Examples of TestHighlightRunner

org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

  public void testMaxSizeHighlight() throws Exception {
    final MockAnalyzer analyzer = new MockAnalyzer(random, MockTokenizer.SIMPLE, true, (CharArraySet) StopAnalyzer.ENGLISH_STOP_WORDS_SET, true);
    // we disable MockTokenizer checks because we will forcefully limit the 
    // tokenstream and call end() before incrementToken() returns false.
    analyzer.setEnableChecks(false);
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        numHighlights = 0;
        doSearching("meat");
        TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(texts[0]));
        Highlighter highlighter = getHighlighter(query, FIELD_NAME, tokenStream,
            HighlighterTest.this);// new Highlighter(this, new
        // QueryTermScorer(query));
        highlighter.setMaxDocCharsToAnalyze(30);


        highlighter.getBestFragment(tokenStream, texts[0]);
        assertTrue("Setting MaxDocBytesToAnalyze should have prevented "
            + "us from finding matches for this record: " + numHighlights + " found",
            numHighlights == 0);
      }
    };


    helper.start();
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner


    helper.start();
  }


  public void testMaxSizeHighlightTruncates() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        String goodWord = "goodtoken";
        Set<String> stopWords = new HashSet<String>(1);
        stopWords.add("stoppedtoken");


        TermQuery query = new TermQuery(new Term("data", goodWord));


        String match = null;
        StringBuilder sb = new StringBuilder();
        sb.append(goodWord);
        for (int i = 0; i < 10000; i++) {
          sb.append(" ");
          // only one stopword
          sb.append(stopWords.iterator().next());
        }
        SimpleHTMLFormatter fm = new SimpleHTMLFormatter();
        Highlighter hg = getHighlighter(query, "data", new StandardAnalyzer(TEST_VERSION_CURRENT, stopWords).tokenStream(
            "data", new StringReader(sb.toString())), fm);// new Highlighter(fm,
        // new
        // QueryTermScorer(query));
        hg.setTextFragmenter(new NullFragmenter());
        hg.setMaxDocCharsToAnalyze(100);
        match = hg.getBestFragment(new StandardAnalyzer(TEST_VERSION_CURRENT, stopWords), "data", sb.toString());
        assertTrue("Matched text should be no more than 100 chars in length ", match.length() < hg
            .getMaxDocCharsToAnalyze());


        // add another tokenized word to the overrall length - but set way
        // beyond
        // the length of text under consideration (after a large slug of stop
        // words
        // + whitespace)
        sb.append(" ");
        sb.append(goodWord);
        match = hg.getBestFragment(new StandardAnalyzer(TEST_VERSION_CURRENT, stopWords), "data", sb.toString());
        assertTrue("Matched text should be no more than 100 chars in length ", match.length() < hg
            .getMaxDocCharsToAnalyze());
      }
    };


    helper.start();


  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

    helper.start();


  }
  
  public void testMaxSizeEndHighlight() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {
      @Override
      public void run() throws Exception {
        Set<String> stopWords = new HashSet<String>();
        stopWords.add("in");
        stopWords.add("it");
        TermQuery query = new TermQuery(new Term("text", "searchterm"));


        String text = "this is a text with searchterm in it";
        SimpleHTMLFormatter fm = new SimpleHTMLFormatter();
        Highlighter hg = getHighlighter(query, "text", new StandardAnalyzer(TEST_VERSION_CURRENT, 
            stopWords).tokenStream("text", new StringReader(text)), fm);
        hg.setTextFragmenter(new NullFragmenter());
        hg.setMaxDocCharsToAnalyze(36);
        String match = hg.getBestFragment(new StandardAnalyzer(TEST_VERSION_CURRENT, stopWords), "text", text);
        assertTrue(
            "Matched text should contain remainder of text after highlighted query ",
            match.endsWith("in it"));
      }
    };
    helper.start();
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

    };
    helper.start();
  }


  public void testUnRewrittenQuery() throws Exception {
    final TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        numHighlights = 0;
        // test to show how rewritten query can still be used
        if (searcher != null) searcher.close();
        searcher = new IndexSearcher(ramDir, true);
        Analyzer analyzer = new StandardAnalyzer(TEST_VERSION_CURRENT);


        QueryParser parser = new QueryParser(TEST_VERSION_CURRENT, FIELD_NAME, analyzer);
        Query query = parser.parse("JF? or Kenned*");
        if (VERBOSE) System.out.println("Searching with primitive query");
        // forget to set this and...
        // query=query.rewrite(reader);
        TopDocs hits = searcher.search(query, null, 1000);


        // create an instance of the highlighter with the tags used to surround
        // highlighted text
        // QueryHighlightExtractor highlighter = new
        // QueryHighlightExtractor(this,
        // query, new StandardAnalyzer(TEST_VERSION));


        int maxNumFragmentsRequired = 3;


        for (int i = 0; i < hits.totalHits; i++) {
          String text = searcher.doc(hits.scoreDocs[i].doc).get(FIELD_NAME);
          TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
          Highlighter highlighter = getHighlighter(query, FIELD_NAME, tokenStream, HighlighterTest.this, false);


          highlighter.setTextFragmenter(new SimpleFragmenter(40));


