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

Example 31 with UTFDataFormatException

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

the class UTF8UtilTest method testMissingSecondByteOfTwo.

/**
 * Tries to skip characters where the data is incomplete.
 * <p>
 * In this test, the encoding states there is a character represented by
 * two bytes present. However, only one byte is provided.
 */
public void testMissingSecondByteOfTwo() throws IOException {
    // 0xdf = 11011111
    byte[] data = { 'a', (byte) 0xdf };
    InputStream is = new ByteArrayInputStream(data);
    try {
        UTF8Util.skipFully(is, 2);
        fail("Reading invalid UTF-8 should fail");
    } catch (UTFDataFormatException udfe) {
    // As expected
    }
}

Example 32 with UTFDataFormatException

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

the class UTF8UtilTest method testInvalidUTF8Encoding.

/**
 * Tries to read a stream of data where there is an invalid UTF-8 encoded
 * byte.
 */
public void testInvalidUTF8Encoding() throws IOException {
    // 0xf8 = 11111000 <-- invalid UTF-8 encoding
    byte[] data = { 'a', 'b', 'c', (byte) 0xf8, 'e', 'f' };
    InputStream is = new ByteArrayInputStream(data);
    try {
        UTF8Util.skipFully(is, 6);
        fail("Reading invalid UTF-8 should fail");
    } catch (UTFDataFormatException udfe) {
    // As expected when reading invalid data
    }
}

Example 33 with UTFDataFormatException

use of java.io.UTFDataFormatException in project openj9 by eclipse.

the class Util method convertUTF8WithBuf.

public static String convertUTF8WithBuf(byte[] buf, char[] out, int offset, int utfSize) throws UTFDataFormatException {
    int count = 0, s = 0, a;
    while (count < utfSize) {
        if ((out[s] = (char) buf[offset + count++]) < '\u0080')
            s++;
        else if (((a = out[s]) & 0xe0) == 0xc0) {
            if (count >= utfSize)
                /*[MSG "K0062", "Second byte at {0} does not match UTF8 Specification"]*/
                throw // $NON-NLS-1$
                new UTFDataFormatException(com.ibm.oti.util.Msg.getString("K0062", count));
            int b = buf[count++];
            if ((b & 0xC0) != 0x80)
                /*[MSG "K0062", "Second byte at {0} does not match UTF8 Specification"]*/
                throw // $NON-NLS-1$
                new UTFDataFormatException(com.ibm.oti.util.Msg.getString("K0062", (count - 1)));
            out[s++] = (char) (((a & 0x1F) << 6) | (b & 0x3F));
        } else if ((a & 0xf0) == 0xe0) {
            if (count + 1 >= utfSize)
                /*[MSG "K0063", "Third byte at {0} does not match UTF8 Specification"]*/
                throw // $NON-NLS-1$
                new UTFDataFormatException(com.ibm.oti.util.Msg.getString("K0063", (count + 1)));
            int b = buf[count++];
            int c = buf[count++];
            if (((b & 0xC0) != 0x80) || ((c & 0xC0) != 0x80))
                /*[MSG "K0064", "Second or third byte at {0} does not match UTF8 Specification"]*/
                throw // $NON-NLS-1$
                new UTFDataFormatException(com.ibm.oti.util.Msg.getString("K0064", (count - 2)));
            out[s++] = (char) (((a & 0x0F) << 12) | ((b & 0x3F) << 6) | (c & 0x3F));
        } else {
            // $NON-NLS-1$
            throw new UTFDataFormatException(com.ibm.oti.util.Msg.getString("K0065", (count - 1)));
        }
    }
    return new String(out, 0, s);
}

Example 34 with UTFDataFormatException

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

the class CodeByteStream method readUTF.

public char[] readUTF() throws UTFDataFormatException {
    int utflen = readByte();
    if (utflen == 255) {
        // long UTF
        int high = readByte();
        int low = readByte();
        utflen = (high << 8) + low;
    }
    char[] str = new char[utflen];
    int count = 0;
    int strlen = 0;
    while (count < utflen) {
        int c = readByte();
        int char2, char3;
        switch(c >> 4) {
            case 0:
            case 1:
            case 2:
            case 3:
            case 4:
            case 5:
            case 6:
            case 7:
                // 0xxxxxxx
                count++;
                str[strlen++] = (char) c;
                break;
            case 12:
            case 13:
                // 110x xxxx   10xx xxxx
                count += 2;
                if (count > utflen)
                    throw new UTFDataFormatException();
                char2 = readByte();
                if ((char2 & 0xC0) != 0x80)
                    throw new UTFDataFormatException();
                str[strlen++] = (char) (((c & 0x1F) << 6) | (char2 & 0x3F));
                break;
            case 14:
                // 1110 xxxx  10xx xxxx  10xx xxxx
                count += 3;
                if (count > utflen)
                    throw new UTFDataFormatException();
                char2 = readByte();
                char3 = readByte();
                if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
                    throw new UTFDataFormatException();
                str[strlen++] = (char) (((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0));
                break;
            default:
                // 10xx xxxx,  1111 xxxx
                throw new UTFDataFormatException();
        }
    }
    if (strlen < utflen)
        System.arraycopy(str, 0, str = new char[strlen], 0, strlen);
    return str;
}

Example 35 with UTFDataFormatException

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

the class Field method getUTF.

public char[] getUTF(int offset) throws UTFDataFormatException {
    int pos = this.offset + offset;
    int utflen = getUInt2(pos);
    pos += 2;
    char[] str = new char[utflen];
    int count = 0;
    int strlen = 0;
    while (count < utflen) {
        int c = buffer[pos++] & 0xFF;
        int char2, char3;
        switch(c >> 4) {
            case 0:
            case 1:
            case 2:
            case 3:
            case 4:
            case 5:
            case 6:
            case 7:
                // 0xxxxxxx
                count++;
                str[strlen++] = (char) c;
                break;
            case 12:
            case 13:
                // 110x xxxx   10xx xxxx
                count += 2;
                if (count > utflen)
                    throw new UTFDataFormatException();
                char2 = buffer[pos++] & 0xFF;
                if ((char2 & 0xC0) != 0x80)
                    throw new UTFDataFormatException();
                str[strlen++] = (char) (((c & 0x1F) << 6) | (char2 & 0x3F));
                break;
            case 14:
                // 1110 xxxx  10xx xxxx  10xx xxxx
                count += 3;
                if (count > utflen)
                    throw new UTFDataFormatException();
                char2 = buffer[pos++] & 0xFF;
                char3 = buffer[pos++] & 0xFF;
                if (((char2 & 0xC0) != 0x80) || ((char3 & 0xC0) != 0x80))
                    throw new UTFDataFormatException();
                str[strlen++] = (char) (((c & 0x0F) << 12) | ((char2 & 0x3F) << 6) | ((char3 & 0x3F) << 0));
                break;
            default:
                // 10xx xxxx,  1111 xxxx
                throw new UTFDataFormatException();
        }
    }
    if (strlen < utflen)
        System.arraycopy(str, 0, str = new char[strlen], 0, strlen);
    return str;
}