Does any one know how to convert special characters to HTML in Javascript?
Example:
& (ampersand) becomes &." (double quote) becomes " when ENT_NOQUOTES is not set.' (single quote) becomes ' only when ENT_QUOTES is set.< (less than) becomes <.> (greater than) becomes >.This question is related to
javascript
From Mozilla ...
Note that charCodeAt will always return a value that is less than 65,536. This is because the higher code points are represented by a pair of (lower valued) "surrogate" pseudo-characters which are used to comprise the real character. Because of this, in order to examine or reproduce the full character for individual characters of value 65,536 and above, for such characters, it is necessary to retrieve not only charCodeAt(i), but also charCodeAt(i+1) (as if examining/reproducing a string with two >letters).
The Best Solution
/**
* (c) 2012 Steven Levithan <http://slevithan.com/>
* MIT license
*/
if (!String.prototype.codePointAt) {
String.prototype.codePointAt = function (pos) {
pos = isNaN(pos) ? 0 : pos;
var str = String(this),
code = str.charCodeAt(pos),
next = str.charCodeAt(pos + 1);
// If a surrogate pair
if (0xD800 <= code && code <= 0xDBFF && 0xDC00 <= next && next <= 0xDFFF) {
return ((code - 0xD800) * 0x400) + (next - 0xDC00) + 0x10000;
}
return code;
};
}
/**
* Encodes special html characters
* @param string
* @return {*}
*/
function html_encode(string) {
var ret_val = '';
for (var i = 0; i < string.length; i++) {
if (string.codePointAt(i) > 127) {
ret_val += '&#' + string.codePointAt(i) + ';';
} else {
ret_val += string.charAt(i);
}
}
return ret_val;
}
Usage example:
html_encode("?");
<!doctype html>
<html lang="en">
<head>
<meta charset="utf-8">
<title>html</title>
<script>
$(function() {
document.getElementById('test').innerHTML = "&";
});
</script>
</head>
<body>
<div id="test"></div>
</body>
</html>
you can simply convert special characters to html using above code.
As was mentioned by dragon the cleanest way to do it is with jQuery:
function HtmlEncode(s) {
return $('<div>').text(s).html();
}
function HtmlDecode(s) {
return $('<div>').html(s).text();
}
function char_convert() {
var chars = ["©","Û","®","ž","Ü","Ÿ","Ý","$","Þ","%","¡","ß","¢","à","£","á","À","¤","â","Á","¥","ã","Â","¦","ä","Ã","§","å","Ä","¨","æ","Å","©","ç","Æ","ª","è","Ç","«","é","È","¬","ê","É","","ë","Ê","®","ì","Ë","¯","í","Ì","°","î","Í","±","ï","Î","²","ð","Ï","³","ñ","Ð","´","ò","Ñ","µ","ó","Õ","¶","ô","Ö","·","õ","Ø","¸","ö","Ù","¹","÷","Ú","º","ø","Û","»","ù","Ü","@","¼","ú","Ý","½","û","Þ","€","¾","ü","ß","¿","ý","à","‚","À","þ","á","ƒ","Á","ÿ","å","„","Â","æ","…","Ã","ç","†","Ä","è","‡","Å","é","ˆ","Æ","ê","‰","Ç","ë","Š","È","ì","‹","É","í","Œ","Ê","î","Ë","ï","Ž","Ì","ð","Í","ñ","Î","ò","‘","Ï","ó","’","Ð","ô","“","Ñ","õ","”","Ò","ö","•","Ó","ø","–","Ô","ù","—","Õ","ú","˜","Ö","û","™","×","ý","š","Ø","þ","›","Ù","ÿ","œ","Ú"];
var codes = ["©","Û","®","ž","Ü","Ÿ","Ý","$","Þ","%","¡","ß","¢","à","£","á","À","¤","â","Á","¥","ã","Â","¦","ä","Ã","§","å","Ä","¨","æ","Å","©","ç","Æ","ª","è","Ç","«","é","È","¬","ê","É","­","ë","Ê","®","ì","Ë","¯","í","Ì","°","î","Í","±","ï","Î","²","ð","Ï","³","ñ","Ð","´","ò","Ñ","µ","ó","Õ","¶","ô","Ö","·","õ","Ø","¸","ö","Ù","¹","÷","Ú","º","ø","Û","»","ù","Ü","@","¼","ú","Ý","½","û","Þ","€","¾","ü","ß","¿","ý","à","‚","À","þ","á","ƒ","Á","ÿ","å","„","Â","æ","…","Ã","ç","†","Ä","è","‡","Å","é","ˆ","Æ","ê","‰","Ç","ë","Š","È","ì","‹","É","í","Œ","Ê","î","Ë","ï","Ž","Ì","ð","Í","ñ","Î","ò","‘","Ï","ó","’","Ð","ô","“","Ñ","õ","”","Ò","ö","•","Ó","ø","–","Ô","ù","—","Õ","ú","˜","Ö","û","™","×","ý","š","Ø","þ","›","Ù","ÿ","œ","Ú"];
