-
- private static String guessEncoding(byte[] bytes) {
- if (ASSUME_SHIFT_JIS) {
- return SHIFT_JIS;
- }
- // Does it start with the UTF-8 byte order mark? then guess it's UTF-8
- if (bytes.length > 3 && bytes[0] == (byte) 0xEF && bytes[1] == (byte) 0xBB && bytes[2] == (byte) 0xBF) {
- return UTF8;
- }
- // For now, merely tries to distinguish ISO-8859-1, UTF-8 and Shift_JIS,
- // which should be by far the most common encodings. ISO-8859-1
- // should not have bytes in the 0x80 - 0x9F range, while Shift_JIS
- // uses this as a first byte of a two-byte character. If we see this
- // followed by a valid second byte in Shift_JIS, assume it is Shift_JIS.
- // If we see something else in that second byte, we'll make the risky guess
- // that it's UTF-8.
- int length = bytes.length;
- boolean canBeISO88591 = true;
- boolean lastWasPossibleDoubleByteStart = false;
- for (int i = 0; i < length; i++) {
- int value = bytes[i] & 0xFF;
- if (value >= 0x80 && value <= 0x9F && i < length - 1) {
- canBeISO88591 = false;
- // ISO-8859-1 shouldn't use this, but before we decide it is Shift_JIS,
- // just double check that it is followed by a byte that's valid in
- // the Shift_JIS encoding
- if (lastWasPossibleDoubleByteStart) {
- // If we just checked this and the last byte for being a valid double-byte
- // char, don't check starting on this byte. If the this and the last byte
- // formed a valid pair, then this shouldn't be checked to see if it starts
- // a double byte pair of course.
- lastWasPossibleDoubleByteStart = false;
- } else {
- // ... otherwise do check to see if this plus the next byte form a valid
- // double byte pair encoding a character.
- lastWasPossibleDoubleByteStart = true;
- int nextValue = bytes[i + 1] & 0xFF;
- if ((value & 0x1) == 0) {
- // if even, next value should be in [0x9F,0xFC]
- // if not, we'll guess UTF-8
- if (nextValue < 0x9F || nextValue > 0xFC) {
- return UTF8;
- }
- } else {
- // if odd, next value should be in [0x40,0x9E]
- // if not, we'll guess UTF-8
- if (nextValue < 0x40 || nextValue > 0x9E) {
- return UTF8;
- }
- }
- }
- }
+
+ private static int parseECIValue(BitSource bits) {
+ int firstByte = bits.readBits(8);
+ if ((firstByte & 0x80) == 0) {
+ // just one byte
+ return firstByte & 0x7F;
+ } else if ((firstByte & 0xC0) == 0x80) {
+ // two bytes
+ int secondByte = bits.readBits(8);
+ return ((firstByte & 0x3F) << 8) | secondByte;
+ } else if ((firstByte & 0xE0) == 0xC0) {
+ // three bytes
+ int secondThirdBytes = bits.readBits(16);
+ return ((firstByte & 0x1F) << 16) | secondThirdBytes;