Example usage for org.apache.lucene.search.vectorhighlight FieldPhraseList FieldPhraseList

Introduction

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

Prototype

public FieldPhraseList(FieldTermStack fieldTermStack, FieldQuery fieldQuery) 

Source Link

Document

create a FieldPhraseList that has no limit on the number of phrases to analyze

Usage

From source file:net.sourceforge.docfetcher.model.search.HighlightService.java

License:Open Source License

@MutableCopy
@NotNull/*from   w w  w.  j  a  v a  2  s.  c  o  m*/
@SuppressWarnings("unchecked")
private static List<Range> highlightPhrases(@NotNull Query query, @NotNull String text)
        throws CheckedOutOfMemoryError {
    // FastVectorHighlighter only supports TermQuery, PhraseQuery and BooleanQuery
    FastVectorHighlighter highlighter = new FastVectorHighlighter(true, true, null, null);
    FieldQuery fieldQuery = highlighter.getFieldQuery(query);
    Directory directory = new RAMDirectory();
    try {
        /*
         * Hack: We have to put the given text in a RAM index, because the
         * fast-vector highlighter can only work on index readers
         */
        IndexWriterAdapter writer = new IndexWriterAdapter(directory);
        Document doc = new Document();
        doc.add(Fields.createContent(text, true)); // must store token positions and offsets
        writer.add(doc);
        Closeables.closeQuietly(writer); // flush unwritten documents into index
        IndexReader indexReader = IndexReader.open(directory);

        // This might throw an OutOfMemoryError
        FieldTermStack fieldTermStack = new FieldTermStack(indexReader, 0, Fields.CONTENT.key(), fieldQuery);

        FieldPhraseList fieldPhraseList = new FieldPhraseList(fieldTermStack, fieldQuery);

        // Hack: We'll use reflection to access a private field
        java.lang.reflect.Field field = fieldPhraseList.getClass().getDeclaredField("phraseList");
        field.setAccessible(true);
        LinkedList<WeightedPhraseInfo> infoList = (LinkedList<WeightedPhraseInfo>) field.get(fieldPhraseList);

        List<Range> ranges = new ArrayList<Range>(infoList.size());
        for (WeightedPhraseInfo phraseInfo : infoList) {
            int start = phraseInfo.getStartOffset();
            int end = phraseInfo.getEndOffset();
            ranges.add(new Range(start, end - start));
        }
        return ranges;
    } catch (OutOfMemoryError e) {
        throw new CheckedOutOfMemoryError(e);
    } catch (Exception e) {
        return new ArrayList<Range>(0);
    }
}

---

From source file:net.sourceforge.docfetcher.model.search.HighlightServiceTest.java

License:Open Source License

@SuppressWarnings("unchecked")
@Test/*w  w w  . j a v  a 2s  .co m*/
public void testPhraseHighlighter() throws Exception {
    // Create index
    Directory directory = new RAMDirectory();
    Analyzer analyzer = new StandardAnalyzer(IndexRegistry.LUCENE_VERSION, Collections.EMPTY_SET);
    IndexWriterAdapter writer = new IndexWriterAdapter(directory);
    Document doc = new Document();
    doc.add(new Field("content", "some text", Store.NO, Index.ANALYZED, TermVector.WITH_POSITIONS_OFFSETS));
    writer.add(doc);
    Closeables.closeQuietly(writer); // flush unwritten documents into index

    // Perform phrase search
    QueryParser queryParser = new QueryParser(IndexRegistry.LUCENE_VERSION, "content", analyzer);
    Query query = queryParser.parse("\"text\"");
    FastVectorHighlighter highlighter = new FastVectorHighlighter(true, true, null, null);
    FieldQuery fieldQuery = highlighter.getFieldQuery(query);
    IndexSearcher searcher = null;
    try {
        searcher = new IndexSearcher(directory);
        TopDocs docs = searcher.search(query, 10);
        assertEquals(1, docs.scoreDocs.length);
        int docId = docs.scoreDocs[0].doc;

        // Get phrase highlighting offsets
        FieldTermStack fieldTermStack = new FieldTermStack(searcher.getIndexReader(), docId, "content",
                fieldQuery);
        FieldPhraseList fieldPhraseList = new FieldPhraseList(fieldTermStack, fieldQuery);
        java.lang.reflect.Field field = fieldPhraseList.getClass().getDeclaredField("phraseList");
        field.setAccessible(true);
        LinkedList<WeightedPhraseInfo> list = (LinkedList<WeightedPhraseInfo>) field.get(fieldPhraseList);
        assertEquals(5, list.get(0).getStartOffset());
        assertEquals(9, list.get(0).getEndOffset());
    } finally {
        Closeables.closeQuietly(searcher);
    }
}

---

From source file:net.sourceforge.vaticanfetcher.model.search.HighlightServiceTest.java

License:Open Source License

@SuppressWarnings("unchecked")
@Test//  w  w w  .  j a  va2 s .  c o  m
public void testPhraseHighlighter() throws Exception {
    // Create index
    Directory directory = new RAMDirectory();
    Analyzer analyzer = new StandardAnalyzer(IndexRegistry.LUCENE_VERSION, Collections.EMPTY_SET);
    IndexWriterAdapter writer = new IndexWriterAdapter(directory);
    Document doc = new Document();
    doc.add(new Field("content", "some text", Store.NO, Index.ANALYZED, TermVector.WITH_POSITIONS_OFFSETS));
    writer.add(doc);
    Closeables.closeQuietly(writer); // flush unwritten documents into index

    // Perform phrase search
    QueryParser queryParser = new QueryParser(IndexRegistry.LUCENE_VERSION, "content", analyzer);
    Query query = queryParser.parse("\"text\"");
    FastVectorHighlighter highlighter = new FastVectorHighlighter(true, true, null, null);
    FieldQuery fieldQuery = highlighter.getFieldQuery(query);
    IndexSearcher searcher = new IndexSearcher(directory);
    TopDocs docs = searcher.search(query, 10);
    assertEquals(1, docs.scoreDocs.length);
    int docId = docs.scoreDocs[0].doc;

    // Get phrase highlighting offsets
    FieldTermStack fieldTermStack = new FieldTermStack(searcher.getIndexReader(), docId, "content", fieldQuery);
    FieldPhraseList fieldPhraseList = new FieldPhraseList(fieldTermStack, fieldQuery);
    java.lang.reflect.Field field = fieldPhraseList.getClass().getDeclaredField("phraseList");
    field.setAccessible(true);
    LinkedList<WeightedPhraseInfo> list = (LinkedList<WeightedPhraseInfo>) field.get(fieldPhraseList);
    assertEquals(5, list.get(0).getStartOffset());
    assertEquals(9, list.get(0).getEndOffset());
}

---