for(x=0; x<chars.length; x++){
for (i=0; i<arguments.length; i++){
arguments[i].value = arguments[i].value.replace(chars[x], codes[x]);
}
}
}
char_convert(this);
This generic function encodes every non alphabetic character to its htmlcode (numeric):
function HTMLEncode(str) {
var i = str.length,
aRet = [];
while (i--) {
var iC = str[i].charCodeAt();
if (iC < 65 || iC > 127 || (iC>90 && iC<97)) {
aRet[i] = '&#'+iC+';';
} else {
aRet[i] = str[i];
}
}
return aRet.join('');
}
public static string HtmlEncode (string text)
{
string result;
using (StringWriter sw = new StringWriter())
{
var x = new HtmlTextWriter(sw);
x.WriteEncodedText(text);
result = sw.ToString();
}
return result;
}
a workaround:
var temp = $("div").text("<");
var afterEscape = temp.html(); // afterEscape == "<"
In a PRE tag -and in most other HTML tags- plain text for a batch file that uses the output redirection characters (< and >) will break the HTML, but here is my tip: anything goes in a TEXTAREA element -it will not break the HTML, mainly because we are inside a control instanced and handled by the OS, and therefore its content are not being parsed by the HTML engine.
As an example, say I want to highlight the syntax of my batch file using javascript. I simply paste the code in a textarea without worrying about the HTML reserved characters, and have the script process the innerHTML property of the textarea, which evaluates to the text with the HTML reserved characters replaced by their corresponding ISO-8859-1 entities.
Browsers will escape special characters automatically when you retrieve the innerHTML (and outerHTML) property of an element. Using a textarea (and who knows, maybe an input of type text) just saves you from doing the conversion (manually or through code).
I use this trick to test my syntax highlighter, and when I'm done authoring and testing, I simply hide the textarea from view.
function escape (text)
{
return text.replace(/[<>\&\"\']/g, function(c) {
return '&#' + c.charCodeAt(0) + ';';
});
}
alert(escape("<>&'\""));
See JavaScript htmlentities http://phpjs.org/functions/htmlentities:425
var swapCodes = new Array(8211, 8212, 8216, 8217, 8220, 8221, 8226, 8230, 8482, 169, 61558, 8226, 61607);
var swapStrings = new Array("--", "--", "'", "'", '"', '"', "*", "...", "™", "©", "•", "•", "•");
var TextCheck = {
doCWBind:function(div){
$(div).bind({
bind:function(){
TextCheck.cleanWord(div);
},
focus:function(){
TextCheck.cleanWord(div);
},
paste:function(){
TextCheck.cleanWord(div);
}
});
},
cleanWord:function(div){
var output = $(div).val();
for (i = 0; i < swapCodes.length; i++) {
var swapper = new RegExp("\\u" + swapCodes[i].toString(16), "g");
output = output.replace(swapper, swapStrings[i]);
}
$(div).val(output);
}
}
Another one that we use now that works. One above I have it calling a script instead and returns the converted code. Only good on small textareas (meaning not a full on article/blog ect...)
