Example usage for org.apache.lucene.index IndexReader close

List of usage examples for org.apache.lucene.index IndexReader close

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexReader
  6. close

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexReader close.

Prototype

@Override
public final synchronized void close() throws IOException

Source Link

Document

Closes files associated with this index.

Usage

From source file:index.reader.LuceneQuery.java

License:Apache License

/**
 * Simple command-line based search demo.
 *//*from   w  w  w .ja  va  2s  .c  om*/
public static void main(String[] args) throws Exception {
    String usage = "Usage:\tindex.reader.LuceneQuery "
            + "[-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);
    }

    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(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    // :Post-Release-Update-Version.LUCENE_XY:
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);

    BufferedReader in = null;
    if (queries != null) {
        in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), StandardCharsets.UTF_8));
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
    }
    // :Post-Release-Update-Version.LUCENE_XY:
    QueryParser parser = new QueryParser(Version.LUCENE_40, 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, null, 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:indexer.IndexHtmlToText.java

static String getHTMLFromDocId(String indexDirPath, String docId) throws Exception {
    IndexReader reader;
    IndexSearcher searcher;/*from  w ww  . j  a v  a 2  s.c o m*/

    File indexDir = new File(indexDirPath);
    reader = DirectoryReader.open(FSDirectory.open(indexDir));
    searcher = new IndexSearcher(reader);

    TopScoreDocCollector collector;
    TopDocs topDocs;

    Query query = new TermQuery(new Term(TrecDocIndexer.FIELD_ID, docId));
    collector = TopScoreDocCollector.create(1, true);
    searcher.search(query, collector);
    topDocs = collector.topDocs();
    ScoreDoc sd = topDocs.scoreDocs[0];

    Document doc = reader.document(sd.doc);
    String htmlDecompressed = decompress(doc.getBinaryValue(WTDOC_FIELD_HTML).bytes);
    System.out.println(htmlDecompressed);

    reader.close();
    return htmlDecompressed;
}

From source file:indexer.IndexSplitter.java

public void split() throws Exception {
    IndexReader reader = DirectoryReader.open(FSDirectory.open(indexDir));
    final int numDocs = reader.numDocs();
    IndexWriter pWriter; // pointer variable

    for (int i = 0; i < numDocs; i++) {
        Document d = reader.document(i);
        pWriter = d.get(FIELD_CODEMIXED).equals("1") ? mixedIndexWriter : pureIndexWriter;
        pWriter.addDocument(d);/*from w  w  w  .j ava 2s .  c o m*/
    }

    reader.close();
    pureIndexWriter.close();
    mixedIndexWriter.close();
}

From source file:indexer.OptimizedRealValuedVecIndexer.java

void processAllTermWise() throws Exception {
    Cell cell, requantizedCell;//from w  w  w . j  a va 2s  .c  o  m

    copyIndex();
    IndexReader currentReader = DirectoryReader.open(writer, true);

    List<Cell> splitCells = new ArrayList<>();

    Fields fields = MultiFields.getFields(reader);
    Terms terms = fields.terms(DocVector.FIELD_CELL_ID);
    TermsEnum te = terms.iterator();

    // Iterate through every term (a cell docName) and requantize the
    // points within the cell if required.
    while (te.next() != null) {
        String cellId = te.term().utf8ToString();
        cell = new Cell(cellId);

        if (cell.toSplit(reader)) {
            splitCells.add(cell);
            List<DocVector> containedPoints = cell.getVectors(currentReader, terms, numDimensions);

            for (DocVector p : containedPoints) {
                requantizedCell = cell.quantize(p); // this function returns a new object
                p.quantize(requantizedCell); // update quantization info (cell docName)
                Document doc = p.constructDoc();

                Term t = new Term(DocVector.FIELD_ID, p.docName);
                writer.deleteDocuments(t);
                writer.addDocument(doc);
            }
            //Much faster if we don't commit here...
            //writer.commit();
        }
    }

    saveSplitCells(writer, splitCells);

    currentReader.close();
    reader.close();
    writer.close();
}

From source file:info.johtani.jjug.lucene.sample.SearcherSample.java

License:Apache License

public static void main(String[] args) {

    String indexDirectory = "./indexdir";
    //String keyword = "";
    String keyword = "johtani";
    IndexReader reader = null;

    try {/*from w w w. jav  a2s  . com*/
        //??
        Directory dir = FSDirectory.open(new File(indexDirectory));
        //IndexReader??
        reader = DirectoryReader.open(dir);
        //IndexSearcher??
        IndexSearcher searcher = new IndexSearcher(reader);
        Analyzer analyzer;
        //Standard
        analyzer = new StandardAnalyzer();
        //
        //analyzer = new JapaneseAnalyzer();
        //??
        QueryParser parser = new QueryParser("content", analyzer);
        //????
        Query query = parser.parse(keyword);
        //?????1?????
        TopDocs hits = searcher.search(query, 10);

