/* * Copyright (c) 2009, 2010, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 only, as * published by the Free Software Foundation. Oracle designates this * particular file as subject to the "Classpath" exception as provided * by Oracle in the LICENSE file that accompanied this code. * * This code is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * version 2 for more details (a copy is included in the LICENSE file that * accompanied this code). * * You should have received a copy of the GNU General Public License version * 2 along with this work; if not, write to the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA * or visit www.oracle.com if you need additional information or have any * questions. */ package sun.nio.cs.ext; import java.nio.ByteBuffer;import java.nio.CharBuffer;import java.nio.charset.Charset;import java.nio.charset.CharsetDecoder;import java.nio.charset.CharsetEncoder;import java.nio.charset.CoderResult;import java.util.Arrays;import sun.nio.cs.Surrogate;import static sun.nio.cs.CharsetMapping.*; /* * Four types of "DoubleByte" charsets are implemented in this class * (1)DoubleByte * The "mostly widely used" multibyte charset, a combination of * a singlebyte character set (usually the ASCII charset) and a * doublebyte character set. The codepoint values of singlebyte * and doublebyte don't overlap. Microsoft's multibyte charsets * and IBM's "DBCS_ASCII" charsets, such as IBM1381, 942, 943, * 948, 949 and 950 are such charsets. * * (2)DoubleByte_EBCDIC * IBM EBCDIC Mix multibyte charset. Use SO and SI to shift (switch) * in and out between the singlebyte character set and doublebyte * character set. * * (3)DoubleByte_SIMPLE_EUC * It's a "simple" form of EUC encoding scheme, only have the * singlebyte character set G0 and one doublebyte character set * G1 are defined, G2 (with SS2) and G3 (with SS3) are not used. * So it is actually the same as the "typical" type (1) mentioned * above, except it return "malformed" for the SS2 and SS3 when * decoding. * * (4)DoubleByte ONLY * A "pure" doublebyte only character set. From implementation * point of view, this is the type (1) with "decodeSingle" always * returns unmappable. * * For simplicity, all implementations share the same decoding and * encoding data structure. * * Decoding: * * char[][] b2c; * char[] b2cSB; * int b2Min, b2Max * * public char decodeSingle(int b) { * return b2cSB.[b]; * } * * public char decodeDouble(int b1, int b2) { * if (b2 < b2Min || b2 > b2Max) * return UNMAPPABLE_DECODING; * return b2c[b1][b2 - b2Min]; * } * * (1)b2Min, b2Max are the corresponding min and max value of the * low-half of the double-byte. * (2)The high 8-bit/b1 of the double-byte are used to indexed into * b2c array. * * Encoding: * * char[] c2b; * char[] c2bIndex; * * public int encodeChar(char ch) { * return c2b[c2bIndex[ch >> 8] + (ch & 0xff)]; * } * */ public class DoubleByte { public final static char[] B2C_UNMAPPABLE; static { B2C_UNMAPPABLE = new char[0x100]; Arrays.fill(B2C_UNMAPPABLE, UNMAPPABLE_DECODING); } public static class Decoder extends CharsetDecoder implements DelegatableDecoder { final char[][] b2c; final char[] b2cSB; final int b2Min; final int b2Max; // for SimpleEUC override protected CoderResult crMalformedOrUnderFlow(int b) { return CoderResult.UNDERFLOW; } protected CoderResult crMalformedOrUnmappable(int b) { return CoderResult.unmappableForLength(2); } Decoder(Charset cs, float avgcpb, float maxcpb, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, avgcpb, maxcpb); this.b2c = b2c; this.b2cSB = b2cSB; this.b2Min = b2Min; this.b2Max = b2Max; } Decoder(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { this(cs, 0.5f, 1.0f, b2c, b2cSB, b2Min, b2Max); } protected CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { byte[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); char[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { while (sp < sl && dp < dl) { // inline the decodeSingle/Double() for better performance int inSize = 1; int b1 = sa[sp] & 0xff; char c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) { if (sl - sp < 2) return crMalformedOrUnderFlow(b1); int b2 = sa[sp + 1] & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { return crMalformedOrUnmappable(b1); } inSize++; } da[dp++] = c; sp += inSize; } return (sp >= sl) ? CoderResult.UNDERFLOW : CoderResult.OVERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { int mark = src.position(); try { while (src.hasRemaining() && dst.hasRemaining()) { int b1 = src.get() & 0xff; char c = b2cSB[b1]; int inSize = 1; if (c == UNMAPPABLE_DECODING) { if (src.remaining() < 1) return crMalformedOrUnderFlow(b1); int b2 = src.get() & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) return crMalformedOrUnmappable(b1); inSize++; } dst.put(c); mark += inSize; } return src.hasRemaining()? CoderResult.OVERFLOW : CoderResult.UNDERFLOW; } finally { src.position(mark); } } // Make some protected methods public for use by JISAutoDetect public CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { if (src.hasArray() && dst.hasArray()) return decodeArrayLoop(src, dst); else return decodeBufferLoop(src, dst); } public void implReset() { super.implReset(); } public CoderResult implFlush(CharBuffer out) { return super.implFlush(out); } // decode loops are not using decodeSingle/Double() for performance // reason. public char decodeSingle(int b) { return b2cSB[b]; } public char decodeDouble(int b1, int b2) { if (b2 < b2Min || b2 > b2Max) return UNMAPPABLE_DECODING; return b2c[b1][b2 - b2Min]; } } // IBM_EBCDIC_DBCS public static class Decoder_EBCDIC extends Decoder { private static final int SBCS = 0; private static final int DBCS = 1; private static final int SO = 0x0e; private static final int SI = 0x0f; private int currentState; Decoder_EBCDIC(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, b2c, b2cSB, b2Min, b2Max); } public void implReset() { currentState = SBCS; } // Check validity of dbcs ebcdic byte pair values // // First byte : 0x41 -- 0xFE // Second byte: 0x41 -- 0xFE // Doublebyte blank: 0x4040 // // The validation implementation in "old" DBCS_IBM_EBCDIC and sun.io // as // if ((b1 != 0x40 || b2 != 0x40) && // (b2 < 0x41 || b2 > 0xfe)) {...} // is not correct/complete (range check for b1) // private static boolean isDoubleByte(int b1, int b2) { return (0x41 <= b1 && b1 <= 0xfe && 0x41 <= b2 && b2 <= 0xfe) || (b1 == 0x40 && b2 == 0x40); // DBCS-HOST SPACE } protected CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { byte[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); char[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { // don't check dp/dl together here, it's possible to // decdoe a SO/SI without space in output buffer. while (sp < sl) { int b1 = sa[sp] & 0xff; int inSize = 1; if (b1 == SO) { // Shift out if (currentState != SBCS) return CoderResult.malformedForLength(1); else currentState = DBCS; } else if (b1 == SI) { if (currentState != DBCS) return CoderResult.malformedForLength(1); else currentState = SBCS; } else { char c = UNMAPPABLE_DECODING; if (currentState == SBCS) { c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) return CoderResult.unmappableForLength(1); } else { if (sl - sp < 2) return CoderResult.UNDERFLOW; int b2 = sa[sp + 1] & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { if (!isDoubleByte(b1, b2)) return CoderResult.malformedForLength(2); return CoderResult.unmappableForLength(2); } inSize++; } if (dl - dp < 1) return CoderResult.OVERFLOW; da[dp++] = c; } sp += inSize; } return CoderResult.UNDERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { int mark = src.position(); try { while (src.hasRemaining()) { int b1 = src.get() & 0xff; int inSize = 1; if (b1 == SO) { // Shift out if (currentState != SBCS) return CoderResult.malformedForLength(1); else currentState = DBCS; } else if (b1 == SI) { if (currentState != DBCS) return CoderResult.malformedForLength(1); else currentState = SBCS; } else { char c = UNMAPPABLE_DECODING; if (currentState == SBCS) { c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) return CoderResult.unmappableForLength(1); } else { if (src.remaining() < 1) return CoderResult.UNDERFLOW; int b2 = src.get()&0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { if (!isDoubleByte(b1, b2)) return CoderResult.malformedForLength(2); return CoderResult.unmappableForLength(2); } inSize++; } if (dst.remaining() < 1) return CoderResult.OVERFLOW; dst.put(c); } mark += inSize; } return CoderResult.UNDERFLOW; } finally { src.position(mark); } } } // EBCDIC_DBCS_ONLY public static class Decoder_EBCDIC_DBCSONLY extends Decoder { static final char[] b2cSB; static { b2cSB = new char[0x100]; Arrays.fill(b2cSB, UNMAPPABLE_DECODING); } Decoder_EBCDIC_DBCSONLY(Charset cs, char[][] b2c, int b2Min, int b2Max) { super(cs, 0.5f, 1.0f, b2c, b2cSB, b2Min, b2Max); } } // EUC_SIMPLE // The only thing we need to "override" is to check SS2/SS3 and // return "malformed" if found public static class Decoder_EUC_SIM extends Decoder { private final int SS2 = 0x8E; private final int SS3 = 0x8F; Decoder_EUC_SIM(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, b2c, b2cSB, b2Min, b2Max); } // No support provided for G2/G3 for SimpleEUC protected CoderResult crMalformedOrUnderFlow(int b) { if (b == SS2 || b == SS3 ) return CoderResult.malformedForLength(1); return CoderResult.UNDERFLOW; } protected CoderResult crMalformedOrUnmappable(int b) { if (b == SS2 || b == SS3 ) return CoderResult.malformedForLength(1); return CoderResult.unmappableForLength(2); } } public static class Encoder extends CharsetEncoder { final int MAX_SINGLEBYTE = 0xff; private final char[] c2b; private final char[] c2bIndex; Surrogate.Parser sgp; protected Encoder(Charset cs, char[] c2b, char[] c2bIndex) { super(cs, 2.0f, 2.0f); this.c2b = c2b; this.c2bIndex = c2bIndex; } Encoder(Charset cs, float avg, float max, byte[] repl, char[] c2b, char[] c2bIndex) { super(cs, avg, max, repl); this.c2b = c2b; this.c2bIndex = c2bIndex; } public boolean canEncode(char c) { return encodeChar(c) != UNMAPPABLE_ENCODING; } Surrogate.Parser sgp() { if (sgp == null) sgp = new Surrogate.Parser(); return sgp; } protected CoderResult encodeArrayLoop(CharBuffer src, ByteBuffer dst) { char[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); byte[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { while (sp < sl) { char c = sa[sp]; int bb = encodeChar(c); if (bb == UNMAPPABLE_ENCODING) { if (Character.isSurrogate(c)) { if (sgp().parse(c, sa, sp, sl) < 0) return sgp.error(); return sgp.unmappableResult(); } return CoderResult.unmappableForLength(1); } if (bb > MAX_SINGLEBYTE) { // DoubleByte if (dl - dp < 2) return CoderResult.OVERFLOW; da[dp++] = (byte)(bb >> 8); da[dp++] = (byte)bb; } else { // SingleByte if (dl - dp < 1) return CoderResult.OVERFLOW; da[dp++] = (byte)bb; } sp++; } return CoderResult.UNDERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult encodeBufferLoop(CharBuffer src, ByteBuffer dst) { int mark = src.position(); try { while (src.hasRemaining()) { char c = src.get(); int bb = encodeChar(c); if (bb == UNMAPPABLE_ENCODING) { if (Character.isSurrogate(c)) { if (sgp().parse(c, src) < 0) return sgp.error(); return sgp.unmappableResult(); } return CoderResult.unmappableForLength(1); } if (bb > MAX_SINGLEBYTE) { // DoubleByte if (dst.remaining() < 2) return CoderResult.OVERFLOW; dst.put((byte)(bb >> 8)); dst.put((byte)(bb)); } else { if (dst.remaining() < 1)Lines 1–500 of 752. Load more
