Here you can find the source of decodeString(byte[] bytearr)
Parameter | Description |
---|---|
bytearr | byte data to decode |
Parameter | Description |
---|---|
UTFDataFormatException | if the byte data is not valid UTF-8 |
public static String decodeString(byte[] bytearr) throws UTFDataFormatException
//package com.java2s; /**// w w w .j a v a 2 s . com * Copyright (C) 2009 - present by OpenGamma Inc. and other contributors. * * Licensed under the Apache License, Version 2.0 (the "License"); * you may not use this file except in compliance with the License. * You may obtain a copy of the License at * * http://www.apache.org/licenses/LICENSE-2.0 * * Unless required by applicable law or agreed to in writing, software * distributed under the License is distributed on an "AS IS" BASIS, * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. * See the License for the specific language governing permissions and * limitations under the License. */ import java.io.UTFDataFormatException; public class Main { /** * @param bytearr byte data to decode * @return the decoded string * @throws UTFDataFormatException if the byte data is not valid UTF-8 */ public static String decodeString(byte[] bytearr) throws UTFDataFormatException { int utflen = bytearr.length; char[] chararr = new char[utflen]; int c, char2, char3; int count = 0; int chararr_count = 0; while (count < utflen) { c = (int) bytearr[count] & 0xff; if (c > 127) break; count++; chararr[chararr_count++] = (char) c; } while (count < utflen) { c = (int) bytearr[count] & 0xff; switch (c >> 4) { case 0: case 1: case 2: case 3: case 4: case 5: case 6: case 7: /* 0xxxxxxx*/ count++; chararr[chararr_count++] = (char) c; break; case 12: case 13: /* 110x xxxx 10xx xxxx*/ count += 2; if (count > utflen) throw new UTFDataFormatException("malformed input: partial character at end"); char2 = (int) bytearr[count - 1]; if ((char2 & 0xC0) != 0x80) throw new UTFDataFormatException("malformed input around byte " + count); chararr[chararr_count++] = (char) (((c & 0x1F) << 6) | (char2 & 0x3F)); break; case 14: /* 1110 xxxx 10xx xxxx 10xx xxxx */ count += 3; if (count > utflen) throw new UTFDataFormatException("malformed input: partial character at end"); char2 = (int) bytearr[count - 2]; char3 = (int) bytearr[count - 1]; if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80)) throw new UTFDataFormatException("malformed input around byte " + (count - 1)); chararr[chararr_count++] = (char) (((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0)); break; default: /* 10xx xxxx, 1111 xxxx */ throw new UTFDataFormatException("malformed input around byte " + count); } } // The number of chars produced may be less than utflen return new String(chararr, 0, chararr_count); } }