Examples with IndexReader org.apache.lucene.index.IndexReader used on opensource projects

Example 91 with IndexReader

use of org.apache.lucene.index.IndexReader in project lucene-solr by apache.

the class TestUnifiedHighlighter method testEncode.

public void testEncode() throws Exception {
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Field body = new Field("body", "", fieldType);
    Document doc = new Document();
    doc.add(body);
    body.setStringValue("This is a test. Just a test highlighting from <i>postings</i>. Feel free to ignore.");
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer) {

        @Override
        protected PassageFormatter getFormatter(String field) {
            return new DefaultPassageFormatter("<b>", "</b>", "... ", true);
        }
    };
    Query query = new TermQuery(new Term("body", "highlighting"));
    TopDocs topDocs = searcher.search(query, 10, Sort.INDEXORDER);
    assertEquals(1, topDocs.totalHits);
    String[] snippets = highlighter.highlight("body", query, topDocs);
    assertEquals(1, snippets.length);
    assertEquals("Just&#32;a&#32;test&#32;<b>highlighting</b>&#32;from&#32;&lt;i&gt;postings&lt;&#x2F;i&gt;&#46;&#32;", snippets[0]);
    ir.close();
}

Example 92 with IndexReader

use of org.apache.lucene.index.IndexReader in project lucene-solr by apache.

the class TestUnifiedHighlighter method testCambridgeMA.

public void testCambridgeMA() throws Exception {
    BufferedReader r = new BufferedReader(new InputStreamReader(this.getClass().getResourceAsStream("CambridgeMA.utf8"), StandardCharsets.UTF_8));
    String text = r.readLine();
    r.close();
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Field body = new Field("body", text, fieldType);
    Document document = new Document();
    document.add(body);
    iw.addDocument(document);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    BooleanQuery query = new BooleanQuery.Builder().add(new TermQuery(new Term("body", "porter")), BooleanClause.Occur.SHOULD).add(new TermQuery(new Term("body", "square")), BooleanClause.Occur.SHOULD).add(new TermQuery(new Term("body", "massachusetts")), BooleanClause.Occur.SHOULD).build();
    TopDocs topDocs = searcher.search(query, 10);
    assertEquals(1, topDocs.totalHits);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    highlighter.setMaxLength(Integer.MAX_VALUE - 1);
    String[] snippets = highlighter.highlight("body", query, topDocs, 2);
    assertEquals(1, snippets.length);
    assertTrue(snippets[0].contains("<b>Square</b>"));
    assertTrue(snippets[0].contains("<b>Porter</b>"));
    ir.close();
}

Example 93 with IndexReader

use of org.apache.lucene.index.IndexReader in project lucene-solr by apache.

the class TestUnifiedHighlighter method testCuriousGeorge.

public void testCuriousGeorge() throws Exception {
    String text = "It’s the formula for success for preschoolers—Curious George and fire trucks! " + "Curious George and the Firefighters is a story based on H. A. and Margret Rey’s " + "popular primate and painted in the original watercolor and charcoal style. " + "Firefighters are a famously brave lot, but can they withstand a visit from one curious monkey?";
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Field body = new Field("body", text, fieldType);
    Document document = new Document();
    document.add(body);
    iw.addDocument(document);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    PhraseQuery query = new PhraseQuery.Builder().add(new Term("body", "curious")).add(new Term("body", "george")).build();
    TopDocs topDocs = searcher.search(query, 10);
    assertEquals(1, topDocs.totalHits);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    highlighter.setHighlightPhrasesStrictly(false);
    String[] snippets = highlighter.highlight("body", query, topDocs, 2);
    assertEquals(1, snippets.length);
    assertFalse(snippets[0].contains("<b>Curious</b>Curious"));
    ir.close();
}

Example 94 with IndexReader

use of org.apache.lucene.index.IndexReader in project lucene-solr by apache.

the class TestUnifiedHighlighter method testMultipleSnippetSizes.

public void testMultipleSnippetSizes() throws Exception {
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Field body = new Field("body", "", fieldType);
    Field title = new Field("title", "", UHTestHelper.randomFieldType(random()));
    Document doc = new Document();
    doc.add(body);
    doc.add(title);
    body.setStringValue("This is a test. Just a test highlighting from postings. Feel free to ignore.");
    title.setStringValue("This is a test. Just a test highlighting from postings. Feel free to ignore.");
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    BooleanQuery query = new BooleanQuery.Builder().add(new TermQuery(new Term("body", "test")), BooleanClause.Occur.SHOULD).add(new TermQuery(new Term("title", "test")), BooleanClause.Occur.SHOULD).build();
    Map<String, String[]> snippets = highlighter.highlightFields(new String[] { "title", "body" }, query, new int[] { 0 }, new int[] { 1, 2 });
    String titleHighlight = snippets.get("title")[0];
    String bodyHighlight = snippets.get("body")[0];
    assertEquals("This is a <b>test</b>. ", titleHighlight);
    assertEquals("This is a <b>test</b>. Just a <b>test</b> highlighting from postings. ", bodyHighlight);
    ir.close();
}

Example 95 with IndexReader

use of org.apache.lucene.index.IndexReader in project lucene-solr by apache.

the class TestUnifiedHighlighter method testCustomEmptyHighlights.

/**
   * Make sure highlighter we can customize how emtpy
   * highlight is returned.
   */
public void testCustomEmptyHighlights() throws Exception {
    indexAnalyzer.setPositionIncrementGap(10);
    RandomIndexWriter iw = new RandomIndexWriter(random(), dir, indexAnalyzer);
    Document doc = new Document();
    Field body = new Field("body", "test this is.  another sentence this test has.  far away is that planet.", fieldType);
    doc.add(body);
    iw.addDocument(doc);
    IndexReader ir = iw.getReader();
    iw.close();
    IndexSearcher searcher = newSearcher(ir);
    UnifiedHighlighter highlighter = new UnifiedHighlighter(searcher, indexAnalyzer);
    // don't want any default summary
    highlighter.setMaxNoHighlightPassages(0);
    Query query = new TermQuery(new Term("body", "highlighting"));
    int[] docIDs = new int[] { 0 };
    String[] snippets = highlighter.highlightFields(new String[] { "body" }, query, docIDs, new int[] { 2 }).get("body");
    assertEquals(1, snippets.length);
    assertNull(snippets[0]);
    ir.close();
}