Example usage for org.apache.lucene.util BytesRefArray size

List of usage examples for org.apache.lucene.util BytesRefArray size

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.util.*
  5. BytesRefArray
  6. size

Introduction

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

Prototype

@Override
public int size()

Source Link

Document

Returns the current size of this BytesRefArray

Usage

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

License:Open Source License

@SuppressWarnings({ "resource", "ObjectAllocationInLoop", "ImplicitNumericConversion" })
@Test/*from w  ww .  j  a  va  2  s.  c  om*/
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// w w w . j a va  2 s. com
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/*  www.j av a 2s . c om*/
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//from   w  w w .  j av a  2 s . c o  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 w w. ja  v  a2  s.com
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.  ja v a 2 s.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  w  w w . java 2 s  . com
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()));
    }
}

From source file:de.unihildesheim.iw.lucene.query.QueryUtils.java

License:Open Source License

/**
 * Remove terms from the given collection, if they are not found in the
 * collection./*from  www .  j ava2s . com*/
 *
 * @param dataProv IndexDataProvider
 * @param terms Collection of terms to check against the collection
 * @return Passed in terms with non-collection terms removed
 */
@SuppressFBWarnings("LO_APPENDED_STRING_IN_FORMAT_STRING")
private static BytesRefArray removeUnknownTerms(@NotNull final IndexDataProvider dataProv,
        @NotNull final BytesRefArray terms) {
    final StringBuilder sb = new StringBuilder("Skipped terms (stopword or not in collection): [");
    final FixedBitSet bits = new FixedBitSet(terms.size());
    final BytesRefBuilder spare = new BytesRefBuilder();
    BytesRef term;

    if (terms.size() == 0) {
        return terms;
    } else {
        for (int i = terms.size() - 1; i >= 0; i--) {
            term = terms.get(spare, i);
            if (dataProv.getTermFrequency(term) <= 0L) {
                sb.append(term.utf8ToString()).append(' ');
                bits.set(i);
            }
        }

        if (bits.cardinality() > 0) {
            LOG.warn(sb.toString().trim() + "].");
            final BytesRefArray cleanTerms = new BytesRefArray(Counter.newCounter(false));
            for (int i = terms.size() - 1; i >= 0; i--) {
                if (!bits.get(i)) {
                    term = terms.get(spare, i);
                    cleanTerms.append(term); // copies bytes
                }
            }
            return cleanTerms;
        }
        return terms;
    }
}

From source file:de.unihildesheim.iw.lucene.query.QueryUtils.java

License:Open Source License

/**
 * Tokenizes a query string using Lucenes analyzer. This also removes
 * stopwords from the query string. The {@link IndexDataProvider} instance is
 * used to skip terms no found in the collection.
 *
 * @param query Query string to tokenize
 * @param qAnalyzer Analyzer to use//from   w w w  .  jav a 2 s.c om
 * @param dataProv IndexDataProvider
 * @return List of tokens from original query with stop-words removed
 * @see #tokenizeQuery(String, Analyzer, IndexDataProvider)
 */
public static List<String> tokenizeQueryString(@NotNull final String query, @NotNull final Analyzer qAnalyzer,
        @Nullable final IndexDataProvider dataProv) {
    final BytesRefArray tokenizedQuery = tokenizeQuery(query, qAnalyzer, dataProv);
    final List<String> tokenizedQueryStr = new ArrayList<>(tokenizedQuery.size());
    tokenizedQueryStr.addAll(
            StreamUtils.stream(tokenizedQuery).map(BytesRef::utf8ToString).collect(Collectors.toList()));
    return tokenizedQueryStr;
}

From source file:de.unihildesheim.iw.lucene.query.QueryUtilsTest.java

License:Open Source License

@SuppressWarnings("ImplicitNumericConversion")
@Test//ww  w .j  av a  2s  .co m
public void testTokenizeQuery_noMetrics() throws Exception {
    final BytesRefArray bra = QueryUtils.tokenizeQuery("foo bar baz", ANALYZER, null);

    Assert.assertEquals("Extracted terms count mismatch.", 3L, bra.size());

    final BytesRefIterator braIt = bra.iterator();
    BytesRef term;
    while ((term = braIt.next()) != null) {
        final String termStr = term.utf8ToString();
        switch (termStr) {
        case "foo":
        case "bar":
        case "baz":
            break;
        default:
            Assert.fail("Unknown term found.");
            break;
        }
    }
}