I am making an html page which is a typer of a foreign script.
my progress: HERE
Here's the entire javascript:
function getReplacedText(latinText) {
if (!latinText) {
return "";
}
var replacedText = "";
for (var i = 0, len = latinText.length; i < len; i++) {
var curLetter = latinText[i];
var pos1Txt = latinText[i + 1];
var pos2Txt = latinText[i + 2];
if (!(curLetter == "")) {
var dualLetter = latreplaced[curLetter + pos1Txt];
if (dualLetter) {
replacedText += dualLetter;
i++;
continue;
}
}
replacedText += latreplaced[curLetter] || curLetter;
}
return replacedText;
}
var latreplaced = {
"u":"う",
"ku":"く",
"tsu":"つ",
};
function onLatinTextChange(txt) {
var replacedTextareaElem = document.getElementById("replaced_textarea");
var div = document.createElement("div");
var replacedHtmlEntities = getReplacedText(txt);
div.innerHTML = replacedHtmlEntities;
replacedTextareaElem.value = div.innerText;
}
The purpose of this project is to create a virtual phonetic keyboard to type certain forign scripts by only using Latin alphabets, without its keyboard setting installed.
Basically, if you enter an alphabet into the input <textarea>, it renders its corresponding foreign alphabet. (For instance, input 'u' > output 'う', input 'ku' > output 'く')
Here is my problem: So far I have enabled rendering an output when one or two alphabet is typed into the input box. But I cannot figure out how to enable the same by entering three alphabets. (For instance, input 'tsu' > output 'つ')
"u":"う", // <- can convert
"ku":"く", // <- can convert
"tsu":"つ", // <- cannot convert!
In the javascript code, there is a var called dualLetter, which goes by the following script:
var dualLetter = latreplaced[curLetter + pos1Txt];
How can I edit this part of code (or the entire javascript) to be able to convert 3 or more input alphabets? Do I need to make var tripleLetter, or create a whole new system? Any alternative ways would also be helpful.
[edit] a solution inspired by your code :
I changed the main function but this definitively works
live demo : https://jsfiddle.net/alias_gui3/wds426mq/12/
source code :
var dictionnary = {
"u":"う",
"ku":"く",
"tsu":"つ",
"test for spaces": "😍"
};
var maxLength = Object.keys(dictionnary)
.reduce((a, b) => a.length > b.length ? a : b) // get the longest word
.length; // and it's length
function translate (text) {
var translated = "";
var cur = 0;
while (cur < text.length) {
var testedPhoneme;
var symbol = undefined;
for (var length = maxLength; length > 0; length --) {
testedPhoneme = text.substr(cur, length);
if (dictionnary[testedPhoneme]) {
symbol = dictionnary[testedPhoneme];
break; // stop the loop
}
}
if (symbol) {
translated += symbol;
cur += testedPhoneme.length;
}
else {
translated += text[cur]
cur++;
}
}
return translated
}
function onLatinTextChange(txt) {
var replacedTextareaElem = document.getElementById("replaced_textarea");
var div = document.createElement("div");
var replacedHtmlEntities = translate(txt);
div.innerHTML = replacedHtmlEntities;
replacedTextareaElem.value = div.innerText;
}
[previous post] a simple solution :
I suggest you split your text using spaces
If i understand well, you want to type u ku tsu to get うくつ, not ukutsu, if this is right then something like that could work :
const dictionnary = {
"u": "う",
"ku": "く",
"tsu": "つ"
var phonemes = text.split(' ') // split text by spaces
var translatedArray = phonemes.map(function (phoneme) {
return dictionnary[phoneme] || phoneme
// will return the latin phoneme if it is not in the dictionnary
})
translatedString = translatedArray.join('')
I have a script (with a lot of stolen parts you may recognise) that runs through a selected group of images, copies the image and filename and applies to a template in Photoshop. Everything works just fine, except that Photoshop somehow strips umlauts from my strings, ie, Björn becomes Bjorn.
"Logging" through an alert inside of Photoshop (line #30 below) shows that it has the correct string all the way until it's applied as the textItem.contents.
Code provided below, thanks for any help!
