Examples with UTFDataFormatException java.io.UTFDataFormatException used on opensource projects

Example 21 with UTFDataFormatException

use of java.io.UTFDataFormatException in project tinker by Tencent.

the class DexDataBuffer method readStringData.

public StringData readStringData() {
    int off = data.position();
    try {
        int expectedLength = readUleb128();
        String result = Mutf8.decode(this, new char[expectedLength]);
        if (result.length() != expectedLength) {
            throw new DexException("Declared length " + expectedLength + " doesn't match decoded length of " + result.length());
        }
        return new StringData(off, result);
    } catch (UTFDataFormatException e) {
        throw new DexException(e);
    }
}

Example 22 with UTFDataFormatException

use of java.io.UTFDataFormatException in project hadoop by apache.

the class UTF8 method readChars.

private static void readChars(DataInput in, StringBuilder buffer, int nBytes) throws UTFDataFormatException, IOException {
    DataOutputBuffer obuf = OBUF_FACTORY.get();
    obuf.reset();
    obuf.write(in, nBytes);
    byte[] bytes = obuf.getData();
    int i = 0;
    while (i < nBytes) {
        byte b = bytes[i++];
        if ((b & 0x80) == 0) {
            // 0b0xxxxxxx: 1-byte sequence
            buffer.append((char) (b & 0x7F));
        } else if ((b & 0xE0) == 0xC0) {
            if (i >= nBytes) {
                throw new UTFDataFormatException("Truncated UTF8 at " + StringUtils.byteToHexString(bytes, i - 1, 1));
            }
            // 0b110xxxxx: 2-byte sequence
            buffer.append((char) (((b & 0x1F) << 6) | (bytes[i++] & 0x3F)));
        } else if ((b & 0xF0) == 0xE0) {
            // 0b1110xxxx: 3-byte sequence
            if (i + 1 >= nBytes) {
                throw new UTFDataFormatException("Truncated UTF8 at " + StringUtils.byteToHexString(bytes, i - 1, 2));
            }
            buffer.append((char) (((b & 0x0F) << 12) | ((bytes[i++] & 0x3F) << 6) | (bytes[i++] & 0x3F)));
        } else if ((b & 0xF8) == 0xF0) {
            if (i + 2 >= nBytes) {
                throw new UTFDataFormatException("Truncated UTF8 at " + StringUtils.byteToHexString(bytes, i - 1, 3));
            }
            // 0b11110xxx: 4-byte sequence
            int codepoint = ((b & 0x07) << 18) | ((bytes[i++] & 0x3F) << 12) | ((bytes[i++] & 0x3F) << 6) | ((bytes[i++] & 0x3F));
            buffer.append(highSurrogate(codepoint)).append(lowSurrogate(codepoint));
        } else {
            // The UTF8 standard describes 5-byte and 6-byte sequences, but
            // these are no longer allowed as of 2003 (see RFC 3629)
            // Only show the next 6 bytes max in the error code - in case the
            // buffer is large, this will prevent an exceedingly large message.
            int endForError = Math.min(i + 5, nBytes);
            throw new UTFDataFormatException("Invalid UTF8 at " + StringUtils.byteToHexString(bytes, i - 1, endForError));
        }
    }
}

Example 23 with UTFDataFormatException

use of java.io.UTFDataFormatException in project robovm by robovm.

the class ModifiedUtf8 method decode.

