/// <summary> See ISO 16022:2006, 5.2.8 and Annex C Table C.3</summary> private static void decodeEdifactSegment(BitSource bits, System.Text.StringBuilder result) { bool unlatch = false; do { // If there is only two or less bytes left then it will be encoded as ASCII if (bits.available() <= 16) { return ; } for (int i = 0; i < 4; i++) { int edifactValue = bits.readBits(6); // Check for the unlatch character if (edifactValue == 0x2B67) { // 011111 unlatch = true; // If we encounter the unlatch code then continue reading because the Codeword triple // is padded with 0's } if (!unlatch) { if ((edifactValue & 32) == 0) { // no 1 in the leading (6th) bit edifactValue |= 64; // Add a leading 01 to the 6 bit binary value } result.Append(edifactValue); } } } while (!unlatch && bits.available() > 0); }
/// <summary> See ISO 16022:2006, 5.2.6 and Annex C, Table C.2</summary> private static void decodeTextSegment(BitSource bits, System.Text.StringBuilder result) { // Three Text values are encoded in a 16-bit value as // (1600 * C1) + (40 * C2) + C3 + 1 // TODO(bbrown): The Upper Shift with Text doesn't work in the 4 value scenario all the time bool upperShift = false; int[] cValues = new int[3]; do { // If there is only one byte left then it will be encoded as ASCII if (bits.available() == 8) { return ; } int firstByte = bits.readBits(8); if (firstByte == 254) { // Unlatch codeword return ; } parseTwoBytes(firstByte, bits.readBits(8), cValues); int shift = 0; for (int i = 0; i < 3; i++) { int cValue = cValues[i]; switch (shift) { case 0: if (cValue < 3) { shift = cValue + 1; } else { if (upperShift) { result.Append((char) (TEXT_BASIC_SET_CHARS[cValue] + 128)); upperShift = false; } else { result.Append(TEXT_BASIC_SET_CHARS[cValue]); } } break; case 1: if (upperShift) { result.Append((char) (cValue + 128)); upperShift = false; } else { result.Append(cValue); } shift = 0; break; case 2: // Shift 2 for Text is the same encoding as C40 if (cValue < 27) { if (upperShift) { result.Append((char) (C40_SHIFT2_SET_CHARS[cValue] + 128)); upperShift = false; } else { result.Append(C40_SHIFT2_SET_CHARS[cValue]); } } else if (cValue == 27) { // FNC1 throw ReaderException.Instance; } else if (cValue == 30) { // Upper Shift upperShift = true; } else { throw ReaderException.Instance; } shift = 0; break; case 3: if (upperShift) { result.Append((char) (TEXT_SHIFT3_SET_CHARS[cValue] + 128)); upperShift = false; } else { result.Append(TEXT_SHIFT3_SET_CHARS[cValue]); } shift = 0; break; default: throw ReaderException.Instance; } } } while (bits.available() > 0); }
/// <summary> See ISO 16022:2006, 5.2.3 and Annex C, Table C.2</summary> private static int decodeAsciiSegment(BitSource bits, System.Text.StringBuilder result, System.Text.StringBuilder resultTrailer) { bool upperShift = false; do { int oneByte = bits.readBits(8); if (oneByte == 0) { throw ReaderException.Instance; } else if (oneByte <= 128) { // ASCII data (ASCII value + 1) oneByte = upperShift?(oneByte + 128):oneByte; upperShift = false; result.Append((char) (oneByte - 1)); return ASCII_ENCODE; } else if (oneByte == 129) { // Pad return PAD_ENCODE; } else if (oneByte <= 229) { // 2-digit data 00-99 (Numeric Value + 130) int value_Renamed = oneByte - 130; if (value_Renamed < 10) { // padd with '0' for single digit values result.Append('0'); } result.Append(value_Renamed); } else if (oneByte == 230) { // Latch to C40 encodation return C40_ENCODE; } else if (oneByte == 231) { // Latch to Base 256 encodation return BASE256_ENCODE; } else if (oneByte == 232) { // FNC1 //throw ReaderException.getInstance(); // Ignore this symbol for now } else if (oneByte == 233) { // Structured Append //throw ReaderException.getInstance(); // Ignore this symbol for now } else if (oneByte == 234) { // Reader Programming //throw ReaderException.getInstance(); // Ignore this symbol for now } else if (oneByte == 235) { // Upper Shift (shift to Extended ASCII) upperShift = true; } else if (oneByte == 236) { // 05 Macro result.Append("[)>\u001E05\u001D"); resultTrailer.Insert(0, "\u001E\u0004"); } else