X-Git-Url: http://git.rot13.org/?p=zxing.git;a=blobdiff_plain;f=core%2Fsrc%2Fcom%2Fgoogle%2Fzxing%2Fqrcode%2Fdecoder%2FDecodedBitStreamParser.java;h=94325d3dbeaf550280da731cb220d1de4944991c;hp=aee1b943a41bdc71239a87ebd344c6dccd6a04bd;hb=9ba879aa77a14e6a3d42b59c670937eeb64c706e;hpb=c26bc66322aae731c3f06149fc4741db2ae97e51 diff --git a/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java b/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java index aee1b943..94325d3d 100644 --- a/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java +++ b/core/src/com/google/zxing/qrcode/decoder/DecodedBitStreamParser.java @@ -16,12 +16,14 @@ package com.google.zxing.qrcode.decoder; -import com.google.zxing.ReaderException; +import com.google.zxing.FormatException; import com.google.zxing.common.BitSource; import com.google.zxing.common.CharacterSetECI; import com.google.zxing.common.DecoderResult; +import com.google.zxing.common.StringUtils; import java.io.UnsupportedEncodingException; +import java.util.Hashtable; import java.util.Vector; /** @@ -43,23 +45,14 @@ final class DecodedBitStreamParser { 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', ' ', '$', '%', '*', '+', '-', '.', '/', ':' }; - private static final String SHIFT_JIS = "SJIS"; - private static final String EUC_JP = "EUC_JP"; - private static final boolean ASSUME_SHIFT_JIS; - private static final String UTF8 = "UTF8"; - private static final String ISO88591 = "ISO8859_1"; - - static { - String platformDefault = System.getProperty("file.encoding"); - ASSUME_SHIFT_JIS = SHIFT_JIS.equalsIgnoreCase(platformDefault) || EUC_JP.equalsIgnoreCase(platformDefault); - } private DecodedBitStreamParser() { } - static DecoderResult decode(byte[] bytes, Version version, ErrorCorrectionLevel ecLevel) throws ReaderException { + static DecoderResult decode(byte[] bytes, Version version, ErrorCorrectionLevel ecLevel, Hashtable hints) + throws FormatException { BitSource bits = new BitSource(bytes); - StringBuffer result = new StringBuffer(); + StringBuffer result = new StringBuffer(50); CharacterSetECI currentCharacterSetECI = null; boolean fc1InEffect = false; Vector byteSegments = new Vector(1); @@ -73,7 +66,7 @@ final class DecodedBitStreamParser { try { mode = Mode.forBits(bits.readBits(4)); // mode is encoded by 4 bits } catch (IllegalArgumentException iae) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } } if (!mode.equals(Mode.TERMINATOR)) { @@ -89,7 +82,7 @@ final class DecodedBitStreamParser { int value = parseECIValue(bits); currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value); if (currentCharacterSetECI == null) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } } else { // How many characters will follow, encoded in this mode? @@ -99,11 +92,11 @@ final class DecodedBitStreamParser { } else if (mode.equals(Mode.ALPHANUMERIC)) { decodeAlphanumericSegment(bits, result, count, fc1InEffect); } else if (mode.equals(Mode.BYTE)) { - decodeByteSegment(bits, result, count, currentCharacterSetECI, byteSegments); + decodeByteSegment(bits, result, count, currentCharacterSetECI, byteSegments, hints); } else if (mode.equals(Mode.KANJI)) { decodeKanjiSegment(bits, result, count); } else { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } } } @@ -114,7 +107,7 @@ final class DecodedBitStreamParser { private static void decodeKanjiSegment(BitSource bits, StringBuffer result, - int count) throws ReaderException { + int count) throws FormatException { // Each character will require 2 bytes. Read the characters as 2-byte pairs // and decode as Shift_JIS afterwards byte[] buffer = new byte[2 * count]; @@ -137,9 +130,9 @@ final class DecodedBitStreamParser { } // Shift_JIS may not be supported in some environments: try { - result.append(new String(buffer, SHIFT_JIS)); + result.append(new String(buffer, StringUtils.SHIFT_JIS)); } catch (UnsupportedEncodingException uee) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } } @@ -147,10 +140,11 @@ final class DecodedBitStreamParser { StringBuffer result, int count, CharacterSetECI currentCharacterSetECI, - Vector byteSegments) throws ReaderException { + Vector