Example usage for org.apache.lucene.search.vectorhighlight FastVectorHighlighter getBestFragment

List of usage examples for org.apache.lucene.search.vectorhighlight FastVectorHighlighter getBestFragment

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.search.vectorhighlight.*
  5. FastVectorHighlighter
  6. getBestFragment

Introduction

In this page you can find the example usage for org.apache.lucene.search.vectorhighlight FastVectorHighlighter getBestFragment.

Prototype

public final String getBestFragment(final FieldQuery fieldQuery, IndexReader reader, int docId,
        String fieldName, int fragCharSize) throws IOException

Source Link

Document

return the best fragment.

Usage

From source file:aos.lucene.tools.FastVectorHighlighterSample.java

License:Apache License

static void searchIndex(String filename) throws Exception {
    QueryParser parser = new QueryParser(Version.LUCENE_46, F, analyzer);
    Query query = parser.parse(QUERY);
    FastVectorHighlighter highlighter = getHighlighter(); // #C
    FieldQuery fieldQuery = highlighter.getFieldQuery(query); // #D
    IndexSearcher searcher = new IndexSearcher(dir);
    TopDocs docs = searcher.search(query, 10);

    FileWriter writer = new FileWriter(filename);
    writer.write("<html>");
    writer.write("<body>");
    writer.write("<p>QUERY : " + QUERY + "</p>");
    for (ScoreDoc scoreDoc : docs.scoreDocs) {
        String snippet = highlighter.getBestFragment( // #E
                fieldQuery, searcher.getIndexReader(), // #E
                scoreDoc.doc, F, 100); // #E
        if (snippet != null) {
            writer.write(scoreDoc.doc + " : " + snippet + "<br/>");
        }/*ww w.j  av  a2  s .  co  m*/
    }
    writer.write("</body></html>");
    writer.close();
}

From source file:com.mathworks.xzheng.tools.FastVectorHighlighterSample.java

License:Apache License

static void searchIndex(String filename) throws Exception {
    QueryParser parser = new QueryParser(Version.LUCENE_46, F, analyzer);
    Query query = parser.parse(QUERY);
    FastVectorHighlighter highlighter = getHighlighter(); // #C
    FieldQuery fieldQuery = highlighter.getFieldQuery(query); // #D
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(dir));
    TopDocs docs = searcher.search(query, 10);

    FileWriter writer = new FileWriter(filename);
    writer.write("<html>");
    writer.write("<body>");
    writer.write("<p>QUERY : " + QUERY + "</p>");
    for (ScoreDoc scoreDoc : docs.scoreDocs) {
        String snippet = highlighter.getBestFragment( // #E
                fieldQuery, searcher.getIndexReader(), // #E
                scoreDoc.doc, F, 100); // #E
        if (snippet != null) {
            writer.write(scoreDoc.doc + " : " + snippet + "<br/>");
        }//from  w w w.ja v a2 s .c o m
    }
    writer.write("</body></html>");
    writer.close();

}

From source file:lia.tools.FastVectorHighlighterSample.java

License:Apache License

static void searchIndex(String filename) throws Exception {
    QueryParser parser = new QueryParser(Version.LUCENE_30, F, analyzer);
    Query query = parser.parse(QUERY);
    FastVectorHighlighter highlighter = getHighlighter(); // #C
    FieldQuery fieldQuery = highlighter.getFieldQuery(query); // #D
    IndexSearcher searcher = new IndexSearcher(dir);
    TopDocs docs = searcher.search(query, 10);

    FileWriter writer = new FileWriter(filename);
    writer.write("<html>");
    writer.write("<body>");
    writer.write("<p>QUERY : " + QUERY + "</p>");
    for (ScoreDoc scoreDoc : docs.scoreDocs) {
        String snippet = highlighter.getBestFragment( // #E
                fieldQuery, searcher.getIndexReader(), // #E
                scoreDoc.doc, F, 100); // #E
        if (snippet != null) {
            writer.write(scoreDoc.doc + " : " + snippet + "<br/>");
        }/*w  w w.j a  va2s .  c o  m*/
    }
    writer.write("</body></html>");
    writer.close();
    searcher.close();
}