#target photoshop
app.displayDialogs = DialogModes.NO;
var templateRef = app.activeDocument;
var templatePath = templateRef.path;
var photo = app.activeDocument.layers.getByName("Photo"); // keycard_template.psd is the active document
// Check if photo layer is SmartObject;
if (photo.kind != "LayerKind.SMARTOBJECT") {
alert("selected layer is not a smart object")
} else {
// Select Files;
if ($.os.search(/windows/i) != -1) {
var photos = File.openDialog("Select photos", "*.png;*.jpg", true)
} else {
var photos = File.openDialog("Select photos", getPhotos, true)
};
if (photos.length) replaceItems();
}
function replaceItems() {
for (var m = 0; m < photos.length; m++) {
if (photos.length > 0) {
// Extract name
var nameStr = photos[m].name;
var nameNoExt = nameStr.split(".");
var name = nameNoExt[0].replace(/\_/g, " ");
// Replace photo and text in template
photo = replacePhoto(photos[m], photo);
// alert(name);
replaceText(templateRef, 'Name', name);
templateRef.saveAs((new File(templatePath + "/keycards/" + name + ".jpg")), jpgOptions, true);
}
}
}
// OS X file picker
function getPhotos(thePhoto) {
if (thePhoto.name.match(/\.(png|jpg)$/i) != null || thePhoto.constructor.name == "Folder") {
return true
};
};
// JPG output options;
var jpgOptions = new JPEGSaveOptions();
jpgOptions.quality = 12; //enter number or create a variable to set quality
jpgOptions.embedColorProfile = true;
jpgOptions.formatOptions = FormatOptions.STANDARDBASELINE;
// Replace SmartObject Contents
function replacePhoto(newFile, theSO) {
app.activeDocument.activeLayer = theSO;
// =======================================================
var idplacedLayerReplaceContents = stringIDToTypeID("placedLayerReplaceContents");
var desc3 = new ActionDescriptor();
var idnull = charIDToTypeID("null");
desc3.putPath(idnull, new File(newFile));
var idPgNm = charIDToTypeID("PgNm");
desc3.putInteger(idPgNm, 1);
executeAction(idplacedLayerReplaceContents, desc3, DialogModes.NO);
return app.activeDocument.activeLayer
};
// Replace text strings
function replaceText(doc, layerName, newTextString) {
for (var i = 0, max = doc.layers.length; i < max; i++) {
var layerRef = doc.layers[i];
if (layerRef.typename === "ArtLayer") {
if (layerRef.name === layerName && layerRef.kind === LayerKind.TEXT) {
layerRef.textItem.contents = decodeURI(newTextString);
}
} else {
replaceText(layerRef, layerName, newTextString);
}
}
}
Had the same problem and tried everything I had in my developer toolbox... for around 3 hours ! without any success and then I found a little hack !
It seems that photoshop is uri encoding the name of the file but don't do it in a way that allow us to do a decodeURI() and get back those special characters.
For exemple instead of "%C3%A9" that should be "é" we get "e%CC%81". So what i do is a replace on the file name to the right UTF-8 code and then a decodeURI. Exemple :
var fileName = file.name
var result = fileName.replace(/e%CC%81/g, '%C3%A9') // allow é in file name
var myTextLayer.contents = decodeURI(result);
Then you can successfully get special chars and in my case accent from filename in your text layer.
You can do a replace for each characters you need for me it was :
'e%CC%81': '%C3%A9', //é
'o%CC%82': '%C3%B4', //ô
'e%CC%80': '%C3%A8', //è
'u%CC%80': '%C3%B9', //ù
'a%CC%80': '%C3%A0', //à
'e%CC%82': '%C3%AA' //ê
I took UTF-8 code from this HTML URL Encoding reference : https://www.w3schools.com/tags/ref_urlencode.asp
Hope it will help somebody one day because nothing existed online on this bug.
I have a problem with the javascript replace function and I don't succeed to resolve it.
This is my code : https://jsfiddle.net/r36k20sa/1/
var tags = ['zazie', 'johnny'];
tags.forEach(function(element) {
content = content.replace(
new RegExp("(?!<a.*?>.*?)(\\b" + element + "\\b)(?!.*?<\\/a>)", "igm"),
'$1'
);
});
In the tags array, if I reverse the array "johnny" then "zazie" all tags are well selected otherwise, some tags are missing. (The last in this example). What can be the trick?
What can be explained that ? It seems like the javascript replace function runs asynchronous?
Thanks for your help.
Are you seriously using regex to process HTML when you have a DOM parser at your fingertips?
var content = document.getElementById('content');
function findTextNodes(root,ret) {
// recursively descend into child nodes and return an array of text nodes
var children = root.childNodes, l = children.length, i;
ret = ret || [];
for( i=0; i<l; i++) {
if( children[i].nodeType == 1) { // ElementNode
// excluding A tags here, you might also want to exclude BUTTON tags
if( children[i].nodeName != "A") {
findTextNodes(children[i],ret);
}
}
if( children[i].nodeType == 3) { // TextNode
ret.push(children[i]);
}
}
return ret;
}
var textNodes = findTextNodes(content);
// now search those text node contents for matching tags.
var tags = ['zazie','johnny'], tagcount = tags.length, regexes, tag;
for( tag=0; tag<tagcount; tag++) {
regexes[tag] = new RegExp("\b"+tags[tag]+"\b","i");
}
var node, match, index, tagtext, newnode;
while(node = textNodes.shift()) {
for( tag=0; tag<tagcount; tag++) {
if( match = node.nodeValue.match(regexes[tag])) {
index = match.index;
textNodes.unshift(node.splitText(index + tags[tag].length));
tagtext = node.splitText(index);
newnode = document.createElement('a');
newnode.href = "";
newnode.className = "esk-seo-plu-link";
newnode.style.cssText = "background:red;color:white";
tagtext.parentNode.replaceChild(newnode,tagtext);
newnode.appendChild(tagtext);
}
}
}
// and done - no more action needed since it was in-place.
