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

Introduction

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

Prototype

public BytesRefIterator iterator() 

Source Link

Document

sugar for #iterator(Comparator) with a null comparator

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  o  m
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 .ja v  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//from   w w w  .j ava 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  av  a2 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/*  w w w. j av  a2 s .c o m*/
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  ava 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   ww  w. j a  va 2  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 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.QueryUtilsTest.java

License:Open Source License

@SuppressWarnings("ImplicitNumericConversion")
@Test/*from w ww. jav  a 2s  . c  o 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;
        }
    }
}

---

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

License:Open Source License

/**
 * Test tokenizing with skipping terms not present in index.
 *
 * @throws Exception/*from w  w  w .  ja  v  a2s .c om*/
 */
@SuppressWarnings("ImplicitNumericConversion")
@Test
public void testTokenizeQuery() throws Exception {
    try (TestMemIndex idx = new TestMemIndex()) {
        final IndexDataProvider idp = idx.getIdp();

        final BytesRefArray bra = QueryUtils.tokenizeQuery("foo bar field baz value", ANALYZER, idp);

        Assert.assertEquals("Extracted terms count mismatch.", 2L, 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":
                Assert.fail("Non-index term found.");
                break;
            case "value":
            case "field":
                // pass
                break;
            default:
                Assert.fail("Unknown term found.");
                break;
            }
        }
    }
}

---

From source file:de.unihildesheim.iw.lucene.util.BytesRefUtilsTest.java

License:Open Source License

@SuppressWarnings("ImplicitNumericConversion")
@Test/*from ww w.j av  a2 s .  c  om*/
public void testHashToArray() throws Exception {
    final Collection<String> data = new HashSet<>(3);
    data.add("foo");
    data.add("bar");
    data.add("baz");

    final BytesRefHash brh = new BytesRefHash();
    data.stream().map(BytesRef::new).forEach(brh::add);

    final BytesRefArray bra = BytesRefUtils.hashToArray(brh);

    Assert.assertEquals("Not all terms found.", data.size(), bra.size());

    final BytesRefIterator bri = bra.iterator();
    BytesRef br;
    while ((br = bri.next()) != null) {
        Assert.assertNotSame("BytesRef not found.", -1, brh.find(br));
    }
}

---