blob: df3f3159dc5b82ca4fe587c3b6bd27ffd6a69559 [file] [log] [blame]
/*
* Copyright (C) 2011 The Android Open Source Project
*
* 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.
*/
package com.android.dex;
import com.android.dex.util.ByteInput;
import java.io.UTFDataFormatException;
/**
* Modified UTF-8 as described in the dex file format spec.
*/
public final class Mutf8 {
private Mutf8() {}
/**
* Decodes bytes from {@code in} into {@code out} until a delimiter 0x00 is
* encountered. Returns a new string containing the decoded characters.
*/
public static String decode(ByteInput in, char[] out) throws UTFDataFormatException {
int s = 0;
while (true) {
char a = (char) (in.readByte() & 0xff);
if (a == 0) {
return new String(out, 0, s);
}
out[s] = a;
if (a < '\u0080') {
s++;
} else if ((a & 0xe0) == 0xc0) {
int b = in.readByte() & 0xff;
if ((b & 0xC0) != 0x80) {
throw new UTFDataFormatException("bad second byte");
}
out[s++] = (char) (((a & 0x1F) << 6) | (b & 0x3F));
} else if ((a & 0xf0) == 0xe0) {
int b = in.readByte() & 0xff;
int c = in.readByte() & 0xff;
if (((b & 0xC0) != 0x80) || ((c & 0xC0) != 0x80)) {
throw new UTFDataFormatException("bad second or third byte");
}
out[s++] = (char) (((a & 0x0F) << 12) | ((b & 0x3F) << 6) | (c & 0x3F));
} else {
throw new UTFDataFormatException("bad byte");
}
}
}
/**
* Returns the number of bytes the modified UTF8 representation of 's' would take.
*/
private static long countBytes(String s, boolean shortLength) throws UTFDataFormatException {
long result = 0;
final int length = s.length();
for (int i = 0; i < length; ++i) {
char ch = s.charAt(i);
if (ch != 0 && ch <= 127) { // U+0000 uses two bytes.
++result;
} else if (ch <= 2047) {
result += 2;
} else {
result += 3;
}
if (shortLength && result > 65535) {
throw new UTFDataFormatException("String more than 65535 UTF bytes long");
}
}
return result;
}
/**
* Encodes the modified UTF-8 bytes corresponding to {@code s} into {@code
* dst}, starting at {@code offset}.
*/
public static void encode(byte[] dst, int offset, String s) {
final int length = s.length();
for (int i = 0; i < length; i++) {
char ch = s.charAt(i);
if (ch != 0 && ch <= 127) { // U+0000 uses two bytes.
dst[offset++] = (byte) ch;
} else if (ch <= 2047) {
dst[offset++] = (byte) (0xc0 | (0x1f & (ch >> 6)));
dst[offset++] = (byte) (0x80 | (0x3f & ch));
} else {
dst[offset++] = (byte) (0xe0 | (0x0f & (ch >> 12)));
dst[offset++] = (byte) (0x80 | (0x3f & (ch >> 6)));
dst[offset++] = (byte) (0x80 | (0x3f & ch));
}
}
}
/**
* Returns an array containing the <i>modified UTF-8</i> form of {@code s}.
*/
public static byte[] encode(String s) throws UTFDataFormatException {
int utfCount = (int) countBytes(s, true);
byte[] result = new byte[utfCount];
encode(result, 0, s);
return result;
}
}