search-result__header">' + header + '</p>');
|
||
});
|
||
|
||
var renderItem = function(index, title, url) {
|
||
return $('<li class="search-result__item" data-index="' + index + '"><a class="button" href="' + url + '">' + title + '</a></li>');
|
||
};
|
||
|
||
function render(data) {
|
||
if (!data) { return null; }
|
||
var $root = $('<ul></ul>'), i, j, key, keys, cur, itemIndex = 0;
|
||
keys = Object.keys(data);
|
||
for (i = 0; i < keys.length; i++) {
|
||
key = keys[i];
|
||
$root.append(renderHeader(key));
|
||
for (j = 0; j < data[key].length; j++) {
|
||
cur = data[key][j];
|
||
$root.append(renderItem(itemIndex++, cur.title, cur.url));
|
||
}
|
||
}
|
||
return $root;
|
||
}
|
||
|
||
// search box
|
||
var $result = $('.js-search-result'), $resultItems;
|
||
var lastActiveIndex, activeIndex;
|
||
|
||
function clear() {
|
||
$result.html(null);
|
||
$resultItems = $('.search-result__item'); activeIndex = 0;
|
||
}
|
||
function onInputNotEmpty(val) {
|
||
$result.html(render(searchByQuery(val)));
|
||
$resultItems = $('.search-result__item'); activeIndex = 0;
|
||
$resultItems.eq(0).addClass('active');
|
||
}
|
||
|
||
search.clear = clear;
|
||
search.onInputNotEmpty = onInputNotEmpty;
|
||
|
||
function updateResultItems() {
|
||
lastActiveIndex >= 0 && $resultItems.eq(lastActiveIndex).removeClass('active');
|
||
activeIndex >= 0 && $resultItems.eq(activeIndex).addClass('active');
|
||
}
|
||
|
||
function moveActiveIndex(direction) {
|
||
var itemsCount = $resultItems ? $resultItems.length : 0;
|
||
if (itemsCount > 1) {
|
||
lastActiveIndex = activeIndex;
|
||
if (direction === 'up') {
|
||
activeIndex = (activeIndex - 1 + itemsCount) % itemsCount;
|
||
} else if (direction === 'down') {
|
||
activeIndex = (activeIndex + 1 + itemsCount) % itemsCount;
|
||
}
|
||
updateResultItems();
|
||
}
|
||
}
|
||
|
||
// Char Code: 13 Enter, 37 ⬅, 38 ⬆, 39 ➡, 40 ⬇
|
||
$(window).on('keyup', function(e) {
|
||
var modalVisible = search.getModalVisible && search.getModalVisible();
|
||
if (modalVisible) {
|
||
if (e.which === 38) {
|
||
modalVisible && moveActiveIndex('up');
|
||
} else if (e.which === 40) {
|
||
modalVisible && moveActiveIndex('down');
|
||
} else if (e.which === 13) {
|
||
modalVisible && $resultItems && activeIndex >= 0 && $resultItems.eq(activeIndex).children('a')[0].click();
|
||
}
|
||
}
|
||
});
|
||
|
||
$result.on('mouseover', '.search-result__item > a', function() {
|
||
var itemIndex = $(this).parent().data('index');
|
||
itemIndex >= 0 && (lastActiveIndex = activeIndex, activeIndex = itemIndex, updateResultItems());
|
||
});
|
||
});
|
||
</script>
|
||
</div></div>
|
||
|
||
|
||
<script>(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
function scrollToAnchor(anchor, duration, callback) {
|
||
var $root = this;
|
||
$root.animate({ scrollTop: $(anchor).position().top }, duration, function() {
|
||
window.history.replaceState(null, '', window.location.href.split('#')[0] + anchor);
|
||
callback && callback();
|
||
});
|
||
}
|
||
$.fn.scrollToAnchor = scrollToAnchor;
|
||
});
|
||
})();
|
||
(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
function affix(options) {
|
||
var $root = this, $window = $(window), $scrollTarget, $scroll,
|
||
offsetBottom = 0, scrollTarget = window, scroll = window.document, disabled = false, isOverallScroller = true,
|
||
rootTop, rootLeft, rootHeight, scrollBottom, rootBottomTop,
|
||
hasInit = false, curState;
|
||
|
||
function setOptions(options) {
|
||
var _options = options || {};
|
||
_options.offsetBottom && (offsetBottom = _options.offsetBottom);
|
||
_options.scrollTarget && (scrollTarget = _options.scrollTarget);
|
||
_options.scroll && (scroll = _options.scroll);
|
||
_options.disabled !== undefined && (disabled = _options.disabled);
|
||
$scrollTarget = $(scrollTarget);
|
||
isOverallScroller = window.isOverallScroller($scrollTarget[0]);
|
||
$scroll = $(scroll);
|
||
}
|
||