See it in action
Please replace . with \\.
var tags = ['zazie', 'johnny'];
tags.forEach(function(element) {
content = content.replace(
new RegExp("(?!<a.*?>\\.*?)(\\b" + element + "\\b)(?!\\.*?<\\/a>)", "igm"),
'$1'
);
});
I’m using JavaScript to pull a value out from a hidden field and display it in a textbox. The value in the hidden field is encoded.
For example,
<input id='hiddenId' type='hidden' value='chalk & cheese' />
gets pulled into
<input type='text' value='chalk & cheese' />
via some jQuery to get the value from the hidden field (it’s at this point that I lose the encoding):
$('#hiddenId').attr('value')
The problem is that when I read chalk & cheese from the hidden field, JavaScript seems to lose the encoding. I do not want the value to be chalk & cheese. I want the literal amp; to be retained.
Is there a JavaScript library or a jQuery method that will HTML-encode a string?
EDIT: This answer was posted a long ago, and the htmlDecode function introduced a XSS vulnerability. It has been modified changing the temporary element from a div to a textarea reducing the XSS chance. But nowadays, I would encourage you to use the DOMParser API as suggested in other anwswer.
I use these functions:
function htmlEncode(value){
// Create a in-memory element, set its inner text (which is automatically encoded)
// Then grab the encoded contents back out. The element never exists on the DOM.
return $('<textarea/>').text(value).html();
}
function htmlDecode(value){
return $('<textarea/>').html(value).text();
}
Basically a textarea element is created in memory, but it is never appended to the document.
On the htmlEncode function I set the innerText of the element, and retrieve the encoded innerHTML; on the htmlDecode function I set the innerHTML value of the element and the innerText is retrieved.
Check a running example here.
The jQuery trick doesn't encode quote marks and in IE it will strip your whitespace.
Based on the escape templatetag in Django, which I guess is heavily used/tested already, I made this function which does what's needed.
It's arguably simpler (and possibly faster) than any of the workarounds for the whitespace-stripping issue - and it encodes quote marks, which is essential if you're going to use the result inside an attribute value for example.
function htmlEscape(str) {
return str
.replace(/&/g, '&')
.replace(/"/g, '"')
.replace(/'/g, ''')
.replace(/</g, '<')
.replace(/>/g, '>');
}
// I needed the opposite function today, so adding here too:
function htmlUnescape(str){
return str
.replace(/"/g, '"')
.replace(/'/g, "'")
.replace(/</g, '<')
.replace(/>/g, '>')
.replace(/&/g, '&');
}
Update 2013-06-17:
In the search for the fastest escaping I have found this implementation of a replaceAll method:
http://dumpsite.com/forum/index.php?topic=4.msg29#msg29
(also referenced here: Fastest method to replace all instances of a character in a string)
Some performance results here:
http://jsperf.com/htmlencoderegex/25
It gives identical result string to the builtin replace chains above. I'd be very happy if someone could explain why it's faster!?
Update 2015-03-04:
I just noticed that AngularJS are using exactly the method above:
https://github.com/angular/angular.js/blob/v1.3.14/src/ngSanitize/sanitize.js#L435
They add a couple of refinements - they appear to be handling an obscure Unicode issue as well as converting all non-alphanumeric characters to entities. I was under the impression the latter was not necessary as long as you have an UTF8 charset specified for your document.
I will note that (4 years later) Django still does not do either of these things, so I'm not sure how important they are:
https://github.com/django/django/blob/1.8b1/django/utils/html.py#L44
Update 2016-04-06:
You may also wish to escape forward-slash /. This is not required for correct HTML encoding, however it is recommended by OWASP as an anti-XSS safety measure. (thanks to #JNF for suggesting this in comments)
.replace(/\//g, '/');
Here's a non-jQuery version that is considerably faster than both the jQuery .html() version and the .replace() version. This preserves all whitespace, but like the jQuery version, doesn't handle quotes.
function htmlEncode( html ) {
return document.createElement( 'a' ).appendChild(
document.createTextNode( html ) ).parentNode.innerHTML;
};
Speed: http://jsperf.com/htmlencoderegex/17
Demo:
Output:
Script:
function htmlEncode( html ) {
return document.createElement( 'a' ).appendChild(
document.createTextNode( html ) ).parentNode.innerHTML;
};
function htmlDecode( html ) {
var a = document.createElement( 'a' ); a.innerHTML = html;
return a.textContent;
};
document.getElementById( 'text' ).value = htmlEncode( document.getElementById( 'hidden' ).value );
//sanity check
var html = '<div> & hello</div>';
document.getElementById( 'same' ).textContent =
'html === htmlDecode( htmlEncode( html ) ): '
+ ( html === htmlDecode( htmlEncode( html ) ) );
HTML:
<input id="hidden" type="hidden" value="chalk & cheese" />
<input id="text" value="" />
<div id="same"></div>
I know this is an old one, but I wanted to post a variation of the accepted answer that will work in IE without removing lines:
function multiLineHtmlEncode(value) {
var lines = value.split(/\r\n|\r|\n/);
for (var i = 0; i < lines.length; i++) {
lines[i] = htmlEncode(lines[i]);
}
return lines.join('\r\n');
}
function htmlEncode(value) {
return $('<div/>').text(value).html();
}
Underscore provides _.escape() and _.unescape() methods that do this.
