Examples with FastVectorHighlighter org.apache.lucene.search.vectorhighlight.FastVectorHighlighter used on opensource projects

Example 1 with FastVectorHighlighter

use of org.apache.lucene.search.vectorhighlight.FastVectorHighlighter in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighterNoTermVector.

public void testVectorHighlighterNoTermVector() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    document.add(new TextField("content", "the big bad dog", Field.Store.YES));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    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());
}

Example 2 with FastVectorHighlighter

use of org.apache.lucene.search.vectorhighlight.FastVectorHighlighter in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighter.

public void testVectorHighlighter() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    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"));
}

Example 3 with FastVectorHighlighter

use of org.apache.lucene.search.vectorhighlight.FastVectorHighlighter in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighterNoStore.

public void testVectorHighlighterNoStore() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_NOT_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    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());
}

Example 4 with FastVectorHighlighter

use of org.apache.lucene.search.vectorhighlight.FastVectorHighlighter in project elasticsearch by elastic.

the class VectorHighlighterTests method testVectorHighlighterPrefixQuery.

public void testVectorHighlighterPrefixQuery() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter indexWriter = new IndexWriter(dir, new IndexWriterConfig(Lucene.STANDARD_ANALYZER));
    Document document = new Document();
    document.add(new TextField("_id", "1", Field.Store.YES));
    FieldType vectorsType = new FieldType(TextField.TYPE_STORED);
    vectorsType.setStoreTermVectors(true);
    vectorsType.setStoreTermVectorPositions(true);
    vectorsType.setStoreTermVectorOffsets(true);
    document.add(new Field("content", "the big bad dog", vectorsType));
    indexWriter.addDocument(document);
    IndexReader reader = DirectoryReader.open(indexWriter);
    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_REWRITE.getClass().getName()));
    String fragment = highlighter.getBestFragment(highlighter.getFieldQuery(prefixQuery), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, nullValue());
    prefixQuery.setRewriteMethod(PrefixQuery.SCORING_BOOLEAN_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_REWRITE.getClass().getName()));
    fragment = highlighter.getBestFragment(new CustomFieldQuery(prefixQuery, reader, highlighter), reader, topDocs.scoreDocs[0].doc, "content", 30);
    assertThat(fragment, notNullValue());
}

Example 5 with FastVectorHighlighter

use of org.apache.lucene.search.vectorhighlight.FastVectorHighlighter in project lucene-solr by apache.

the class TermVectorReusingLeafReader method doHighlightingOfField.

protected Object doHighlightingOfField(Document doc, int docId, SchemaField schemaField, FvhContainer fvhContainer, Query query, IndexReader reader, SolrQueryRequest req, SolrParams params) throws IOException {
    Object fieldHighlights;
    if (schemaField == null) {
        fieldHighlights = null;
    } else if (schemaField.getType() instanceof org.apache.solr.schema.TrieField) {
        // TODO: highlighting numeric fields is broken (Lucene) - so we disable them until fixed (see LUCENE-3080)!
        fieldHighlights = null;
    } else if (useFastVectorHighlighter(params, schemaField)) {
        if (fvhContainer.fieldQuery == null) {
            FastVectorHighlighter fvh = new FastVectorHighlighter(// FVH cannot process hl.usePhraseHighlighter parameter per-field basis
            params.getBool(HighlightParams.USE_PHRASE_HIGHLIGHTER, true), // FVH cannot process hl.requireFieldMatch parameter per-field basis
            params.getBool(HighlightParams.FIELD_MATCH, false));
            fvh.setPhraseLimit(params.getInt(HighlightParams.PHRASE_LIMIT, SolrHighlighter.DEFAULT_PHRASE_LIMIT));
            fvhContainer.fvh = fvh;
            fvhContainer.fieldQuery = fvh.getFieldQuery(query, reader);
        }
        fieldHighlights = doHighlightingByFastVectorHighlighter(doc, docId, schemaField, fvhContainer, reader, req);
    } else {
        // standard/default highlighter
        fieldHighlights = doHighlightingByHighlighter(doc, docId, schemaField, query, reader, req);
    }
    return fieldHighlights;
}