For Above. Works on most chars.
var swapCodes = new Array(8211, 8212, 8216, 8217, 8220, 8221, 8226, 8230, 8482, 61558, 8226, 61607,161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 338, 339, 352, 353, 376, 402);
var swapStrings = new Array("--", "--", "'", "'", '"', '"', "*", "...", "™", "•", "•", "•", "¡", "¢", "£", "¤", "¥", "¦", "§", "¨", "©", "ª", "«", "¬", "­", "®", "¯", "°", "±", "²", "³", "´", "µ", "¶", "·", "¸", "¹", "º", "»", "¼", "½", "¾", "¿", "À", "Á", "Â", "Ã", "Ä", "Å", "Æ", "Ç", "È", "É", "Ê", "Ë", "Ì", "Í", "Î", "Ï", "Ð", "Ñ", "Ò", "Ó", "Ô", "Õ", "Ö", "×", "Ø", "Ù", "Ú", "Û", "Ü", "Ý", "Þ", "ß", "à", "á", "â", "ã", "ä", "å", "æ", "ç", "è", "é", "ê", "ë", "ì", "í", "î", "ï", "ð", "ñ", "ò", "ó", "ô", "õ", "ö", "÷", "ø", "ù", "ú", "û", "ü", "ý", "þ", "ÿ", "Œ", "œ", "Š", "š", "Ÿ", "ƒ");
I create a javascript file that has a lot of functionality including the above. http://www.neotropicsolutions.com/JSChars.zip
All files needed are included. I added jQuery 1.4.4. Simply because I saw issues in other versions, yet to try them out.
Requires: jQuery & jQuery Impromptu from: http://trentrichardson.com/Impromptu/index.php
1. Word Count
2. Character Conversion
3. Checks to ensure this is not passed: "notsomeverylongstringmissingspaces"
4. Checks to make sure ALL IS NOT ALL UPPERCASE.
5. Strip HTML
// Word Counter
$.getScript('js/characters.js',function(){
$('#adtxt').bind("keyup click blur focus change paste",
function(event){
TextCheck.wordCount(30, "#adtxt", "#adtxt_count", event);
});
$('#adtxt').blur(
function(event){
TextCheck.check_length('#adtxt'); // unsures properly spaces-not one long word
TextCheck.doCWBind('#adtxt');// char conversion
});
TextCheck.wordCount(30, "#adtxt", "#adtxt_count", false);
});
//HTML
<textarea name="adtxt" id="adtxt" rows="10" cols="70" class="wordCount"></textarea>
<div id="adtxt_count" class="clear"></div>
// Just Character Conversions:
TextCheck.doCWBind('#myfield');
// Run through form fields in a form for case checking.
// Alerts user when field is blur'd.
var labels = new Array("Brief Description","Website URL","Contact Name","Website","Email","Linkback URL");
var checking = new Array("descr","title","fname","website","email","linkback");
TextCheck.check_it(checking,labels);
// Extra security to check again, make sure form is not submitted
var pass = TextCheck.validate(checking,labels);
if(pass){
//do form actions
}
//Strip HTML
<textarea name="adtxt" id="adtxt" rows="10" cols="70" onblur="TextCheck.stripHTML(this);"></textarea>
For those who want to decode an integer char code like &#xxx; inside a string, use this function:
function decodeHtmlCharCodes(str) { _x000D_
return str.replace(/(&#(\d+);)/g, function(match, capture, charCode) {_x000D_
return String.fromCharCode(charCode);_x000D_
});_x000D_
}_x000D_
_x000D_
// Will output "The show that gained int’l reputation’!"_x000D_
console.log(decodeHtmlCharCodes('The show that gained int’l reputation’!'));const decodeHtmlCharCodes = str => _x000D_
str.replace(/(&#(\d+);)/g, (match, capture, charCode) => _x000D_
String.fromCharCode(charCode));_x000D_
_x000D_
// Will output "The show that gained int’l reputation’!"_x000D_
console.log(decodeHtmlCharCodes('The show that gained int’l reputation’!'));Yes, but if you need to insert the resulting string somewhere without it being converted back, you need to do:
str.replace(/'/g,"&amp;#39;"); // and so on
Create a function that uses string replace
function convert(str)
{
str = str.replace(/&/g, "&");
str = str.replace(/>/g, ">");
str = str.replace(/</g, "<");
str = str.replace(/"/g, """);
str = str.replace(/'/g, "'");
return str;
}
Here's a good library I've found very useful in this context.
