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

Introduction

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

Prototype

public IndexSearcher(IndexReaderContext context) 

Source Link

Document

Creates a searcher searching the provided top-level IndexReaderContext .

Usage

From source file:com.esri.gpt.server.assertion.index.AsnIndexAdapter.java

License:Apache License

/**
 * Loads the assertion previously cast for the active subject, predicate and user.
 * @param context the assertion operation context
 * @return the previously cast assertion (can be null)
 * @throws Exception if an exception occurs
 */// w w  w. ja v  a  2  s .c  om
public Assertion loadPreviousUserAssertion(AsnContext context) throws Exception {
    AsnOperation operation = context.getOperation();
    String userKey = Val.chkStr(operation.getUserPart().getKey());
    String username = Val.chkStr(operation.getUserPart().getName());
    boolean isAnonymous = username.equalsIgnoreCase(AsnConstants.ANONYMOUS_USERNAME);
    if (!isAnonymous && (userKey.length() > 0)) {
        IndexReader reader = null;
        IndexSearcher searcher = null;
        try {
            reader = this.makeIndexReader();
            searcher = new IndexSearcher(reader);
            this.loadPreviousUserAssertion(context, searcher);
        } finally {
            this.closeReader(reader);
            this.closeSearcher(searcher);
        }
    }
    return null;
}

---

From source file:com.evoapps.lucene.SearchFiles.java

License:Apache License

/** Simple command-line based search demo. */
public ArrayList<Publication> search(String queryTerm) throws Exception {

    list.clear();/*w  ww .j av  a2s  . com*/
    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 field = "Abstract";
    String queries = null;
    int repeat = 0;
    boolean raw = false;
    String queryString = queryTerm;
    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++;
      }
    }
    */
    // index = "/home/subhash/LuceneFolder/Indexer";
    index = "/home/subhash/Dropbox/LuceneFolder/IndexNewData";

    IndexReader reader = DirectoryReader.open(FSDirectory.open(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);

    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_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");
        }

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

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

    return list;
}

---

From source file:com.example.analyzer.server.database.DbFullTextIndex.java

License:Open Source License

public void search(String searchText, DbFullTextCollector collector) {
    try {/*from   w  ww  .  ja va2s . c  om*/
        long beginTime = System.currentTimeMillis();
        IndexReader reader = IndexReader.open(ramDirectory, true);
        Searcher searcher = new IndexSearcher(reader);
        collector.setSearcher(searcher);
        QueryParser queryParser = new QueryParser(Version.LUCENE_30, VALUE,
                new StandardAnalyzer(Version.LUCENE_30));
        Query query = queryParser.parse(searchText);
        searcher.search(query, collector);
        searcher.close();
        long endTime = System.currentTimeMillis();
        long elapsedTime = endTime - beginTime;
        System.out.println("executed query in " + elapsedTime + " ms");
    } catch (CorruptIndexException e) {
        throw new RuntimeException(e);
    } catch (IOException e) {
        throw new RuntimeException(e);
    } catch (ParseException e) {
        throw new RuntimeException(e);
    }
}

---

From source file:com.example.search.SearchFiles.java

License:Apache License

public static ArrayList<SearchResult> find(String input, int startPage) throws Exception {
    //String index = ".\\WebContent\\index";//D:\Users\admin\workspace\TestJsp\WebContent\index
    String index = "./index";
    //   System.out.println("index:"+index);
    String field = "content";
    String queries = null;/*from  w w  w.j a  v a2  s.  com*/
    int repeat = 0;
    boolean raw = false;
    String queryString = null;
    int hitsPerPage = HitsPerPage;
    IndexReader reader = IndexReader.open(FSDirectory.open(new File(index)));
    IndexSearcher searcher = new IndexSearcher(reader);
    // Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
    Analyzer analyzer = new ICTCLASAnalyzer();
    BufferedReader in = null;
    // in = new BufferedReader(input);
    int pos;
    ArrayList<SearchResult> result = new ArrayList<SearchResult>();
    if (((pos = input.indexOf('\r')) != -1) || (pos = input.indexOf('\n')) != -1)
        input = input.substring(0, pos);
    QueryParser parser = new QueryParser(Version.LUCENE_31, field, analyzer);
    // while (true) {
    // if (queries == null && queryString == null) { // prompt the user
    // System.out.println("Enter query: ");
    // }
    String line = queryString != null ? queryString : input;
    if (line == null || line.length() == -1) {
        searcher.close();
        reader.close();
        return result;
    }

    line = line.trim();
    if (line.length() == 0) {
        searcher.close();
        reader.close();
        return result;
    }

    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, result,
            startPage);
    searcher.close();
    reader.close();
    return result;
}

---

From source file:com.facebook.presto.example.LuceneRecordCursor.java

License:Apache License

public LuceneRecordCursor(List<LuceneColumnHandle> columnHandles) throws ParseException {

    this.columnHandles = columnHandles;

