Here you can find the source of toUTFBody(String str)
public static String toUTFBody(String str) throws IOException
//package com.java2s; //License from project: Open Source License import java.io.IOException; import java.io.UTFDataFormatException; public class Main { public static String toUTFBody(String str) throws IOException { int strlen = str.length(); int utflen = 0; int c, count = 0; /* use charAt instead of copying String to char array */ for (int i = 0; i < strlen; i++) { c = str.charAt(i);// w ww .j a v a2 s. co m if ((c >= 0x0001) && (c <= 0x007F)) { utflen++; } else if (c > 0x07FF) { utflen += 3; } else { utflen += 2; } } if (utflen > 65535) throw new UTFDataFormatException("encoded string too long: " + utflen + " bytes"); byte[] bytearr = new byte[utflen]; // bytearr[count++] = (byte) ((utflen >>> 8) & 0xFF); // bytearr[count++] = (byte) ((utflen >>> 0) & 0xFF); int i = 0; for (i = 0; i < strlen; i++) { c = str.charAt(i); if (!((c >= 0x0001) && (c <= 0x007F))) break; bytearr[count++] = (byte) c; } for (; i < strlen; i++) { c = str.charAt(i); if ((c >= 0x0001) && (c <= 0x007F)) { bytearr[count++] = (byte) c; } else if (c > 0x07FF) { bytearr[count++] = (byte) (0xE0 | ((c >> 12) & 0x0F)); bytearr[count++] = (byte) (0x80 | ((c >> 6) & 0x3F)); bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F)); } else { bytearr[count++] = (byte) (0xC0 | ((c >> 6) & 0x1F)); bytearr[count++] = (byte) (0x80 | ((c >> 0) & 0x3F)); } } // out.write(bytearr, 0, utflen + 2); // return utflen + 2; return new String(bytearr, "UTF-8"); } }