com.google.zxing.common.StringUtils Java Examples

The following examples show how to use com.google.zxing.common.StringUtils. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: DecodedBitStreamParser.java    From Telegram-FOSS with GNU General Public License v2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #2
Source File: DecodedBitStreamParser.java    From reacteu-app with MIT License 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x003BF) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException uee) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #3
Source File: DecodedBitStreamParser.java    From reacteu-app with MIT License 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException uee) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #4
Source File: DecodedBitStreamParser.java    From reacteu-app with MIT License 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count << 3 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException uce) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #5
Source File: m.java    From MiBandDecompiled with Apache License 2.0 5 votes vote down vote up
private static void a(BitSource bitsource, StringBuilder stringbuilder, int i, CharacterSetECI characterseteci, Collection collection, Map map)
{
    if (i << 3 > bitsource.available())
    {
        throw FormatException.getFormatInstance();
    }
    byte abyte0[] = new byte[i];
    for (int j = 0; j < i; j++)
    {
        abyte0[j] = (byte)bitsource.readBits(8);
    }

    String s;
    if (characterseteci == null)
    {
        s = StringUtils.guessEncoding(abyte0, map);
    } else
    {
        s = characterseteci.name();
    }
    try
    {
        stringbuilder.append(new String(abyte0, s));
    }
    catch (UnsupportedEncodingException unsupportedencodingexception)
    {
        throw FormatException.getFormatInstance();
    }
    collection.add(abyte0);
}
 
Example #6
Source File: DecodedBitStreamParser.java    From RipplePower with Apache License 2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
	// Don't crash trying to read more bits than we have available.
	if (count * 13 > bits.available()) {
		throw FormatException.getFormatInstance();
	}

	// Each character will require 2 bytes. Read the characters as 2-byte
	// pairs
	// and decode as GB2312 afterwards
	byte[] buffer = new byte[2 * count];
	int offset = 0;
	while (count > 0) {
		// Each 13 bits encodes a 2-byte character
		int twoBytes = bits.readBits(13);
		int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
		if (assembledTwoBytes < 0x003BF) {
			// In the 0xA1A1 to 0xAAFE range
			assembledTwoBytes += 0x0A1A1;
		} else {
			// In the 0xB0A1 to 0xFAFE range
			assembledTwoBytes += 0x0A6A1;
		}
		buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
		buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
		offset += 2;
		count--;
	}

	try {
		result.append(new String(buffer, StringUtils.GB2312));
	} catch (UnsupportedEncodingException ignored) {
		throw FormatException.getFormatInstance();
	}
}
 
Example #7
Source File: DecodedBitStreamParser.java    From RipplePower with Apache License 2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
	// Don't crash trying to read more bits than we have available.
	if (count * 13 > bits.available()) {
		throw FormatException.getFormatInstance();
	}

	// 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];
	int offset = 0;
	while (count > 0) {
		// Each 13 bits encodes a 2-byte character
		int twoBytes = bits.readBits(13);
		int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
		if (assembledTwoBytes < 0x01F00) {
			// In the 0x8140 to 0x9FFC range
			assembledTwoBytes += 0x08140;
		} else {
			// In the 0xE040 to 0xEBBF range
			assembledTwoBytes += 0x0C140;
		}
		buffer[offset] = (byte) (assembledTwoBytes >> 8);
		buffer[offset + 1] = (byte) assembledTwoBytes;
		offset += 2;
		count--;
	}
	// Shift_JIS may not be supported in some environments:
	try {
		result.append(new String(buffer, StringUtils.SHIFT_JIS));
	} catch (UnsupportedEncodingException ignored) {
		throw FormatException.getFormatInstance();
	}
}
 
Example #8
Source File: DecodedBitStreamParser.java    From RipplePower with Apache License 2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits, StringBuilder result, int count,
		CharacterSetECI currentCharacterSetECI, Collection<byte[]> byteSegments, Map<DecodeHintType, ?> hints)
		throws FormatException {
	// Don't crash trying to read more bits than we have available.
	if (8 * count > bits.available()) {
		throw FormatException.getFormatInstance();
	}

	byte[] readBytes = new byte[count];
	for (int i = 0; i < count; i++) {
		readBytes[i] = (byte) bits.readBits(8);
	}
	String encoding;
	if (currentCharacterSetECI == null) {
		// The spec isn't clear on this mode; see
		// section 6.4.5: t does not say which encoding to assuming
		// 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 = StringUtils.guessEncoding(readBytes, hints);
	} else {
		encoding = currentCharacterSetECI.name();
	}
	try {
		result.append(new String(readBytes, encoding));
	} catch (UnsupportedEncodingException ignored) {
		throw FormatException.getFormatInstance();
	}
	byteSegments.add(readBytes);
}
 
