0N/A/*
2362N/A * Copyright (c) 1996, 2008, Oracle and/or its affiliates. All rights reserved.
0N/A * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
0N/A *
0N/A * This code is free software; you can redistribute it and/or modify it
0N/A * under the terms of the GNU General Public License version 2 only, as
2362N/A * published by the Free Software Foundation. Oracle designates this
0N/A * particular file as subject to the "Classpath" exception as provided
2362N/A * by Oracle in the LICENSE file that accompanied this code.
0N/A *
0N/A * This code is distributed in the hope that it will be useful, but WITHOUT
0N/A * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
0N/A * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
0N/A * version 2 for more details (a copy is included in the LICENSE file that
0N/A * accompanied this code).
0N/A *
0N/A * You should have received a copy of the GNU General Public License version
0N/A * 2 along with this work; if not, write to the Free Software Foundation,
0N/A * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
0N/A *
2362N/A * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
2362N/A * or visit www.oracle.com if you need additional information or have any
2362N/A * questions.
0N/A */
0N/A
0N/Apackage sun.io;
0N/A
749N/Aimport static sun.nio.cs.CharsetMapping.*;
749N/A
0N/A/**
0N/A* A table driven conversion from char to byte for single byte
0N/A* character sets. Tables will reside in the class CharToByteYYYYY,
0N/A* where YYYYY is a unique character set identifier
0N/A
0N/A < TBD: Tables are of the form... >
0N/A
0N/A*
0N/A* @author Lloyd Honomichl
0N/A* @author Asmus Freytag
749N/A* @version 8/28/96
0N/A*/
0N/A
0N/Apublic abstract class CharToByteSingleByte extends CharToByteConverter {
0N/A
0N/A /*
0N/A * 1st level index, provided by subclass
0N/A */
749N/A protected char[] index1;
0N/A
0N/A /*
0N/A * 2nd level index, provided by subclass
0N/A */
749N/A protected char[] index2;
0N/A
0N/A /*
0N/A * Mask to isolate bits for 1st level index, from subclass
0N/A */
0N/A protected int mask1;
0N/A
0N/A /*
0N/A * Mask to isolate bits for 2nd level index, from subclass
0N/A */
0N/A protected int mask2;
0N/A
0N/A /*
0N/A * Shift to isolate bits for 1st level index, from subclass
0N/A */
0N/A protected int shift;
0N/A
0N/A private char highHalfZoneCode;
0N/A
749N/A public char[] getIndex1() {
0N/A return index1;
0N/A }
0N/A
749N/A public char[] getIndex2() {
0N/A return index2;
0N/A }
0N/A public int flush(byte[] output, int outStart, int outEnd)
0N/A throws MalformedInputException
0N/A {
0N/A if (highHalfZoneCode != 0) {
0N/A highHalfZoneCode = 0;
0N/A badInputLength = 0;
0N/A throw new MalformedInputException();
0N/A }
0N/A byteOff = charOff = 0;
0N/A return 0;
0N/A }
0N/A
0N/A /**
0N/A * Converts characters to sequences of bytes.
0N/A * Conversions that result in Exceptions can be restarted by calling
0N/A * convert again, with appropriately modified parameters.
0N/A * @return the characters written to output.
0N/A * @param input char array containing text in Unicode
0N/A * @param inStart offset in input array
0N/A * @param inEnd offset of last byte to be converted
0N/A * @param output byte array to receive conversion result
0N/A * @param outStart starting offset
0N/A * @param outEnd offset of last byte to be written to
0N/A * @throw MalformedInputException for any sequence of chars that is
0N/A * illegal in Unicode (principally unpaired surrogates
0N/A * and \uFFFF or \uFFFE), including any partial surrogate pair
0N/A * which occurs at the end of an input buffer.
0N/A * @throw UnsupportedCharacterException for any character that
0N/A * that cannot be converted to the external character set.
0N/A */
0N/A public int convert(char[] input, int inOff, int inEnd,
0N/A byte[] output, int outOff, int outEnd)
0N/A throws MalformedInputException,
0N/A UnknownCharacterException,
0N/A ConversionBufferFullException
0N/A {
0N/A char inputChar; // Input character to be converted
0N/A byte[] outputByte; // Output byte written to output
0N/A int inputSize; // Size of input
0N/A int outputSize; // Size of output
0N/A
0N/A byte[] tmpArray = new byte[1];
0N/A
0N/A // Record beginning offsets
0N/A charOff = inOff;
0N/A byteOff = outOff;
0N/A
0N/A if (highHalfZoneCode != 0) {
0N/A inputChar = highHalfZoneCode;
0N/A highHalfZoneCode = 0;
0N/A if (input[inOff] >= 0xdc00 && input[inOff] <= 0xdfff) {
0N/A // This is legal UTF16 sequence.
