Example usage for org.apache.lucene.util BytesRef BytesRef

Introduction

In this page you can find the example usage for org.apache.lucene.util BytesRef BytesRef.

Prototype

public BytesRef(CharSequence text) 

Source Link

Document

Initialize the byte[] from the UTF8 bytes for the provided String.

Usage

From source file:com.hrhih.index.suggest.Input.java

License:Apache License

public Input(String term, long v) {
    this(new BytesRef(term), v, null, false, null, false);
}

---

From source file:com.hrhih.index.suggest.Input.java

License:Apache License

public Input(String term, int v, BytesRef payload, Set<BytesRef> contexts) {
    this(new BytesRef(term), v, payload, true, contexts, true);
}

---

From source file:com.ibm.watson.developer_cloud.professor_languo.ingestion.indexing.RetrieveAndRankIndexerTest.java

License:Open Source License

/**
 * check if the deserialized candidate answers are exactly the same as the candidate answers we
 * expected. Since the query is "question Title: what is right", the expected candidate answers
 * should be the entire corpus.//from www  .  j a  v a  2 s.c  om
 * 
 * @throws IngestionException
 */
private void compare_indexed_records_to_corpus() throws IngestionException {
    indexdCorpus = corpusBuilder.getUniqueThreadSetFromBinFiles();

    // Check that the size of the corpus is the same as the size of the
    // indexed documents
    assertTrue("Wrong number of documents indexed", indexedRecords.size() == indexdCorpus.size());

    // Check that the indexed document in the corpus is in the index
    File serFile = new File(corpusBuilder.getUniqueThreadDirPath()).listFiles()[0];
    StackExchangeThread thread = StackExchangeThreadSerializer.deserializeThreadFromBinFile(serFile.getPath());

    final Document luceneDoc = new LuceneDocumentMapper().createDocument(thread);
    SolrInputDocument recordDoc = indexedRecords.get(0);

    for (IndexableField field : luceneDoc.getFields()) {
        BytesRef bin = luceneDoc.getBinaryValue(field.name());

        // Check that indexed fields (title and id) are indexed correctly
        if (field.name().equals(IndexDocumentFieldName.THREAD_TITLE.toString())
                || field.name().equals(IndexDocumentFieldName.THREAD_POST_ID.toString())) {

            String value = luceneDoc.get(field.name());
            assertEquals(value, recordDoc.getFieldValue(field.name()).toString());
        }

        // Check that indexed serialized field is indexed correctly
        if (bin != null) {
            BytesRef recordbin = new BytesRef((byte[]) recordDoc.getFieldValue(field.name()));
            assertEquals(bin, recordbin);
        }

    }
}

---

From source file:com.lorelib.analyzer.query.IKQueryExpressionParser.java

License:Apache License

/**
 * TermRangeQuery//from  ww  w . ja  v a2 s.  c o m
 * @param elements
 * @return
 */
private TermRangeQuery toTermRangeQuery(Element fieldNameEle, LinkedList<Element> elements) {

    boolean includeFirst = false;
    boolean includeLast = false;
    String firstValue = null;
    String lastValue = null;
    //?[{
    Element first = elements.getFirst();
    if ('[' == first.type) {
        includeFirst = true;
    } else if ('{' == first.type) {
        includeFirst = false;
    } else {
        throw new IllegalStateException("?");
    }
    //??]}
    Element last = elements.getLast();
    if (']' == last.type) {
        includeLast = true;
    } else if ('}' == last.type) {
        includeLast = false;
    } else {
        throw new IllegalStateException("?, RangeQuery??");
    }
    if (elements.size() < 4 || elements.size() > 5) {
        throw new IllegalStateException("?, RangeQuery ");
    }
    //
    Element e2 = elements.get(1);
    if ('\'' == e2.type) {
        firstValue = e2.toString();
        //
        Element e3 = elements.get(2);
        if (',' != e3.type) {
            throw new IllegalStateException("?, RangeQuery?");
        }
        //
        Element e4 = elements.get(3);
        if ('\'' == e4.type) {
            lastValue = e4.toString();
        } else if (e4 != last) {
            throw new IllegalStateException("?RangeQuery?");
        }
    } else if (',' == e2.type) {
        firstValue = null;
        //
        Element e3 = elements.get(2);
        if ('\'' == e3.type) {
            lastValue = e3.toString();
        } else {
            throw new IllegalStateException("?RangeQuery?");
        }

    } else {
        throw new IllegalStateException("?, RangeQuery?");
    }

    return new TermRangeQuery(fieldNameEle.toString(), new BytesRef(firstValue), new BytesRef(lastValue),
            includeFirst, includeLast);
}

---

From source file:com.lucure.core.codec.CompressingStoredFieldsReader.java

License:Apache License

private CompressingStoredFieldsReader(CompressingStoredFieldsReader reader) {
    this.version = reader.version;
    this.fieldInfos = reader.fieldInfos;
    this.fieldsStream = reader.fieldsStream.clone();
    this.indexReader = reader.indexReader.clone();
    this.maxPointer = reader.maxPointer;
    this.chunkSize = reader.chunkSize;
    this.packedIntsVersion = reader.packedIntsVersion;
    this.compressionMode = reader.compressionMode;
    this.decompressor = reader.decompressor.clone();
    this.numDocs = reader.numDocs;
    this.bytes = new BytesRef(reader.bytes.bytes.length);
    this.closed = false;
}