Example #9
Source File: DecodedBitStreamParser.java    From Telegram-FOSS with GNU General Public License v2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x00A00) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #10
Source File: DecodedBitStreamParser.java    From Telegram-FOSS with GNU General Public License v2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #11
Source File: DecodedBitStreamParser.java    From barcodescanner-lib-aar with MIT License 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #12
Source File: DecodedBitStreamParser.java    From barterli_android with Apache License 2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count * 13 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    // Each character will require 2 bytes. Read the characters as 2-byte
    // pairs
    // and decode as GB2312 afterwards
    byte[] buffer = new byte[2 * count];
    int offset = 0;
    while (count > 0) {
        // Each 13 bits encodes a 2-byte character
        int twoBytes = bits.readBits(13);
        int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
        if (assembledTwoBytes < 0x003BF) {
            // In the 0xA1A1 to 0xAAFE range
            assembledTwoBytes += 0x0A1A1;
        } else {
            // In the 0xB0A1 to 0xFAFE range
            assembledTwoBytes += 0x0A6A1;
        }
        buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
        buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
        offset += 2;
        count--;
    }

    try {
        result.append(new String(buffer, StringUtils.GB2312));
    } catch (UnsupportedEncodingException uee) {
        throw FormatException.getFormatInstance();
    }
}
 
Example #13
Source File: DecodedBitStreamParser.java    From barterli_android with Apache License 2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count * 13 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    // 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];
    int offset = 0;
    while (count > 0) {
        // Each 13 bits encodes a 2-byte character
        int twoBytes = bits.readBits(13);
        int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
        if (assembledTwoBytes < 0x01F00) {
            // In the 0x8140 to 0x9FFC range
            assembledTwoBytes += 0x08140;
        } else {
            // In the 0xE040 to 0xEBBF range
            assembledTwoBytes += 0x0C140;
        }
        buffer[offset] = (byte) (assembledTwoBytes >> 8);
        buffer[offset + 1] = (byte) assembledTwoBytes;
        offset += 2;
        count--;
    }
    // Shift_JIS may not be supported in some environments:
    try {
        result.append(new String(buffer, StringUtils.SHIFT_JIS));
    } catch (UnsupportedEncodingException uee) {
        throw FormatException.getFormatInstance();
    }
}
 
Example #14
Source File: DecodedBitStreamParser.java    From barterli_android with Apache License 2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits, StringBuilder result, int count, CharacterSetECI currentCharacterSetECI,
        Collection<byte[]> byteSegments, Map<DecodeHintType, ?> hints) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count << 3 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    byte[] readBytes = new byte[count];
    for (int i = 0; i < count; i++) {
        readBytes[i] = (byte) bits.readBits(8);
    }
    String encoding;
    if (currentCharacterSetECI == null) {
        // The spec isn't clear on this mode; see
        // section 6.4.5: t does not say which encoding to assuming
        // 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 = StringUtils.guessEncoding(readBytes, hints);
    } else {
        encoding = currentCharacterSetECI.name();
    }
    try {
        result.append(new String(readBytes, encoding));
    } catch (UnsupportedEncodingException uce) {
        throw FormatException.getFormatInstance();
    }
    byteSegments.add(readBytes);
}
 
Example #15
Source File: DecodedBitStreamParser.java    From android-quick-response-code with Apache License 2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count * 13 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    // Each character will require 2 bytes. Read the characters as 2-byte
    // pairs
    // and decode as GB2312 afterwards
    byte[] buffer = new byte[2 * count];
    int offset = 0;
    while (count > 0) {
        // Each 13 bits encodes a 2-byte character
        int twoBytes = bits.readBits(13);
        int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
        if (assembledTwoBytes < 0x003BF) {
            // In the 0xA1A1 to 0xAAFE range
            assembledTwoBytes += 0x0A1A1;
        } else {
            // In the 0xB0A1 to 0xFAFE range
            assembledTwoBytes += 0x0A6A1;
        }
        buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
        buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
        offset += 2;
        count--;
    }

    try {
        result.append(new String(buffer, StringUtils.GB2312));
    } catch (UnsupportedEncodingException uee) {
        throw FormatException.getFormatInstance();
    }
}
 
Example #16
Source File: DecodedBitStreamParser.java    From android-quick-response-code with Apache License 2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits, StringBuilder result, int count) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count * 13 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    // 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];
    int offset = 0;
    while (count > 0) {
        // Each 13 bits encodes a 2-byte character
        int twoBytes = bits.readBits(13);
        int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
        if (assembledTwoBytes < 0x01F00) {
            // In the 0x8140 to 0x9FFC range
            assembledTwoBytes += 0x08140;
        } else {
            // In the 0xE040 to 0xEBBF range
            assembledTwoBytes += 0x0C140;
        }
        buffer[offset] = (byte) (assembledTwoBytes >> 8);
        buffer[offset + 1] = (byte) assembledTwoBytes;
        offset += 2;
        count--;
    }
    // Shift_JIS may not be supported in some environments:
    try {
        result.append(new String(buffer, StringUtils.SHIFT_JIS));
    } catch (UnsupportedEncodingException uee) {
        throw FormatException.getFormatInstance();
    }
}
 
