Example usage for org.apache.lucene.util AttributeSource hasAttribute

Introduction

In this page you can find the example usage for org.apache.lucene.util AttributeSource hasAttribute.

Prototype

public final boolean hasAttribute(Class<? extends Attribute> attClass) 

Source Link

Document

The caller must pass in a Class<?

Usage

From source file:org.apache.solr.handler.AnalysisRequestHandlerBase.java

License:Apache License

/**
 * Converts the list of Tokens to a list of NamedLists representing the tokens.
 *
 * @param tokenList  Tokens to convert/*from   ww  w  .  j  a v  a  2  s.  c om*/
 * @param context The analysis context
 *
 * @return List of NamedLists containing the relevant information taken from the tokens
 */
private List<NamedList> convertTokensToNamedLists(final List<AttributeSource> tokenList,
        AnalysisContext context) {
    final List<NamedList> tokensNamedLists = new ArrayList<NamedList>();
    final FieldType fieldType = context.getFieldType();
    final AttributeSource[] tokens = tokenList.toArray(new AttributeSource[tokenList.size()]);

    // sort the tokens by absoulte position
    ArrayUtil.timSort(tokens, new Comparator<AttributeSource>() {
        @Override
        public int compare(AttributeSource a, AttributeSource b) {
            return arrayCompare(a.getAttribute(TokenTrackingAttribute.class).getPositions(),
                    b.getAttribute(TokenTrackingAttribute.class).getPositions());
        }

        private int arrayCompare(int[] a, int[] b) {
            int p = 0;
            final int stop = Math.min(a.length, b.length);
            while (p < stop) {
                int diff = a[p] - b[p];
                if (diff != 0)
                    return diff;
                p++;
            }
            // One is a prefix of the other, or, they are equal:
            return a.length - b.length;
        }
    });

    for (int i = 0; i < tokens.length; i++) {
        AttributeSource token = tokens[i];
        final NamedList<Object> tokenNamedList = new SimpleOrderedMap<Object>();
        final TermToBytesRefAttribute termAtt = token.getAttribute(TermToBytesRefAttribute.class);
        BytesRef rawBytes = termAtt.getBytesRef();
        termAtt.fillBytesRef();
        final String text = fieldType.indexedToReadable(rawBytes, new CharsRef(rawBytes.length)).toString();
        tokenNamedList.add("text", text);

        if (token.hasAttribute(CharTermAttribute.class)) {
            final String rawText = token.getAttribute(CharTermAttribute.class).toString();
            if (!rawText.equals(text)) {
                tokenNamedList.add("raw_text", rawText);
            }
        }

        tokenNamedList.add("raw_bytes", rawBytes.toString());

        if (context.getTermsToMatch().contains(rawBytes)) {
            tokenNamedList.add("match", true);
        }

        token.reflectWith(new AttributeReflector() {
            @Override
            public void reflect(Class<? extends Attribute> attClass, String key, Object value) {
                // leave out position and bytes term
                if (TermToBytesRefAttribute.class.isAssignableFrom(attClass))
                    return;
                if (CharTermAttribute.class.isAssignableFrom(attClass))
                    return;
                if (PositionIncrementAttribute.class.isAssignableFrom(attClass))
                    return;

                String k = attClass.getName() + '#' + key;

                // map keys for "standard attributes":
                if (ATTRIBUTE_MAPPING.containsKey(k)) {
                    k = ATTRIBUTE_MAPPING.get(k);
                }

                if (value instanceof BytesRef) {
                    final BytesRef p = (BytesRef) value;
                    value = p.toString();
                }

                tokenNamedList.add(k, value);
            }
        });

        tokensNamedLists.add(tokenNamedList);
    }

    return tokensNamedLists;
}

---