Solr: exact phrase query with a EdgeNGramFilterFactory

Question

In Solr (3.3), is it possible to make a field letter-by-letter searchable through a EdgeNGramFilterFactory and also sensitive to phrase queries?

By example,

Answer 1

I've made a fix to EdgeNGramFilter so positions within a token are not incremented anymore:

    public class CustomEdgeNGramTokenFilterFactory extends TokenFilterFactory {
    private int maxGramSize = 0;

    private int minGramSize = 0;

    @Override
    public void init(Map args) {
        super.init(args);
        String maxArg = args.get("maxGramSize");
        maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
                : EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);

        String minArg = args.get("minGramSize");
        minGramSize = (minArg != null ? Integer.parseInt(minArg)
                : EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE);

    }

    @Override
    public CustomEdgeNGramTokenFilter create(TokenStream input) {
        return new CustomEdgeNGramTokenFilter(input, minGramSize, maxGramSize);
    }
}

public class CustomEdgeNGramTokenFilter extends TokenFilter {
    private final int minGram;
    private final int maxGram;
    private char[] curTermBuffer;
    private int curTermLength;
    private int curGramSize;

    private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
    private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
    private final PositionIncrementAttribute positionIncrementAttribute = addAttribute(PositionIncrementAttribute.class);

    /**
     * Creates EdgeNGramTokenFilter that can generate n-grams in the sizes of the given range
     *
     * @param input   {@link org.apache.lucene.analysis.TokenStream} holding the input to be tokenized
     * @param minGram the smallest n-gram to generate
     * @param maxGram the largest n-gram to generate
     */
    public CustomEdgeNGramTokenFilter(TokenStream input, int minGram, int maxGram) {
        super(input);

        if (minGram < 1) {
            throw new IllegalArgumentException("minGram must be greater than zero");
        }

        if (minGram > maxGram) {
            throw new IllegalArgumentException("minGram must not be greater than maxGram");
        }

        this.minGram = minGram;
        this.maxGram = maxGram;
    }

@Override
public final boolean incrementToken() throws IOException {
    while (true) {
        int positionIncrement = 0;
        if (curTermBuffer == null) {
            if (!input.incrementToken()) {
                return false;
            } else {
                positionIncrement = positionIncrementAttribute.getPositionIncrement();
                curTermBuffer = termAtt.buffer().clone();
                curTermLength = termAtt.length();
                curGramSize = minGram;
            }
        }
        if (curGramSize <= maxGram) {
            if (!(curGramSize > curTermLength         // if the remaining input is too short, we can't generate any n-grams
                    || curGramSize > maxGram)) {       // if we have hit the end of our n-gram size range, quit
                // grab gramSize chars from front
                int start = 0;
                int end = start + curGramSize;
                offsetAtt.setOffset(start, end);
                positionIncrementAttribute.setPositionIncrement(positionIncrement);
                termAtt.copyBuffer(curTermBuffer, start, curGramSize);
                curGramSize++;

                return true;
            }
        }
        curTermBuffer = null;
    }
}

    @Override
    public void reset() throws IOException {
        super.reset();
        curTermBuffer = null;
    }
}