> _.unescape( "chalk & cheese" );
"chalk & cheese"
> _.escape( "chalk & cheese" );
"chalk & cheese"
Good answer. Note that if the value to encode is undefined or null with jQuery 1.4.2 you might get errors such as:
jQuery("<div/>").text(value).html is not a function
OR
Uncaught TypeError: Object has no method 'html'
The solution is to modify the function to check for an actual value:
function htmlEncode(value){
if (value) {
return jQuery('<div/>').text(value).html();
} else {
return '';
}
}
For those who prefer plain javascript, here is the method I have used successfully:
function escapeHTML (str)
{
var div = document.createElement('div');
var text = document.createTextNode(str);
div.appendChild(text);
return div.innerHTML;
}
FWIW, the encoding is not being lost. The encoding is used by the markup parser (browser) during the page load. Once the source is read and parsed and the browser has the DOM loaded into memory, the encoding has been parsed into what it represents. So by the time your JS is execute to read anything in memory, the char it gets is what the encoding represented.
I may be operating strictly on semantics here, but I wanted you to understand the purpose of encoding. The word "lost" makes it sound like something isn't working like it should.
Faster without Jquery. You can encode every character in your string:
function encode(e){return e.replace(/[^]/g,function(e){return"&#"+e.charCodeAt(0)+";"})}
Or just target the main characters to worry about (&, inebreaks, <, >, " and ') like:
function encode(r){
return r.replace(/[\x26\x0A\<>'"]/g,function(r){return"&#"+r.charCodeAt(0)+";"})
}
test.value=encode('Encode HTML entities!\n\n"Safe" escape <script id=\'\'> & useful in <pre> tags!');
testing.innerHTML=test.value;
/*************
* \x26 is &ersand (it has to be first),
* \x0A is newline,
*************/
<textarea id=test rows="9" cols="55"></textarea>
<div id="testing">www.WHAK.com</div>
Prototype has it built-in the String class. So if you are using/plan to use Prototype, it does something like:
'<div class="article">This is an article</div>'.escapeHTML();
// -> "<div class="article">This is an article</div>"
Here is a simple javascript solution. It extends String object with a method "HTMLEncode" which can be used on an object without parameter, or with a parameter.
String.prototype.HTMLEncode = function(str) {
var result = "";
var str = (arguments.length===1) ? str : this;
for(var i=0; i<str.length; i++) {
var chrcode = str.charCodeAt(i);
result+=(chrcode>128) ? "&#"+chrcode+";" : str.substr(i,1)
}
return result;
}
// TEST
console.log("stetaewteaw æø".HTMLEncode());
console.log("stetaewteaw æø".HTMLEncode("æåøåæå"))
I have made a gist "HTMLEncode method for javascript".
Based on angular's sanitize... (es6 module syntax)
// ref: https://github.com/angular/angular.js/blob/v1.3.14/src/ngSanitize/sanitize.js
const SURROGATE_PAIR_REGEXP = /[\uD800-\uDBFF][\uDC00-\uDFFF]/g;
const NON_ALPHANUMERIC_REGEXP = /([^\#-~| |!])/g;
const decodeElem = document.createElement('pre');
/**
* Decodes html encoded text, so that the actual string may
* be used.
* #param value
* #returns {string} decoded text
*/
export function decode(value) {
if (!value) return '';
decodeElem.innerHTML = value.replace(/</g, '<');
return decodeElem.textContent;
}
/**
* Encodes all potentially dangerous characters, so that the
* resulting string can be safely inserted into attribute or
* element text.
* #param value
* #returns {string} encoded text
*/
export function encode(value) {
if (value === null || value === undefined) return '';
return String(value).
replace(/&/g, '&').
replace(SURROGATE_PAIR_REGEXP, value => {
var hi = value.charCodeAt(0);
var low = value.charCodeAt(1);
return '&#' + (((hi - 0xD800) * 0x400) + (low - 0xDC00) + 0x10000) + ';';
}).
replace(NON_ALPHANUMERIC_REGEXP, value => {
return '&#' + value.charCodeAt(0) + ';';
}).
replace(/</g, '<').
replace(/>/g, '>');
}
export default {encode,decode};
My pure-JS function:
/**
* HTML entities encode
*
* #param {string} str Input text
* #return {string} Filtered text
*/
function htmlencode (str){
var div = document.createElement('div');
div.appendChild(document.createTextNode(str));
return div.innerHTML;
}
JavaScript HTML Entities Encode & Decode
As far as I know there isn't any straight forward HTML Encode/Decode method in javascript.
However, what you can do, is to use JS to create an arbitrary element, set its inner text, then read it using innerHTML.
Let's say, with jQuery, this should work:
var helper = $('chalk & cheese').hide().appendTo('body');
var htmled = helper.html();
helper.remove();
Or something along these lines.
You shouldn't have to escape/encode values in order to shuttle them from one input field to another.
