Example usage for org.apache.lucene.search TopScoreDocCollector create

Introduction

In this page you can find the example usage for org.apache.lucene.search TopScoreDocCollector create.

Prototype

public static TopScoreDocCollector create(int numHits, int totalHitsThreshold) 

Source Link

Document

Creates a new TopScoreDocCollector given the number of hits to collect and the number of hits to count accurately.

Usage

From source file:org.xeustechnologies.treeing.TreeingTest.java

License:Open Source License

@Test
public void testSearch() throws Exception {
    FSDirectory index = FSDirectory.open(new File("C:/test/luc"));

    String querystr = "hello";
    Query q = new QueryParser(Version.LUCENE_CURRENT, "contents", new StandardAnalyzer(Version.LUCENE_CURRENT))
            .parse(querystr);//from  ww  w  .jav  a2s .  c  o  m

    int hitsPerPage = 10;
    IndexSearcher searcher = new IndexSearcher(index, true);
    TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
    searcher.search(q, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    System.out.println(collector.getTotalHits());

    for (int i = 0; i < hits.length; ++i) {
        int docId = hits[i].doc;
        Document d = searcher.doc(docId);
        System.out.println((i + 1) + ". " + d.get("url"));
    }
}

---

From source file:parts.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.// ww  w  .  j a  v a2 s.c o 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, Searcher searcher, Query query, int hitsPerPage,
        boolean raw, boolean interactive) throws IOException {

    // Collect enough docs to show 5 pages
    TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
    searcher.search(query, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    int numTotalHits = collector.getTotalHits();
    System.out.println(numTotalHits + " total matching documents");

    int start = 0;
    // int end = Math.min(numTotalHits, hitsPerPage);
    int end = Math.min(numTotalHits, hitsPerPage);

    while (true) {
        if (end > hits.length) {
            System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                    + " total matching documents collected.");
            System.out.println("Collect more (y/n) ?");
            String line = in.readLine();
            if (line.length() == 0 || line.charAt(0) == 'n') {
                break;
            }

            collector = TopScoreDocCollector.create(numTotalHits, false);
            searcher.search(query, collector);
            hits = collector.topDocs().scoreDocs;
        }

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

        for (int i = start; i < end; i++) {
            if (raw) { // 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((i + 1) + ". " + path);
                String title = doc.get("title");
                if (title != null) {
                    System.out.println("   Title: " + doc.get("title"));
                }
            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }

        if (!interactive) {
            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:persistence.lucene.search.QueryExecutorHelper.java

License:Open Source License

List<QueryResult> queryDocuments(final String query, final String[] fields, final String user)
        throws ParseException, IOException, InvalidTokenOffsetsException {
    int hitsPerPage = 10;
    MultiFieldQueryParser queryParser = new MultiFieldQueryParser(fields, new StandardAnalyzer());

    Query luceneQuery = queryParser.parse(query);
    Highlighter highlighter = new Highlighter(new QueryScorer(luceneQuery));

    DirectoryReader indexReader = DirectoryReader.open(directory);
    IndexSearcher searcher = new IndexSearcher(indexReader);

    TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
    TermsFilter filter = new TermsFilter(new Term(FullTextSearchResource.DOCUMENT_OWNER, user.toLowerCase()));
    searcher.search(luceneQuery, filter, collector);

    ScoreDoc[] docs = collector.topDocs().scoreDocs;
    List<QueryResult> resultBeans = new ArrayList<>(docs.length);
    for (ScoreDoc doc : docs) {
        Document document = searcher.doc(doc.doc);
        String text = document.get(FullTextSearchResource.DOCUMENT_CONTENT_FIELD);
        TokenStream tokenStream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), doc.doc,
                FullTextSearchResource.DOCUMENT_CONTENT_FIELD, standardAnalyzer);
        TextFragment[] fragments = highlighter.getBestTextFragments(tokenStream, text, false, 10);

        resultBeans.add(new QueryResult(doc.doc, doc.score, document, fragments));
    }// w w  w .j a v a 2 s .c  om

    indexReader.close();
    return resultBeans;
}

---

From source file:pt.ua.ieeta.biomedhub.dictionaries.wrappers.CTakesLucene.java

License:Open Source License

public Multimap readBlocks(int blockSize) throws IOException {

    try {/*from w w  w  . j  av  a  2s  .  c om*/
        if (!DirectoryReader.indexExists(index)) {
            return null;
        }
    } catch (IOException ex) {
        Logger.getLogger("lucene").log(Level.SEVERE, null, ex);
    }