          String highlightedText = highlighter.getBestFragments(tokenStream, text,
              maxNumFragmentsRequired, "...");


          if (VERBOSE) System.out.println(highlightedText);
        }
        // We expect to have zero highlights if the query is multi-terms and is
        // not
        // rewritten!
        assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
            numHighlights == 0);
      }
    };


    helper.start();
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner


    helper.start();
  }


  public void testNoFragments() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        doSearching("AnInvalidQueryWhichShouldYieldNoResults");


        for (int i = 0; i < texts.length; i++) {
          String text = texts[i];
          TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
          Highlighter highlighter = getHighlighter(query, FIELD_NAME, tokenStream,
              HighlighterTest.this);
          String result = highlighter.getBestFragment(tokenStream, text);
          assertNull("The highlight result should be null for text with no query terms", result);
        }
      }
    };


    helper.start();
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

    ramDir1.close();
    ramDir2.close();
  }


  public void testFieldSpecificHighlighting() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        String docMainText = "fred is one of the people";
        QueryParser parser = new QueryParser(TEST_VERSION_CURRENT, FIELD_NAME, analyzer);
        Query query = parser.parse("fred category:people");


        // highlighting respects fieldnames used in query


        Scorer fieldSpecificScorer = null;
        if (mode == TestHighlightRunner.QUERY) {
          fieldSpecificScorer = new QueryScorer(query, FIELD_NAME);
        } else if (mode == TestHighlightRunner.QUERY_TERM) {
          fieldSpecificScorer = new QueryTermScorer(query, "contents");
        }
        Highlighter fieldSpecificHighlighter = new Highlighter(new SimpleHTMLFormatter(),
            fieldSpecificScorer);
        fieldSpecificHighlighter.setTextFragmenter(new NullFragmenter());
        String result = fieldSpecificHighlighter.getBestFragment(analyzer, FIELD_NAME, docMainText);
        assertEquals("Should match", result, "<B>fred</B> is one of the people");


        // highlighting does not respect fieldnames used in query
        Scorer fieldInSpecificScorer = null;
        if (mode == TestHighlightRunner.QUERY) {
          fieldInSpecificScorer = new QueryScorer(query, null);
        } else if (mode == TestHighlightRunner.QUERY_TERM) {
          fieldInSpecificScorer = new QueryTermScorer(query);
        }


        Highlighter fieldInSpecificHighlighter = new Highlighter(new SimpleHTMLFormatter(),
            fieldInSpecificScorer);
        fieldInSpecificHighlighter.setTextFragmenter(new NullFragmenter());
        result = fieldInSpecificHighlighter.getBestFragment(analyzer, FIELD_NAME, docMainText);
        assertEquals("Should match", result, "<B>fred</B> is one of the <B>people</B>");


        reader.close();
      }
    };


    helper.start();


  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

      }
    };
  }


  public void testOverlapAnalyzer2() throws Exception {
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        String s = "Hi-Speed10 foo";


        Query query;
        Highlighter highlighter;
        String result;


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("foo");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("Hi-Speed10 <B>foo</B>", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("10");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("Hi-Speed<B>10</B> foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hi");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("<B>Hi</B>-Speed10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("speed");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("Hi-<B>Speed</B>10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hispeed");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("<B>Hi-Speed</B>10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hi speed");
        highlighter = getHighlighter(query, "text", getTS2(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2(), s, 3, "...");
        assertEquals("<B>Hi-Speed</B>10 foo", result);


        // ///////////////// same tests, just put the bigger overlapping token
        // first
        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("foo");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("Hi-Speed10 <B>foo</B>", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("10");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("Hi-Speed<B>10</B> foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hi");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("<B>Hi</B>-Speed10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("speed");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("Hi-<B>Speed</B>10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hispeed");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("<B>Hi-Speed</B>10 foo", result);


        query = new QueryParser(TEST_VERSION_CURRENT, "text", new MockAnalyzer(random, MockTokenizer.WHITESPACE, false)).parse("hi speed");
        highlighter = getHighlighter(query, "text", getTS2a(), HighlighterTest.this);
        result = highlighter.getBestFragments(getTS2a(), s, 3, "...");
        assertEquals("<B>Hi-Speed</B>10 foo", result);
      }
    };


    helper.start();
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

  public void testNearSpanSimpleQuery() throws Exception {
    doSearching(new SpanNearQuery(new SpanQuery[] {
        new SpanTermQuery(new Term(FIELD_NAME, "beginning")),
        new SpanTermQuery(new Term(FIELD_NAME, "kennedy")) }, 3, false));


    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        mode = QUERY;
        doStandardHighlights(analyzer, searcher, hits, query, HighlighterTest.this);
      }
    };


    helper.run();


    assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
        numHighlights == 2);
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

        new SpanTermQuery(new Term(FIELD_NAME, "wordc")) }, 1, false);
    BooleanQuery bquery = new BooleanQuery();
    bquery.add(query1, Occur.SHOULD);
    bquery.add(query2, Occur.SHOULD);
    doSearching(bquery);
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        mode = QUERY;
        doStandardHighlights(analyzer, searcher, hits, query, HighlighterTest.this);
      }
    };


    helper.run();
    assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
        numHighlights == 7);
  }

View Full Code Here

Examples of org.apache.lucene.search.highlight.SynonymTokenizer.TestHighlightRunner

  public void testNotSpanSimpleQuery() throws Exception {
    doSearching(new SpanNotQuery(new SpanNearQuery(new SpanQuery[] {
        new SpanTermQuery(new Term(FIELD_NAME, "shot")),
        new SpanTermQuery(new Term(FIELD_NAME, "kennedy")) }, 3, false), new SpanTermQuery(
        new Term(FIELD_NAME, "john"))));
    TestHighlightRunner helper = new TestHighlightRunner() {


      @Override
      public void run() throws Exception {
        mode = QUERY;
        doStandardHighlights(analyzer, searcher, hits, query, HighlighterTest.this);
      }
    };


    helper.run();
    assertTrue("Failed to find correct number of highlights " + numHighlights + " found",
        numHighlights == 4);
  }

View Full Code Here

0 1 2 3 4 5

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.