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

Introduction

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

Prototype

public final List<LeafReaderContext> leaves() 

Source Link

Document

Returns the reader's leaves, or itself if this reader is atomic.

Usage

From source file:org.exist.indexing.lucene.XMLToQuery.java

License:Open Source License

private Term[] expandTerms(String field, String queryStr) throws XPathException {
    List<Term> termList = new ArrayList<>(8);
    Automaton automaton = WildcardQuery.toAutomaton(new Term(field, queryStr));
    CompiledAutomaton compiled = new CompiledAutomaton(automaton);
    IndexReader reader = null;
    try {/* ww  w.  j  a v  a 2  s .c  o m*/
        reader = index.getReader();

        for (AtomicReaderContext atomic : reader.leaves()) {
            Terms terms = atomic.reader().terms(field);
            if (terms != null) {
                TermsEnum termsEnum = compiled.getTermsEnum(terms);
                BytesRef data = termsEnum.next();
                while (data != null) {
                    String term = data.utf8ToString();
                    termList.add(new Term(field, term));
                    data = termsEnum.next();
                }
            }
        }
    } catch (IOException e) {
        throw new XPathException("Lucene index error while creating query: " + e.getMessage(), e);
    } finally {
        index.releaseReader(reader);
    }
    Term[] matchingTerms = new Term[termList.size()];
    return termList.toArray(matchingTerms);
}

---

From source file:org.exist.indexing.range.RangeIndexWorker.java

License:Open Source License

private void scan(DocumentSet docs, NodeSet nodes, String start, String end, long max,
        TreeMap<String, Occurrences> map, IndexReader reader, String field) throws IOException {
    List<AtomicReaderContext> leaves = reader.leaves();
    for (AtomicReaderContext context : leaves) {
        NumericDocValues docIdValues = context.reader().getNumericDocValues(FIELD_DOC_ID);
        BinaryDocValues nodeIdValues = context.reader().getBinaryDocValues(FIELD_NODE_ID);
        Bits liveDocs = context.reader().getLiveDocs();
        Terms terms = context.reader().terms(field);
        if (terms == null)
            continue;
        TermsEnum termsIter = terms.iterator(null);
        if (termsIter.next() == null) {
            continue;
        }//from ww w.j av  a 2  s .  c o m
        do {
            if (map.size() >= max) {
                break;
            }
            BytesRef ref = termsIter.term();
            String term = ref.utf8ToString();
            boolean include = true;
            if (end != null) {
                if (term.compareTo(end) > 0)
                    include = false;
            } else if (start != null && !term.startsWith(start))
                include = false;
            if (include) {
                DocsEnum docsEnum = termsIter.docs(null, null);
                while (docsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
                    if (liveDocs != null && !liveDocs.get(docsEnum.docID())) {
                        continue;
                    }
                    int docId = (int) docIdValues.get(docsEnum.docID());
                    DocumentImpl storedDocument = docs.getDoc(docId);
                    if (storedDocument == null)
                        continue;
                    NodeId nodeId = null;
                    if (nodes != null) {
                        BytesRef nodeIdRef = new BytesRef(buf);
                        nodeIdValues.get(docsEnum.docID(), nodeIdRef);
                        int units = ByteConversion.byteToShort(nodeIdRef.bytes, nodeIdRef.offset);
                        nodeId = index.getBrokerPool().getNodeFactory().createFromData(units, nodeIdRef.bytes,
                                nodeIdRef.offset + 2);
                    }
                    if (nodeId == null || nodes.get(storedDocument, nodeId) != null) {
                        Occurrences oc = map.get(term);
                        if (oc == null) {
                            oc = new Occurrences(term);
                            map.put(term, oc);
                        }
                        oc.addDocument(storedDocument);
                        oc.addOccurrences(docsEnum.freq());
                    }
                }
            }
        } while (termsIter.next() != null);
    }
}

---

From source file:org.hibernate.search.test.directoryProvider.FSDirectoryTest.java

License:LGPL

/**
 * Project a field as a String from a Lucene Document matching the provided term.
 * The method asserts that one match is found, and no more.
 *//* w  w w  .  ja  va  2 s  .  com*/
private String projectSingleField(IndexReader reader, String fieldName, Term term) throws IOException {
    String projection = null;
    for (LeafReaderContext leaf : reader.leaves()) {
        final LeafReader atomicReader = leaf.reader();
        final DocsEnum termDocsEnum = atomicReader.termDocsEnum(term);
        while (termDocsEnum.nextDoc() != DocsEnum.NO_MORE_DOCS) {
            final int docID = termDocsEnum.docID();
            org.apache.lucene.document.Document document = reader.document(docID);
            String value = document.get(fieldName);
            Assert.assertNull(
                    "duplicate matches found! This method assumes a single document will match the Term.",
                    projection);
            projection = value;
        }
    }
    Assert.assertNotNull(projection);
    return projection;
}

---

From source file:org.meresco.lucene.search.SuperIndexSearcher.java

License:Open Source License

public SuperIndexSearcher(IndexReader reader, ExecutorService executor, int tasks) {
    super(reader);
    this.executor = executor;
    this.grouped_leaves = this.group_leaves(reader.leaves(), tasks);
    //        for (List<AtomicReaderContext> l : this.grouped_leaves) {
    //            int t = 0;
    //            for (AtomicReaderContext ctx : l)
    //                t += ctx.reader().numDocs();
    //             System.out.print(" " + t + " ");
    //        }//from  ww  w .  j  a v a 2  s. c o m
    //        System.out.println();
}