    IndexReader reader = null;//from   w w w  .  j  a  v  a  2  s .  c o  m
    try {
        reader = DirectoryReader
                .open(FSDirectory.open(Paths.get("/home/liyong/workspace-neno/lucenetest/index")));
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
    searcher = new IndexSearcher(reader);
    this.NumDoc = reader.maxDoc();

    fieldToColumnIndex = new int[columnHandles.size()];
    for (int i = 0; i < columnHandles.size(); i++) {
        LuceneColumnHandle columnHandle = columnHandles.get(i);
        fieldToColumnIndex[i] = columnHandle.getOrdinalPosition();
    }
}

---

From source file:com.facebook.presto.operator.HashAggregationOperator.java

License:Apache License

private Map<String, Long> GetGroupByResult() throws IOException {

    IndexReader reader = null;/*  w w w . java  2s.c  o m*/
    Map<String, Long> returnMap = new HashMap<String, Long>();
    try {
        reader = DirectoryReader
                .open(FSDirectory.open(Paths.get("/home/liyong/workspace-neno/lucenetest/index")));
    } catch (IOException e) {
        e.printStackTrace();
    }
    IndexSearcher searcher = new IndexSearcher(reader);

    Terms terms = MultiFields.getTerms(searcher.getIndexReader(), "orderpriority");
    TermsEnum te = terms.iterator();
    while (te.next() != null) {

        String name = te.term().utf8ToString();
        int count = te.docFreq();
        returnMap.put(name, Long.valueOf(count));
    }

    return returnMap;
}

---

From source file:com.facebook.presto.operator.ScanFilterAndProjectOperator.java

License:Apache License

private Map<String, Long> getCountResult() throws IOException {

    IndexReader reader = null;/*from  w  w w.java2s . co  m*/
    Map<String, Long> returnMap = new HashMap<String, Long>();
    try {
        reader = DirectoryReader
                .open(FSDirectory.open(Paths.get("/home/liyong/workspace-neno/lucenetest/index")));
    } catch (IOException e) {
        e.printStackTrace();
    }
    IndexSearcher searcher = new IndexSearcher(reader);

    Terms terms = MultiFields.getTerms(searcher.getIndexReader(), "orderpriority");
    TermsEnum te = terms.iterator();
    while (te.next() != null) {

        String name = te.term().utf8ToString();
        int count = te.docFreq();
        returnMap.put(name, Long.valueOf(count));
    }

    return returnMap;
}

---

From source file:com.flaptor.hounder.indexer.IndexManager.java

License:Apache License

/**
 * Performs the deletes and remove duplicates from the index.
 *//*w  w  w.  java  2  s  .  c  o  m*/
private synchronized void applyDeletes() {
    IndexReader reader = null;
    IndexSearcher searcher = null;
    try {
        reader = IndexReader.open(indexDirectory);
        Set<Integer> documentsToDelete = new HashSet<Integer>();
        Enumeration keysEnum = lastOperation.keys();
        //First we collect the lucene ids of document to be deleted.
        while (keysEnum.hasMoreElements()) {
            searcher = new IndexSearcher(reader);
            String key = (String) keysEnum.nextElement();
            // if the last operation is a delete lastAddition will be 0 and we'll find no match in the index.
            //This way, all the documents with that DocumentId will be erased.
            String lastAddition = String.valueOf((Long) (lastOperation.get(key)));
            if (logger.isEnabledFor(Level.DEBUG)) {
                logger.debug("Applying deletes: searching " + docIdName + " = [" + key + "]");
            }
            ScorelessHitCollector collector = new HashSetScorelessHitCollector();
            searcher.search(new TermQuery(new Term(docIdName, key)), collector);
            Set<Integer> docIds = collector.getMatchingDocuments();
            if (logger.isEnabledFor(Level.DEBUG)) {
                logger.debug("Applying deletes: found matches: " + docIds.size());
            }
            for (Integer docId : docIds) {
                Document d = searcher.doc(docId);
                String addId = d.get("AddId");
                if (!lastAddition.equals(addId)) {
                    if (logger.isEnabledFor(Level.DEBUG)) {
                        logger.debug("Applying deletes: deleting AddId:" + addId);
                    }
                    documentsToDelete.add(docId);
                }
            }
        }
        //Now we have all lucene's ids of documents to be deleted and we can
        //proceed with the actual deletion.
        for (Integer i : documentsToDelete) {
            reader.deleteDocument(i);
        }

