To get the length of a string containing Chinese
In practical development applications, such as word limit typesetting, the string.length of string length with Chinese is not reliable due to the position of a Chinese character in two English characters. There are two ways to solve
| The code is as follows |
Copy Code |
String.prototype.cnLength = function () {
var arr = This.match (/[^x00-xff]/ig);
return this.length + (arr = null 0:arr.length);
};
Alert ("Hi Hello". cnlength ()); Test Results 6
|
Programme II:
| The code is as follows |
Copy Code |
String.prototype.cnLength = function () {
var len = 0;
var ch;
for (var i = 0; i < this.length; i++) {
ch = this.charcodeat (i);
if (ch >= 0 && ch <= 255) {
len++;
}
else {
Len + 2;
}
}
return Len;
};
Alert ("Hi Hello". cnlength ()); Test Results 6 |
After a length of 10000+ string test, the scheme is approximately 2ms, and the Scheme II is about 12ms. The scheme is a triumph, once again embodies the strength of the regular expression.
Intercept Chinese characters
| The code is as follows |
Copy Code |
| <meta http-equiv= "Content-type" content= "text/html; CHARSET=GBK "/>
<script type= "Text/javascript" >
String.prototype.gblen = function () {
var len = 0;
for (var i=0; i<this.length; i++) {
if (This.charcodeat (i) >127 | | this.charcodeat (i) ==94) {
Len + 2;
} else {
Len + +;
}
}
return Len;
}
String.prototype.gbtrim = function (len, s) {
var str = ";
var sp = s | | ”;
var len2 = 0;
for (var i=0; i<this.length; i++) {
if (This.charcodeat (i) >127 | | this.charcodeat (i) ==94) {
Len2 + 2;
} else {
Len2 + +;
}
}
if (len2 <= len) {
return this;
}
len2 = 0;
Len = (len > sp.length)? Len-sp.length:len;
for (var i=0; i<this.length; i++) {
if (This.charcodeat (i) >127 | | this.charcodeat (i) ==94) {
Len2 + 2;
} else {
Len2 + +;
}
if (Len2 > Len) {
STR + SP;
Break
}
STR + + This.charat (i);
}
return str;
}
var str1 = ' World ah Ah sssl occurrence of the law ';
document.write (' str1 = ' + str1 + ' <br/> ');
document.write (' length = ' + str1.gblen () + ' <br/> ');
document.write (' Gbtrim "= ' + Str1.gbtrim (+) + ' <br/> ');
document.write (' Gbtrim, ' ... ') = ' + Str1.gbtrim (Ten, ' ... ') + ' <br/> ');
document.write (' Gbtrim, '-') = ' + Str1.gbtrim ('-') + ' <br/> '); Gbtrim (len intercept length, calculated in English byte length, s truncated after the ellipsis character, such as "...")
Note: Here the characters are calculated as two lengths, so Len in Gbtrim is 10 o'clock and displays up to 5 characters.
When the number of Chinese characters is greater than 5 o'clock, the "..." is added after the interception, so only 4 characters are displayed.
Note Chinese coding
</script> |