https://github.com/mathiasbynens/he
According to its author:
It supports all standardized named character references as per HTML, handles ambiguous ampersands and other edge cases just like a browser would, has an extensive test suite, and — contrary to many other JavaScript solutions — he handles astral Unicode symbols just fine
This doesn't direcly answer your question, but if you are using innerHTML in order to write text within an element and you ran into encoding issues, just use textContent, i.e.:
var s = "Foo 'bar' baz <qux>";
var element = document.getElementById('foo');
element.textContent = s;
// <div id="foo">Foo 'bar' baz <qux></div>
You can fix it by replacing the function .text() to .html(). its working for me.
Following is the simple function to encode xml escape chars in JS
Encoder.htmlEncode(unsafeText);
Here are a couple methods I use without the need of 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 safe encoding characters to worry about (&, inebreaks, <, >, " and ') like:
function encode(r){_x000D_
return r.replace(/[\x26\x0A\<>'"]/g,function(r){return"&#"+r.charCodeAt(0)+";"})_x000D_
}_x000D_
_x000D_
test.value=encode('How to encode\nonly html tags &<>\'" nice & fast!');_x000D_
_x000D_
/*************_x000D_
* \x26 is &ersand (it has to be first),_x000D_
* \x0A is newline,_x000D_
*************/<textarea id=test rows="9" cols="55">www.WHAK.com</textarea>The best way in my opinion is to use the browser's inbuilt HTML escape functionality to handle many of the cases. To do this simply create a element in the DOM tree and set the innerText of the element to your string. Then retrieve the innerHTML of the element. The browser will return an HTML encoded string.
function HtmlEncode(s)
{
var el = document.createElement("div");
el.innerText = el.textContent = s;
s = el.innerHTML;
return s;
}
Test run:
alert(HtmlEncode('&;\'><"'));
Output:
&;'><"
This method of escaping HTML is also used by the Prototype JS library though differently from the simplistic sample I have given.
Note: You will still need to escape quotes (double and single) yourself. You can use any of the methods outlined by others here.
function ConvChar( str ) {
c = {'<':'<', '>':'>', '&':'&', '"':'"', "'":''',
'#':'#' };
return str.replace( /[<&>'"#]/g, function(s) { return c[s]; } );
}
alert( ConvChar('<-"-&-"->-<-\'-#-\'->') );
Result:
<-"-&-"->-<-'-#-'->
In testarea tag:
<-"-&-"->-<-'-#-'->
If you'll just change a little chars in long code...
We can use javascript DOMParser for special characters conversion.
const parser = new DOMParser();
const convertedValue = (parser.parseFromString("' & ' < >", "application/xml").body.innerText;
If you need support for all standardized named character references, unicode and ambiguous ampersands, the he library is the only 100% reliable solution I'm aware of!
he.encode('foo © bar ? baz qux');
// Output : 'foo © bar ≠ baz 𝌆 qux'
he.decode('foo © bar ≠ baz 𝌆 qux');
// Output : 'foo © bar ? baz qux'
<html>
<body>
<script type="text/javascript">
var str= "&\"'<>";
alert('B4 Change:\n' + str);
str= str.replace(/\&/g,'&');
str= str.replace(/</g,'<');
str= str.replace(/>/g,'>');
str= str.replace(/\"/g,'"');
str= str.replace(/\'/g,''');
alert('After change:\n' + str);
</script>
</body>
</html>
use this to test: http://www.w3schools.com/js/tryit.asp?filename=tryjs_text
Source: Stackoverflow.com