package com.google.zxing.qrcode.decoder;
import com.google.zxing.ReaderException;
+import com.google.zxing.common.BitSource;
import java.io.UnsupportedEncodingException;
/**
* See ISO 18004:2006, 6.4.4 Table 5
*/
- private static final char[] ALPHANUMERIC_CHARS = new char[]{
+ private static final char[] ALPHANUMERIC_CHARS = {
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9', 'A', 'B',
'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N',
'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z',
' ', '$', '%', '*', '+', '-', '.', '/', ':'
};
private static final String SHIFT_JIS = "Shift_JIS";
+ private static final String EUC_JP = "EUC-JP";
private static final boolean ASSUME_SHIFT_JIS;
+ private static final String UTF8 = "UTF-8";
+ private static final String ISO88591 = "ISO-8859-1";
static {
String platformDefault = System.getProperty("file.encoding");
- ASSUME_SHIFT_JIS = SHIFT_JIS.equalsIgnoreCase(platformDefault) ||
- "EUC-JP".equalsIgnoreCase(platformDefault);
+ ASSUME_SHIFT_JIS = SHIFT_JIS.equalsIgnoreCase(platformDefault) || EUC_JP.equalsIgnoreCase(platformDefault);
}
private DecodedBitStreamParser() {
Mode mode;
do {
// While still another segment to read...
- mode = Mode.forBits(bits.readBits(4)); // mode is encoded by 4 bits
+ if (bits.available() == 0) {
+ // 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
+ }
if (!mode.equals(Mode.TERMINATOR)) {
- // How many characters will follow, encoded in this mode?
- int count = bits.readBits(mode.getCharacterCountBits(version));
- if (mode.equals(Mode.NUMERIC)) {
- decodeNumericSegment(bits, result, count);
- } else if (mode.equals(Mode.ALPHANUMERIC)) {
- decodeAlphanumericSegment(bits, result, count);
- } else if (mode.equals(Mode.BYTE)) {
- decodeByteSegment(bits, result, count);
- } else if (mode.equals(Mode.KANJI)) {
- decodeKanjiSegment(bits, result, count);
+ if (mode.equals(Mode.ECI)) {
+ // Count doesn't apply to ECI
+ parseECI(bits);
+ // We don't currently do anything with ECI, since there seems to be no reference
+ // defining what each value means. AIM's "Extended Channel Interpretations" does
+ // not define it. I have never observed a QR Code using it. So for now, we at least
+ // parse it but don't know how to take action on it.
} else {
- throw new ReaderException("Unsupported mode indicator");
+ // How many characters will follow, encoded in this mode?
+ int count = bits.readBits(mode.getCharacterCountBits(version));
+ if (mode.equals(Mode.NUMERIC)) {
+ decodeNumericSegment(bits, result, count);
+ } else if (mode.equals(Mode.ALPHANUMERIC)) {
+ decodeAlphanumericSegment(bits, result, count);
+ } else if (mode.equals(Mode.BYTE)) {
+ decodeByteSegment(bits, result, count);
+ } else if (mode.equals(Mode.KANJI)) {
+ decodeKanjiSegment(bits, result, count);
+ } else {
+ throw new ReaderException("Unsupported mode indicator");
+ }
}
}
} while (!mode.equals(Mode.TERMINATOR));
return result.toString();
}
+ private static int parseECI(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 secondByte = bits.readBits(8);
+ int thirdByte = bits.readBits(8);
+ return ((firstByte & 0x1F) << 16) | (secondByte << 8) | thirdByte;
+ }
+ }
+
private static void decodeKanjiSegment(BitSource bits,
StringBuffer result,
int count) throws ReaderException {
}
// Shift_JIS may not be supported in some environments:
try {
- result.append(new String(buffer, "Shift_JIS"));
+ result.append(new String(buffer, SHIFT_JIS));
} catch (UnsupportedEncodingException uee) {
- throw new ReaderException("Can't decode SHIFT_JIS string: " + uee);
+ throw new ReaderException(SHIFT_JIS + " encoding is not supported on this device");
}
}
if (ASSUME_SHIFT_JIS) {
return SHIFT_JIS;
}
- // For now, merely tries to distinguish ISO-8859-1 and 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
- int nextValue = bytes[i + 1] & 0xFF;
- if ((value & 0x1) == 0) {
- // if even,
- if (nextValue >= 0x40 && nextValue <= 0x9E) {
- return SHIFT_JIS;
- }
+ 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 {
- if (nextValue >= 0x9F && nextValue <= 0x7C) {
- return SHIFT_JIS;
+ // ... 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;
+ }
}
}
}
}
- return "ISO-8859-1";
+ return canBeISO88591 ? ISO88591 : SHIFT_JIS;
}
}