<form>
<input id="button" type="button" value="Click me">
<input type="hidden" id="hiddenId" name="hiddenId" value="I like cheese">
<input type="text" id="output" name="output">
</form>
<script>
$(document).ready(function(e) {
$('#button').click(function(e) {
$('#output').val($('#hiddenId').val());
});
});
</script>
JS doesn't go inserting raw HTML or anything; it just tells the DOM to set the value property (or attribute; not sure). Either way, the DOM handles any encoding issues for you. Unless you're doing something odd like using document.write or eval, HTML-encoding will be effectively transparent.
If you're talking about generating a new textbox to hold the result...it's still as easy. Just pass the static part of the HTML to jQuery, and then set the rest of the properties/attributes on the object it returns to you.
$box = $('<input type="text" name="whatever">').val($('#hiddenId').val());
I had a similar problem and solve it using the function encodeURIComponent from JavaScript (documentation)
For example, in your case if you use:
<input id='hiddenId' type='hidden' value='chalk & cheese' />
and
encodeURIComponent($('#hiddenId').attr('value'))
you will get chalk%20%26%20cheese. Even spaces are kept.
In my case, I had to encode one backslash and this code works perfectly
encodeURIComponent('name/surname')
and I got name%2Fsurname
Here's a little bit that emulates the Server.HTMLEncode function from Microsoft's ASP, written in pure JavaScript:
function htmlEncode(s) {
var ntable = {
"&": "amp",
"<": "lt",
">": "gt",
"\"": "quot"
};
s = s.replace(/[&<>"]/g, function(ch) {
return "&" + ntable[ch] + ";";
})
s = s.replace(/[^ -\x7e]/g, function(ch) {
return "&#" + ch.charCodeAt(0).toString() + ";";
});
return s;
}
The result does not encode apostrophes, but encodes the other HTML specials and any character outside the 0x20-0x7e range.
If you want to use jQuery. I found this:
http://www.jquerysdk.com/api/jQuery.htmlspecialchars
(part of jquery.string plugin offered by jQuery SDK)
The problem with Prototype I believe is that it extends base objects in JavaScript and will be incompatible with any jQuery you may have used. Of course, if you are already using Prototype and not jQuery, it won't be a problem.
EDIT: Also there is this, which is a port of Prototype's string utilities for jQuery:
http://stilldesigning.com/dotstring/
var htmlEnDeCode = (function() {
var charToEntityRegex,
entityToCharRegex,
charToEntity,
entityToChar;
function resetCharacterEntities() {
charToEntity = {};
entityToChar = {};
// add the default set
addCharacterEntities({
'&' : '&',
'>' : '>',
'<' : '<',
'"' : '"',
''' : "'"
});
}
function addCharacterEntities(newEntities) {
var charKeys = [],
entityKeys = [],
key, echar;
for (key in newEntities) {
echar = newEntities[key];
entityToChar[key] = echar;
charToEntity[echar] = key;
charKeys.push(echar);
entityKeys.push(key);
}
charToEntityRegex = new RegExp('(' + charKeys.join('|') + ')', 'g');
entityToCharRegex = new RegExp('(' + entityKeys.join('|') + '|&#[0-9]{1,5};' + ')', 'g');
}
function htmlEncode(value){
var htmlEncodeReplaceFn = function(match, capture) {
return charToEntity[capture];
};
return (!value) ? value : String(value).replace(charToEntityRegex, htmlEncodeReplaceFn);
}
function htmlDecode(value) {
var htmlDecodeReplaceFn = function(match, capture) {
return (capture in entityToChar) ? entityToChar[capture] : String.fromCharCode(parseInt(capture.substr(2), 10));
};
return (!value) ? value : String(value).replace(entityToCharRegex, htmlDecodeReplaceFn);
}
resetCharacterEntities();
return {
htmlEncode: htmlEncode,
htmlDecode: htmlDecode
};
})();
This is from ExtJS source code.
<script>
String.prototype.htmlEncode = function () {
return String(this)
.replace(/&/g, '&')
.replace(/"/g, '"')
.replace(/'/g, ''')
.replace(/</g, '<')
.replace(/>/g, '>');
}
var aString = '<script>alert("I hack your site")</script>';
console.log(aString.htmlEncode());
</script>
Will output: <script>alert("I hack your site")</script>
.htmlEncode() will be accessible on all strings once defined.
HtmlEncodes the given value
var htmlEncodeContainer = $('<div />');
function htmlEncode(value) {
if (value) {
return htmlEncodeContainer.text(value).html();
} else {
return '';
}
}
I ran into some issues with backslash in my Domain\User string.
I added this to the other escapes from Anentropic's answer
.replace(/\\/g, '\')
Which I found here:
How to escape backslash in JavaScript?
Picking what escapeHTML() is doing in the prototype.js
Adding this script helps you escapeHTML:
String.prototype.escapeHTML = function() {
return this.replace(/&/g,'&').replace(/</g,'<').replace(/>/g,'>')
}
now you can call escapeHTML method on strings in your script, like:
var escapedString = "<h1>this is HTML</h1>".escapeHTML();
// gives: "<h1>this is HTML</h1>"
Hope it helps anyone looking for a simple solution without having to include the entire prototype.js
Using some of the other answers here I made a version that replaces all the pertinent characters in one pass irrespective of the number of distinct encoded characters (only one call to replace()) so will be faster for larger strings.