        //????
        System.out.println("Found " + hits.totalHits + " document(s)");

        //????
        for (ScoreDoc scoreDoc : hits.scoreDocs) {
            System.out.println("--- " + scoreDoc.doc + " ---");
            //ID??
            Document doc = searcher.doc(scoreDoc.doc);
            //???
            System.out.println(doc.get("content"));
            System.out.println("---------");
        }

    } catch (IOException | ParseException e) {
        e.printStackTrace();
    } finally {
        try {
            if (reader != null) {
                reader.close();
            }
        } catch (IOException e) {
            // ignore
        }
    }

}

From source file:InformationRetrieval.Search.java

License:Apache License

/** Simple command-line based search demo. 
* @throws ParseException *//*w  ww.  j a  va2  s.  c  o  m*/
public static ArrayList<Store> search(String stringQuery) throws IOException, Exception {
    ArrayList<Store> list = null;
    //    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);
    //    }

    String index = "index";
    String field = "contents";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 50;

    //    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(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_41);

    BufferedReader in = null;
    if (queries != null) {
        in = new BufferedReader(new InputStreamReader(new FileInputStream(queries), "UTF-8"));
    } else {
        in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));
    }
    QueryParser parser = new QueryParser(Version.LUCENE_41, field, analyzer);
    //    while (true) {
    //      if (queries == null && queryString == null) {                        // prompt the user
    //        System.out.println("Enter query: ");
    //      }

    String line = queryString != null ? queryString : stringQuery;

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

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

    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, null, 100);
        }
        Date end = new Date();
        System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
    }

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

    if (queryString != null) {
        return null;
    }

    reader.close();
    return list;
}

From source file:insa.luyten.SearchCISI.java

License:Apache License

private void search() throws Exception {
    StandardAnalyzer standardAnalyzer = new StandardAnalyzer(Version.LUCENE_47);
    EnglishAnalyzer englishAnalyzer = new EnglishAnalyzer(Version.LUCENE_47);

    String[] fields = { "content", "title", "authors", "references" };
    Analyzer[] analysers = { englishAnalyzer, englishAnalyzer, standardAnalyzer, englishAnalyzer };

    String index = "index";
    String field = fields[0];/*  w ww.j  a  v  a  2s.c  om*/
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = 10;

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    // :Post-Release-Update-Version.LUCENE_XY:

    Analyzer analyzer = analysers[0];

    BufferedReader in = new BufferedReader(new InputStreamReader(System.in, "UTF-8"));

    // :Post-Release-Update-Version.LUCENE_XY:
    while (true) {
        System.out.println("\nChoose query field :");

        for (int i = 0; i < fields.length; i++) {
            System.out.println(i + 1 + ". " + fields[i]);
        }

        int n = Integer.parseInt(in.readLine()) - 1;
        field = fields[n];
        analyzer = analysers[n];

        QueryParser parser = new QueryParser(Version.LUCENE_47, field, analyzer);

        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, null, 100);
            }
            Date end = new Date();
            System.out.println("Time: " + (end.getTime() - start.getTime()) + "ms");
        }

        //catch NewQueryException
        queryString = null; //by default
        int nq = 0;
        try {
            this.doPagingSearch(in, searcher, query, field, hitsPerPage, raw,
                    queries == null && queryString == null);
        } catch (NewQueryException e) {
            String newQueryString = e.getMessage();
            System.out.println("Is \"" + newQueryString + "\" a new query ?");

            do {
                System.out.println(" Enter (y)es or (n)o.");
                String l = in.readLine();
                if (l.length() == 1 && l.charAt(0) == 'y')
                    nq = 1;
                else if (l.length() == 1 && l.charAt(0) == 'n')
                    nq = -1;
            } while (nq == 0);

            if (nq == 1) {
                queryString = newQueryString;
            }
        }
        if (queryString != null && nq == 1) // it's okay
            ;
        else if (queryString != null)
            break;

    }
    reader.close();
}

From source file:integration.ForumTermCollocationTest.java

License:Apache License

private void extractCollocations() throws IOException, CorruptIndexException {
    Directory dir = FSDirectory.open(new File(indexDir));
    IndexReader reader = DirectoryReader.open(dir);
    CollocationExtractor collocationExtractor = new CollocationExtractor(reader);
    CollocationIndexer collocationIndexer = new CollocationIndexer(collocsDir,
            new StandardAnalyzer(Version.LUCENE_48));
    collocationExtractor.extract(collocationIndexer);
    collocationIndexer.close();/*from w w w.  ja v a 2 s  .  com*/
    reader.close();
}

