Example usage for org.apache.lucene.queryparser.classic QueryParser QueryParser

Introduction

In this page you can find the example usage for org.apache.lucene.queryparser.classic QueryParser QueryParser.

Prototype

public QueryParser(String f, Analyzer a) 

Source Link

Document

Create a query parser.

Usage

From source file:SearchFiles.java

License:Apache License

/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
    String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        System.out.println(usage);
        System.exit(0);//from w  ww.ja va2  s.  c o m
    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;

    for (int i = 0; i < args.length; i++) {
        if ("-index".equals(args[i])) {
            index = args[i + 1];
            i++;
        } else if ("-field".equals(args[i])) {
            field = args[i + 1];
            i++;
        } else if ("-queries".equals(args[i])) {
            queries = args[i + 1];
            i++;
        } else if ("-query".equals(args[i])) {
            queryString = args[i + 1];
            i++;
        } else if ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-paging".equals(args[i])) {
            hitsPerPage = Integer.parseInt(args[i + 1]);
            if (hitsPerPage <= 0) {
                System.err.println("There must be at least 1 hit per page.");
                System.exit(1);
            }
            i++;
        }
    }

    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    if (queries != null) {
        in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    QueryParser parser = new QueryParser(field, analyzer);
    while (true) {
        if (queries == null && queryString == null) { // prompt the user
            System.out.println("Enter query: ");
        }

        String line = queryString != null ? queryString : in.readLine();

        if (line == null || line.length() == -1) {
            break;
        }

        line = line.trim();
        if (line.length() == 0) {
            break;
        }

        Query query = parser.parse(line);
        System.out.println("Searching for: " + query.toString(field));

        if (repeat > 0) { // repeat & time as benchmark
            Date start = new Date();
            for (int i = 0; i < repeat; i++) {
                searcher.search(query, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

        if (queryString != null) {
            break;
        }
    }
    reader.close();
}

---

From source file:MyServlet.java

private void gotoSearch(PrintWriter out, HttpServletRequest request, HttpServletResponse response) {
    try {//  ww  w.j a  va2 s .c  o  m
        //   Text to search
        String querystr = request.getParameter("keyword");

        log.addHistory(querystr);

        //   The \"title\" arg specifies the default field to use when no field is explicitly specified in the query
        Query q = new QueryParser("Classes", analyzer).parse(querystr);

        // Searching code
        int hitsPerPage = 10;
        IndexReader reader = DirectoryReader.open(index);
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage);
        searcher.search(q, collector);
        ScoreDoc[] hits = collector.topDocs().scoreDocs;

        //   Code to display the results of search
        //out.println("Found " + hits.length + " Classes Matching your Requirement");
        courseList = new ArrayList();
        for (int i = 0; i < hits.length; ++i) {
            int docId = hits[i].doc;
            Document d = searcher.doc(docId);
            Course course = new Course(d.get("Number"), d.get("Classes"), d.get("Time"), d.get("Department"));
            //out.println((i + 1) + ". " +  d.get("Number")+ d.get("Classes") );
            courseList.add(course);
        }
        request.setAttribute("course", courseList);
        RequestDispatcher de = request.getRequestDispatcher("/table.jsp");
        de.forward(request, response);

        // reader can only be closed when there is no need to access the documents any more
        reader.close();
    } catch (Exception e) {
        System.out.println(e.getMessage());
    }
}

---

From source file:SearcherTest.java

/**
 * ??/*  w ww . jav  a 2s.  c om*/
 * QueryParser?????Query?
 *
 * @throws Exception
 */
@Test
public void testQueryParser() throws Exception {
    Analyzer analyzer = new StandardAnalyzer(); // ?
    String searchField = "contents";
    String q = "xxxxxxxxx$";
    //??
    QueryParser parser = new QueryParser(searchField, analyzer);
    //
    Query query = parser.parse(q);
    TopDocs hits = is.search(query, 100);
    System.out.println("? " + q + "" + hits.totalHits + "");
    for (ScoreDoc scoreDoc : hits.scoreDocs) {
        Document doc = is.doc(scoreDoc.doc);
        System.out.println(doc.get("fullPath"));
    }
}

---

From source file:IrqaQuery.java

License:Apache License

public static List<Document> query(String index, String stoppath, String question, int numResult, String sim)
        throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);

    Analyzer analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(mygetStopwords(stoppath)));

    if (sim.equals("TFIDF"))
        searcher.setSimilarity(new ClassicSimilarity());
    else if (sim.equals("BM25"))
        searcher.setSimilarity(new BM25Similarity());
    else/* www.ja  v  a2s . co m*/
        searcher.setSimilarity(new BM25Similarity());

    String field = "contents";
    QueryParser parser = new QueryParser(field, analyzer);
    Query query = parser.parse(parser.escape(question));

    TopDocs results = searcher.search(query, numResult);
    ScoreDoc[] hits = results.scoreDocs;
    List<Document> docs = new ArrayList<Document>();

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

    int end = Math.min(numTotalHits, numResult);