It doesn't rely on the DOM API to exist or on other libraries.
window.encodeHTML = (function() {
function escapeRegex(s) {
return s.replace(/[-\/\\^$*+?.()|[\]{}]/g, '\\$&');
}
var encodings = {
'&' : '&',
'"' : '"',
'\'' : ''',
'<' : '<',
'>' : '>',
'\\' : '/'
};
function encode(what) { return encodings[what]; };
var specialChars = new RegExp('[' +
escapeRegex(Object.keys(encodings).join('')) +
']', 'g');
return function(text) { return text.replace(specialChars, encode); };
})();
Having ran that once, you can now call
encodeHTML('<>&"\'')
To get <>&"'
function encodeHTML(str) {
return document.createElement("a").appendChild(
document.createTextNode(str)).parentNode.innerHTML;
};
function decodeHTML(str) {
var element = document.createElement("a");
element.innerHTML = str;
return element.textContent;
};
var str = "<"
var enc = encodeHTML(str);
var dec = decodeHTML(enc);
console.log("str: " + str, "\nenc: " + enc, "\ndec: " + dec);
Necromancing.
There's certainly no jQuery required for that !
Here a JavaScript port from System.Web.HttpUtility (C# - disclaimer: not very tested):
"use strict";
function htmlDecode(s) {
if (s == null)
return null;
if (s.length == 0)
return "";
if (s.indexOf('&') == -1)
return s;
function isDigit(str) {
return /^\d+$/.test(str);
}
function isHexDigit(str) {
return /[0-9A-Fa-f]{6}/g.test(str);
}
function initEntities() {
var entities = {};
entities["nbsp"] = '\u00A0';
entities["iexcl"] = '\u00A1';
entities["cent"] = '\u00A2';
entities["pound"] = '\u00A3';
entities["curren"] = '\u00A4';
entities["yen"] = '\u00A5';
entities["brvbar"] = '\u00A6';
entities["sect"] = '\u00A7';
entities["uml"] = '\u00A8';
entities["copy"] = '\u00A9';
entities["ordf"] = '\u00AA';
entities["laquo"] = '\u00AB';
entities["not"] = '\u00AC';
entities["shy"] = '\u00AD';
entities["reg"] = '\u00AE';
entities["macr"] = '\u00AF';
entities["deg"] = '\u00B0';
entities["plusmn"] = '\u00B1';
entities["sup2"] = '\u00B2';
entities["sup3"] = '\u00B3';
entities["acute"] = '\u00B4';
entities["micro"] = '\u00B5';
entities["para"] = '\u00B6';
entities["middot"] = '\u00B7';
entities["cedil"] = '\u00B8';
entities["sup1"] = '\u00B9';
entities["ordm"] = '\u00BA';
entities["raquo"] = '\u00BB';
entities["frac14"] = '\u00BC';
entities["frac12"] = '\u00BD';
entities["frac34"] = '\u00BE';
entities["iquest"] = '\u00BF';
entities["Agrave"] = '\u00C0';
entities["Aacute"] = '\u00C1';
entities["Acirc"] = '\u00C2';
entities["Atilde"] = '\u00C3';
entities["Auml"] = '\u00C4';
entities["Aring"] = '\u00C5';
entities["AElig"] = '\u00C6';
entities["Ccedil"] = '\u00C7';
entities["Egrave"] = '\u00C8';
entities["Eacute"] = '\u00C9';
entities["Ecirc"] = '\u00CA';
entities["Euml"] = '\u00CB';
entities["Igrave"] = '\u00CC';
entities["Iacute"] = '\u00CD';
entities["Icirc"] = '\u00CE';
entities["Iuml"] = '\u00CF';
entities["ETH"] = '\u00D0';
entities["Ntilde"] = '\u00D1';
entities["Ograve"] = '\u00D2';
entities["Oacute"] = '\u00D3';
entities["Ocirc"] = '\u00D4';
entities["Otilde"] = '\u00D5';
entities["Ouml"] = '\u00D6';
entities["times"] = '\u00D7';
entities["Oslash"] = '\u00D8';
entities["Ugrave"] = '\u00D9';
entities["Uacute"] = '\u00DA';
entities["Ucirc"] = '\u00DB';
entities["Uuml"] = '\u00DC';
entities["Yacute"] = '\u00DD';
entities["THORN"] = '\u00DE';
entities["szlig"] = '\u00DF';
entities["agrave"] = '\u00E0';
entities["aacute"] = '\u00E1';
entities["acirc"] = '\u00E2';
entities["atilde"] = '\u00E3';
entities["auml"] = '\u00E4';
entities["aring"] = '\u00E5';
entities["aelig"] = '\u00E6';
entities["ccedil"] = '\u00E7';
entities["egrave"] = '\u00E8';
entities["eacute"] = '\u00E9';
entities["ecirc"] = '\u00EA';
entities["euml"] = '\u00EB';
entities["igrave"] = '\u00EC';
entities["iacute"] = '\u00ED';
entities["icirc"] = '\u00EE';
entities["iuml"] = '\u00EF';
entities["eth"] = '\u00F0';
entities["ntilde"] = '\u00F1';
entities["ograve"] = '\u00F2';
entities["oacute"] = '\u00F3';
