Example usage for org.apache.lucene.analysis.tokenattributes CharTermAttribute setLength

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.tokenattributes CharTermAttribute setLength.

Prototype

public CharTermAttribute setLength(int length);

Source Link

Document

Set number of valid characters (length of the term) in the termBuffer array.

Usage

From source file:com.sindicetech.siren.analysis.attributes.NodeNumericTermAttributeImpl.java

License:Open Source License

private void bytesRefToChar(final CharTermAttribute termAtt) {
    final char[] buffer;
    final int prefixSize = numericTypeCharArray.length + precisionStepCharArray.length;

    switch (valueSize) {
    case 64:/*  w ww.  j  a va 2 s.co  m*/
        NumericUtils.longToPrefixCoded(value, shift, bytesRef);
        buffer = termAtt.resizeBuffer(NumericUtils.BUF_SIZE_LONG + prefixSize);
        break;

    case 32:
        NumericUtils.intToPrefixCoded((int) value, shift, bytesRef);
        buffer = termAtt.resizeBuffer(NumericUtils.BUF_SIZE_INT + prefixSize);
        break;

    default:
        // should not happen
        throw new IllegalArgumentException("valueSize must be 32 or 64");
    }

    // Prepend the numericType
    System.arraycopy(numericTypeCharArray, 0, buffer, 0, numericTypeCharArray.length);
    // Prepend the precision step
    System.arraycopy(precisionStepCharArray, 0, buffer, numericTypeCharArray.length,
            precisionStepCharArray.length);
    // append the numeric encoded value
    for (int i = bytesRef.offset; i < bytesRef.length; i++) {
        buffer[prefixSize + i] = (char) bytesRef.bytes[i];
    }
    termAtt.setLength(prefixSize + bytesRef.length);
}

---

From source file:si.virag.solr.UnicodeUtil.java

License:Apache License

public static int UTF8toUTF16(ByteBuffer utf8, int length, CharTermAttribute outputAttr) {
    char[] output = outputAttr.buffer();
    int offset = 0;
    int out_offset = 0;
    final int limit = length;
    while (offset < limit) {
        int b = utf8.get() & 0xff;

        // Check for NUL terminator
        if (b == 0x0)
            break;

        // Resize output buffer if necessary
        if (out_offset == output.length) {
            output = outputAttr.resizeBuffer(output.length * 2);
        }//from w ww .  j  av  a 2  s .c  o  m

        if (b < 0xc0) {
            assert b < 0x80;
            output[out_offset++] = (char) b;
        } else if (b < 0xe0) {
            output[out_offset++] = (char) (((b & 0x1f) << 6) + (utf8.get() & 0x3f));
        } else if (b < 0xf0) {
            output[out_offset++] = (char) (((b & 0xf) << 12) + ((utf8.get() & 0x3f) << 6)
                    + (utf8.get() & 0x3f));
            offset += 2;
        } else {
            assert b < 0xf8 : "b = 0x" + Integer.toHexString(b);
            int ch = ((b & 0x7) << 18) + ((utf8.get() & 0x3f) << 12) + ((utf8.get() & 0x3f) << 6)
                    + (utf8.get() & 0x3f);

            if (ch < UNI_MAX_BMP) {
                output[out_offset++] = (char) ch;
            } else {
                int chHalf = ch - 0x0010000;
                output[out_offset++] = (char) ((chHalf >> 10) + 0xD800);
                output[out_offset++] = (char) ((chHalf & HALF_MASK) + 0xDC00);
            }
        }
    }

    outputAttr.setLength(out_offset);
    return out_offset;
}

---