    String searchResult = "";
    //        System.out.println("Only results 1 - " + hits.length);

    for (int i = 0; i < end; i++) {
        Document doc = searcher.doc(hits[i].doc);
        docs.add(doc);
    }

    return docs;
}

---

From source file:Get_Top_Documents_Based_on_Lucene.java

License:Apache License

/** Simple command-line based search demo. */
public static void main(String[] args) throws Exception {
    String usage = "Usage:\tjava org.apache.lucene.demo.SearchFiles [-index dir] [-field f] [-repeat n] [-queries file] [-query string] [-raw] [-paging hitsPerPage]\n\nSee http://lucene.apache.org/core/4_1_0/demo/ for details.";
    if (args.length > 0 && ("-h".equals(args[0]) || "-help".equals(args[0]))) {
        System.out.println(usage);
        System.exit(0);//from  www  .j  ava2  s.c o  m
    }

    //String index = "index";
    //String index = "index_wiki_2";
    String index = "index_external_links_v1/";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 20;

    for (int i = 0; i < args.length; i++) {
        if ("-index".equals(args[i])) {
            index = args[i + 1];
            i++;
        } else if ("-field".equals(args[i])) {
            field = args[i + 1];
            i++;
        } else if ("-queries".equals(args[i])) {
            queries = args[i + 1];
            i++;
        } else if ("-query".equals(args[i])) {
            queryString = args[i + 1];
            i++;
        } else if ("-repeat".equals(args[i])) {
            repeat = Integer.parseInt(args[i + 1]);
            i++;
        } else if ("-raw".equals(args[i])) {
            raw = true;
        } else if ("-paging".equals(args[i])) {
            hitsPerPage = Integer.parseInt(args[i + 1]);
            if (hitsPerPage <= 0) {
                System.err.println("There must be at least 1 hit per page.");
                System.exit(1);
            }
            i++;
        }
    }

    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    if (queries != null) {
        in = Files.newBufferedReader(Paths.get(queries), StandardCharsets.UTF_8);
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    QueryParser parser = new QueryParser(field, analyzer);

    // Read Question in Training Data line by line
    //String path_train = "data/training_set.tsv";
    //String path_output = "data/lucene_search_result_train.txt";
    //String path_train = "data/validation_set.tsv";
    //String path_output = "data/lucene_search_result_validation_index_wiki_2.txt";
    String path_train = "data/training_set.tsv";
    String path_output = "data/lucene_search_result_train_index_wiki_external_links_v1.txt";
    Writer writer = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(path_output), "UTF-8"));
    try (BufferedReader br = new BufferedReader(new FileReader(path_train))) {
        String line;
        while ((line = br.readLine()) != null) {
            line = line.trim();
            String[] lst = line.split("\t");
            String query_s = lst[1];
            if (query_s == "question") {
                continue;
            }
            System.out.println("query_s: " + query_s);
            writer.write(query_s + "\t");
            try {
                Query query = parser.parse(query_s);
                System.out.println("Searching for: " + query.toString(field));
                doPagingSearch(in, writer, searcher, query, hitsPerPage, raw,
                        queries == null && queryString == null);
            } catch (org.apache.lucene.queryparser.classic.ParseException e) {
                continue;
            }
        } // while
    }
    writer.close();
    /*
    while (true) {
      if (queries == null && queryString == null) {                        // prompt the user
        System.out.println("Enter query: ");
      }
            
      String line = queryString != null ? queryString : in.readLine();
            
      if (line == null || line.length() == -1) {
        break;
      }
            
      line = line.trim();
      if (line.length() == 0) {
        break;
      }
              
      Query query = parser.parse(line);
      System.out.println("Searching for: " + query.toString(field));
            
      if (repeat > 0) {                           // repeat & time as benchmark
        Date start = new Date();
        for (int i = 0; i < repeat; i++) {
          searcher.search(query, 100);
        }
        Date end = new Date();
        System.out.println("Time: "+(end.getTime()-start.getTime())+"ms");
      }
            
      doPagingSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);
            
      if (queryString != null) {
        break;
      }
    } // while (True)
    */
    reader.close();
}

---

From source file:luceneInterface.java

License:Apache License

public static List<Document> query(String index, String stoppath, String question, int numResult, String sim)
        throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(index)));
    IndexSearcher searcher = new IndexSearcher(reader);

    Analyzer analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(mygetStopwords(stoppath)));

    if (sim.equals("TFIDF"))
        searcher.setSimilarity(new ClassicSimilarity());
    else if (sim.equals("BM25"))
        searcher.setSimilarity(new BM25Similarity());
    else/*w  w w  . ja v  a 2  s  . c om*/
        searcher.setSimilarity(new BM25Similarity());

    String field = "contents";
    QueryParser parser = new QueryParser(field, analyzer);
    Query query = parser.parse(parser.escape(question));

    BooleanQuery.Builder bqb = new BooleanQuery.Builder();
    bqb.add(new TermQuery(new Term("contents", parser.escape(question))), BooleanClause.Occur.SHOULD);
    bqb.add(new TermQuery(new Term("sec", parser.escape(question))), BooleanClause.Occur.SHOULD);

    //        Term term = new Term(field, question);
    //        Query query = new TermQuery(term);