if (oneByte == 237) { // 06 Macro result.Append("[)>\u001E06\u001D"); resultTrailer.Insert(0, "\u001E\u0004"); } else if (oneByte == 238) { // Latch to ANSI X12 encodation return ANSIX12_ENCODE; } else if (oneByte == 239) { // Latch to Text encodation return TEXT_ENCODE; } else if (oneByte == 240) { // Latch to EDIFACT encodation return EDIFACT_ENCODE; } else if (oneByte == 241) { // ECI Character // TODO(bbrown): I think we need to support ECI //throw ReaderException.getInstance(); // Ignore this symbol for now } else if (oneByte >= 242) { // Not to be used in ASCII encodation throw ReaderException.Instance; } } while (bits.available() > 0); return ASCII_ENCODE; }
/// <summary> See ISO 16022:2006, 5.2.9 and Annex B, B.2</summary> private static void decodeBase256Segment(BitSource bits, System.Text.StringBuilder result, System.Collections.ArrayList byteSegments) { // Figure out how long the Base 256 Segment is. int d1 = bits.readBits(8); int count; if (d1 == 0) { // Read the remainder of the symbol count = bits.available() / 8; } else if (d1 < 250) { count = d1; } else { count = 250 * (d1 - 249) + bits.readBits(8); } sbyte[] bytes = new sbyte[count]; for (int i = 0; i < count; i++) { bytes[i] = unrandomize255State(bits.readBits(8), i); } byteSegments.Add(SupportClass.ToByteArray(bytes)); try { //UPGRADE_TODO: The differences in the Format of parameters for constructor 'java.lang.String.String' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'" result.Append(System.Text.Encoding.GetEncoding("ISO8859_1").GetString(SupportClass.ToByteArray(bytes))); } catch (System.IO.IOException uee) { //UPGRADE_TODO: The equivalent in .NET for method 'java.lang.Throwable.toString' may return a different value. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1043'" throw new System.SystemException("Platform does not support required encoding: " + uee); } }
internal static DecoderResult decode(sbyte[] bytes, Version version, ErrorCorrectionLevel ecLevel) { BitSource bits = new BitSource(bytes); System.Text.StringBuilder result = new System.Text.StringBuilder(50); CharacterSetECI currentCharacterSetECI = null; bool fc1InEffect = false; System.Collections.ArrayList byteSegments = System.Collections.ArrayList.Synchronized(new System.Collections.ArrayList(1)); Mode mode; do { // While still another segment to read... if (bits.available() < 4) { // OK, assume we're done. Really, a TERMINATOR mode should have been recorded here mode = Mode.TERMINATOR; } else { try { mode = Mode.forBits(bits.readBits(4)); // mode is encoded by 4 bits } catch (System.ArgumentException) { throw ReaderException.Instance; } } 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_Renamed = parseECIValue(bits); currentCharacterSetECI = CharacterSetECI.getCharacterSetECIByValue(value_Renamed); if (currentCharacterSetECI == null) { throw ReaderException.Instance; } } else { // 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, fc1InEffect); } else if (mode.Equals(Mode.BYTE)) { decodeByteSegment(bits, result, count, currentCharacterSetECI, byteSegments); } else if (mode.Equals(Mode.KANJI)) { decodeKanjiSegment(bits, result, count); } else { throw ReaderException.Instance; } } } } while (!mode.Equals(Mode.TERMINATOR)); return new DecoderResult(bytes, result.ToString(), (byteSegments.Count == 0)?null:byteSegments, ecLevel); }
/// <summary> See ISO 16022:2006, 5.2.7</summary> private static void decodeAnsiX12Segment(BitSource bits, System.Text.StringBuilder result) { // Three ANSI X12 values are encoded in a 16-bit value as // (1600 * C1) + (40 * C2) + C3 + 1 int[] cValues = new int[3]; do { // If there is only one byte left then it will be encoded as ASCII if (bits.available() == 8) { return ; } int firstByte = bits.readBits(8); if (firstByte == 254) { // Unlatch codeword return ; } parseTwoBytes(firstByte, bits.readBits(8), cValues); for (int i = 0; i < 3; i++) { int cValue = cValues[i]; if (cValue == 0) { // X12 segment terminator <CR> result.Append('\r'); } else if (cValue == 1) { // X12 segment separator * result.Append('*'); } else if (cValue == 2) { // X12 sub-element separator > result.Append('>'); } else if (cValue == 3) { // space result.Append(' '); } else if (cValue < 14) { // 0 - 9 result.Append((char) (cValue + 44)); } else if (cValue < 40) { // A - Z result.Append((char) (cValue + 51)); } else { throw ReaderException.Instance; } } } while (bits.available() > 0); }