    String querystr = "*:*";
    Query q = null;
    try {
        q = new QueryParser(Version.LUCENE_4_9, "title", analyzer).parse(querystr);
    } catch (ParseException ex) {
        Logger.getLogger(CTakesLucene.class.getName()).log(Level.SEVERE, null, ex);
    }
    int hitsPerPage = 100;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopScoreDocCollector collector = TopScoreDocCollector.create(200000, true);
    searcher.search(q, collector);

    ScoreDoc[] hits = collector.topDocs().scoreDocs;
    System.out.println("Found " + hits.length + " hits.");
    for (int i = 0; i < hits.length; ++i) {
        int docId = hits[i].doc;
        Document d = searcher.doc(docId);
        //System.out.println((i + 1) + ". " + d.get("first_word") + "\t" + d.get("code"));
        System.out.print(".");
        synons.put(d.get("code"), d.get("first_word"));
    }

    return synons;

}

---

From source file:retrievability.SampledQuery.java

TopDocs execute(IndexSearcher searcher) throws Exception {
    TopScoreDocCollector collector = TopScoreDocCollector.create(sampler.getNumWanted(), true);
    searcher.search(this.lucquery, collector);
    return collector.topDocs();
}

---

From source file:retrievability.UserQueryIndex.java

public static void printing_indexes() throws Exception {

    ScoreDoc[] hits = null;/*from w ww .  ja v a 2 s.  c  om*/
    TopDocs topDocs = null;

    System.out.println("Searching for --- ");
    Directory index = FSDirectory.open(new File(indexDir));
    IndexReader indexReader = IndexReader.open(index);
    IndexSearcher indexSearcher = new IndexSearcher(indexReader);
    //Searcher searcher=new Searcher();
    Query queryDocid = new TermQuery(new Term("user_id", "ayaisthebest"));
    //Analyzer analyzer = new SimpleAnalyzer(Version.LUCENE_CURRENT);
    //QueryParser queryParser = new QueryParser(Version.LUCENE_3_0, user_id, analyzer);

    TopScoreDocCollector collectorDocSearch = TopScoreDocCollector.create(100, true);

    indexSearcher.search(queryDocid, collectorDocSearch);
    topDocs = collectorDocSearch.topDocs();
    hits = topDocs.scoreDocs;
    System.out.println(hits.length);

    if (hits == null) {
        System.out.println("Nothing found");
        //return -1;
    } else {

        for (int i = 0; i < hits.length; i++) {
            System.out.println("printing ayaisthebest---" + hits[i]);
            int docId = hits[i].doc;
            Document d = indexSearcher.doc(docId);
            String prev_search = d.get("search_query");
            // do something with current hit
            System.err.println("docID:" + docId + d.get("search_query"));
            System.err.println("");

        }
        //return hits[0].doc;
    }
}

---

From source file:retriever.TermFreq.java

public float batchRetrieveTREC(CubicBezierTF dtfFunc) throws Exception {
    System.out.println("Batch retrieving for TREC " + this.getTrecCode());

    Similarity sim = new GeneralizedTfIdfSimilarity(dtfFunc);
    searcher.setSimilarity(sim);//from  w w  w.  java  2s .  c om

    List<TRECQuery> queries = constructQueries(trecCode);
    float map = 0f;

    for (TRECQuery query : queries) {
        System.out.println("Retrieving for query " + query.id + ": " + query);
        TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
        Query luceneQuery = buildQuery(query.title);
        searcher.search(luceneQuery, collector);

        TopDocs initialList = collector.topDocs();
        map += evaluator.computeAP(query.id, initialList);

        /*
        // Re-rank based on the custom tf functions for doc and qry
        DoclistReranker reranker = new DoclistReranker(reader,
            dtfFunc, luceneQuery, initialList);
        TopDocs rerankedDocs = reranker.rerank();
                
        map += evaluator.computeAP(query.id, rerankedDocs);
        */
    }

    float numQueries = (float) queries.size();
    map /= numQueries;
    System.out.println("MAP " + dtfFunc.toString() + ": " + map);

    // Evaluate
    // TODO: Write code here to evaluate and keep track of the
    // function settings which yields the highest MAP till now.
    dtfFunc.setMAP(map);
    return map;
}

---

From source file:reviews.searching.SearchReviews.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 ww  w . ja  v  a2s  . c  o  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, Searcher searcher, Query query, int hitsPerPage,
        boolean raw, boolean interactive) throws IOException {

    // Collect enough docs to show 5 pages
    TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
    searcher.search(query, collector);
    ScoreDoc[] hits = collector.topDocs().scoreDocs;

    int numTotalHits = collector.getTotalHits();
    System.out.println(numTotalHits + " total matching documents");

    int start = 0;
    int end = Math.min(numTotalHits, hitsPerPage);

    while (true) {
        if (end > hits.length) {
            System.out.println("Only results 1 - " + hits.length + " of " + numTotalHits
                    + " total matching documents collected.");
            System.out.println("Collect more (y/n) ?");
            String line = in.readLine();
            if (line.length() == 0 || line.charAt(0) == 'n') {
                break;
            }

            collector = TopScoreDocCollector.create(numTotalHits, false);
            searcher.search(query, collector);
            hits = collector.topDocs().scoreDocs;
        }