    //        TopDocs results = searcher.search(query, numResult);
    TopDocs results = searcher.search(parser.parse(bqb.build().toString()), numResult);

    ScoreDoc[] hits = results.scoreDocs;
    List<Document> docs = new ArrayList<Document>();

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

    int end = Math.min(numTotalHits, numResult);

    String searchResult = "";
    //        System.out.println("Only results 1 - " + hits.length);

    for (int i = 0; i < end; i++) {
        Document doc = searcher.doc(hits[i].doc);
        docs.add(doc);
    }

    return docs;
}

---

From source file:ac.simons.tweetarchive.tweets.TweetRepositoryImpl.java

License:Apache License

@Override
@Transactional(readOnly = true)//  w  w w  .j  a v a  2  s  .c o  m
public List<TweetEntity> searchByQuery(final String query) {
    final FullTextEntityManager fullTextEntityManager = Search.getFullTextEntityManager(entityManager);
    List<TweetEntity> rv;
    try {
        final QueryParser queryParser = new QueryParser("content",
                fullTextEntityManager.getSearchFactory().getAnalyzer(TweetEntity.class));
        rv = fullTextEntityManager.createFullTextQuery(queryParser.parse(query), TweetEntity.class)
                .getResultList();
    } catch (ParseException e) {
        log.error("Could not parse query", e);
        rv = new ArrayList<>();
    }
    return rv;
}

---

From source file:ai.castor.idf.FetchTermIDF.java

License:Apache License

public double getTermIDF(String term) throws ParseException {
    Analyzer analyzer = new EnglishAnalyzer(CharArraySet.EMPTY_SET);
    QueryParser qp = new QueryParser(FIELD_BODY, analyzer);
    ClassicSimilarity similarity = new ClassicSimilarity();

    String esTerm = qp.escape(term);
    double termIDF = 0.0;
    try {//from w  ww  .j  a  va2s. c  om
        TermQuery q = (TermQuery) qp.parse(esTerm);
        Term t = q.getTerm();
        termIDF = similarity.idf(reader.docFreq(t), reader.numDocs());

        System.out.println(term + '\t' + esTerm + '\t' + q + '\t' + t + '\t' + termIDF);
    } catch (Exception e) {
        System.err.println("Exception in fetching IDF(" + term + "): " + e.toString());
    }
    return termIDF;
}

---

From source file:ai.castor.idf.IDFScorer.java

License:Apache License

public double calcIDF(String query, String answer, boolean analyze) throws ParseException {
    Analyzer analyzer;/* ww w.  j  a  v a2 s  .  co  m*/
    if (analyze) {
        analyzer = new EnglishAnalyzer(StopFilter.makeStopSet(stopWords));
    } else {
        analyzer = new WhitespaceAnalyzer();
    }

    QueryParser qp = new QueryParser(FIELD_BODY, analyzer);
    ClassicSimilarity similarity = new ClassicSimilarity();

    String escapedQuery = qp.escape(query);
    Query question = qp.parse(escapedQuery);
    HashSet<String> questionTerms = new HashSet<>(Arrays.asList(question.toString().trim().split("\\s+")));

    double idf = 0.0;
    HashSet<String> seenTerms = new HashSet<>();

    String[] terms = answer.split("\\s+");
    for (String term : terms) {
        try {
            TermQuery q = (TermQuery) qp.parse(term);
            Term t = q.getTerm();

            if (questionTerms.contains(t.toString()) && !seenTerms.contains(t.toString())) {
                idf += similarity.idf(reader.docFreq(t), reader.numDocs());
                seenTerms.add(t.toString());
            } else {
                idf += 0.0;
            }
        } catch (Exception e) {
            continue;
        }
    }
    return idf;
}

---

From source file:app.finder.topicsource.service.SearchFiles.java

License:Apache License

public List<TopicSource> getTopicSources(String queryString) throws IOException, ParseException {
    String field = "contents";
    String queries = null;/*from  w  w  w . j av a 2s .  c  om*/
    int repeat = 0;
    boolean raw = false;

    int hitsPerPage = SEARCH_MAX_SIZE; // 100;
    IndexReader reader = DirectoryReader.open(FSDirectory.open(Paths.get(indexDir)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer();

    BufferedReader in = null;
    QueryParser parser = new QueryParser(field, analyzer);

    Query query = parser.parse(queryString);

    //System.out.println("Searching for: " + query.toString(field));
    searcher.search(query, null, SEARCH_MAX_SIZE);

    List<String> list = doSearch(in, searcher, query, hitsPerPage, raw, queries == null && queryString == null);

    reader.close();

    List<TopicSource> topicSourceList = new ArrayList<TopicSource>();
    TopicSource topicSource = null;
    int counter = 0;
    for (String fileName : list) {
        topicSource = new TopicSource();
        File file = new File(fileName);

        topicSource.setFileName("" + (++counter) + ". " + file.getName());
        topicSource.setPath(file.getCanonicalPath());
        topicSource.setText(readFile(file));
        topicSourceList.add(topicSource);
    }

    return topicSourceList;
}

---

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