Example usage for org.apache.lucene.search IndexSearcher setSimilarity

Introduction

In this page you can find the example usage for org.apache.lucene.search IndexSearcher setSimilarity.

Prototype

public void setSimilarity(Similarity similarity)

Source Link

Document

Expert: Set the Similarity implementation used by this IndexSearcher.

Usage

From source file:trabajo.SearchFiles.java

License:Apache License

/**
 * This demonstrates a typical paging search scenario, where the search
 * engine presents pages of size n to the user. The user can then go to the
 * next page if interested in the next hits.
 * //from  w  w w  .j  a v a 2s  .  co m
 * When the query is executed for the first time, then only enough results
 * are collected to fill 5 result pages. If the user wants to page beyond
 * this limit, then the query is executed another time and all hits are
 * collected.
 * 
 */
public static void doPagingSearch(BufferedReader in, IndexSearcher searcher, Query query, int hitsPerPage,
        boolean interactive, FileWriter bw, String id) throws IOException {

    searcher.setSimilarity(new BM25Similarity());
    // Collect enough docs to show 5 pages
    TopDocs results = searcher.search(query, 5 * hitsPerPage);
    ScoreDoc[] hits = results.scoreDocs;

    int numTotalHits = results.totalHits;
    System.out.println(numTotalHits + " total matching documents");

    int start = 0;
    int end = numTotalHits;

    while (true) {

        if (end > hits.length) {
            System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                    + " total matching documents collected.");
            hits = searcher.search(query, numTotalHits).scoreDocs;
        }

        end = Math.min(hits.length, start + hitsPerPage);

        for (int i = start; i < end; i++) {
            // System.out.println(searcher.explain(query, hits[i].doc));

            // if (false) { // output raw format
            // System.out.println("doc="+hits[i].doc+" score="+hits[i].score);
            // continue;
            // }

            Document doc = searcher.doc(hits[i].doc);
            String path = doc.get("path");
            if (path != null) {
                System.out.println(id + "\t" + path.substring(22, path.length()));
                bw.write(id + "\t" + path.substring(22, path.length()) + "\n");
            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }

        if (!interactive || end == 0) {
            break;
        }

        if (numTotalHits >= end) {
            boolean quit = false;
            while (true) {
                System.out.print("Press ");
                if (start - hitsPerPage >= 0) {
                    System.out.print("(p)revious page, ");
                }
                if (start + hitsPerPage < numTotalHits) {
                    System.out.print("(n)ext page, ");
                }
                System.out.println("(q)uit or enter number to jump to a page.");

                String line = in.readLine();
                if (line.length() == 0 || line.charAt(0) == 'q') {
                    quit = true;
                    break;
                }
                if (line.charAt(0) == 'p') {
                    start = Math.max(0, start - hitsPerPage);
                    break;
                } else if (line.charAt(0) == 'n') {
                    if (start + hitsPerPage < numTotalHits) {
                        start += hitsPerPage;
                    }
                    break;
                } else {
                    int page = Integer.parseInt(line);
                    if ((page - 1) * hitsPerPage < numTotalHits) {
                        start = (page - 1) * hitsPerPage;
                        break;
                    } else {
                        System.out.println("No such page");
                    }
                }
            }
            if (quit)
                break;
            end = Math.min(numTotalHits, start + hitsPerPage);
        }
    }
}

From source file:uk.co.flax.luwak.DocumentBatch.java

License:Apache License

/**
 * @return an {@link IndexSearcher} over the documents in this batch
 * @throws IOException on error/*from w  w  w  . j  a va 2  s . c om*/
 */
public IndexSearcher getSearcher() throws IOException {
    IndexSearcher searcher = new IndexSearcher(getIndexReader());
    searcher.setSimilarity(similarity);
    return searcher;
}