entities["ocirc"] = '\u00F4';
entities["otilde"] = '\u00F5';
entities["ouml"] = '\u00F6';
entities["divide"] = '\u00F7';
entities["oslash"] = '\u00F8';
entities["ugrave"] = '\u00F9';
entities["uacute"] = '\u00FA';
entities["ucirc"] = '\u00FB';
entities["uuml"] = '\u00FC';
entities["yacute"] = '\u00FD';
entities["thorn"] = '\u00FE';
entities["yuml"] = '\u00FF';
entities["fnof"] = '\u0192';
entities["Alpha"] = '\u0391';
entities["Beta"] = '\u0392';
entities["Gamma"] = '\u0393';
entities["Delta"] = '\u0394';
entities["Epsilon"] = '\u0395';
entities["Zeta"] = '\u0396';
entities["Eta"] = '\u0397';
entities["Theta"] = '\u0398';
entities["Iota"] = '\u0399';
entities["Kappa"] = '\u039A';
entities["Lambda"] = '\u039B';
entities["Mu"] = '\u039C';
entities["Nu"] = '\u039D';
entities["Xi"] = '\u039E';
entities["Omicron"] = '\u039F';
entities["Pi"] = '\u03A0';
entities["Rho"] = '\u03A1';
entities["Sigma"] = '\u03A3';
entities["Tau"] = '\u03A4';
entities["Upsilon"] = '\u03A5';
entities["Phi"] = '\u03A6';
entities["Chi"] = '\u03A7';
entities["Psi"] = '\u03A8';
entities["Omega"] = '\u03A9';
entities["alpha"] = '\u03B1';
entities["beta"] = '\u03B2';
entities["gamma"] = '\u03B3';
entities["delta"] = '\u03B4';
entities["epsilon"] = '\u03B5';
entities["zeta"] = '\u03B6';
entities["eta"] = '\u03B7';
entities["theta"] = '\u03B8';
entities["iota"] = '\u03B9';
entities["kappa"] = '\u03BA';
entities["lambda"] = '\u03BB';
entities["mu"] = '\u03BC';
entities["nu"] = '\u03BD';
entities["xi"] = '\u03BE';
entities["omicron"] = '\u03BF';
entities["pi"] = '\u03C0';
entities["rho"] = '\u03C1';
entities["sigmaf"] = '\u03C2';
entities["sigma"] = '\u03C3';
entities["tau"] = '\u03C4';
entities["upsilon"] = '\u03C5';
entities["phi"] = '\u03C6';
entities["chi"] = '\u03C7';
entities["psi"] = '\u03C8';
entities["omega"] = '\u03C9';
entities["thetasym"] = '\u03D1';
entities["upsih"] = '\u03D2';
entities["piv"] = '\u03D6';
entities["bull"] = '\u2022';
entities["hellip"] = '\u2026';
entities["prime"] = '\u2032';
entities["Prime"] = '\u2033';
entities["oline"] = '\u203E';
entities["frasl"] = '\u2044';
entities["weierp"] = '\u2118';
entities["image"] = '\u2111';
entities["real"] = '\u211C';
entities["trade"] = '\u2122';
entities["alefsym"] = '\u2135';
entities["larr"] = '\u2190';
entities["uarr"] = '\u2191';
entities["rarr"] = '\u2192';
entities["darr"] = '\u2193';
entities["harr"] = '\u2194';
entities["crarr"] = '\u21B5';
entities["lArr"] = '\u21D0';
entities["uArr"] = '\u21D1';
entities["rArr"] = '\u21D2';
entities["dArr"] = '\u21D3';
entities["hArr"] = '\u21D4';
entities["forall"] = '\u2200';
entities["part"] = '\u2202';
entities["exist"] = '\u2203';
entities["empty"] = '\u2205';
entities["nabla"] = '\u2207';
entities["isin"] = '\u2208';
entities["notin"] = '\u2209';
entities["ni"] = '\u220B';
entities["prod"] = '\u220F';
entities["sum"] = '\u2211';
entities["minus"] = '\u2212';
entities["lowast"] = '\u2217';
entities["radic"] = '\u221A';
entities["prop"] = '\u221D';
entities["infin"] = '\u221E';
entities["ang"] = '\u2220';
entities["and"] = '\u2227';
entities["or"] = '\u2228';
entities["cap"] = '\u2229';
entities["cup"] = '\u222A';
entities["int"] = '\u222B';
entities["there4"] = '\u2234';
entities["sim"] = '\u223C';
entities["cong"] = '\u2245';
entities["asymp"] = '\u2248';
entities["ne"] = '\u2260';
entities["equiv"] = '\u2261';
entities["le"] = '\u2264';
entities["ge"] = '\u2265';
entities["sub"] = '\u2282';
entities["sup"] = '\u2283';
entities["nsub"] = '\u2284';
entities["sube"] = '\u2286';
entities["supe"] = '\u2287';
entities["oplus"] = '\u2295';
entities["otimes"] = '\u2297';
entities["perp"] = '\u22A5';
entities["sdot"] = '\u22C5';
entities["lceil"] = '\u2308';
entities["rceil"] = '\u2309';
entities["lfloor"] = '\u230A';
entities["rfloor"] = '\u230B';
entities["lang"] = '\u2329';
entities["rang"] = '\u232A';
entities["loz"] = '\u25CA';
entities["spades"] = '\u2660';
entities["clubs"] = '\u2663';
