Example usage for org.apache.lucene.index IndexReader maxDoc

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexReader maxDoc.

Prototype

public abstract int maxDoc();

Source Link

Document

Returns one greater than the largest possible document number.

Usage

From source file:org.fao.geonet.kernel.search.SearchManager.java

License:Open Source License

/**
 * TODO javadoc./*from  w w  w. java  2 s .c  om*/
 *
 * @return
 * @throws Exception
 */
public Set<Integer> getDocsWithXLinks() throws Exception {
    IndexReader reader = getIndexReader(null);
    try {
        FieldSelector idXLinkSelector = new FieldSelector() {
            public final FieldSelectorResult accept(String name) {
                if (name.equals("_id") || name.equals("_hasxlinks"))
                    return FieldSelectorResult.LOAD;
                else
                    return FieldSelectorResult.NO_LOAD;
            }
        };

        Set<Integer> docs = new LinkedHashSet<Integer>();
        for (int i = 0; i < reader.maxDoc(); i++) {
            if (reader.isDeleted(i))
                continue; // FIXME: strange lucene hack: sometimes it tries to load a deleted document
            Document doc = reader.document(i, idXLinkSelector);
            String id = doc.get("_id");
            String hasxlinks = doc.get("_hasxlinks");
            if (Log.isDebugEnabled(Geonet.INDEX_ENGINE))
                Log.debug(Geonet.INDEX_ENGINE, "Got id " + id + " : '" + hasxlinks + "'");
            if (id == null) {
                Log.error(Geonet.INDEX_ENGINE, "Document with no _id field skipped! Document is " + doc);
                continue;
            }
            if (hasxlinks.trim().equals("1")) {
                docs.add(new Integer(id));
            }
        }
        return docs;
    } finally {
        releaseIndexReader(reader);
    }
}

---

From source file:org.fao.geonet.kernel.search.SearchManager.java

License:Open Source License

/**
 * TODO javadoc.//from w  w w . j a  v  a2  s. c om
 *
 * @return
 * @throws Exception
 */
public Map<String, String> getDocsChangeDate() throws Exception {
    IndexReader reader = getIndexReader(null);
    try {
        FieldSelector idChangeDateSelector = new FieldSelector() {
            public final FieldSelectorResult accept(String name) {
                if (name.equals("_id") || name.equals("_changeDate"))
                    return FieldSelectorResult.LOAD;
                else
                    return FieldSelectorResult.NO_LOAD;
            }
        };

        int capacity = (int) (reader.maxDoc() / 0.75) + 1;
        Map<String, String> docs = new HashMap<String, String>(capacity);
        for (int i = 0; i < reader.maxDoc(); i++) {
            if (reader.isDeleted(i))
                continue; // FIXME: strange lucene hack: sometimes it tries to load a deleted document
            Document doc = reader.document(i, idChangeDateSelector);
            String id = doc.get("_id");
            if (id == null) {
                Log.error(Geonet.INDEX_ENGINE, "Document with no _id field skipped! Document is " + doc);
                continue;
            }
            docs.put(id, doc.get("_changeDate"));
        }
        return docs;
    } finally {
        releaseIndexReader(reader);
    }
}

---

From source file:org.fao.geonet.kernel.search.spatial.FullScanFilter.java

License:Open Source License

public BitSet bits(final IndexReader reader) throws IOException {
    final BitSet bits = new BitSet(reader.maxDoc());

    final Set<String> matches = loadMatches();

    new IndexSearcher(reader).search(_query, new Collector() {
        private int docBase;

        // ignore scorer
        public void setScorer(Scorer scorer) {
        }//from  w  ww  .ja  va2  s .  c o  m

        // accept docs out of order (for a BitSet it doesn't matter)
        public boolean acceptsDocsOutOfOrder() {
            return true;
        }

        public final void collect(int doc) {
            Document document;
            try {
                document = reader.document(doc, _selector);
                if (matches.contains(document.get("_id"))) {
                    bits.set(docBase + doc);
                }
            } catch (Exception e) {
                throw new RuntimeException(e);
            }
        }

        public void setNextReader(IndexReader reader, int docBase) {
            this.docBase = docBase;
        }
    });
    return bits;
}

---

From source file:org.fao.geonet.kernel.search.spatial.SpatialFilter.java

License:Open Source License

public DocIdSet getDocIdSet(final IndexReader reader) throws IOException {
    final OpenBitSet bits = new OpenBitSet(reader.maxDoc());

    final Map<String, FeatureId> unrefinedSpatialMatches = unrefinedSpatialMatches();
    final Set<FeatureId> matches = new HashSet<FeatureId>();
    final Multimap<FeatureId, Integer> docIndexLookup = HashMultimap.create();

    if (unrefinedSpatialMatches.isEmpty())
        return bits;

    new IndexSearcher(reader).search(_query, new Collector() {
        private int docBase;
        private Document document;

        // ignore scorer
        public void setScorer(Scorer scorer) {
        }//from w w w  .  jav a  2 s  . c  o m

        // accept docs out of order (for a BitSet it doesn't matter)
        public boolean acceptsDocsOutOfOrder() {
            return true;
        }

        public void collect(int doc) {
            doc = doc + docBase;
            try {
                document = reader.document(doc, _selector);
                String key = document.get("_id");
                FeatureId featureId = unrefinedSpatialMatches.get(key);
                if (featureId != null) {
                    matches.add(featureId);
                    docIndexLookup.put(featureId, doc + docBase);
                }
            } catch (Exception e) {
                throw new RuntimeException(e);
            }
        }

        public void setNextReader(IndexReader reader, int docBase) {
            this.docBase = docBase;
        }
    });

    if (matches.isEmpty()) {
        return bits;
    } else {
        return applySpatialFilter(matches, docIndexLookup, bits);
    }
}