From source file:org.elasticsearch.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);//from www .j av a 2 s  .co  m

    IndexReader reader = DirectoryReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(
            highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
    assertThat(fragment, equalTo("the big <b>bad</b> dog"));
}

From source file:org.elasticsearch.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighterPrefixQuery() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);/*  w  ww  . j  a v  a2  s .c  o m*/

    IndexReader reader = DirectoryReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();

    PrefixQuery prefixQuery = new PrefixQuery(new Term("content", "ba"));
    assertThat(prefixQuery.getRewriteMethod().getClass().getName(),
            equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(prefixQuery), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());

    prefixQuery.setRewriteMethod(PrefixQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    Query rewriteQuery = prefixQuery.rewrite(reader);
    fragment = highlighter.getBestFragment(highlighter.getFieldQuery(rewriteQuery), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());

    // now check with the custom field query
    prefixQuery = new PrefixQuery(new Term("content", "ba"));
    assertThat(prefixQuery.getRewriteMethod().getClass().getName(),
            equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
    fragment = highlighter.getBestFragment(new CustomFieldQuery(prefixQuery, reader, highlighter), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
}

From source file:org.elasticsearch.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighterNoStore() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.NO, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);//w ww. ja  v a2  s .  c o  m

    IndexReader reader = DirectoryReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(
            highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
}

From source file:org.elasticsearch.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighterNoTermVector() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.NO));
    indexWriter.addDocument(document);//from  ww  w. j  av a  2 s.c o  m

    IndexReader reader = DirectoryReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(
            highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
}

From source file:org.elasticsearch.test.unit.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);//  w ww. ja  va 2 s  . c o m

    IndexReader reader = IndexReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(
            highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
    assertThat(fragment, equalTo("the big <b>bad</b> dog"));
}

From source file:org.elasticsearch.test.unit.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighterPrefixQuery() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);/* www. ja v a2  s.  c  om*/

    IndexReader reader = IndexReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();

    PrefixQuery prefixQuery = new PrefixQuery(new Term("content", "ba"));
    assertThat(prefixQuery.getRewriteMethod().getClass().getName(),
            equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(prefixQuery), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());

    prefixQuery.setRewriteMethod(PrefixQuery.SCORING_BOOLEAN_QUERY_REWRITE);
    Query rewriteQuery = prefixQuery.rewrite(reader);
    fragment = highlighter.getBestFragment(highlighter.getFieldQuery(rewriteQuery), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());

    System.out.println(fragment);

    // now check with the custom field query
    prefixQuery = new PrefixQuery(new Term("content", "ba"));
    assertThat(prefixQuery.getRewriteMethod().getClass().getName(),
            equalTo(PrefixQuery.CONSTANT_SCORE_AUTO_REWRITE_DEFAULT.getClass().getName()));
    fragment = highlighter.getBestFragment(new CustomFieldQuery(prefixQuery, reader, highlighter), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());

    System.out.println(fragment);
}

From source file:org.elasticsearch.test.unit.deps.lucene.VectorHighlighterTests.java

License:Apache License

@Test
public void testVectorHighlighterNoStore() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir,
            new IndexWriterConfig(Lucene.VERSION, Lucene.STANDARD_ANALYZER));

    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new Field("content", "the big bad dog", Field.Store.NO, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));
    indexWriter.addDocument(document);//from   w  w w .ja  v  a2  s . c  o m

    IndexReader reader = IndexReader.open(indexWriter, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs topDocs = searcher.search(new TermQuery(new Term("_id", "1")), 1);

    assertThat(topDocs.totalHits, equalTo(1));

    FastVectorHighlighter highlighter = new FastVectorHighlighter();
    String fragment = highlighter.getBestFragment(
            highlighter.getFieldQuery(new TermQuery(new Term("content", "bad"))), reader,
            topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
}