Package org.apache.lucene.index

Examples of org.apache.lucene.index.IndexReader

53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
            EntityManager em = (EntityManager) Component.getInstance("entityManager");
            FullTextSession ftSession = (FullTextSession)em.getDelegate();

            // Delete all documents with "_hibernate_class" term of the selected entity
            DirectoryProvider dirProvider = ftSession.getSearchFactory().getDirectoryProviders(entityClass)[0];
            IndexReader reader = IndexReader.open(dirProvider.getDirectory());

            // TODO: This is using an internal term of HSearch
            reader.deleteDocuments(new Term("_hibernate_class", entityClass.getName()));
            reader.close();

            // Optimize index
            progress.setStatus("Optimizing index");
            log.debug("optimizing index (merging segments)");
            ftSession.getSearchFactory().optimize(entityClass);
View Full Code Here
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
        EntityManager em = (EntityManager) Component.getInstance("entityManager");

        for (SearchableEntity indexedEntity : indexedEntities) {
            DirectoryProvider dirProvider = ((FullTextSession)em.getDelegate()).getSearchFactory().getDirectoryProviders(indexedEntity.getClazz())[0];
            IndexReader reader = IndexReader.open(dirProvider.getDirectory());

            indexedEntity.setNumOfIndexedDocuments(reader.numDocs());

            TermEnum te = reader.terms();
            long numTerms = 0;
            while (te.next()) numTerms++;
            indexedEntity.setNumOfIndexedTerms(numTerms);

            long size = 0;
            String [] fileNames = dirProvider.getDirectory().list();
            for (String fileName : fileNames) {
                size += dirProvider.getDirectory().fileLength(fileName);
            }
            indexedEntity.setIndexSizeInBytes(size);

            reader.close();
        }
    }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
          deleteQueue.clear();
        }
        // 1. Open Index Reader
        File indexFile = new File(indexPath);
        Directory directory = FSDirectory.open(indexFile);
        IndexReader indexReader = IndexReader.open(directory);

        log.info("befor delete: indexReader.numDocs()=" + indexReader.numDocs());
        // 2. Delete old Document
        // loop over all documents in updateQueue
        for (int i = 0; i < updateCopy.size(); i++) {
          String resourceUrl = updateCopy.get(i).get(OlatDocument.RESOURCEURL_FIELD_NAME);
          Term term = new Term(OlatDocument.RESOURCEURL_FIELD_NAME, resourceUrl );
          log.info("updateQueue:delete documents with resourceUrl=" + resourceUrl );
          indexReader.deleteDocuments(term);         
        }
        // loop over all documents in deleteQueue
        for (int i = 0; i < deleteCopy.size(); i++) {
          String resourceUrl = deleteCopy.get(i).get(OlatDocument.RESOURCEURL_FIELD_NAME);
          Term term = new Term(OlatDocument.RESOURCEURL_FIELD_NAME, resourceUrl );
          log.info("deleteQueue:delete documents with resourceUrl='" + resourceUrl + "'");
          indexReader.deleteDocuments(term);
         
        }
        log.info("after delete: indexReader.numDocs()=" + indexReader.numDocs());
        // 3. Close reader
        indexReader.close();
        directory.close();
       
        // 4. open writer
        IndexWriter indexWriter = new IndexWriter(directory, new StandardAnalyzer(Version.LUCENE_CURRENT), false, IndexWriter.MaxFieldLength.UNLIMITED);
        indexWriter.setMergeFactor(INDEX_MERGE_FACTOR); //for better performance
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
   * Creates a new spell-check index based on search-index
   *
   */
  public void createSpellIndex() {
    if (isSpellCheckEnabled) {
      IndexReader indexReader = null;
      try {
        log.info("Start generating Spell-Index...");
        long startSpellIndexTime = 0;
        if (log.isDebug()) startSpellIndexTime = System.currentTimeMillis();
        Directory indexDir = FSDirectory.open(new File(indexPath));
        indexReader = IndexReader.open(indexDir);
        // 1. Create content spellIndex
        File spellDictionaryFile = new File(spellDictionaryPath);
        Directory contentSpellIndexDirectory = FSDirectory.open(new File(spellDictionaryPath + CONTENT_PATH));//true
        SpellChecker contentSpellChecker = new SpellChecker(contentSpellIndexDirectory);
        Dictionary contentDictionary = new LuceneDictionary(indexReader, OlatDocument.CONTENT_FIELD_NAME);
        contentSpellChecker.indexDictionary(contentDictionary);
        // 2. Create title spellIndex
        Directory titleSpellIndexDirectory = FSDirectory.open(new File(spellDictionaryPath + TITLE_PATH));//true
        SpellChecker titleSpellChecker = new SpellChecker(titleSpellIndexDirectory);
        Dictionary titleDictionary = new LuceneDictionary(indexReader, OlatDocument.TITLE_FIELD_NAME);
        titleSpellChecker.indexDictionary(titleDictionary);
        // 3. Create description spellIndex
        Directory descriptionSpellIndexDirectory = FSDirectory.open(new File(spellDictionaryPath + DESCRIPTION_PATH));//true
        SpellChecker descriptionSpellChecker = new SpellChecker(descriptionSpellIndexDirectory);
        Dictionary descriptionDictionary = new LuceneDictionary(indexReader, OlatDocument.DESCRIPTION_FIELD_NAME);
        descriptionSpellChecker.indexDictionary(descriptionDictionary);
        // 4. Create author spellIndex
        Directory authorSpellIndexDirectory = FSDirectory.open(new File(spellDictionaryPath + AUTHOR_PATH));//true
        SpellChecker authorSpellChecker = new SpellChecker(authorSpellIndexDirectory);
        Dictionary authorDictionary = new LuceneDictionary(indexReader, OlatDocument.AUTHOR_FIELD_NAME);
        authorSpellChecker.indexDictionary(authorDictionary);
       
