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

List of usage examples for org.apache.lucene.util BytesRef BytesRef

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.util.*
  5. BytesRef
  6. 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:de.jetsli.lumeo.RawLucene.java

License:Apache License

public Document findByUserId(final String uId) {
    return searchSomething(new SearchExecutor<Document>() {

        @Override//w  w w.j a va  2  s  . c  o m
        public Document execute(final IndexSearcher searcher) throws IOException {
            final BytesRef bytes = new BytesRef(uId);
            Document doc = null;
            //IndexReaderContext trc = searcher.getTopReaderContext();
            //trc.children();

            //TODO -MH  search subreaders - share common subreader code in findByID?

            //Hopefully Lucene should bail after collecting our result of 1
            TopDocs results = searcher.search(new TermQuery(new Term(UID, bytes)), 1);
            if (results.totalHits > 1) {
                throw new IllegalStateException("Document with " + UID + "=" + uId + " not the only one");
            }
            if (results.totalHits == 1) {
                doc = searcher.document(results.scoreDocs[0].doc, null);
            }

            //                new MyGather(searcher.getIndexReader()) {
            //
            //                    @Override protected boolean runLeaf(int base, AtomicReader leaf) throws IOException {
            //                        DocsEnum docs = leaf.termDocsEnum(leaf.getLiveDocs(), UID, bytes, false);
            //                        if (docs == null)
            //                            return true;
            //
            //                        int docID = docs.nextDoc();
            //                        if (docID == DocsEnum.NO_MORE_DOCS)
            //                            return true;
            //
            //                        if (docs.nextDoc() != DocsEnum.NO_MORE_DOCS)
            //                            throw new IllegalStateException("Document with " + UID + "=" + uId + " not the only one");
            //
            //                        doc = searcher.doc(base + docID);
            //                        return false;
            //                    }
            //                }.run();
            return doc;
        }
    });
}

From source file:de.jetsli.lumeo.util.Mapping.java

License:Apache License

public BytesRef toBytes(String fieldName, Object o) {
    if (o instanceof String) {
        if (getAnalyzerFor(fieldName) == KEYWORD_ANALYZER_LC)
            return new BytesRef(((String) o).toLowerCase());
        else/* w  ww.  ja va2  s  . com*/
            return new BytesRef((String) o);
    } else if (o instanceof Integer)
        return LuceneHelper.newRefFromInt((Integer) o);
    else if (o instanceof Long)
        return LuceneHelper.newRefFromLong((Long) o);
    else if (o instanceof Double)
        return LuceneHelper.newRefFromDouble((Double) o);
    else if (o instanceof Date)
        return new BytesRef(DateTools.timeToString(((Date) o).getTime(), DateTools.Resolution.MINUTE));
    else
        throw new UnsupportedOperationException("Couldn't find bytesRef usage for object  " + o);
}

From source file:de.qaware.chronix.lucene.client.add.LuceneAddingService.java

License:Apache License

/**
 * Tries to cast field value (object) to a string or byte[].
 * If the field value is not a string or a byte[] then the method ignores the field.
 * <p>//from  w w  w . j a  va  2  s  .  c o m
 * If the value is a string or byte[] than the value is warped into a matching lucene field (Field for String,
 * StoredField for byte[]) and added to the lucene document.
 *
 * @param document   the lucene document to add the number
 * @param fieldName  the field name
 * @param fieldValue the field value
 */
private static void handleStringsAndBytes(Document document, String fieldName, Object fieldValue) {
    if (fieldValue instanceof String) {
        document.add(new Field(fieldName, fieldValue.toString(), TextField.TYPE_STORED));
    } else if (fieldValue instanceof byte[]) {
        document.add(new StoredField(fieldName, new BytesRef((byte[]) fieldValue)));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.EnglishAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test//www  .j  av a  2  s.  com
public void testTokenStream_noStopwords() throws Exception {
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new EnglishAnalyzer();
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 4L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "foo".equals(term.utf8ToString()) || "bar".equals(term.utf8ToString())
                        || "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.EnglishAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test//from w w  w  .jav a2  s .c om
public void testTokenStream() throws Exception {
    final CharArraySet csa = new CharArraySet(Arrays.asList("foo", "bar"), true);
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new EnglishAnalyzer(csa);
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 2L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.FrenchAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test/* w  w  w  . j  av  a  2s .  c o  m*/
public void testTokenStream_noStopwords() throws Exception {
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new FrenchAnalyzer();
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 4L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "foo".equals(term.utf8ToString()) || "bar".equals(term.utf8ToString())
                        || "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.FrenchAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test// w  w w  . j a va2 s .co  m
public void testTokenStream() throws Exception {
    final CharArraySet csa = new CharArraySet(Arrays.asList("foo", "bar"), true);
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new FrenchAnalyzer(csa);
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 2L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.FrenchAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test//from   w ww  .j a  v  a2s . c om
public void testTokenStream_elisions() throws Exception {
    final CharArraySet csa = new CharArraySet(Arrays.asList("foo", "bar"), true);
    final StringBuilder query = new StringBuilder("foo bar baz bam ");
    // add all elisions to the query
    for (final String s : FrenchAnalyzer.DEFAULT_ELISIONS) {
        query.append(s).append("\'bim ");
    }
    final Analyzer analyzer = new FrenchAnalyzer(csa);
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query.toString())) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 2L + FrenchAnalyzer.DEFAULT_ELISIONS.length, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()) ||
                // elisions should be removed from this
                        "bim".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.GermanAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test/*from   w  w w  .j  a  v  a  2s  . c  o m*/
public void testTokenStream_noStopwords() throws Exception {
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new GermanAnalyzer();
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 4L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "foo".equals(term.utf8ToString()) || "bar".equals(term.utf8ToString())
                        || "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}

From source file:de.unihildesheim.iw.lucene.analyzer.GermanAnalyzerTest.java

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test//from ww w  .  j a  va2s  .c om
public void testTokenStream() throws Exception {
    final CharArraySet csa = new CharArraySet(Arrays.asList("foo", "bar"), true);
    final String query = "foo bar baz bam";
    final Analyzer analyzer = new GermanAnalyzer(csa);
    final BytesRefArray result = new BytesRefArray(Counter.newCounter(false));

    try (TokenStream stream = analyzer.tokenStream(null, query)) {
        stream.reset();
        while (stream.incrementToken()) {
            final BytesRef term = new BytesRef(stream.getAttribute(CharTermAttribute.class));
            if (term.length > 0) {
                result.append(term);
            }
        }
    }

    Assert.assertEquals("Not all terms returned.", 2L, result.size());

    final BytesRefIterator bri = result.iterator();
    BytesRef term;
    while ((term = bri.next()) != null) {
        Assert.assertTrue("Unknown term found.",
                "baz".equals(term.utf8ToString()) || "bam".equals(term.utf8ToString()));
    }
}