From source file:invertedindex.LineNumberSearcher.java

public ArrayList<String> search(String keyword, String filePath) throws IOException {

    String indexLocation = getLineIndexLocation();
    //    System.out.println("Inside LINE search method");

    try {//from  ww w. j  av  a 2 s . com
        IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexLocation)));
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(topDocs, true);

        String queryContent = keyword;

        queryContent = "\"" + queryContent + "\"";
        //      queryContent = "*" + queryContent + "*";

        String queryFilePath = filePath;
        //                System.out.println("FIELPATH "+queryFilePath);
        queryFilePath = "\"" + queryFilePath + "\"";
        //      queryFilePath = "*" + queryFilePath + "*";

        QueryParser queryParserContent = new QueryParser(Version.LUCENE_47, "contents", analyzer);
        QueryParser queryParserFilePath = new QueryParser(Version.LUCENE_47, "path", analyzer);

        queryParserContent.setAllowLeadingWildcard(true);
        //queryParserFileName.setAllowLeadingWildcard(true);
        //               Query q = queryParser.parse(query);
        Query qContent = queryParserContent.parse(queryContent);
        Query qFileName = queryParserFilePath.parse(queryFilePath);
        //                System.out.println("FIELPATH "+qFileName);
        BooleanQuery q = new BooleanQuery();
        q.add(qContent, Occur.MUST); // MUST implies that the keyword must occur.
        q.add(qFileName, Occur.MUST);

        searcher.search(q, collector);
        ScoreDoc[] hits = collector.topDocs().scoreDocs;

        //      System.out.println("Found " + hits.length + " hits.");
        lineNumbersList = new ArrayList<>();
        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("filename")
            //             + " score=" + hits[i].score);
            //                    System.out.println("Line Number is "+d.get("lineNumber"));
            //                    System.out.println("Content is "+d.get("contents"));
            //                    String filePath = d.get("path");
            lineNumbersList.add(d.get("lineNumber"));
        }

        reader.close();
        return lineNumbersList;

    } catch (Exception e) {
        System.out.println("Error searching in line number search " + indexLocation + " : " + e.getMessage());

    }

    return lineNumbersList;

}

From source file:invertedindex.SearchIndex.java

public ArrayList<SearchResults> search(String keyword) throws IOException {

    String indexLocation = this.getIndexLocation();
    //    System.out.println("Inside search method");

    //        indexLocation = "";
    //        BufferedReader br = new BufferedReader(new InputStreamReader(System.in));
    //        while (true) {
    try {//  w  w  w  . j  a  v  a2  s.co  m
        IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(indexLocation)));
        IndexSearcher searcher = new IndexSearcher(reader);
        TopScoreDocCollector collector = TopScoreDocCollector.create(topDocs, true);

        String query = keyword;

        query = "\"" + query + "\"";

        Query q = new QueryParser(Version.LUCENE_47, "contents", analyzer).parse(query);

        SimpleFragListBuilder fragListBuilder = new SimpleFragListBuilder();
        ScoreOrderFragmentsBuilder fragBuilder = new ScoreOrderFragmentsBuilder();
        FastVectorHighlighter fvh = new FastVectorHighlighter(FastVectorHighlighter.DEFAULT_PHRASE_HIGHLIGHT,
                FastVectorHighlighter.DEFAULT_FIELD_MATCH, fragListBuilder, fragBuilder);
        fvh = new FastVectorHighlighter(FastVectorHighlighter.DEFAULT_PHRASE_HIGHLIGHT,
                FastVectorHighlighter.DEFAULT_FIELD_MATCH, fragListBuilder, fragBuilder);

        //      System.out.println(q);

        //                

        searcher.search(q, collector);
        //                searcher.search(q, null,topDocs);
        ScoreDoc[] hits = collector.topDocs().scoreDocs;

        // 4. display results
        System.out.println("Found " + hits.length + " hits.");
        totalHits = hits.length;
        searchResulsAL = new ArrayList<>();

        for (int i = 0; i < hits.length; ++i) {
            int docId = hits[i].doc;
            FieldQuery fq = fvh.getFieldQuery(q);
            //                    System.out.println("fq "+fq);

            String[] fragments = fvh.getBestFragments(fq, searcher.getIndexReader(), docId, "contents", 50, 10);
            //String[] lineFragments = fvh.getBestFragments(fq, searcher.getIndexReader(), docId, "contents", 18,10);

            Document d = searcher.doc(docId);

