Example usage for org.apache.lucene.search DocIdSetIterator nextDoc

Introduction

In this page you can find the example usage for org.apache.lucene.search DocIdSetIterator nextDoc.

Prototype

public abstract int nextDoc() throws IOException;

Source Link

Document

Advances to the next document in the set and returns the doc it is currently on, or #NO_MORE_DOCS if there are no more docs in the set.
NOTE: after the iterator has exhausted you should not call this method, as it may result in unpredicted behavior.

Usage

From source file:proj.zoie.impl.indexing.internal.LuceneIndexDataLoader.java

License:Apache License

protected final int purgeDocuments() {
    synchronized (_optimizeMonitor) {
        if (_purgeFilter != null) {
            BaseSearchIndex<R> idx = getSearchIndex();
            IndexReader writeReader = null;

            log.info("purging docs started...");
            int count = 0;
            long start = System.currentTimeMillis();

            ZoieIndexReader<R> reader = null;
            try {
                synchronized (idx) {

                    idx.refresh(false);//from  w ww.j a  v  a2s.  c  o  m

                    reader = idx.openIndexReader();
                    if (reader != null)
                        reader.incZoieRef();
                }

                if (reader != null) {
                    writeReader = idx.openIndexReaderForDelete();
                    if (writeReader != null) {
                        DocIdSetIterator iter = _purgeFilter.getDocIdSet(reader).iterator();

                        int doc;
                        while ((doc = iter.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
                            count++;
                            writeReader.deleteDocument(doc);
                        }
                    }
                }
            } catch (Throwable th) {
                log.error("problem creating purge filter: " + th.getMessage(), th);
            } finally {
                if (reader != null) {
                    reader.decZoieRef();
                }
                if (writeReader != null) {
                    try {
                        writeReader.close();
                    } catch (IOException ioe) {
                        ZoieHealth.setFatal();
                        log.error(ioe.getMessage(), ioe);
                    }
                }
            }

            long end = System.currentTimeMillis();
            log.info("purging docs completed in " + (end - start) + "ms");
            log.info("total docs purged: " + count);
            return count;
        }
        return 0;
    }
}

From source file:tech.beshu.ror.es.security.DocumentFilterReader.java

License:Open Source License

private DocumentFilterReader(LeafReader reader, Query query) throws IOException {
    super(reader);
    final IndexSearcher searcher = new IndexSearcher(this);
    searcher.setQueryCache(null);// w  w  w .j  av a  2 s .  c o  m
    final boolean needsScores = false;
    final Weight preserveWeight = searcher.createWeight(query, needsScores, 0);

    final int maxDoc = this.in.maxDoc();
    final FixedBitSet bits = new FixedBitSet(maxDoc);
    final Scorer preserveScorer = preserveWeight.scorer(this.getContext());
    if (preserveScorer != null) {
        bits.or(preserveScorer.iterator());
    }

    if (in.hasDeletions()) {
        final Bits oldLiveDocs = in.getLiveDocs();
        assert oldLiveDocs != null;
        final DocIdSetIterator it = new BitSetIterator(bits, 0L);
        for (int i = it.nextDoc(); i != DocIdSetIterator.NO_MORE_DOCS; i = it.nextDoc()) {
            if (!oldLiveDocs.get(i)) {
                bits.clear(i);
            }
        }
    }

    this.liveDocs = bits;
    this.numDocs = bits.cardinality();
}

From source file:tw.com.kyle.luminance.corpus.compute.CollocateFromIndex.java

private List<Integer> get_discourse_doc_id() throws IOException {
    Query cq = new TermQuery(new Term("class", "discourse"));
    IndexSearcher searcher = new IndexSearcher(reader);
    Weight w = cq.createWeight(searcher, false);
    List<Integer> docid_list = new ArrayList<>();
    for (LeafReaderContext ctx : reader.leaves()) {
        Scorer scorer = w.scorer(ctx);//from  www . java2  s  .co  m
        DocIdSetIterator doc_it = scorer.iterator();
        int nxtDoc = 0;
        while ((nxtDoc = doc_it.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
            int doc_freq = scorer.freq();
            docid_list.add(nxtDoc);
        }
    }
    return docid_list;
}

From source file:tw.com.kyle.luminance.corpus.compute.ExpNetwork.java

private int get_common_doc_count(String node_x, String node_y, String doc_type, String start_date_str,
        String end_date_str) throws IOException {
    int n_doc = 0;
    Query query_a = build_phrase_query(node_x);
    Query query_b = build_phrase_query(node_y);
    Query query_c = new TermQuery(new Term("class", doc_type));

    BooleanQuery.Builder bquery = new BooleanQuery.Builder();
    bquery.add(query_a, BooleanClause.Occur.MUST);
    bquery.add(query_b, BooleanClause.Occur.MUST);
    bquery.add(query_c, BooleanClause.Occur.MUST);

    Weight w = bquery.build().createWeight(searcher, false);

    for (LeafReaderContext ctx : reader.leaves()) {
        SortedDocValues sorted_dv = ctx.reader().getSortedDocValues("timestamp");
        Scorer scorer = w.scorer(ctx);/*from  w w  w . j av a  2  s .c om*/
        if (scorer == null) {
            continue;
        }
        DocIdSetIterator doc_it = scorer.iterator();
        int nxtDoc = 0;
        while ((nxtDoc = doc_it.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
            String timestamp = new String(sorted_dv.get(nxtDoc).bytes, StandardCharsets.UTF_8);
            //! note that both timestamp, (start|end)_date_str are both
            //! formatted so can be ordered lexically
            int dbg1 = timestamp.compareTo(start_date_str);
            int dbg2 = timestamp.compareTo(end_date_str);
            if (timestamp.compareTo(start_date_str) >= 0 && timestamp.compareTo(end_date_str) < 0) {
                n_doc += 1;
            }
        }
    }
    return n_doc;
}

From source file:tw.com.kyle.luminance.corpus.compute.ExpNetwork.java

private int get_token_count_timerange(String node_x, String start_date_str, String end_date_str)
        throws IOException {
    int n_doc = 0;
    Query query_a = build_phrase_query(node_x);
    Weight w = query_a.createWeight(searcher, false);

    for (LeafReaderContext ctx : reader.leaves()) {
        SortedDocValues sorted_dv = ctx.reader().getSortedDocValues("timestamp");
        Scorer scorer = w.scorer(ctx);// ww  w . j  av a2s.co m
        if (scorer == null) {
            continue;
        }
        DocIdSetIterator doc_it = scorer.iterator();
        int nxtDoc = 0;
        while ((nxtDoc = doc_it.nextDoc()) != DocIdSetIterator.NO_MORE_DOCS) {
            String timestamp = new String(sorted_dv.get(nxtDoc).bytes, StandardCharsets.UTF_8);
            //! note that both timestamp, (start|end)_date_str are both
            //! formatted so can be ordered lexically
            int dbg1 = timestamp.compareTo(start_date_str);
            int dbg2 = timestamp.compareTo(end_date_str);
            if (timestamp.compareTo(start_date_str) >= 0 && timestamp.compareTo(end_date_str) < 0) {
                n_doc += 1;
            }
        }
    }
    return n_doc;
}