entities["hearts"] = '\u2665';
entities["diams"] = '\u2666';
entities["quot"] = '\u0022';
entities["amp"] = '\u0026';
entities["lt"] = '\u003C';
entities["gt"] = '\u003E';
entities["OElig"] = '\u0152';
entities["oelig"] = '\u0153';
entities["Scaron"] = '\u0160';
entities["scaron"] = '\u0161';
entities["Yuml"] = '\u0178';
entities["circ"] = '\u02C6';
entities["tilde"] = '\u02DC';
entities["ensp"] = '\u2002';
entities["emsp"] = '\u2003';
entities["thinsp"] = '\u2009';
entities["zwnj"] = '\u200C';
entities["zwj"] = '\u200D';
entities["lrm"] = '\u200E';
entities["rlm"] = '\u200F';
entities["ndash"] = '\u2013';
entities["mdash"] = '\u2014';
entities["lsquo"] = '\u2018';
entities["rsquo"] = '\u2019';
entities["sbquo"] = '\u201A';
entities["ldquo"] = '\u201C';
entities["rdquo"] = '\u201D';
entities["bdquo"] = '\u201E';
entities["dagger"] = '\u2020';
entities["Dagger"] = '\u2021';
entities["permil"] = '\u2030';
entities["lsaquo"] = '\u2039';
entities["rsaquo"] = '\u203A';
entities["euro"] = '\u20AC';
return entities;
}
var Entities = initEntities();
var rawEntity = [];
var entity = [];
var output = [];
var len = s.length;
var state = 0;
var number = 0;
var is_hex_value = false;
var have_trailing_digits = false;
for (var i = 0; i < len; i++) {
var c = s[i];
if (state == 0) {
if (c == '&') {
entity.push(c);
rawEntity.push(c);
state = 1;
}
else {
output.push(c);
}
continue;
}
if (c == '&') {
state = 1;
if (have_trailing_digits) {
entity.push(number.toString());
have_trailing_digits = false;
}
output.push(entity.join(""));
entity = [];
entity.push('&');
continue;
}
if (state == 1) {
if (c == ';') {
state = 0;
output.push(entity.join(""));
output.push(c);
entity = [];
}
else {
number = 0;
is_hex_value = false;
if (c != '#') {
state = 2;
}
else {
state = 3;
}
entity.push(c);
rawEntity.push(c);
}
}
else if (state == 2) {
entity.push(c);
if (c == ';') {
var key = entity.join("");
if (key.length > 1 && Entities.hasOwnProperty(key.substr(1, key.length - 2)))
key = Entities[key.substr(1, key.length - 2)].toString();
output.push(key);
state = 0;
entity = [];
rawEntity = [];
}
}
else if (state == 3) {
if (c == ';') {
if (number == 0)
output.push(rawEntity.join("") + ";");
else if (number > 65535) {
output.push("&#");
output.push(number.toString());
output.push(";");
}
else {
output.push(String.fromCharCode(number));
}
state = 0;
entity = [];
rawEntity = [];
have_trailing_digits = false;
}
else if (is_hex_value && isHexDigit(c)) {
number = number * 16 + parseInt(c, 16);
have_trailing_digits = true;
rawEntity.push(c);
}
else if (isDigit(c)) {
number = number * 10 + (c.charCodeAt(0) - '0'.charCodeAt(0));
have_trailing_digits = true;
rawEntity.push(c);
}
else if (number == 0 && (c == 'x' || c == 'X')) {
is_hex_value = true;
rawEntity.push(c);
}
else {
state = 2;
if (have_trailing_digits) {
entity.push(number.toString());
have_trailing_digits = false;
}
entity.push(c);
}
}
}
if (entity.length > 0) {
output.push(entity.join(""));
}
else if (have_trailing_digits) {
output.push(number.toString());
}
return output.join("");
}
function htmlEncode(s) {
if (s == null)
return null;
if (s.length == 0)
return s;
var needEncode = false;
for (var i = 0; i < s.length; i++) {
var c = s[i];
if (c == '&' || c == '"' || c == '<' || c == '>' || c.charCodeAt(0) > 159
|| c == '\'') {
needEncode = true;
break;
}
}
if (!needEncode)
return s;
var output = [];
var len = s.length;
for (var i = 0; i < len; i++) {
var ch = s[i];
switch (ch) {
case '&':
output.push("&");
break;
case '>':
output.push(">");
break;
case '<':
output.push("<");
break;
case '"':
output.push(""");
break;
case '\'':
output.push("'");
break;
case '\uff1c':
output.push("<");
break;
case '\uff1e':
output.push(">");
break;
default:
if (ch.charCodeAt(0) > 159 && ch.charCodeAt(0) < 256) {
output.push("&#");
output.push(ch.charCodeAt(0).toString());
output.push(";");
}
else
output.push(ch);
break;
}
}
return output.join("");
}