            String filePath = d.get("path");

            for (int j = 0; j < fragments.length; j++) {
                //                                    System.out.println("FRAGMENT iS "+fragments[j]);
                //                                int k=0;
                //                                for(k=0;k<lineFragments.length;k++){
                //                                    fragments[j].getSc
                String temp = Jsoup.parse(fragments[j]).text();
                //                                    
                LineNumberSearcher lns = new LineNumberSearcher();

                //lineNumbersList = new ArrayList<>();
                lineNumberArrayList = new ArrayList<>();
                lineNumber = "null";
                boolean g = Pattern.compile("\\n").matcher(fragments[j]).find();
                if (!g) {
                    //                                        System.out.println("NO G");
                    lineNumbersList = lns.search(temp, filePath);
                    //                                        for(String s : lineNumbersList){
                    //                                            System.out.println("s is "+s);
                    //                                        }
                    //                                        if(lineNumbersList.get(0).isEmpty()){
                    //                                            lineNumber = "Not Found";
                    //                                        }else {
                    if (!lineNumbersList.isEmpty()) {
                        //                                                System.out.println("in line number");
                        lineNumber = lineNumbersList.get(0);
                    }

                    //                                        }

                }

                //here is the tried code for enter space
                /*       
                else{
                  System.out.println("YES G");
                   String lines[] = fragments[j].split("\\r?\\n");
                //                                         ArrayList<String> newLines = new ArrayList<>();
                  ArrayList<String> newLines = new ArrayList<>(Arrays.asList(lines));
                  System.out.println("Here 3");
                  int special = 0;
                   for(String line : newLines){
                       if(Pattern.compile("^$").matcher(line).find()){
                           newLines.remove(line);
                           special++;
                       }
                   }
                   System.out.println("Here 4");
                //                                          List<String> list = Arrays.asList(lines);
                //                                          if(list.contains(temp)){
                //                                              
                //                                          }
                          
                //                                        for(String line: newLines){
                //                                            System.out.println("LINE IS "+line);
                //                                        }
                  if(newLines.size()==1){
                //                                            System.out.println("Yes G but NOT G");
                      lineNumbersList = lns.search(temp,filePath);
                      if(!lineNumberArrayList.isEmpty()){
                          lineNumber = lineNumbersList.get(0);
                      }
                      System.out.println("Here 1");
                  }else{
                      System.out.println("Here 2");
                          ArrayList<String> a0 = lns.search(Jsoup.parse(newLines.get(0)).text(),filePath);
                  ArrayList<String> a1 = lns.search(Jsoup.parse(newLines.get(1)).text(),filePath);
                  int k,l;
                  outerloop:
                  for(k=0;k<a0.size();k++){
                      for(l=0;l<a1.size();l++){
                          int secondline = Integer.parseInt(a1.get(l));
                //                                                System.out.println("second line is"+ secondline);
                          int firstline = Integer.parseInt(a0.get(k));
                //                                                System.out.println("first line is"+firstline);
                          int diff = secondline - firstline;
                //                                                System.out.println("DIFFERENCE IS "+diff);
                //                                                System.out.println("Special IS "+special);
                          if(diff == special+1){
                              insideLoopFlag = true;
                //                                                    System.out.println("K IS "+k);
                //                                                    System.out.println("IN BREAK ");
                              break outerloop;
                          }
                      }
                //                                            System.out.println("K IS "+k);
                  }
                //                                        System.out.println("OUT OF FOR LOOP");
                //                                        System.out.println("K IS "+k);
                  if(insideLoopFlag==true){
                  lineNumber = String.valueOf(a0.get(k));
                  }
                //                                        System.out.println("LINE NUMBER IS "+lineNumber);
                  }
                          
                          
                }
                */

                //                                }
                fragments[j] = fragments[j].replaceAll("\\n", " ");
                //                                System.out.println("\t\t" + fragments[j] + "...");
                fragments[j] = fragments[j] + "....";
                if (!(lineNumber.equals("null"))) {
                    //                                    System.out.println("in line number");
                    fragments[j] = fragments[j] + " at Line " + lineNumber;
                }

            }

            //Setting Results
            SearchResults sr = new SearchResults();
            sr.setFilename(d.get("filename"));
            sr.setScore(hits[i].score);
            sr.setFragments(fragments);
            sr.setPath(filePath);
            sr.setContentType(d.get("contentType"));
            //                    sr.setLineNumber(lineNumber);

            searchResulsAL.add(sr);

            //                    
        }
        //      writer.close();
        reader.close();

    } catch (Exception e) {
        System.out.println("Error searching in search index " + e + " : " + e.getMessage());
        //      break;
    }

    //    }

    return searchResulsAL;

}