Example usage for org.apache.lucene.index LeafReader postings

Introduction

In this page you can find the example usage for org.apache.lucene.index LeafReader postings.

Prototype

public final PostingsEnum postings(Term term) throws IOException 

Source Link

Document

Returns PostingsEnum for the specified term with PostingsEnum#FREQS .

Usage

From source file:com.shaie.annots.AnnotationSearchExample.java

License:Apache License

public static void main(String[] args) throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriterConfig conf = new IndexWriterConfig(new WhitespaceAnalyzer());
    IndexWriter writer = new IndexWriter(dir, conf);

    // we need to add the annotation as a TokenStream field, therefore cannot use an Analyzer passed in the
    // IndexWriterConfig.
    Tokenizer tokenizer = new WhitespaceTokenizer();
    tokenizer.setReader(new StringReader("quick brown fox ate the blue red chicken"));
    TeeSinkTokenFilter textStream = new TeeSinkTokenFilter(tokenizer);
    TokenStream colorAnnotationStream = new AnnotatingTokenFilter(
            textStream.newSinkTokenStream(new ColorsSinkFilter()), COLOR_ANNOT_TERM);

    Document doc = new Document();
    doc.add(new TextField("text", textStream));
    doc.add(new TextField("annot", colorAnnotationStream));
    writer.addDocument(doc);//from ww  w  .  j a v a 2  s.  c  om

    writer.close();

    DirectoryReader reader = DirectoryReader.open(dir);
    LeafReader ar = reader.leaves().get(0).reader(); // we only have one segment
    printFieldTerms(ar, "text");
    System.out.println();

    final ByteArrayDataInput in = new ByteArrayDataInput();
    PostingsEnum dape = ar.postings(new Term("annot", COLOR_ANNOT_TERM));
    int docID = dape.nextDoc();
    int freq = dape.freq();
    System.out.println("Color annotation spans: doc=" + docID + ", freq=" + freq);
    for (int i = 0; i < freq; i++) {
        dape.nextPosition();
        BytesRef payload = dape.getPayload();
        in.reset(payload.bytes, payload.offset, payload.length);
        System.out.println("  start=" + in.readVInt() + ", length=" + in.readVInt());
    }

    IndexSearcher searcher = new IndexSearcher(reader);

    System.out.println("\nsearching for 'red WITHIN color':");
    Query q = new SpanWithinQuery(new SpanAnnotationTermQuery(new Term("annot", COLOR_ANNOT_TERM)),
            new SpanInclusivePositionTermQuery(new Term("text", "red")));
    TopDocs td = searcher.search(q, 10);
    System.out.println("  num results: " + td.scoreDocs.length);

    System.out.println("\nsearching for 'ate WITHIN color':");
    q = new SpanWithinQuery(new SpanAnnotationTermQuery(new Term("annot", COLOR_ANNOT_TERM)),
            new SpanInclusivePositionTermQuery(new Term("text", "ate")));
    td = searcher.search(q, 10);
    System.out.println("  num results: " + td.scoreDocs.length);

    reader.close();
    dir.close();
}

---

From source file:com.shaie.PhraseVsSpanQuery.java

License:Apache License

@SuppressWarnings("resource")
public static void main(String[] args) throws Exception {
    final Directory dir = new RAMDirectory();
    final IndexWriterConfig conf = new IndexWriterConfig(new WhitespaceAnalyzer());
    final IndexWriter writer = new IndexWriter(dir, conf);

    final Document doc = new Document();
    doc.add(new TextField("f", new TokenStream() {
        final PositionIncrementAttribute pos = addAttribute(PositionIncrementAttribute.class);
        final CharTermAttribute term = addAttribute(CharTermAttribute.class);
        boolean first = true, done = false;

        @Override/*from w ww . j  a va 2  s . c  om*/
        public boolean incrementToken() throws IOException {
            if (done) {
                return false;
            }
            if (first) {
                term.setEmpty().append("a");
                pos.setPositionIncrement(1);
                first = false;
            } else {
                term.setEmpty().append("b");
                pos.setPositionIncrement(0);
                done = true;
            }
            return true;
        }
    }));
    writer.addDocument(doc);
    writer.close();

    final DirectoryReader reader = DirectoryReader.open(dir);
    final IndexSearcher searcher = new IndexSearcher(reader);
    final LeafReader ar = reader.leaves().get(0).reader();
    final TermsEnum te = ar.terms("f").iterator();
    BytesRef scratch = new BytesRef();
    while ((scratch = te.next()) != null) {
        System.out.println(scratch.utf8ToString());
        final PostingsEnum dape = ar.postings(new Term("f", scratch.utf8ToString()));
        System.out.println("  doc=" + dape.nextDoc() + ", pos=" + dape.nextPosition());
    }