function preCalc() {
|
||
top();
|
||
rootHeight = $root.outerHeight();
|
||
rootTop = $root.offset().top + (isOverallScroller ? 0 : $scrollTarget.scrollTop());
|
||
rootLeft = $root.offset().left;
|
||
}
|
||
function calc(needPreCalc) {
|
||
needPreCalc && preCalc();
|
||
scrollBottom = $scroll.outerHeight() - offsetBottom - rootHeight;
|
||
rootBottomTop = scrollBottom - rootTop;
|
||
}
|
||
function top() {
|
||
if (curState !== 'top') {
|
||
$root.removeClass('fixed').css({
|
||
left: 0,
|
||
top: 0
|
||
});
|
||
curState = 'top';
|
||
}
|
||
}
|
||
function fixed() {
|
||
if (curState !== 'fixed') {
|
||
$root.addClass('fixed').css({
|
||
left: rootLeft + 'px',
|
||
top: 0
|
||
});
|
||
curState = 'fixed';
|
||
}
|
||
}
|
||
function bottom() {
|
||
if (curState !== 'bottom') {
|
||
$root.removeClass('fixed').css({
|
||
left: 0,
|
||
top: rootBottomTop + 'px'
|
||
});
|
||
curState = 'bottom';
|
||
}
|
||
}
|
||
function setState() {
|
||
var scrollTop = $scrollTarget.scrollTop();
|
||
if (scrollTop >= rootTop && scrollTop <= scrollBottom) {
|
||
fixed();
|
||
} else if (scrollTop < rootTop) {
|
||
top();
|
||
} else {
|
||
bottom();
|
||
}
|
||
}
|
||
function init() {
|
||
if(!hasInit) {
|
||
var interval, timeout;
|
||
calc(true); setState();
|
||
// run calc every 100 millisecond
|
||
interval = setInterval(function() {
|
||
calc();
|
||
}, 100);
|
||
timeout = setTimeout(function() {
|
||
clearInterval(interval);
|
||
}, 45000);
|
||
window.pageLoad.then(function() {
|
||
setTimeout(function() {
|
||
clearInterval(interval);
|
||
clearTimeout(timeout);
|
||
}, 3000);
|
||
});
|
||
$scrollTarget.on('scroll', function() {
|
||
disabled || setState();
|
||
});
|
||
$window.on('resize', function() {
|
||
disabled || (calc(true), setState());
|
||
});
|
||
hasInit = true;
|
||
}
|
||
}
|
||
|
||
setOptions(options);
|
||
if (!disabled) {
|
||
init();
|
||
}
|
||
$window.on('resize', window.throttle(function() {
|
||
init();
|
||
}, 200));
|
||
return {
|
||
setOptions: setOptions,
|
||
refresh: function() {
|
||
calc(true, { animation: false }); setState();
|
||
}
|
||
};
|
||
}
|
||
$.fn.affix = affix;
|
||
});
|
||
})();
|
||
(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
function toc(options) {
|
||
var $root = this, $window = $(window), $scrollTarget, $scroller, $tocUl = $('<ul class="toc toc--ellipsis"></ul>'), $tocLi, $headings, $activeLast, $activeCur,
|
||
selectors = 'h1,h2,h3', container = 'body', scrollTarget = window, scroller = 'html, body', disabled = false,
|
||
headingsPos, scrolling = false, hasRendered = false, hasInit = false;
|
||
|
||
function setOptions(options) {
|
||
var _options = options || {};
|
||
_options.selectors && (selectors = _options.selectors);
|
||
_options.container && (container = _options.container);
|
||
_options.scrollTarget && (scrollTarget = _options.scrollTarget);
|
||
_options.scroller && (scroller = _options.scroller);
|
||
_options.disabled !== undefined && (disabled = _options.disabled);
|
||
$headings = $(container).find(selectors).filter('[id]');
|
||
$scrollTarget = $(scrollTarget);
|
||
$scroller = $(scroller);
|
||
}
|
||
function calc() {
|
||
headingsPos = [];
|
||
$headings.each(function() {
|
||
headingsPos.push(Math.floor($(this).position().top));
|
||
});
|
||
}
|
||
function setState(element, disabled) {
|
||
var scrollTop = $scrollTarget.scrollTop(), i;
|
||
if (disabled || !headingsPos || headingsPos.length < 1) { return; }
|
||
if (element) {
|
||
$activeCur = element;
|
||
} else {
|
||
for (i = 0; i < headingsPos.length; i++) {
|
||
if (scrollTop >= headingsPos[i]) {
|
||
$activeCur = $tocLi.eq(i);
|
||
} else {
|
||
$activeCur || ($activeCur = $tocLi.eq(i));
|
||
break;
|
||
}
|
||
}
|
||
}
|
||
$activeLast && $activeLast.removeClass('active');
|
||
($activeLast = $activeCur).addClass('active');
|
||
}
|
||
function render() {
|
||
if(!hasRendered) {
|
||
$root.append($tocUl);
|
||