/* * Copyright (c) 2009, 2010, Oracle and/or its affiliates. All rights reserved. * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. * * This code is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 only, as * published by the Free Software Foundation. Oracle designates this * particular file as subject to the "Classpath" exception as provided * by Oracle in the LICENSE file that accompanied this code. * * This code is distributed in the hope that it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License * version 2 for more details (a copy is included in the LICENSE file that * accompanied this code). * * You should have received a copy of the GNU General Public License version * 2 along with this work; if not, write to the Free Software Foundation, * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. * * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA * or visit www.oracle.com if you need additional information or have any * questions. */ package sun.nio.cs.ext; import java.nio.ByteBuffer; import java.nio.CharBuffer; import java.nio.charset.Charset; import java.nio.charset.CharsetDecoder; import java.nio.charset.CharsetEncoder; import java.nio.charset.CoderResult; import java.util.Arrays; import sun.nio.cs.Surrogate; import static sun.nio.cs.CharsetMapping.*; /* * Four types of "DoubleByte" charsets are implemented in this class * (1)DoubleByte * The "mostly widely used" multibyte charset, a combination of * a singlebyte character set (usually the ASCII charset) and a * doublebyte character set. The codepoint values of singlebyte * and doublebyte don't overlap. Microsoft's multibyte charsets * and IBM's "DBCS_ASCII" charsets, such as IBM1381, 942, 943, * 948, 949 and 950 are such charsets. * * (2)DoubleByte_EBCDIC * IBM EBCDIC Mix multibyte charset. Use SO and SI to shift (switch) * in and out between the singlebyte character set and doublebyte * character set. * * (3)DoubleByte_SIMPLE_EUC * It's a "simple" form of EUC encoding scheme, only have the * singlebyte character set G0 and one doublebyte character set * G1 are defined, G2 (with SS2) and G3 (with SS3) are not used. * So it is actually the same as the "typical" type (1) mentioned * above, except it return "malformed" for the SS2 and SS3 when * decoding. * * (4)DoubleByte ONLY * A "pure" doublebyte only character set. From implementation * point of view, this is the type (1) with "decodeSingle" always * returns unmappable. * * For simplicity, all implementations share the same decoding and * encoding data structure. * * Decoding: * * char[][] b2c; * char[] b2cSB; * int b2Min, b2Max * * public char decodeSingle(int b) { * return b2cSB.[b]; * } * * public char decodeDouble(int b1, int b2) { * if (b2 < b2Min || b2 > b2Max) * return UNMAPPABLE_DECODING; * return b2c[b1][b2 - b2Min]; * } * * (1)b2Min, b2Max are the corresponding min and max value of the * low-half of the double-byte. * (2)The high 8-bit/b1 of the double-byte are used to indexed into * b2c array. * * Encoding: * * char[] c2b; * char[] c2bIndex; * * public int encodeChar(char ch) { * return c2b[c2bIndex[ch >> 8] + (ch & 0xff)]; * } * */ public class DoubleByte { public final static char[] B2C_UNMAPPABLE; static { B2C_UNMAPPABLE = new char[0x100]; Arrays.fill(B2C_UNMAPPABLE, UNMAPPABLE_DECODING); } public static class Decoder extends CharsetDecoder implements DelegatableDecoder { final char[][] b2c; final char[] b2cSB; final int b2Min; final int b2Max; // for SimpleEUC override protected CoderResult crMalformedOrUnderFlow(int b) { return CoderResult.UNDERFLOW; } protected CoderResult crMalformedOrUnmappable(int b) { return CoderResult.unmappableForLength(2); } Decoder(Charset cs, float avgcpb, float maxcpb, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, avgcpb, maxcpb); this.b2c = b2c; this.b2cSB = b2cSB; this.b2Min = b2Min; this.b2Max = b2Max; } Decoder(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { this(cs, 0.5f, 1.0f, b2c, b2cSB, b2Min, b2Max); } protected CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { byte[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); char[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { