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.codelibs.elasticsearch.search.suggest.phrase.DirectCandidateGenerator.java

License:Apache License

public DirectCandidateGenerator(DirectSpellChecker spellchecker, String field, SuggestMode suggestMode,
        IndexReader reader, double nonErrorLikelihood, int numCandidates, Analyzer preFilter,
        Analyzer postFilter, Terms terms) throws IOException {
    if (terms == null) {
        throw new IllegalArgumentException("generator field [" + field + "] doesn't exist");
    }//from w w  w .  j a v a2 s.  c o m
    this.spellchecker = spellchecker;
    this.field = field;
    this.numCandidates = numCandidates;
    this.suggestMode = suggestMode;
    this.reader = reader;
    final long dictSize = terms.getSumTotalTermFreq();
    this.useTotalTermFrequency = dictSize != -1;
    this.dictSize = dictSize == -1 ? reader.maxDoc() : dictSize;
    this.preFilter = preFilter;
    this.postFilter = postFilter;
    this.nonErrorLikelihood = nonErrorLikelihood;
    float thresholdFrequency = spellchecker.getThresholdFrequency();
    this.frequencyPlateau = thresholdFrequency >= 1.0f ? (int) thresholdFrequency
            : (int) (dictSize * thresholdFrequency);
    termsEnum = terms.iterator();
}

From source file:org.codelibs.elasticsearch.search.suggest.phrase.WordScorer.java

License:Apache License

public WordScorer(IndexReader reader, Terms terms, String field, double realWordLikelyHood, BytesRef separator)
        throws IOException {
    this.field = field;
    if (terms == null) {
        throw new IllegalArgumentException("Field: [" + field + "] does not exist");
    }/*from   w ww.  j  a  va  2 s  . c  o  m*/
    this.terms = terms;
    final long vocSize = terms.getSumTotalTermFreq();
    this.vocabluarySize = vocSize == -1 ? reader.maxDoc() : vocSize;
    this.useTotalTermFreq = vocSize != -1;
    this.numTerms = terms.size();
    this.termsEnum = new FreqTermsEnum(reader, field, !useTotalTermFreq, useTotalTermFreq, null,
            BigArrays.NON_RECYCLING_INSTANCE); // non recycling for now
    this.reader = reader;
    this.realWordLikelyhood = realWordLikelyHood;
    this.separator = separator;
}

From source file:org.compass.core.lucene.engine.transaction.readcommitted.BitSetByAliasFilter.java

License:Apache License

public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
    DocIdSet bitSet = deletedBitSets.get(reader);
    if (bitSet != null) {
        return bitSet;
    }//from w w w. j av  a 2s.  c  o m
    bitSet = allBitSets.get(reader);
    if (bitSet == null) {
        bitSet = new AllSetBitSet(reader.maxDoc());
        allBitSets.put(reader, bitSet);
    }
    return bitSet;
}

From source file:org.compass.core.lucene.support.ChainedFilter.java

License:Apache License

private OpenBitSetDISI initialResult(IndexReader reader, int logic, int[] index) throws IOException {
    OpenBitSetDISI result;/* w w  w.java 2s  .  com*/
    /**
     * First AND operation takes place against a completely false
     * bitset and will always return zero results.
     */
    if (logic == AND) {
        result = new OpenBitSetDISI(getDISI(chain[index[0]], reader), reader.maxDoc());
        ++index[0];
    } else if (logic == ANDNOT) {
        result = new OpenBitSetDISI(getDISI(chain[index[0]], reader), reader.maxDoc());
        result.flip(0, reader.maxDoc()); // NOTE: may set bits for deleted docs.
        ++index[0];
    } else {
        result = new OpenBitSetDISI(reader.maxDoc());
    }
    return result;
}

From source file:org.compass.core.lucene.support.ChainedFilter.java

License:Apache License

/**
 * Delegates to each filter in the chain.
 *
 * @param reader IndexReader/*from  w  ww . j  a v a2s.c o  m*/
 * @param logic  Logical operation
 * @return DocIdSet
 */
private DocIdSet getDocIdSet(IndexReader reader, int logic, int[] index) throws IOException {
    OpenBitSetDISI result = initialResult(reader, logic, index);
    for (; index[0] < chain.length; index[0]++) {
        doChain(result, logic, chain[index[0]].getDocIdSet(reader));
    }
    return finalResult(result, reader.maxDoc());
}

From source file:org.compass.core.lucene.support.ChainedFilter.java

License:Apache License

/**
 * Delegates to each filter in the chain.
 *
 * @param reader IndexReader/*from w w  w  .  j a  v  a 2s  .c  o  m*/
 * @param logic  Logical operation
 * @return DocIdSet
 */
private DocIdSet getDocIdSet(IndexReader reader, int[] logic, int[] index) throws IOException {
    if (logic.length != chain.length)
        throw new IllegalArgumentException("Invalid number of elements in logic array");

