private DecodedBitStreamParser() {
}
- static DecoderResult decode(byte[] bytes, Version version) throws ReaderException {
+ static DecoderResult decode(byte[] bytes, Version version, ErrorCorrectionLevel ecLevel) throws ReaderException {
BitSource bits = new BitSource(bytes);
StringBuffer result = new StringBuffer();
CharacterSetECI currentCharacterSetECI = null;
// OK, assume we're done. Really, a TERMINATOR mode should have been recorded here
mode = Mode.TERMINATOR;
} else {
- mode = Mode.forBits(bits.readBits(4)); // mode is encoded by 4 bits
+ try {
+ mode = Mode.forBits(bits.readBits(4)); // mode is encoded by 4 bits
+ } catch (IllegalArgumentException iae) {
+ throw ReaderException.getInstance();
+ }
}
if (!mode.equals(Mode.TERMINATOR)) {
if (mode.equals(Mode.FNC1_FIRST_POSITION) || mode.equals(Mode.FNC1_SECOND_POSITION)) {
// We do little with FNC1 except alter the parsed result a bit according to the spec
fc1InEffect = true;
+ } else if (mode.equals(Mode.STRUCTURED_APPEND)) {
+ // not really supported; all we do is ignore it
+ // Read next 8 bits (symbol sequence #) and 8 bits (parity data), then continue
+ bits.readBits(16);
} else if (mode.equals(Mode.ECI)) {
// Count doesn't apply to ECI
int value = parseECIValue(bits);
- try {
- currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value);
- } catch (IllegalArgumentException iae) {
- // unsupported... just continue?
+ currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value);
+ if (currentCharacterSetECI == null) {
+ throw ReaderException.getInstance();
}
} else {
// How many characters will follow, encoded in this mode?
}
} while (!mode.equals(Mode.TERMINATOR));
- return new DecoderResult(bytes, result.toString(), byteSegments.isEmpty() ? null : byteSegments);
+ return new DecoderResult(bytes, result.toString(), byteSegments.isEmpty() ? null : byteSegments, ecLevel);
}
private static void decodeKanjiSegment(BitSource bits,
int length = bytes.length;
boolean canBeISO88591 = true;
boolean canBeShiftJIS = true;
- boolean sawDoubleByteStart = false;
+ int maybeDoubleByteCount = 0;
int maybeSingleByteKatakanaCount = 0;
boolean sawLatin1Supplement = false;
boolean lastWasPossibleDoubleByteStart = false;
if (!lastWasPossibleDoubleByteStart && ((value >= 0xF0 && value <= 0xFF) || value == 0x80 || value == 0xA0)) {
canBeShiftJIS = false;
}
- if (((value >= 0x81 && value <= 0x9F) || (value >= 0xE0 && value <= 0xEF)) && i < length - 1) {
+ if (((value >= 0x81 && value <= 0x9F) || (value >= 0xE0 && value <= 0xEF))) {
// These start double-byte characters in Shift_JIS. Let's see if it's followed by a valid
// second byte.
- sawDoubleByteStart = true;
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 this and the last byte
// ... 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 (nextValue < 0x40 || nextValue > 0xFC) {
+ if (i >= bytes.length - 1) {
canBeShiftJIS = false;
+ } else {
+ int nextValue = bytes[i + 1] & 0xFF;
+ if (nextValue < 0x40 || nextValue > 0xFC) {
+ canBeShiftJIS = false;
+ } else {
+ maybeDoubleByteCount++;
+ }
+ // There is some conflicting information out there about which bytes can follow which in
+ // double-byte Shift_JIS characters. The rule above seems to be the one that matches practice.
}
- // There is some conflicting information out there about which bytes can follow which in
- // double-byte Shift_JIS characters. The rule above seems to be the one that matches practice.
}
} else {
lastWasPossibleDoubleByteStart = false;
}
// Distinguishing Shift_JIS and ISO-8859-1 can be a little tough. The crude heuristic is:
// - If we saw
- // - at least one byte that starts a double-byte value (bytes that are rare in ISO-8859-1), or
+ // - at least three byte that starts a double-byte value (bytes that are rare in ISO-8859-1), or
// - over 5% of bytes that could be single-byte Katakana (also rare in ISO-8859-1),
// - and, saw no sequences that are invalid in Shift_JIS, then we conclude Shift_JIS
- if (canBeShiftJIS && (sawDoubleByteStart || 20 * maybeSingleByteKatakanaCount > length)) {
+ if (canBeShiftJIS && (maybeDoubleByteCount >= 3 || 20 * maybeSingleByteKatakanaCount > length)) {
return SHIFT_JIS;
}
// Otherwise, we default to ISO-8859-1 unless we know it can't be