    System.out.println();

    // try a phrase query with a slop
    final PhraseQuery pqNoSlop = buildPhraseQuery(0);
    System.out.println("searching for \"a b\"; num results = " + searcher.search(pqNoSlop, 10).totalHits);

    final PhraseQuery pqSlop1 = buildPhraseQuery(1);
    System.out.println("searching for \"a b\"~1; num results = " + searcher.search(pqSlop1, 10).totalHits);

    final PhraseQuery pqSlop3 = buildPhraseQuery(3);
    System.out.println("searching for \"a b\"~3; num results = " + searcher.search(pqSlop3, 10).totalHits);

    final SpanNearQuery snqUnOrdered = new SpanNearQuery(
            new SpanQuery[] { new SpanTermQuery(new Term("f", "a")), new SpanTermQuery(new Term("f", "b")) }, 1,
            false);
    System.out.println("searching for SpanNearUnordered('a', 'b'), slop=1; num results = "
            + searcher.search(snqUnOrdered, 10).totalHits);

    final SpanNearQuery snqOrdered = new SpanNearQuery(
            new SpanQuery[] { new SpanTermQuery(new Term("f", "a")), new SpanTermQuery(new Term("f", "b")) }, 1,
            true);
    System.out.println("searching for SpanNearOrdered('a', 'b'), slop=1; num results = "
            + searcher.search(snqOrdered, 10).totalHits);

    reader.close();
}

---

From source file:io.anserini.integration.IndexerTest.java

License:Apache License

private void dumpPostings(IndexReader reader) throws IOException {
    // This is how you iterate through terms in the postings list.
    LeafReader leafReader = reader.leaves().get(0).reader();
    TermsEnum termsEnum = leafReader.terms("text").iterator();
    BytesRef bytesRef = termsEnum.next();
    while (bytesRef != null) {
        // This is the current term in the dictionary.
        String token = bytesRef.utf8ToString();
        Term term = new Term("text", token);
        System.out.print(token + " (df = " + reader.docFreq(term) + "):");

        PostingsEnum postingsEnum = leafReader.postings(term);
        while (postingsEnum.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
            System.out.print(String.format(" (%s, %s)", postingsEnum.docID(), postingsEnum.freq()));
        }//from  w  w w.ja  v  a  2s.c  om
        System.out.println("");

        bytesRef = termsEnum.next();
    }
}

---

From source file:org.hibernate.search.spatial.impl.SpatialHashQuery.java

License:LGPL

/**
 * Search the index for document having the correct spatial hash cell id at given grid level.
 *
 * @param context the {@link LeafReaderContext} for which to return the {@link DocIdSet}.
 * @return a {@link DocIdSetIterator} with the matching document ids
 */// w w  w . j a  v a2 s. co m
private DocIdSetIterator createDocIdSetIterator(LeafReaderContext context) throws IOException {
    if (spatialHashCellsIds.size() == 0) {
        return null;
    }

    final LeafReader atomicReader = context.reader();

    BitDocIdSet matchedDocumentsIds = new BitDocIdSet(new FixedBitSet(atomicReader.maxDoc()));
    boolean found = false;
    for (int i = 0; i < spatialHashCellsIds.size(); i++) {
        Term spatialHashCellTerm = new Term(fieldName, spatialHashCellsIds.get(i));
        PostingsEnum spatialHashCellsDocs = atomicReader.postings(spatialHashCellTerm);
        if (spatialHashCellsDocs != null) {
            while (true) {
                final int docId = spatialHashCellsDocs.nextDoc();
                if (docId == DocIdSetIterator.NO_MORE_DOCS) {
                    break;
                } else {
                    matchedDocumentsIds.bits().set(docId);
                    found = true;
                }
            }
        }
    }

    if (found) {
        return matchedDocumentsIds.iterator();
    } else {
        return DocIdSetIterator.empty();
    }
}

---