---

From source file:com.mathworks.xzheng.advsearching.MultiSearcherTest.java

License:Apache License

public void testMulti() throws Exception {

    MultiReader multiReader = new MultiReader(searchers[0].getIndexReader(), searchers[1].getIndexReader());
    IndexSearcher searcher = new IndexSearcher(multiReader);

    TermRangeQuery query = new TermRangeQuery("animal", // #3
            new BytesRef("h"), // #3
            new BytesRef("t"), // #3
            true, true);// #3

    TopDocs hits = searcher.search(query, 10);
    assertEquals("tarantula not included", 12, hits.totalHits);
}

---

From source file:com.mathworks.xzheng.extsearch.payloads.BulletinPayloadsFilter.java

License:Apache License

BulletinPayloadsFilter(TokenStream in, float warningBoost) {
    super(in);//from w w w .  j a va2 s .  co  m
    payloadAttr = addAttribute(PayloadAttribute.class);
    termAtt = addAttribute(CharTermAttribute.class);
    boostPayload = new BytesRef(PayloadHelper.encodeFloat(warningBoost));
}

---

From source file:com.mathworks.xzheng.searching.TermRangeQueryTest.java

License:Apache License

public void testTermRangeQuery() throws Exception {
    Directory dir = TestUtil.getBookIndexDirectory();
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    TermRangeQuery query = new TermRangeQuery("title2", new BytesRef("d"), new BytesRef("j"), true, true);

    TopDocs matches = searcher.search(query, 100);
    /*/* w w w.ja  v a  2s  .com*/
    for(int i=0;i<matches.totalHits;i++) {
      System.out.println("match " + i + ": " + searcher.doc(matches.scoreDocs[i].doc).get("title2"));
    }
    */
    assertEquals(3, matches.totalHits);

    dir.close();
}

---

From source file:com.mathworks.xzheng.tools.ChainedFilterTest.java

License:Apache License

public void setUp() throws Exception {
    directory = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46,
            new WhitespaceAnalyzer(Version.LUCENE_46));

    IndexWriter writer = new IndexWriter(directory, config);

    Calendar cal = Calendar.getInstance();
    cal.set(2009, 1, 1, 0, 0); // A

    for (int i = 0; i < MAX; i++) {
        Document doc = new Document();
        doc.add(new Field("key", "" + (i + 1), Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("owner", (i < MAX / 2) ? "bob" : "sue", Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("date", DateTools.timeToString(cal.getTimeInMillis(), DateTools.Resolution.DAY),
                Field.Store.YES, Field.Index.NOT_ANALYZED));
        writer.addDocument(doc);/*from   ww w  . j  a  v a 2  s  . c om*/

        cal.add(Calendar.DATE, 1);
    }

    writer.close();

    searcher = new IndexSearcher(DirectoryReader.open(directory));

    BooleanQuery bq = new BooleanQuery(); // B
    bq.add(new TermQuery(new Term("owner", "bob")), // B
            BooleanClause.Occur.SHOULD); // B
    bq.add(new TermQuery(new Term("owner", "sue")), // B
            BooleanClause.Occur.SHOULD); // B
    query = bq;

    cal.set(2099, 1, 1, 0, 0);
    dateFilter = TermRangeFilter.Less("date", // C
            new BytesRef(DateTools.timeToString( // C
                    cal.getTimeInMillis(), // C
                    DateTools.Resolution.DAY)));// C

    bobFilter = new CachingWrapperFilter( // D
            new QueryWrapperFilter( // D
                    new TermQuery(new Term("owner", "bob")))); // D

    sueFilter = new CachingWrapperFilter( // E
            new QueryWrapperFilter( // E
                    new TermQuery(new Term("owner", "sue")))); // E
}

---

From source file:com.meizu.nlp.classification.BooleanPerceptronClassifier.java

License:Apache License

/**
 * {@inheritDoc}/* w w w .  ja v  a 2 s.c  om*/
 */
@Override
public ClassificationResult<Boolean> assignClass(String text) throws IOException {
    if (textTerms == null) {
        throw new IOException("You must first call Classifier#train");
    }
    Long output = 0l;
    try (TokenStream tokenStream = analyzer.tokenStream(textFieldName, text)) {
        CharTermAttribute charTermAttribute = tokenStream.addAttribute(CharTermAttribute.class);
        tokenStream.reset();
        while (tokenStream.incrementToken()) {
            String s = charTermAttribute.toString();
            Long d = Util.get(fst, new BytesRef(s));
            if (d != null) {
                output += d;
            }
        }
        tokenStream.end();
    }

    return new ClassificationResult<>(output >= threshold, output.doubleValue());
}

---

• «
• 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
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• »