JavaScript function code to determine the length of Chinese characters-JS Tutorial-php.cn

JavaScript function code to determine the length of Chinese characters

高洛峰

Release： 2017-01-20 09:24:30

Original

1366 people have browsed it

JS strings are all string objects. You can use the length attribute of the string object to obtain its length. However, the minimum length unit for Chinese, full-width symbols and English is 1, which is different from PHP's strlen(). .

function strlen(str) { 
var s = 0; 
for(var i = 0; i < str.length; i++) { 
if(str.charAt(i).match(/[u0391-uFFE5]/)) { 
s += 2; 
} else { 
s++; 
} 
} 
return s; 
}

Copy after login

Capture each character. If it matches full-width characters and Chinese characters, it will count as 2 characters, and if it matches the other characters, it will count as 1 character.

<script> 
alert (fucCheckLength("中国a")); 
function fucCheckLength(strTemp) 
{ 
var i,sum; 
sum=0; 
for(i=0;i<strTemp.length;i++) 
{ 
if ((strTemp.charCodeAt(i)>=0) && (strTemp.charCodeAt(i)<=255)) 
sum=sum+1; 
else 
sum=sum+2; 
} 
return sum; 
} 
</script>

Copy after login

The result you will get is: 5 The length of bytes you want to get, right? Please note the difference in bytes and characters. The byte length is related to the encoding. For example, "China a", the gbk/gb2312 encoding is 5 bytes, but if it is UTF-8, it is 7 bytes (usually 3 Chinese characters under UTF-8 byte).
We can convert all characters in gbk and then operate. Example

function Utf8ToUnicode(strUtf8) 
{ 
var bstr = ""; 
var nTotalChars = strUtf8.length; // total chars to be processed. 
var nOffset = 0; // processing point on strUtf8 
var nRemainingBytes = nTotalChars; // how many bytes left to be converted 
var nOutputPosition = 0; 
var iCode, iCode1, iCode2; // the value of the unicode. 
while (nOffset < nTotalChars) 
{ 
iCode = strUtf8.charCodeAt(nOffset); 
if ((iCode & 0x80) == 0) // 1 byte. 
{ 
if ( nRemainingBytes < 1 ) // not enough data 
break; 
bstr += String.fromCharCode(iCode & 0x7F); 
nOffset ++; 
nRemainingBytes -= 1; 
} 
else if ((iCode & 0xE0) == 0xC0) // 2 bytes 
{ 
iCode1 = strUtf8.charCodeAt(nOffset + 1); 
if ( nRemainingBytes < 2 || // not enough data 
(iCode1 & 0xC0) != 0x80 ) // invalid pattern 
{ 
break; 
} 
bstr += String.fromCharCode(((iCode & 0x3F) << 6) | ( iCode1 & 0x3F)); 
nOffset += 2; 
nRemainingBytes -= 2; 
} 
else if ((iCode & 0xF0) == 0xE0) // 3 bytes 
{ 
iCode1 = strUtf8.charCodeAt(nOffset + 1); 
iCode2 = strUtf8.charCodeAt(nOffset + 2); 
if ( nRemainingBytes < 3 || // not enough data 
(iCode1 & 0xC0) != 0x80 || // invalid pattern 
(iCode2 & 0xC0) != 0x80 ) 
{ 
break; 
} 
bstr += String.fromCharCode(((iCode & 0x0F) << 12) | 
((iCode1 & 0x3F) << 6) | 
(iCode2 & 0x3F)); 
nOffset += 3; 
nRemainingBytes -= 3; 
} 
else // 4 or more bytes -- unsupported 
break; 
} 
if (nRemainingBytes != 0) 
{ 
// bad UTF8 string. 
return ""; 
} 
return bstr; 
}

Copy after login

How to solve this problem. This article introduces the method of using js to obtain the length of Chinese characters

First, we define a new The function getBytes() obtains the number of bytes in a string. In JavaScript, this function is a standard function.

　　String.prototype.getBytes = function() { 
　　var cArr = this.match(/[^x00-xff]/ig); 
　　return this.length + (cArr == null ? 0 : cArr.length); 
　　} 
　　function paramCheck(cur){ 
　　if(cur.value.getBytes() > 64){ 
　　alert("字符超过64个字符"); 
　　return false; 
　　} 
　　return true; 
　　}

Copy after login

　getBytes uses regular expressions to determine the number of Chinese characters contained in the string. The Chinese characters contained are placed in the array cArr, so that the length of cArr is the total number of Chinese characters. The getBytes method returns length plus the number of Chinese characters, which is the total number of bytes.
Just use [^x00-xff], which is a bit disgusting. Some special characters can also be matched, such as } and so on.
　But if you use [^u4E00-u9FA5], it cannot match Chinese...

The following are several other methods, you can test it:
One:

function _length(str){ 
var len=0; 
for(var i=0;i<str.length;i++){ 
if(str.charAt(i)>&#39;~&#39;){len+=2;}else{len++;} 
} 
return len; 
}

Copy after login

Two types:

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 = &#39;&#39;; 
var sp = s || &#39;&#39;; 
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 = &#39;世上最牛的@#%&们 世上最牛的@#%&们&#39;; 
document.write(&#39;str1 = &#39;+ str1 +&#39; 
&#39;); 
document.write(&#39;length = &#39;+ str1.gblen() +&#39; 
&#39;); 
document.write(&#39;gbtrim(10) = &#39;+ str1.gbtrim(10) +&#39; 
&#39;); 
document.write(&#39;gbtrim(10, \&#39;…\&#39;) = &#39;+ str1.gbtrim(10, &#39;…&#39;) +&#39; 
&#39;); 
document.write(&#39;gbtrim(12, \&#39;-\&#39; ) = &#39;+ str1.gbtrim(12, &#39;-&#39;) +&#39; 
&#39;); 

// gbtrim(len 截取长度，按英文字节长度计算， s截取后的省略字符，如"…" ) 
// 备注： 这里中文字符都是当作两个长度来计算的，所以gbtrim中的len为10时，是显示最多5个汉字的。 
// 当汉字数大于5时，由于截取后加上“…”，所以只显示4个汉字。

Copy after login

For more javascript function code to determine the length of Chinese characters related articles, please pay attention to the PHP Chinese website!