Example usage for org.apache.lucene.search.highlight SimpleFragmenter SimpleFragmenter

Introduction

In this page you can find the example usage for org.apache.lucene.search.highlight SimpleFragmenter SimpleFragmenter.

Prototype

public SimpleFragmenter() 

Source Link

Usage

From source file:it.cnr.ilc.lc.claviusweb.ClaviusSearch.java

private static List<Annotation> fullTextSearch(String term)
        throws IOException, ParseException, InvalidTokenOffsetsException {

    log.info("fullTextSearch (" + term + ")");
    List<Annotation> result = new ArrayList<>();

    try {//  www . ja  va  2 s .  c o  m
        Directory indexDirectory = FSDirectory
                .open(Paths.get("/var/lucene/clavius-1.0.5/indexes/it.cnr.ilc.lc.claviusweb.entity.PlainText"));
        DirectoryReader ireader = DirectoryReader.open(indexDirectory);

        IndexSearcher searcher = new IndexSearcher(ireader);

        Analyzer fullTextAnalyzer = CustomAnalyzer.builder()
                .addCharFilter("patternReplace", "pattern", "([\\-\\(\\)\\[\\],\\.;:])", "replacement", " $1 ")
                .withTokenizer("whitespace").build();

        //QueryParser parserTerm = new QueryParser("content", fullTextAnalyzer);
        //            AnalyzingQueryParser parser = new AnalyzingQueryParser("content", fullTextAnalyzer);
        //            Query query2 = parser.parse(term);
        //            
        Query query = new WildcardQuery(new Term("content", term));
        TopDocs hits = searcher.search(query, MAX_SEARCH_HITS);

        SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter();
        //Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(query));
        ClaviusHighlighter highlighter = new ClaviusHighlighter(htmlFormatter, new QueryScorer(query));
        highlighter.setTextFragmenter(new SimpleFragmenter());

        log.info("hits.totalHits=(" + hits.totalHits + ")");
        for (int i = 0; i < hits.totalHits; i++) {
            int id = hits.scoreDocs[i].doc;
            Document doc = searcher.doc(id);
            String idDoc = doc.get("idDoc");

            //String text = doc.get("content");
            TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), id, "content",
                    fullTextAnalyzer);

            List<Annotation> frag = highlighter.getBestTextClaviusFragments(tokenStream, doc, false, 10);//highlighter.getBestFragments(tokenStream, text, 3, "...");
            for (int j = 0; j < frag.size(); j++) {
                log.debug("idDoc: " + idDoc + ", Annotation[" + j + "] " + frag.get(j).toString());
            }
            result.addAll(frag);
        }
    } catch (InvalidTokenOffsetsException | IOException e) {
        log.error(e);
    }
    log.info("Full Text Search found " + result.size() + " result(s) for term " + term);
    return result;
}

---