while (sp < sl && dp < dl) { // inline the decodeSingle/Double() for better performance int inSize = 1; int b1 = sa[sp] & 0xff; char c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) { if (sl - sp < 2) return crMalformedOrUnderFlow(b1); int b2 = sa[sp + 1] & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { return crMalformedOrUnmappable(b1); } inSize++; } da[dp++] = c; sp += inSize; } return (sp >= sl) ? CoderResult.UNDERFLOW : CoderResult.OVERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { int mark = src.position(); try { while (src.hasRemaining() && dst.hasRemaining()) { int b1 = src.get() & 0xff; char c = b2cSB[b1]; int inSize = 1; if (c == UNMAPPABLE_DECODING) { if (src.remaining() < 1) return crMalformedOrUnderFlow(b1); int b2 = src.get() & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) return crMalformedOrUnmappable(b1); inSize++; } dst.put(c); mark += inSize; } return src.hasRemaining()? CoderResult.OVERFLOW : CoderResult.UNDERFLOW; } finally { src.position(mark); } } // Make some protected methods public for use by JISAutoDetect public CoderResult decodeLoop(ByteBuffer src, CharBuffer dst) { if (src.hasArray() && dst.hasArray()) return decodeArrayLoop(src, dst); else return decodeBufferLoop(src, dst); } public void implReset() { super.implReset(); } public CoderResult implFlush(CharBuffer out) { return super.implFlush(out); } // decode loops are not using decodeSingle/Double() for performance // reason. public char decodeSingle(int b) { return b2cSB[b]; } public char decodeDouble(int b1, int b2) { if (b2 < b2Min || b2 > b2Max) return UNMAPPABLE_DECODING; return b2c[b1][b2 - b2Min]; } } // IBM_EBCDIC_DBCS public static class Decoder_EBCDIC extends Decoder { private static final int SBCS = 0; private static final int DBCS = 1; private static final int SO = 0x0e; private static final int SI = 0x0f; private int currentState; Decoder_EBCDIC(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, b2c, b2cSB, b2Min, b2Max); } public void implReset() { currentState = SBCS; } // Check validity of dbcs ebcdic byte pair values // // First byte : 0x41 -- 0xFE // Second byte: 0x41 -- 0xFE // Doublebyte blank: 0x4040 // // The validation implementation in "old" DBCS_IBM_EBCDIC and sun.io // as // if ((b1 != 0x40 || b2 != 0x40) && // (b2 < 0x41 || b2 > 0xfe)) {...} // is not correct/complete (range check for b1) // private static boolean isDoubleByte(int b1, int b2) { return (0x41 <= b1 && b1 <= 0xfe && 0x41 <= b2 && b2 <= 0xfe) || (b1 == 0x40 && b2 == 0x40); // DBCS-HOST SPACE } protected CoderResult decodeArrayLoop(ByteBuffer src, CharBuffer dst) { byte[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); char[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { // don't check dp/dl together here, it's possible to // decdoe a SO/SI without space in output buffer. while (sp < sl) { int b1 = sa[sp] & 0xff; int inSize = 1; if (b1 == SO) { // Shift out if (currentState != SBCS) return CoderResult.malformedForLength(1); else currentState = DBCS; } else if (b1 == SI) { if (currentState != DBCS) return CoderResult.malformedForLength(1); else currentState = SBCS; } else { char c = UNMAPPABLE_DECODING; if (currentState == SBCS) { c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) return CoderResult.unmappableForLength(1); } else { if (sl - sp < 2) return CoderResult.UNDERFLOW; int b2 = sa[sp + 1] & 0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { if (!isDoubleByte(b1, b2)) return CoderResult.malformedForLength(2); return CoderResult.unmappableForLength(2); } inSize++; } if (dl - dp < 1) return CoderResult.OVERFLOW; da[dp++] = c; } sp += inSize; } return CoderResult.UNDERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult decodeBufferLoop(ByteBuffer src, CharBuffer dst) { int mark = src.position(); try { while (src.hasRemaining()) { int b1 = src.get() & 0xff; int inSize = 1; if (b1 == SO) { // Shift out if (currentState != SBCS) return CoderResult.malformedForLength(1); else currentState = DBCS; } else if (b1 == SI) { if (currentState != DBCS) return CoderResult.malformedForLength(1); else currentState = SBCS; } else { char c = UNMAPPABLE_DECODING; if (currentState == SBCS) { c = b2cSB[b1]; if (c == UNMAPPABLE_DECODING) return CoderResult.unmappableForLength(1); } else { if (src.remaining() < 1) return CoderResult.UNDERFLOW; int b2 = src.get()&0xff; if (b2 < b2Min || b2 > b2Max || (c = b2c[b1][b2 - b2Min]) == UNMAPPABLE_DECODING) { if (!isDoubleByte(b1, b2)) return CoderResult.malformedForLength(2); return CoderResult.unmappableForLength(2); } inSize++; } if (dst.remaining() < 1) return CoderResult.OVERFLOW; dst.put(c); } mark += inSize; } return CoderResult.UNDERFLOW; } finally { src.position(mark); } } } // EBCDIC_DBCS_ONLY public static class Decoder_EBCDIC_DBCSONLY extends Decoder { static final char[] b2cSB; static { b2cSB = new char[0x100]; Arrays.fill(b2cSB, UNMAPPABLE_DECODING); } Decoder_EBCDIC_DBCSONLY(Charset cs, char[][] b2c, int b2Min, int b2Max) { super(cs, 0.5f, 1.0f, b2c, b2cSB, b2Min, b2Max); } } // EUC_SIMPLE // The only thing we need to "override" is to check SS2/SS3 and // return "malformed" if found public static class Decoder_EUC_SIM extends Decoder { private final int SS2 = 0x8E; private final int SS3 = 0x8F; Decoder_EUC_SIM(Charset cs, char[][] b2c, char[] b2cSB, int b2Min, int b2Max) { super(cs, b2c, b2cSB, b2Min, b2Max); } // No support provided for G2/G3 for SimpleEUC protected CoderResult crMalformedOrUnderFlow(int b) { if (b == SS2 || b == SS3 ) return CoderResult.malformedForLength(1); return CoderResult.UNDERFLOW; } protected CoderResult crMalformedOrUnmappable(int b) { if (b == SS2 || b == SS3 ) return CoderResult.malformedForLength(1); return CoderResult.unmappableForLength(2); } } public static class Encoder extends CharsetEncoder { final int MAX_SINGLEBYTE = 0xff; private final char[] c2b; private final char[] c2bIndex; Surrogate.Parser sgp; protected Encoder(Charset cs, char[] c2b, char[] c2bIndex) { super(cs, 2.0f, 2.0f); this.c2b = c2b; this.c2bIndex = c2bIndex; } Encoder(Charset cs, float avg, float max, byte[] repl, char[] c2b, char[] c2bIndex) { super(cs, avg, max, repl); this.c2b = c2b; this.c2bIndex = c2bIndex; } public boolean canEncode(char c) { return encodeChar(c) != UNMAPPABLE_ENCODING; } Surrogate.Parser sgp() { if (sgp == null) sgp = new Surrogate.Parser(); return sgp; } protected CoderResult encodeArrayLoop(CharBuffer src, ByteBuffer dst) { char[] sa = src.array(); int sp = src.arrayOffset() + src.position(); int sl = src.arrayOffset() + src.limit(); byte[] da = dst.array(); int dp = dst.arrayOffset() + dst.position(); int dl = dst.arrayOffset() + dst.limit(); try { while (sp < sl) { char c = sa[sp]; int bb = encodeChar(c); if (bb == UNMAPPABLE_ENCODING) { if (Character.isSurrogate(c)) { if (sgp().parse(c, sa, sp, sl) < 0) return sgp.error(); return sgp.unmappableResult(); } return CoderResult.unmappableForLength(1); } if (bb > MAX_SINGLEBYTE) { // DoubleByte if (dl - dp < 2) return CoderResult.OVERFLOW; da[dp++] = (byte)(bb >> 8); da[dp++] = (byte)bb; } else { // SingleByte if (dl - dp < 1) return CoderResult.OVERFLOW; da[dp++] = (byte)bb; } sp++; } return CoderResult.UNDERFLOW; } finally { src.position(sp - src.arrayOffset()); dst.position(dp - dst.arrayOffset()); } } protected CoderResult encodeBufferLoop(CharBuffer src, ByteBuffer dst) { int mark = src.position(); try { while (src.hasRemaining()) { char c = src.get(); int bb = encodeChar(c); if (bb == UNMAPPABLE_ENCODING) { if (Character.isSurrogate(c)) { if (sgp().parse(c, src) < 0) return sgp.error(); return sgp.unmappableResult(); } return CoderResult.unmappableForLength(1); } if (bb > MAX_SINGLEBYTE) { // DoubleByte if (dst.remaining() < 2) return CoderResult.OVERFLOW; dst.put((byte)(bb >> 8)); dst.put((byte)(bb)); } else { if (dst.remaining() < 1)