/**
     * Decodes a byte array containing <i>modified UTF-8</i> bytes into a string.
     *
     * <p>Note that although this method decodes the (supposedly impossible) zero byte to U+0000,
     * that's what the RI does too.
     */
public static String decode(byte[] in, char[] out, int offset, int utfSize) throws UTFDataFormatException {
    int count = 0, s = 0, a;
    while (count < utfSize) {
        if ((out[s] = (char) in[offset + count++]) < '€') {
            s++;
        } else if (((a = out[s]) & 0xe0) == 0xc0) {
            if (count >= utfSize) {
                throw new UTFDataFormatException("bad second byte at " + count);
            }
            int b = in[offset + count++];
            if ((b & 0xC0) != 0x80) {
                throw new UTFDataFormatException("bad second byte at " + (count - 1));
            }
            out[s++] = (char) (((a & 0x1F) << 6) | (b & 0x3F));
        } else if ((a & 0xf0) == 0xe0) {
            if (count + 1 >= utfSize) {
                throw new UTFDataFormatException("bad third byte at " + (count + 1));
            }
            int b = in[offset + count++];
            int c = in[offset + count++];
            if (((b & 0xC0) != 0x80) || ((c & 0xC0) != 0x80)) {
                throw new UTFDataFormatException("bad second or third byte at " + (count - 2));
            }
            out[s++] = (char) (((a & 0x0F) << 12) | ((b & 0x3F) << 6) | (c & 0x3F));
        } else {
            throw new UTFDataFormatException("bad byte at " + (count - 1));
        }
    }
    return new String(out, 0, s);
}

Example 24 with UTFDataFormatException

use of java.io.UTFDataFormatException in project ignite by apache.

the class HadoopDirectDataOutput method writeUTF.

/**
 * {@inheritDoc}
 */
@Override
public void writeUTF(@NotNull String str) throws IOException {
    byte[] bytes = str.getBytes(StandardCharsets.UTF_8);
    int len = bytes.length;
    if (len > 65535)
        throw new UTFDataFormatException("UTF8 form of string is longer than 65535 bytes: " + str);
    writeShort((short) len);
    write(bytes);
}

Example 25 with UTFDataFormatException

use of java.io.UTFDataFormatException in project ignite by apache.

the class GridUnsafeDataInput method readUTFSpan.

/**
 * Reads span of UTF-encoded characters out of internal buffer
 * (starting at offset pos and ending at or before offset end),
 * consuming no more than utfLen bytes. Appends read characters to
 * sbuf. Returns the number of bytes consumed.
 *
 * @param sbuf String builder.
 * @param utfLen UTF encoding length.
 * @return Number of bytes consumed.
 * @throws IOException In case of error.
 */
@SuppressWarnings("ThrowFromFinallyBlock")
private long readUTFSpan(StringBuilder sbuf, long utfLen) throws IOException {
    int cpos = 0;
    int start = pos;
    int avail = Math.min(end - pos, CHAR_BUF_SIZE);
    int stop = pos + ((utfLen > avail) ? avail - 2 : (int) utfLen);
    boolean outOfBounds = false;
    try {
        while (pos < stop) {
            int b1 = utfBuf[pos++] & 0xFF;
            int b2, b3;
            switch(b1 >> 4) {
                case 0:
                case 1:
                case 2:
                case 3:
                case 4:
                case 5:
                case 6:
                case 7:
                    // 1 byte format: 0xxxxxxx
                    urfCBuf[cpos++] = (char) b1;
                    break;
                case 12:
                case 13:
                    // 2 byte format: 110xxxxx 10xxxxxx
                    b2 = utfBuf[pos++];
                    if ((b2 & 0xC0) != 0x80)
                        throw new UTFDataFormatException();
                    urfCBuf[cpos++] = (char) (((b1 & 0x1F) << 6) | (b2 & 0x3F));
                    break;
                case 14:
                    // 3 byte format: 1110xxxx 10xxxxxx 10xxxxxx
                    b3 = utfBuf[pos + 1];
                    b2 = utfBuf[pos];
                    pos += 2;
                    if ((b2 & 0xC0) != 0x80 || (b3 & 0xC0) != 0x80)
                        throw new UTFDataFormatException();
                    urfCBuf[cpos++] = (char) (((b1 & 0x0F) << 12) | ((b2 & 0x3F) << 6) | (b3 & 0x3F));
                    break;
                default:
                    // 10xx xxxx, 1111 xxxx
                    throw new UTFDataFormatException();
            }
        }
    } catch (ArrayIndexOutOfBoundsException ignored) {
        outOfBounds = true;
    } finally {
        if (outOfBounds || (pos - start) > utfLen) {
            pos = start + (int) utfLen;
            throw new UTFDataFormatException();
        }
    }
    sbuf.append(urfCBuf, 0, cpos);
    return pos - start;
}