---

From source file:org.meresco.lucene.suggestion.SuggestionNGramIndex.java

License:Open Source License

public void createSuggestions(IndexReader reader, String suggestionFieldname, String keyFieldname,
        IndexingState indexingState) throws IOException {
    Bits liveDocs = MultiFields.getLiveDocs(reader);
    List<AtomicReaderContext> leaves = reader.leaves();
    Terms terms = MultiFields.getTerms(reader, suggestionFieldname);
    if (terms == null)
        return;// w  ww  .j av  a2s  . c  o m
    TermsEnum termsEnum = terms.iterator(null);
    BytesRef term;
    while ((term = termsEnum.next()) != null) {
        List<Long> keys = new ArrayList<>();
        DocsEnum docsEnum = termsEnum.docs(liveDocs, null, DocsEnum.FLAG_NONE);
        while (true) {
            int docId = docsEnum.nextDoc();
            if (docId == DocsEnum.NO_MORE_DOCS) {
                break;
            }
            keys.add(keyForDoc(docId, leaves, keyFieldname));
        }
        if (keys.size() > 0) {
            String[] values = term.utf8ToString().split(SuggestionIndex.CONCAT_MARKER.replace("$", "\\$"));
            indexNGram(values[0], values[1], values[2], keys);
            indexingState.count++;
        }
    }
    this.commit();
}

---

From source file:org.neo4j.kernel.api.impl.schema.sampler.NonUniqueLuceneIndexSampler.java

License:Open Source License

@Override
protected IndexSample performSampling() throws IndexNotFoundKernelException {
    NonUniqueIndexSampler sampler = new NonUniqueIndexSampler(indexSamplingConfig.sampleSizeLimit());
    IndexReader indexReader = indexSearcher.getIndexReader();
    for (LeafReaderContext readerContext : indexReader.leaves()) {
        try {//from ww  w  . j  a  v a 2s.  c  om
            Set<String> fieldNames = getFieldNamesToSample(readerContext);
            for (String fieldName : fieldNames) {
                Terms terms = readerContext.reader().terms(fieldName);
                if (terms != null) {
                    TermsEnum termsEnum = LuceneDocumentStructure.originalTerms(terms, fieldName);
                    BytesRef termsRef;
                    while ((termsRef = termsEnum.next()) != null) {
                        sampler.include(termsRef.utf8ToString(), termsEnum.docFreq());
                        checkCancellation();
                    }
                }
            }
        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    return sampler.result(indexReader.numDocs());
}

---

From source file:org.openrdf.sail.lucene4.LuceneIndex.java

License:BSD License

/**
 * Returns a Document representing the specified document ID (combination of
 * resource and context), or null when no such Document exists yet.
 *///  w w w .j a  v  a  2 s  .  c o m
private Document getDocument(Term idTerm) throws IOException {
    IndexReader reader = getIndexReader();
    List<AtomicReaderContext> leaves = reader.leaves();
    int size = leaves.size();
    for (int i = 0; i < size; i++) {
        AtomicReader lreader = leaves.get(i).reader();
        Document document = getDocument(lreader, idTerm);
        if (document != null) {
            return document;
        }
    }
    // no such Document
    return null;
}

---

From source file:org.openrdf.sail.lucene4.LuceneIndex.java

License:BSD License

/**
 * Returns a list of Documents representing the specified Resource (empty
 * when no such Document exists yet). Each document represent a set of
 * statements with the specified Resource as a subject, which are stored in a
 * specific context/* w ww . j a  v a 2 s  .  co  m*/
 */
private List<Document> getDocuments(Term uriTerm) throws IOException {
    List<Document> result = new ArrayList<Document>();

    IndexReader reader = getIndexReader();
    List<AtomicReaderContext> leaves = reader.leaves();
    int size = leaves.size();
    for (int i = 0; i < size; i++) {
        AtomicReader lreader = leaves.get(i).reader();
        addDocuments(lreader, uriTerm, result);
    }

    return result;
}

---

From source file:org.openrdf.sail.lucene4.LuceneIndex.java

License:BSD License

private static boolean isDeleted(IndexReader reader, int docId) {
    if (reader.hasDeletions()) {
        List<AtomicReaderContext> leaves = reader.leaves();
        int size = leaves.size();
        for (int i = 0; i < size; i++) {
            Bits liveDocs = leaves.get(i).reader().getLiveDocs();
            if (docId < liveDocs.length()) {
                boolean isDeleted = !liveDocs.get(docId);
                if (isDeleted) {
                    return true;
                }//w ww . jav a 2s  . com
            }
        }
        return false;
    } else {
        return false;
    }
}

---

From source file:org.tallison.lucene.search.concordance.TestSimpleAnalyzerUtil.java

License:Apache License

private void executeNeedleTests(Analyzer analyzer) throws Exception {

    String needle = getNeedle(analyzer);
    int numFieldValues = 23;

    Directory directory = buildNeedleIndex(needle, analyzer, numFieldValues);

    IndexReader reader = DirectoryReader.open(directory);

    LeafReaderContext ctx = reader.leaves().get(0);
    LeafReader r = ctx.reader();//from  w w w  . j a  v  a2  s.c o m

    PostingsEnum dpe = r.postings(new Term(FIELD, needle), PostingsEnum.ALL);
    int numTests = 0;
    try {
        while (dpe.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
            int frq = dpe.freq();
            int advanced = 0;

            String[] fieldValues = r.document(dpe.docID()).getValues(FIELD);
            while (++advanced < frq) {
                dpe.nextPosition();
                String rebuilt = SimpleAnalyzerUtil.substringFromMultiValuedFields(dpe.startOffset(),
                        dpe.endOffset(), fieldValues, analyzer.getOffsetGap(FIELD), " | ");
                assertEquals(needle, rebuilt);
                numTests++;
            }
        }
    } finally {
        reader.close();
        directory.close();
    }
    assertEquals("number of tests", numFieldValues - 1, numTests);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• »