        // Merge all part spell indexes (content,title etc.) to one common spell index
        Directory spellIndexDirectory = FSDirectory.open(spellDictionaryFile);//true
        IndexWriter merger = new IndexWriter(spellIndexDirectory, new StandardAnalyzer(Version.LUCENE_CURRENT), true, IndexWriter.MaxFieldLength.UNLIMITED);
        Directory[] directories = { contentSpellIndexDirectory, titleSpellIndexDirectory, descriptionSpellIndexDirectory, authorSpellIndexDirectory};
        merger.addIndexesNoOptimize(directories);
        merger.optimize();
        merger.close();
        spellChecker = new SpellChecker(spellIndexDirectory);
        spellChecker.setAccuracy(0.7f);
         if (log.isDebug()) log.debug("SpellIndex created in " + (System.currentTimeMillis() - startSpellIndexTime) + "ms");
        log.info("New generated Spell-Index ready to use.");
      } catch(IOException ioEx) {
        log.warn("Can not create SpellIndex",ioEx);
      } finally {
        if (indexReader != null) {
            try {
              indexReader.close();
            } catch (IOException e) {
              log.warn("Can not close indexReader properly",e);
            }
        }
      }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
      doc.add(fd);
      writer.addDocument(doc);
      writer.optimize();
      writer.close();
     
      IndexReader reader = IndexReader.open(ramDir);
      String queryString = QUERY;
      QueryParser parser=new QueryParser(FIELD_NAME, /*new StandardAnalyzer()/*/XFactory.getWriterAnalyzer());
      Query query = parser.parse(queryString);
      System.out.println(query);
      Searcher searcher = new IndexSearcher(ramDir);
      query = query.rewrite(reader);
      System.out.println(query);
      System.out.println("Searching for: " + query.toString(FIELD_NAME));
      Hits hits = searcher.search(query);
     
      BoldFormatter formatter = new BoldFormatter();
      Highlighter highlighter =new Highlighter(formatter,new QueryScorer(query));
      highlighter.setTextFragmenter(new SimpleFragmenter(50));
      for (int i = 0; i < hits.length(); i++)
      {
        String text = hits.doc(i).get(FIELD_NAME);
        int maxNumFragmentsRequired = 5;
        String fragmentSeparator = "...";
        TermPositionVector tpv = (TermPositionVector)reader.getTermFreqVector(hits.id(i),FIELD_NAME);
        TokenStream tokenStream=TokenSources.getTokenStream(tpv);
        /*
        TokenStream tokenStream2=
          (new StandardAnalyzer())
          //XFactory.getWriterAnalyzer()
            .tokenStream(FIELD_NAME,new StringReader(text));
       
        do {
          Token t = tokenStream2.next();
          if(t==null)break;
          System.out.println("\t" + t.startOffset() + "," + t.endOffset() + "\t" + t.termText());
        }while(true);
        */
        String result =
          highlighter.getBestFragments(
            tokenStream, text, maxNumFragmentsRequired, fragmentSeparator);
        System.out.println("\n" + result);
      }
      reader.close();
    }catch(Exception e) {
      e.printStackTrace();
    }
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    doc.add(fd);
    writer.addDocument(doc);
    writer.optimize();
    writer.close();