Example #17
Source File: DecodedBitStreamParser.java    From android-quick-response-code with Apache License 2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits, StringBuilder result, int count, CharacterSetECI currentCharacterSetECI,
        Collection<byte[]> byteSegments, Map<DecodeHintType, ?> hints) throws FormatException {
    // Don't crash trying to read more bits than we have available.
    if (count << 3 > bits.available()) {
        throw FormatException.getFormatInstance();
    }

    byte[] readBytes = new byte[count];
    for (int i = 0; i < count; i++) {
        readBytes[i] = (byte) bits.readBits(8);
    }
    String encoding;
    if (currentCharacterSetECI == null) {
        // The spec isn't clear on this mode; see
        // section 6.4.5: t does not say which encoding to assuming
        // 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 = StringUtils.guessEncoding(readBytes, hints);
    } else {
        encoding = currentCharacterSetECI.name();
    }
    try {
        result.append(new String(readBytes, encoding));
    } catch (UnsupportedEncodingException uce) {
        throw FormatException.getFormatInstance();
    }
    byteSegments.add(readBytes);
}
 
Example #18
Source File: DecodedBitStreamParser.java    From Telegram with GNU General Public License v2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x00A00) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #19
Source File: DecodedBitStreamParser.java    From Telegram with GNU General Public License v2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #20
Source File: DecodedBitStreamParser.java    From Telegram with GNU General Public License v2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #21
Source File: DecodedBitStreamParser.java    From ZXing-Orient with Apache License 2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #22
Source File: DecodedBitStreamParser.java    From ScreenCapture with MIT License 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #23
Source File: DecodedBitStreamParser.java    From ScreenCapture with MIT License 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #24
Source File: DecodedBitStreamParser.java    From Tesseract-OCR-Scanner with Apache License 2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x003BF) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #25
Source File: DecodedBitStreamParser.java    From Tesseract-OCR-Scanner with Apache License 2.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #26
Source File: DecodedBitStreamParser.java    From Tesseract-OCR-Scanner with Apache License 2.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #27
Source File: DecodedBitStreamParser.java    From QrCodeScanner with GNU General Public License v3.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x003BF) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #28
Source File: DecodedBitStreamParser.java    From QrCodeScanner with GNU General Public License v3.0 5 votes vote down vote up
private static void decodeKanjiSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // 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];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x0C0) << 8) | (twoBytes % 0x0C0);
    if (assembledTwoBytes < 0x01F00) {
      // In the 0x8140 to 0x9FFC range
      assembledTwoBytes += 0x08140;
    } else {
      // In the 0xE040 to 0xEBBF range
      assembledTwoBytes += 0x0C140;
    }
    buffer[offset] = (byte) (assembledTwoBytes >> 8);
    buffer[offset + 1] = (byte) assembledTwoBytes;
    offset += 2;
    count--;
  }
  // Shift_JIS may not be supported in some environments:
  try {
    result.append(new String(buffer, StringUtils.SHIFT_JIS));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}
 
Example #29
Source File: DecodedBitStreamParser.java    From QrCodeScanner with GNU General Public License v3.0 5 votes vote down vote up
private static void decodeByteSegment(BitSource bits,
                                      StringBuilder result,
                                      int count,
                                      CharacterSetECI currentCharacterSetECI,
                                      Collection<byte[]> byteSegments,
                                      Map<DecodeHintType,?> hints) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (8 * count > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  byte[] readBytes = new byte[count];
  for (int i = 0; i < count; i++) {
    readBytes[i] = (byte) bits.readBits(8);
  }
  String encoding;
  if (currentCharacterSetECI == null) {
    // The spec isn't clear on this mode; see
    // section 6.4.5: t does not say which encoding to assuming
    // 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 = StringUtils.guessEncoding(readBytes, hints);
  } else {
    encoding = currentCharacterSetECI.name();
  }
  try {
    result.append(new String(readBytes, encoding));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
  byteSegments.add(readBytes);
}
 
Example #30
Source File: DecodedBitStreamParser.java    From ZXing-Orient with Apache License 2.0 5 votes vote down vote up
/**
 * See specification GBT 18284-2000
 */
private static void decodeHanziSegment(BitSource bits,
                                       StringBuilder result,
                                       int count) throws FormatException {
  // Don't crash trying to read more bits than we have available.
  if (count * 13 > bits.available()) {
    throw FormatException.getFormatInstance();
  }

  // Each character will require 2 bytes. Read the characters as 2-byte pairs
  // and decode as GB2312 afterwards
  byte[] buffer = new byte[2 * count];
  int offset = 0;
  while (count > 0) {
    // Each 13 bits encodes a 2-byte character
    int twoBytes = bits.readBits(13);
    int assembledTwoBytes = ((twoBytes / 0x060) << 8) | (twoBytes % 0x060);
    if (assembledTwoBytes < 0x003BF) {
      // In the 0xA1A1 to 0xAAFE range
      assembledTwoBytes += 0x0A1A1;
    } else {
      // In the 0xB0A1 to 0xFAFE range
      assembledTwoBytes += 0x0A6A1;
    }
    buffer[offset] = (byte) ((assembledTwoBytes >> 8) & 0xFF);
    buffer[offset + 1] = (byte) (assembledTwoBytes & 0xFF);
    offset += 2;
    count--;
  }

  try {
    result.append(new String(buffer, StringUtils.GB2312));
  } catch (UnsupportedEncodingException ignored) {
    throw FormatException.getFormatInstance();
  }
}