    } catch (IOException e) {
        logger.fatal("applyDeletes: IOException caught.", e);
        throw new RuntimeException(e);
    } finally {
        if (searcher != null) {
            try {
                searcher.close();
            } catch (Exception e) {
                String s = "applyDeletes: Couldn't close searcher, nothing I can do about it" + e;
                logger.error(s);
                throw new IllegalStateException(s);
            }
        }
        if (reader != null) {
            try {
                reader.close();
            } catch (Exception e) {
                logger.warn("Couldn't close reader, nothing I can do about it", e);
            }
        }
    }

    lastOperation.clear();
}

---

From source file:com.flaptor.hounder.indexer.LuceneUnicodeTest.java

License:Apache License

@TestInfo(testType = TestInfo.TestType.UNIT)
public void testIndexedContent() {
    try {/*w ww . ja va  2  s .com*/
        String testString = "otorrinolaring\u00f3logo";
        logger.debug("Using test string: " + testString);
        Document doc = new Document();
        doc.add(new Field("field1", testString, Field.Store.YES, Field.Index.ANALYZED));
        writer.addDocument(doc);
        writer.optimize();
        writer.close();
        IndexReader reader = IndexReader.open(dir);
        IndexSearcher searcher = new IndexSearcher(reader);
        int docId = searcher.search(new TermQuery(new Term("field1", testString)), null, 10).scoreDocs[0].doc;
        Document doc2 = searcher.doc(docId);
        String recoveredString = doc2.get("field1");
        logger.debug("Recovered String: " + recoveredString);
        assertTrue("Strings do not match", testString.equals(recoveredString));
    } catch (Exception e) {
        logger.error("Exception caught:" + e);
        assertTrue("exception", false);
    }
}

---

From source file:com.flaptor.hounder.searcher.spell.SpellChecker.java

License:Apache License

/**
 * Suggest similar words (restricted or not to a field of a user index)
 * @param word String the word you want a spell check done on
 * @param num_sug int the number of suggest words
 * @param ir the indexReader of the user index (can be null see field param)
 * @param field String the field of the user index: if field is not null, the suggested
 * words are restricted to the words present in this field.
 * @param morePopular boolean return only the suggest words that are more frequent than the searched word
 * (only if restricted mode = (indexReader!=null and field!=null)
 * @throws IOException//www.  j a  va2 s. c  om
 * @return String[] the sorted list of the suggest words with this 2 criteria:
 * first criteria: the edit distance, second criteria (only if restricted mode): the popularity
 * of the suggest words in the field of the user index
 */
public String[] suggestSimilar(String word, int num_sug, IndexReader ir, String field, boolean morePopular)
        throws IOException {

    float minScore = min;
    final TRStringDistance sd = new TRStringDistance(word);
    final int lengthWord = word.length();

    final int goalFreq = (morePopular && ir != null) ? ir.docFreq(new Term(field, word)) : 0;
    if (!morePopular && goalFreq > 0) {
        return new String[] { word }; // return the word if it exist in the index and i don't want a more popular word
    }

    BooleanQuery query = new BooleanQuery();
    String[] grams;
    String key;

    for (int ng = getMin(lengthWord); ng <= getMax(lengthWord); ng++) {

        key = "gram" + ng; // form key

        grams = formGrams(word, ng); // form word into ngrams (allow dups too)

        if (grams.length == 0) {
            continue; // hmm
        }
        if (bStart > 0) { // should we boost prefixes?
            add(query, "start" + ng, grams[0], bStart); // matches start of word

        }
        if (bEnd > 0) { // should we boost suffixes
            add(query, "end" + ng, grams[grams.length - 1], bEnd); // matches end of word

        }
        for (int i = 0; i < grams.length; i++) {
            add(query, key, grams[i]);
        }

    }

    IndexSearcher searcher = new IndexSearcher(this.spellindex);
    TopDocCollector collector = new TopDocCollector(10 * num_sug); // go thru more than 'maxr' matches in case the distance filter triggers
    searcher.search(query, collector);
    ScoreDoc[] scoreDocs = collector.topDocs().scoreDocs;

    SuggestWordQueue sugqueue = new SuggestWordQueue(num_sug);
    SuggestWord sugword = new SuggestWord();
    for (int i = 0; i < scoreDocs.length; i++) {

        Document doc = searcher.doc(i);
        sugword.string = doc.get(F_WORD); // get orig word)

        if (sugword.string.equals(word)) {
            continue; // don't suggest a word for itself, that would be silly
        }

        //edit distance/normalize with the min word length
        sugword.score = doc.getBoost() * (1.0f
                - ((float) sd.getDistance(sugword.string) / Math.min(sugword.string.length(), lengthWord)));
        if (sugword.score < minScore) {
            continue;
        }
        if (ir != null) { // use the user index
            sugword.freq = ir.docFreq(new Term(field, sugword.string)); // freq in the index
            if ((morePopular && goalFreq > sugword.freq) || sugword.freq < 1) { // don't suggest a word that is not present in the field
                continue;
            }
        }
        sugqueue.insert(sugword);
        if (sugqueue.size() == num_sug) {
            //if queue full , maintain the min score
            minScore = ((SuggestWord) sugqueue.top()).score;
        }
        sugword = new SuggestWord();
    }

    // convert to array string
    String[] list = new String[sugqueue.size()];
    for (int i = sugqueue.size() - 1; i >= 0; i--) {
        list[i] = ((SuggestWord) sugqueue.pop()).string;
    }

    searcher.close();
    return list;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• »