    IndexReader reader = IndexReader.open(ramDir);
    String queryString = QUERY;
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, FIELD_NAME, analyzer);
    Query query = parser.parse(queryString);
    Searcher searcher = new IndexSearcher(ramDir);
    query = query.rewrite(reader);
    System.out.println("Searching for: " + query.toString(FIELD_NAME));
    TopDocs hits = searcher.search(query, 10);

    BoldFormatter formatter = new BoldFormatter();
    Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
        query));
    highlighter.setTextFragmenter(new SimpleFragmenter(50));
    for (int i = 0; i < hits.scoreDocs.length; i++) {
      int docId = hits.scoreDocs[i].doc;
      Document hit = searcher.doc(docId);
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    doc.add(fd);
    writer.addDocument(doc);
    writer.optimize();
    writer.close();

    IndexReader reader = IndexReader.open(ramDir);
    String queryString = QUERY;
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, FIELD_NAME, analyzer);
    Query query = parser.parse(queryString);
    Searcher searcher = new IndexSearcher(ramDir);
    query = query.rewrite(reader);
    System.out.println("Searching for: " + query.toString(FIELD_NAME));
    TopDocs hits = searcher.search(query, 10);   

    BoldFormatter formatter = new BoldFormatter();
    Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
        query));
    highlighter.setTextFragmenter(new SimpleFragmenter(50));
    for (int i = 0; i < hits.scoreDocs.length; i++) {
      int docId = hits.scoreDocs[i].doc;
      Document hit = searcher.doc(docId);
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    doc.add(fd);
    writer.addDocument(doc);
    writer.optimize();
    writer.close();

    IndexReader reader = IndexReader.open(ramDir);
    String queryString = QUERY;
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, FIELD_NAME, analyzer);
    Query query = parser.parse(queryString);
    Searcher searcher = new IndexSearcher(ramDir);
    query = query.rewrite(reader);
    System.out.println("Searching for: " + query.toString(FIELD_NAME));
    TopDocs hits = searcher.search(query, 10);   

    BoldFormatter formatter = new BoldFormatter();
    Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
        query));
    highlighter.setTextFragmenter(new SimpleFragmenter(50));
    for (int i = 0; i < hits.scoreDocs.length; i++) {
      int docId = hits.scoreDocs[i].doc;
      Document hit = searcher.doc(docId);
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    doc.add(fd);
    writer.addDocument(doc);
    writer.optimize();
    writer.close();

    IndexReader reader = IndexReader.open(ramDir);
    String queryString = QUERY;
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, FIELD_NAME, analyzer);
    Query query = parser.parse(queryString);
    Searcher searcher = new IndexSearcher(ramDir);
    query = query.rewrite(reader);
    System.out.println("Searching for: " + query.toString(FIELD_NAME));
    TopDocs hits = searcher.search(query, 10);

    BoldFormatter formatter = new BoldFormatter();
    Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
        query));
    highlighter.setTextFragmenter(new SimpleFragmenter(50));
    for (int i = 0; i < hits.scoreDocs.length; i++) {
      int docId = hits.scoreDocs[i].doc;
      Document hit = searcher.doc(docId);
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
  }
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
    doc.add(fd);
    writer.addDocument(doc);
    writer.optimize();
    writer.close();

    IndexReader reader = IndexReader.open(ramDir);
    String queryString = QUERY;
    QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, FIELD_NAME, analyzer);
    Query query = parser.parse(queryString);
    Searcher searcher = new IndexSearcher(ramDir);
    query = query.rewrite(reader);
    System.out.println("Searching for: " + query.toString(FIELD_NAME));
    TopDocs hits = searcher.search(query, 10);

    BoldFormatter formatter = new BoldFormatter();
    Highlighter highlighter = new Highlighter(formatter, new QueryScorer(
        query));
    highlighter.setTextFragmenter(new SimpleFragmenter(50));
    for (int i = 0; i < hits.scoreDocs.length; i++) {
      int docId = hits.scoreDocs[i].doc;
      Document hit = searcher.doc(docId);
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.index.IndexReader

  • com.gentics.cr.lucene.autocomplete.Autocompleter
  • com.gentics.cr.lucene.indexaccessor.DefaultIndexAccessor
  • com.gentics.cr.lucene.indexaccessor.DefaultIndexAccessorTest
  • com.gentics.cr.lucene.indexer.index.LuceneIndexUpdateChecker
  • com.gentics.cr.lucene.indexer.index.LuceneMultiIndexLocation
  • com.gentics.cr.lucene.indexer.index.LuceneSingleIndexLocation
  • com.gentics.cr.lucene.information.SpecialDirectoryInformationEntry
  • com.gentics.cr.lucene.search.CRSearcher
  • com.tamingtext.tagging.LuceneCategoryExtractor
  • com.tamingtext.tagging.LuceneTagExtractor
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.