0N/A badInputLength = 1;
0N/A throw new UnknownCharacterException();
0N/A } else {
0N/A // This is illegal UTF16 sequence.
0N/A badInputLength = 0;
0N/A throw new MalformedInputException();
0N/A }
0N/A }
0N/A
0N/A // Loop until we hit the end of the input
0N/A while(charOff < inEnd) {
0N/A
0N/A outputByte = tmpArray;
0N/A
0N/A // Get the input character
0N/A inputChar = input[charOff];
0N/A
0N/A // Default output size
0N/A outputSize = 1;
0N/A
0N/A // Assume this is a simple character
0N/A inputSize = 1;
0N/A
0N/A // Is this a high surrogate?
0N/A if(inputChar >= '\uD800' && inputChar <= '\uDBFF') {
0N/A // Is this the last character in the input?
0N/A if (charOff + 1 >= inEnd) {
0N/A highHalfZoneCode = inputChar;
0N/A break;
0N/A }
0N/A
0N/A // Is there a low surrogate following?
0N/A inputChar = input[charOff + 1];
0N/A if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') {
0N/A // We have a valid surrogate pair. Too bad we don't map
0N/A // surrogates. Is substitution enabled?
0N/A if (subMode) {
0N/A outputByte = subBytes;
0N/A outputSize = subBytes.length;
0N/A inputSize = 2;
0N/A } else {
0N/A badInputLength = 2;
0N/A throw new UnknownCharacterException();
0N/A }
0N/A } else {
0N/A // We have a malformed surrogate pair
0N/A badInputLength = 1;
0N/A throw new MalformedInputException();
0N/A }
0N/A }
0N/A
0N/A // Is this an unaccompanied low surrogate?
0N/A else if (inputChar >= '\uDC00' && inputChar <= '\uDFFF') {
0N/A badInputLength = 1;
0N/A throw new MalformedInputException();
0N/A }
0N/A
0N/A // Not part of a surrogate, so look it up
0N/A else {
0N/A // Get output using two level lookup
0N/A outputByte[0] = getNative(inputChar);
0N/A
0N/A // Might this character be unmappable?
0N/A if (outputByte[0] == 0) {
0N/A // If outputByte is zero because the input was zero
0N/A // then this character is actually mappable
0N/A if (input[charOff] != '\u0000') {
0N/A // We have an unmappable character
0N/A // Is substitution enabled?
0N/A if (subMode) {
0N/A outputByte = subBytes;
0N/A outputSize = subBytes.length;
0N/A } else {
0N/A badInputLength = 1;
0N/A throw new UnknownCharacterException();
0N/A }
0N/A }
0N/A }
0N/A }
0N/A
0N/A // If we don't have room for the output, throw an exception
0N/A if (byteOff + outputSize > outEnd)
0N/A throw new ConversionBufferFullException();
0N/A
0N/A // Put the byte in the output buffer
0N/A for (int i = 0; i < outputSize; i++) {
0N/A output[byteOff++] = outputByte[i];
0N/A }
0N/A charOff += inputSize;
0N/A
0N/A }
0N/A
0N/A // Return the length written to the output buffer
0N/A return byteOff - outOff;
0N/A }
0N/A
0N/A /**
0N/A * the maximum number of bytes needed to hold a converted char
0N/A * @returns the maximum number of bytes needed for a converted char
0N/A */
0N/A public int getMaxBytesPerChar() {
0N/A return 1;
0N/A }
0N/A
749N/A int encodeChar(char ch) {
749N/A char index = index1[ch >> 8];
749N/A if (index == UNMAPPABLE_ENCODING)
749N/A return UNMAPPABLE_ENCODING;
749N/A return index2[index + (ch & 0xff)];
749N/A }
749N/A
0N/A public byte getNative(char inputChar) {
749N/A int b = encodeChar(inputChar);
749N/A if (b == UNMAPPABLE_ENCODING)
749N/A return 0;
749N/A return (byte)b;
0N/A }
0N/A
0N/A /**
0N/A * Resets the converter.
0N/A * Call this method to reset the converter to its initial state
0N/A */
0N/A public void reset() {
0N/A byteOff = charOff = 0;
0N/A highHalfZoneCode = 0;
0N/A }
0N/A
0N/A /**
0N/A * Return whether a character is mappable or not
0N/A * @return true if a character is mappable
0N/A */
0N/A public boolean canConvert(char ch) {
749N/A return encodeChar(ch) != UNMAPPABLE_ENCODING;
0N/A }
0N/A}