$headings.each(function() {
|
||
var $this = $(this);
|
||
$tocUl.append($('<li></li>').addClass('toc-' + $this.prop('tagName').toLowerCase())
|
||
.append($('<a></a>').text($this.text()).attr('href', '#' + $this.prop('id'))));
|
||
});
|
||
$tocLi = $tocUl.children('li');
|
||
$tocUl.on('click', 'a', function(e) {
|
||
e.preventDefault();
|
||
var $this = $(this);
|
||
scrolling = true;
|
||
setState($this.parent());
|
||
$scroller.scrollToAnchor($this.attr('href'), 400, function() {
|
||
scrolling = false;
|
||
});
|
||
});
|
||
}
|
||
hasRendered = true;
|
||
}
|
||
function init() {
|
||
var interval, timeout;
|
||
if(!hasInit) {
|
||
render(); calc(); setState(null, scrolling);
|
||
// run calc every 100 millisecond
|
||
interval = setInterval(function() {
|
||
calc();
|
||
}, 100);
|
||
timeout = setTimeout(function() {
|
||
clearInterval(interval);
|
||
}, 45000);
|
||
window.pageLoad.then(function() {
|
||
setTimeout(function() {
|
||
clearInterval(interval);
|
||
clearTimeout(timeout);
|
||
}, 3000);
|
||
});
|
||
$scrollTarget.on('scroll', function() {
|
||
disabled || setState(null, scrolling);
|
||
});
|
||
$window.on('resize', window.throttle(function() {
|
||
if (!disabled) {
|
||
render(); calc(); setState(null, scrolling);
|
||
}
|
||
}, 100));
|
||
}
|
||
hasInit = true;
|
||
}
|
||
|
||
setOptions(options);
|
||
if (!disabled) {
|
||
init();
|
||
}
|
||
$window.on('resize', window.throttle(function() {
|
||
init();
|
||
}, 200));
|
||
return {
|
||
setOptions: setOptions
|
||
};
|
||
}
|
||
$.fn.toc = toc;
|
||
});
|
||
})();
|
||
/*(function () {
|
||
|
||
})();*/
|
||
</script><script>
|
||
/* toc must before affix, since affix need to konw toc' height. */(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
var TOC_SELECTOR = window.TEXT_VARIABLES.site.toc.selectors;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
var $window = $(window);
|
||
var $articleContent = $('.js-article-content');
|
||
var $tocRoot = $('.js-toc-root'), $col2 = $('.js-col-aside');
|
||
var toc;
|
||
var tocDisabled = false;
|
||
var hasSidebar = $('.js-page-root').hasClass('layout--page--sidebar');
|
||
var hasToc = $articleContent.find(TOC_SELECTOR).length > 0;
|
||
|
||
function disabled() {
|
||
return $col2.css('display') === 'none' || !hasToc;
|
||
}
|
||
|
||
tocDisabled = disabled();
|
||
|
||
toc = $tocRoot.toc({
|
||
selectors: TOC_SELECTOR,
|
||
container: $articleContent,
|
||
scrollTarget: hasSidebar ? '.js-page-main' : null,
|
||
scroller: hasSidebar ? '.js-page-main' : null,
|
||
disabled: tocDisabled
|
||
});
|
||
|
||
$window.on('resize', window.throttle(function() {
|
||
tocDisabled = disabled();
|
||
toc && toc.setOptions({
|
||
disabled: tocDisabled
|
||
});
|
||
}, 100));
|
||
|
||
});
|
||
})();
|
||
(function() {
|
||
var SOURCES = window.TEXT_VARIABLES.sources;
|
||
window.Lazyload.js(SOURCES.jquery, function() {
|
||
var $window = $(window), $pageFooter = $('.js-page-footer');
|
||
var $pageAside = $('.js-page-aside');
|
||
var affix;
|
||
var tocDisabled = false;
|
||
var hasSidebar = $('.js-page-root').hasClass('layout--page--sidebar');
|
||
|
||
affix = $pageAside.affix({
|
||
offsetBottom: $pageFooter.outerHeight(),
|
||
scrollTarget: hasSidebar ? '.js-page-main' : null,
|
||
scroller: hasSidebar ? '.js-page-main' : null,
|
||
scroll: hasSidebar ? $('.js-page-main').children() : null,
|
||
disabled: tocDisabled
|
||
});
|
||
|
||
$window.on('resize', window.throttle(function() {
|
||
affix && affix.setOptions({
|
||
disabled: tocDisabled
|
||
});
|
||
}, 100));
|
||
|
||
window.pageAsideAffix = affix;
|
||
});
|
||
})();
|
||
</script>
|
||
</div>
|
||
<script>(function () {
|
||
var $root = document.getElementsByClassName('root')[0];
|
||
if (window.hasEvent('touchstart')) {
|
||
$root.dataset.isTouch = true;
|
||
document.addEventListener('touchstart', function(){}, false);
|
||
}
|
||
})();
|
||
</script>
|
||
</body>
|
||
</html>
|
||
|