    OpenBitSetDISI result = initialResult(reader, logic[0], index);
    for (; index[0] < chain.length; index[0]++) {
        doChain(result, logic[index[0]], chain[index[0]].getDocIdSet(reader));
    }
    return finalResult(result, reader.maxDoc());
}

From source file:org.compass.core.lucene.util.ChainedFilter.java

License:Apache License

/**
 * Delegates to each filter in the chain.
 *
 * @param reader IndexReader/* www.  j a v  a 2  s  . c  o m*/
 * @param logic  Logical operation
 * @return BitSet
 */
private BitSet bits(IndexReader reader, ChainedFilterType logic) throws IOException {
    BitSet result;
    int i = 0;

    /**
     * First AND operation takes place against a completely false
     * bitset and will always return zero results. Thanks to
     * Daniel Armbrust for pointing this out and suggesting workaround.
     */
    if (logic == ChainedFilterType.AND) {
        result = (BitSet) chain[i].bits(reader).clone();
        ++i;
    } else {
        result = new BitSet(reader.maxDoc());
    }

    for (; i < chain.length; i++) {
        doChain(result, reader, logic, chain[i]);
    }
    return result;
}

From source file:org.compass.core.lucene.util.ChainedFilter.java

License:Apache License

/**
 * Delegates to each filter in the chain.
 *
 * @param reader IndexReader/*from  w ww  . j  a  v a2s.c o m*/
 * @param logic  Logical operation
 * @return BitSet
 */
private BitSet bits(IndexReader reader, ChainedFilterType[] logic) throws IOException {
    if (logic.length != chain.length)
        throw new IllegalArgumentException("Invalid number of elements in logic array");
    BitSet result;
    int i = 0;

    /**
     * First AND operation takes place against a completely false
     * bitset and will always return zero results. Thanks to
     * Daniel Armbrust for pointing this out and suggesting workaround.
     */
    if (logic[0] == ChainedFilterType.AND) {
        result = (BitSet) chain[i].bits(reader).clone();
        ++i;
    } else {
        result = new BitSet(reader.maxDoc());
    }

    for (; i < chain.length; i++) {
        doChain(result, reader, logic[i], chain[i]);
    }
    return result;
}

From source file:org.creativecommons.nutch.CCDeleteUnlicensedTool.java

License:Apache License

/** Delete pages without CC licenes. */
public int deleteUnlicensed() throws IOException {
    int deleteCount = 0;
    for (int index = 0; index < readers.length; index++) {
        IndexReader reader = readers[index];
        int readerMax = reader.maxDoc();
        for (int doc = 0; doc < readerMax; doc++) {
            if (!reader.isDeleted(doc)) {
                Document document = reader.document(doc);
                if (document.get(CCIndexingFilter.FIELD) == null) { // no CC fields
                    reader.deleteDocument(doc); // delete it
                    deleteCount++;/*from  www .  j a v a  2 s  . c om*/
                }
            }
        }
    }
    return deleteCount;
}

From source file:org.creativecommons.nutch.CCDeleteUnlicensedTool.java

License:Apache License

/** Delete duplicates in the indexes in the named directory. */
public static void main(String[] args) throws Exception {
    String usage = "CCDeleteUnlicensedTool <segmentsDir>";

    if (args.length != 1) {
        System.err.println("Usage: " + usage);
        return;/*from  w w w  .  j av  a 2s .co m*/
    }

    String segmentsDir = args[0];

    File[] directories = new File(segmentsDir).listFiles();
    Vector vReaders = new Vector();
    int maxDoc = 0;
    for (int i = 0; i < directories.length; i++) {
        File indexDone = new File(directories[i], Indexer.DONE_NAME);
        if (indexDone.exists() && indexDone.isFile()) {
            File indexDir = new File(directories[i], "index");
            IndexReader reader = IndexReader.open(indexDir);
            maxDoc += reader.maxDoc();
            vReaders.add(reader);
        }
    }

    IndexReader[] readers = new IndexReader[vReaders.size()];
    for (int i = 0; vReaders.size() > 0; i++) {
        readers[i] = (IndexReader) vReaders.remove(0);
    }

    CCDeleteUnlicensedTool dd = new CCDeleteUnlicensedTool(readers);
    int count = dd.deleteUnlicensed();
    if (LOG.isInfoEnabled()) {
        LOG.info("CC: deleted " + count + " out of " + maxDoc);
    }
    dd.close();
}