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; } throw new System.ArgumentException("Bad ECI bits starting with byte " + firstByte); }
private static void decodeNumericSegment(BitSource bits, System.Text.StringBuilder result, int count) { // 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.Instance; } result.Append(ALPHANUMERIC_CHARS[threeDigitsBits / 100]); result.Append(ALPHANUMERIC_CHARS[(threeDigitsBits / 10) % 10]); result.Append(ALPHANUMERIC_CHARS[threeDigitsBits % 10]); count -= 3; } if (count == 2) { // Two digits left over to read, encoded in 7 bits int twoDigitsBits = bits.readBits(7); if (twoDigitsBits >= 100) { throw ReaderException.Instance; } result.Append(ALPHANUMERIC_CHARS[twoDigitsBits / 10]); result.Append(ALPHANUMERIC_CHARS[twoDigitsBits % 10]); } else if (count == 1) { // One digit left over to read int digitBits = bits.readBits(4); if (digitBits >= 10) { throw ReaderException.Instance; } result.Append(ALPHANUMERIC_CHARS[digitBits]); } }
private static void decodeKanjiSegment(BitSource bits, System.Text.StringBuilder result, int count) { // Each character will require 2 bytes. Read the characters as 2-byte pairs // and decode as Shift_JIS afterwards sbyte[] buffer = new sbyte[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] = (sbyte) (assembledTwoBytes >> 8); buffer[offset + 1] = (sbyte) assembledTwoBytes; offset += 2; count--; } // Shift_JIS may not be supported in some environments: try { //UPGRADE_TODO: The differences in the Format of parameters for constructor 'java.lang.String.String' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'" result.Append(System.Text.Encoding.GetEncoding(SHIFT_JIS).GetString(SupportClass.ToByteArray(buffer))); } catch (System.IO.IOException) { throw ReaderException.Instance; } }
private static void decodeByteSegment(BitSource bits, System.Text.StringBuilder result, int count, CharacterSetECI currentCharacterSetECI, System.Collections.ArrayList byteSegments) { sbyte[] readBytes = new sbyte[count]; if (count << 3 > bits.available()) { throw ReaderException.Instance; } for (int i = 0; i < count; i++) { readBytes[i] = (sbyte) bits.readBits(8); } System.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 = guessEncoding(readBytes); } else { encoding = currentCharacterSetECI.EncodingName; } try { //UPGRADE_TODO: The differences in the Format of parameters for constructor 'java.lang.String.String' may cause compilation errors. "ms-help://MS.VSCC.v80/dv_commoner/local/redirect.htm?index='!DefaultContextWindowIndex'&keyword='jlca1092'" result.Append(System.Text.Encoding.GetEncoding(encoding).GetString(SupportClass.ToByteArray(readBytes))); } catch (System.IO.IOException) { throw ReaderException.Instance; } byteSegments.Add(SupportClass.ToByteArray(readBytes)); }
private static void decodeAlphanumericSegment(BitSource bits, System.Text.StringBuilder result, int count, bool fc1InEffect) { // Read two characters at a time int start = result.Length; while (count > 1) { int nextTwoCharsBits = bits.readBits(11); result.Append(ALPHANUMERIC_CHARS[nextTwoCharsBits / 45]); result.Append(ALPHANUMERIC_CHARS[nextTwoCharsBits % 45]); count -= 2; } if (count == 1) { // special case: one character left result.Append(ALPHANUMERIC_CHARS[bits.readBits(6)]); } // See section 6.4.8.1, 6.4.8.2 if (fc1InEffect) { // We need to massage the result a bit if in an FNC1 mode: for (int i = start; i < result.Length; i++) { if (result[i] == '%') { if (i < result.Length - 1 && result[i + 1] == '%') { // %% is rendered as % result.Remove(i + 1, 1); } else { // In alpha mode, % should be converted to FNC1 separator 0x1D result[i] = (char) 0x1D; } } } } }