A UTF-8 encoded Unicode function implemented by php

A UTF-8 encoded Unicode function implemented by php

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 & 0 × 7F ); NOffset ++; NRemainingBytes-= 1; } Else if (iCode & 0xE0) = 0xC0) // 2 bytes { ICode1 = strUtf8.charCodeAt (nOffset + 1 ); If (nRemainingBytes <2 | // not enough data (ICode1 & 0xC0 )! = 0 × 80) // invalid pattern { Break; } Bstr + = String. fromCharCode (iCode & 0 × 3F) <6) | (iCode1 & 0 × 3F )); 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 )! = 0 × 80 | // invalid pattern (ICode2 & 0xC0 )! = 0 × 80) { Break; } Bstr + = String. fromCharCode (iCode & 0 × 0F) <12) | (ICode1 & 0 × 3F) <6) | (ICode2 & 0 × 3F )); NOffset + = 3; NRemainingBytes-= 3; } Else // 4 or more bytes-unsupported Break; } If (nRemainingBytes! = 0) { // Bad UTF8 string. Return ""; } Return bstr; } ?>