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

        for (int i = start; i < end; i++) {
            if (raw) { // 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((i + 1) + ". " + path);
                String title = doc.get("title");
                if (title != null)
                    ;// System.out.println("Title: " + doc.get("title"));

                //      HTMLParser parser = new HTMLParser(new File(path));
                //      Reader reader = parser.getReader();

                /*
                SentenceTokenizer sentTok = new SentenceTokenizer(reader);
                while (sentTok.incrementToken()) {
                   displayTokenStream(sentTok);
                }
                */

                /*   String contents = "";
                   int c;
                   while ((c = reader.read()) != -1) {
                      char buf[] = Character.toChars(c);
                      contents += String.valueOf(buf);
                   }
                        
                   //System.out.println("contents ");
                   //System.out.println(contents);
                           
                   // creates a StanfordCoreNLP object, with POS tagging, parsing 
                   Properties props = new Properties();
                    props.put("annotators", "tokenize, ssplit");
                    StanfordCoreNLP pipeline = new StanfordCoreNLP(props);
                    Annotation document = new Annotation(contents);
                            
                    // run all Annotators on this text
                    pipeline.annotate(document);
                    List<CoreMap> sentences = document.get(SentencesAnnotation.class);
                            
                   for (CoreMap sentence : sentences) {
                      //System.out.println("sentence: " + sentence.toString());
                      System.out.println("sentence: " + sentence.get(TextAnnotation.class));
                              
                      // traversing the words in the current sentence
                      System.out.println("Has the following words: ");
                      for (CoreLabel token : sentence.get(TokensAnnotation.class)) {
                         // this is the text of the token
                         String word = token.get(TextAnnotation.class);
                         System.out.print(word + "  ");
                      }
                      System.out.println();
                   }             
                 */

            } else {
                System.out.println((i + 1) + ". " + "No path for this document");
            }

        }

        if (!interactive) {
            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:searchenginelucene.LuceneSearchEngine.java

public static void searchForQuery(String indexLocation, String s, BufferedReader br) throws IOException {

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexLocation)));
    IndexSearcher searcher = new IndexSearcher(reader);
    PrintWriter writer_query = new PrintWriter("..\\Query-1.csv");

    s = "";/*  w  w w .  ja va2 s . com*/
    while (!s.equalsIgnoreCase("q")) {
        TopScoreDocCollector collector = TopScoreDocCollector.create(100, true);

        try {
            System.out.println("Enter the search query (q=quit):");
            s = br.readLine();
            if (s.equalsIgnoreCase("q")) {
                writer_query.close();
                break;
            }

            Query q = new QueryParser(Version.LUCENE_47, "contents", sAnalyzer).parse(s);
            searcher.search(q, collector);
            ScoreDoc[] hits = collector.topDocs().scoreDocs;

            // Write the results in a file
            System.out.println("Found " + hits.length + " hits.");
            for (int i = 0; i < hits.length; ++i) {
                int docId = hits[i].doc;
                Document d = searcher.doc(docId);
                writer_query.println((i + 1) + "," + s + ", " + d.get("filename") + "," + hits[i].score);
            }
            // 
            // Term termInstance = new Term("contents", s);
            // System.out.println("The term is:" + termInstance.toString());
            // long termFreq = reader.totalTermFreq(termInstance);
            //  long docCount = reader.docFreq(termInstance);
            // System.out.println(s + " Term Frequency " + termFreq
            //        + " - Document Frequency " + docCount);

        } catch (Exception e) {
            System.out.println("Error searching " + s + " : " + e.getMessage());
            break;
        }
        writer_query.close();
    }

}

---

From source file:searcher.CollStat.java

private String retrieve(IndexReader reader, String queryStr) throws Exception {
    ScoreDoc[] hits = null;//w  w w  .j a  va 2s. c om
    TopDocs topDocs = null;

    Query query = buildQuery(queryStr);
    TopScoreDocCollector collector = TopScoreDocCollector.create(numTopDocs, true);

    IndexSearcher searcher = initSearcher(reader);
    searcher.search(query, collector);
    topDocs = collector.topDocs();
    hits = topDocs.scoreDocs;

    if (hits == null || hits.length == 0) {
        return "Nothing found!!";
    }
    return constructJSONForRetrievedSet(reader, query, hits);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• »