---

From source file:org.hibernate.search.filter.ChainedFilter.java

License:Open Source License

@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    int size = chainedFilters.size();
    if (size == 0) {
        throw new AssertionFailure("Chainedfilter has no filters to chain for");
    } else if (size == 1) {
        return chainedFilters.get(0).getDocIdSet(reader);
    } else {/*from ww  w.  java2  s.  c  o  m*/
        List<DocIdSet> subSets = new ArrayList<DocIdSet>(size);
        for (Filter f : chainedFilters) {
            subSets.add(f.getDocIdSet(reader));
        }
        subSets = FilterOptimizationHelper.mergeByBitAnds(subSets);
        if (subSets.size() == 1) {
            return subSets.get(0);
        }
        return new AndDocIdSet(subSets, reader.maxDoc());
    }
}

---

From source file:org.hibernate.search.filter.impl.ChainedFilter.java

License:Open Source License

@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    int size = chainedFilters.size();
    if (size == 0) {
        throw new AssertionFailure("No filters to chain");
    } else if (size == 1) {
        return chainedFilters.get(0).getDocIdSet(reader);
    } else {/*from  w w  w .  j  ava  2s .c  om*/
        List<DocIdSet> subSets = new ArrayList<DocIdSet>(size);
        for (Filter f : chainedFilters) {
            subSets.add(f.getDocIdSet(reader));
        }
        subSets = FilterOptimizationHelper.mergeByBitAnds(subSets);
        if (subSets.size() == 1) {
            return subSets.get(0);
        }
        return new AndDocIdSet(subSets, reader.maxDoc());
    }
}

---

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

License:Open Source License

/**
 * Returns Doc Ids by searching the index for document having the correct Grid Cell Id at given grid level
 *
 * @param reader reader to the index//from   w w  w  . j ava2s . c o  m
 */
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    if (gridCellsIds.size() == 0) {
        return null;
    }

    OpenBitSet matchedDocumentsIds = new OpenBitSet(reader.maxDoc());
    Boolean found = false;
    for (int i = 0; i < gridCellsIds.size(); i++) {
        Term gridCellTerm = new Term(fieldName, gridCellsIds.get(i));
        TermDocs gridCellsDocs = reader.termDocs(gridCellTerm);
        if (gridCellsDocs != null) {
            while (gridCellsDocs.next()) {
                matchedDocumentsIds.fastSet(gridCellsDocs.doc());
                found = true;
            }
        }
    }

    if (found) {
        return matchedDocumentsIds;
    } else {
        return null;
    }
}

---

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

License:Open Source License

/**
 * Returns Doc Ids by searching the index for document having the correct Qud Tree Cell Id at given qud tree level
 *
 * @param reader reader to the index//from   w  ww.  j  a v a2 s  . c o m
 */
@Override
public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    if (quadTreeCellsIds.size() == 0) {
        return null;
    }

    OpenBitSet matchedDocumentsIds = new OpenBitSet(reader.maxDoc());
    Boolean found = false;
    for (int i = 0; i < quadTreeCellsIds.size(); i++) {
        Term quadTreeCellTerm = new Term(fieldName, quadTreeCellsIds.get(i));
        TermDocs quadTreeCellsDocs = reader.termDocs(quadTreeCellTerm);
        if (quadTreeCellsDocs != null) {
            while (quadTreeCellsDocs.next()) {
                matchedDocumentsIds.fastSet(quadTreeCellsDocs.doc());
                found = true;
            }
        }
    }

    if (found) {
        return matchedDocumentsIds;
    } else {
        return null;
    }
}

---

From source file:org.hibernate.search.test.filter.BestDriversFilter.java

License:Open Source License

public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    OpenBitSet bitSet = new OpenBitSet(reader.maxDoc());
    TermDocs termDocs = reader.termDocs(new Term("score", "5"));
    while (termDocs.next()) {
        bitSet.set(termDocs.doc());/*from w  ww.j a va  2s . c  o m*/
    }
    return bitSet;
}

---

From source file:org.hippoecm.repository.FacetedNavigationEngineImpl.java

License:Apache License

private DocIdSet filterDocIdSetJackRabbitQuery(final org.apache.lucene.search.Query query,
        final IndexReader indexReader) throws IOException {
    if ((query instanceof BooleanQuery) && ((BooleanQuery) query).clauses().size() == 0) {
        // no constraints. Return null
        return null;
    }//from  www  . j  a  va  2 s.  co  m

    // TODO CACHE jackrabbit queries still need to be cached. Difficult parts are
    // 1: Jackrabbit Queries do not have hashCode or equals
    // 2: Jackrabbit Query implementations keep REFERENCES (!!) to index readers
    // 3.Jackrabbit creates a *NEW* JackrabbitIndexReader instance for *EVERY* search. Hence
    // if the reader is a JackrabbitIndexReader, the cache would be pointless.
    // Since all index readers in JR extend from FilterIndexReader, we can use
    // reader.getCoreCacheKey() : The FilterIndexReader delegates that call to the
    // wrapped index reader
    // TODO CACHE
    final OpenBitSet bits = new OpenBitSet(indexReader.maxDoc());
    long start = System.currentTimeMillis();
    new IndexSearcher(indexReader).search(query, new AbstractHitCollector() {
        @Override
        public final void collect(int doc, float score) {
            bits.set(doc); // set bit for hit
        }
    });
    log.info("Creating doc id set for Jackrabbit Query took {} ms.",
            String.valueOf(System.currentTimeMillis() - start));
    return new DocIdSetFilter(bits).getDocIdSet(indexReader);

}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• »