byteSegments, + Hashtable hints) throws FormatException { byte[] readBytes = new byte[count]; if (count << 3 > bits.available()) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } for (int i = 0; i < count; i++) { readBytes[i] = (byte) bits.readBits(8); @@ -162,14 +156,14 @@ final class DecodedBitStreamParser { // upon decoding. I have seen ISO-8859-1 used as well as // Shift_JIS -- without anything like an ECI designator to // give a hint. - encoding = guessEncoding(readBytes); + encoding = StringUtils.guessEncoding(readBytes, hints); } else { encoding = currentCharacterSetECI.getEncodingName(); } try { result.append(new String(readBytes, encoding)); } catch (UnsupportedEncodingException uce) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } byteSegments.addElement(readBytes); } @@ -209,13 +203,13 @@ final class DecodedBitStreamParser { private static void decodeNumericSegment(BitSource bits, StringBuffer result, - int count) throws ReaderException { + int count) throws FormatException { // Read three digits at a time while (count >= 3) { // Each 10 bits encodes three digits int threeDigitsBits = bits.readBits(10); if (threeDigitsBits >= 1000) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } result.append(ALPHANUMERIC_CHARS[threeDigitsBits / 100]); result.append(ALPHANUMERIC_CHARS[(threeDigitsBits / 10) % 10]); @@ -226,7 +220,7 @@ final class DecodedBitStreamParser { // Two digits left over to read, encoded in 7 bits int twoDigitsBits = bits.readBits(7); if (twoDigitsBits >= 100) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } result.append(ALPHANUMERIC_CHARS[twoDigitsBits / 10]); result.append(ALPHANUMERIC_CHARS[twoDigitsBits % 10]); @@ -234,102 +228,11 @@ final class DecodedBitStreamParser { // One digit left over to read int digitBits = bits.readBits(4); if (digitBits >= 10) { - throw ReaderException.getInstance(); + throw FormatException.getFormatInstance(); } result.append(ALPHANUMERIC_CHARS[digitBits]); } } - - 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 canBeShiftJIS = true; - int maybeDoubleByteCount = 0; - int maybeSingleByteKatakanaCount = 0; - boolean sawLatin1Supplement = false; - boolean lastWasPossibleDoubleByteStart = false; - for (int i = 0; i < length && (canBeISO88591 || canBeShiftJIS); i++) { - int value = bytes[i] & 0xFF; - if ((value == 0xC2 || value == 0xC3) && i < length - 1) { - // This is really a poor hack. The slightly more exotic characters people might want to put in - // a QR Code, by which I mean the Latin-1 supplement characters (e.g. u-umlaut) have encodings - // that start with 0xC2 followed by [0xA0,0xBF], or start with 0xC3 followed by [0x80,0xBF]. - int nextValue = bytes[i + 1] & 0xFF; - if (nextValue <= 0xBF && ((value == 0xC2 && nextValue >= 0xA0) || (value == 0xC3 && nextValue >= 0x80))) { - sawLatin1Supplement = true; - } - } - if (value >= 0x7F && value <= 0x9F) { - canBeISO88591 = false; - } - if (value >= 0xA1 && value <= 0xDF) { - // count the number of characters that might be a Shift_JIS single-byte Katakana character - if (!lastWasPossibleDoubleByteStart) { - maybeSingleByteKatakanaCount++; - } - } - if (!lastWasPossibleDoubleByteStart && ((value >= 0xF0 && value <= 0xFF) || value == 0x80 || value == 0xA0)) { - canBeShiftJIS = false; - } - 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. - 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 - // 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; - 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. - } - } - } else { - lastWasPossibleDoubleByteStart = false; - } - } - // Distinguishing Shift_JIS and ISO-8859-1 can be a little tough. The crude heuristic is: - // - If we saw - // - 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 && (maybeDoubleByteCount >= 3 || 20 * maybeSingleByteKatakanaCount > length)) { - return SHIFT_JIS; - } - // Otherwise, we default to ISO-8859-1 unless we know it can't be - if (!sawLatin1Supplement && canBeISO88591) { - return ISO88591; - } - // Otherwise, we take a wild guess with UTF-8 - return UTF8; - } private static int parseECIValue(BitSource bits) { int firstByte = bits.readBits(8);