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

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

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

Introduction

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

Prototype

@Override
public void close() throws IOException

Source Link

Document

Closes all open resources and releases the write lock.

Usage

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

License:Open Source License

public DbFullTextIndex(DbTable dbTable, int columnOffset) {
    try {// www. j  a  va2  s.  c o m
        long beginTime = System.currentTimeMillis();
        ramDirectory = new RAMDirectory();
        IndexWriter writer = new IndexWriter(ramDirectory, new StandardAnalyzer(Version.LUCENE_30),
                new MaxFieldLength(50));
        int rowCount = dbTable.getRowCount();
        for (int rowOffset = 0; rowOffset < rowCount; rowOffset++) {
            String value = dbTable.coalesce(rowOffset, columnOffset, "").toString();
            byte[] idArray = getBytes(rowOffset);
            Document document = new Document();
            document.add(new Field(ID, idArray, Field.Store.YES));
            document.add(new Field(VALUE, value, Store.YES, Index.ANALYZED)); // TODO: Determine whether we need to store value
            writer.addDocument(document);
        }
        writer.optimize();
        writer.close();
        long endTime = System.currentTimeMillis();
        long elapsedTime = endTime - beginTime;
        System.out.println("created index in " + elapsedTime + " ms");
    } catch (CorruptIndexException e) {
        throw new RuntimeException(e);
    } catch (LockObtainFailedException e) {
        throw new RuntimeException(e);
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}

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

License:Apache License

/** Index all text files under a directory. */
public static void main(String[] args) {
    String usage = "java org.apache.lucene.demo.IndexFiles"
            + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
            + "This indexes the documents in DOCS_PATH, creating a Lucene index"
            + "in INDEX_PATH that can be searched with SearchFiles";
    String indexPath = "index";
    // String docsPath = "E:\\work\\webExp\\exp\\sina_ansi";
    String docsPath = ".\\doc";
    boolean create = true;
    /*    for(int i=0;i<args.length;i++) {
          if ("-index".equals(args[i])) {
            indexPath = args[i+1];/*from  w  ww .ja v  a  2 s. c  o  m*/
            i++;
          } else if ("-docs".equals(args[i])) {
            docsPath = args[i+1];
            i++;
          } else if ("-update".equals(args[i])) {
            create = false;
          }
        }*/

    /* if (docsPath == null) {
       System.err.println("Usage: " + usage);
       System.exit(1);
     }*/

    final File docDir = new File(docsPath);
    if (!docDir.exists() || !docDir.canRead()) {
        System.out.println("Document directory '" + docDir.getAbsolutePath()
                + "' does not exist or is not readable, please check the path");
        System.exit(1);
    }

    Date start = new Date();
    try {
        System.out.println("Indexing to directory '" + indexPath + "'...");

        Directory dir = FSDirectory.open(new File(indexPath));
        //      Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_31);
        Analyzer analyzer = new ICTCLASAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_31, analyzer);

        if (create) {
            // Create a new index in the directory, removing any
            // previously indexed documents:
            iwc.setOpenMode(OpenMode.CREATE);
        } else {
            // Add new documents to an existing index:
            iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        }

        // Optional: for better indexing performance, if you
        // are indexing many documents, increase the RAM
        // buffer.  But if you do this, increase the max heap
        // size to the JVM (eg add -Xmx512m or -Xmx1g):
        //
        // iwc.setRAMBufferSizeMB(256.0);

        IndexWriter writer = new IndexWriter(dir, iwc);
        indexDocs(writer, docDir);

        // NOTE: if you want to maximize search performance,
        // you can optionally call forceMerge here.  This can be
        // a terribly costly operation, so generally it's only
        // worth it when your index is relatively static (ie
        // you're done adding documents to it):
        //
        // writer.forceMerge(1);

        writer.close();

        Date end = new Date();
        System.out.println(end.getMinutes() - start.getMinutes() + " total minutes");
        System.out.println(end.getTime() - start.getTime() + " total milliseconds");

    } catch (IOException e) {
        System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
    }
}

From source file:com.flaptor.hounder.indexer.util.MergeIndexes.java

License:Apache License

public static void main(String args[]) {
    if (args.length < 3) {
        System.err.println("Usage: MergeIndexes outputIndex index1 index2 [... indexN]");
        System.exit(-1);//from   w w  w .j  a va  2  s . com
    }
    try {
        IndexWriter iw = new IndexWriter(args[0], new StandardAnalyzer(), true,
                IndexWriter.MaxFieldLength.UNLIMITED);
        iw.setMaxBufferedDocs(1000);
        IndexReader readers[] = new IndexReader[args.length - 1];
        for (int i = 0; i < args.length - 1; i++) {
            readers[i] = IndexReader.open(args[i + 1]);
        }
        iw.addIndexes(readers);
        iw.optimize();
        iw.close();
    } catch (IOException e) {
        System.err.println(e);
    }
}

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

License:Apache License

public void clearIndex() throws IOException {
    IndexWriter.unlock(spellindex);/*  w ww  .  ja  v  a2s .c  o m*/
    IndexWriter writer = new IndexWriter(spellindex, null, true, IndexWriter.MaxFieldLength.UNLIMITED);
    writer.close();
}

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

License:Apache License

/**
 * Index a Dictionary//from  w w w  .j  a  v a  2s. co  m
 * @param dict the dictionary to index
 * @throws IOException
 */
public void indexDictionary(Dictionary dict) throws IOException {
    IndexWriter.unlock(spellindex);
    IndexWriter writer = new IndexWriter(spellindex, new WhitespaceAnalyzer(),
            !IndexReader.indexExists(spellindex), IndexWriter.MaxFieldLength.UNLIMITED);
    writer.setMergeFactor(300);
    writer.setMaxBufferedDocs(150);

    for (Pair<String, Float> pair : dict) {
        String word = pair.first();
        float boost = pair.last();

        int len = word.length();
        if (len < 3) {
            continue; // too short we bail but "too long" is fine...
        }

        if (this.exist(word)) { // if the word already exist in the gramindex
            continue;
        }

        // ok index the word
        Document doc = createDocument(word, boost, getMin(len), getMax(len));
        writer.addDocument(doc);
    }
    // close writer
    writer.optimize();
    writer.close();

    // close reader
    reader.close();
    reader = null;
}

From source file:com.flaptor.hounder.util.Idx.java

License:Apache License

public static void main(String arg[]) throws Exception {
    check(arg.length > 1, null);/*from   w ww . j  a  v  a 2s .  c o  m*/
    String cmd = arg[0];
    File idx = new File(arg[1]);
    if ("list".equals(cmd)) {
        int num = (arg.length > 2) ? Integer.parseInt(arg[2]) : -1;
        check(idx.exists(), "Index dir not found");
        IndexReader reader = IndexReader.open(idx);
        int docs = reader.numDocs();
        int max = reader.maxDoc();
        System.err.println("Index contains " + docs + " documents plus " + (max - docs) + " deleted.");
        if (num > -1) {
            if (num == 0)
                num = docs;
            for (int i = 0; i < max && i < num; i++) {
                System.out.println("----------------------------------------");
                if (!reader.isDeleted(i)) {
                    Document doc = reader.document(i);
                    List flds = doc.getFields();
                    Iterator iter = flds.iterator();
                    while (iter.hasNext()) {
                        Field fld = (Field) iter.next();
                        String attr = (fld.isIndexed() ? ",i" : "") + (fld.isStored() ? ",s" : "")
                                + (fld.isTokenized() ? ",t" : "");
                        System.out.println(fld.name() + attr + ": " + fld.stringValue());
                    }
                }
            }
            reader.close();
            System.out.println();
        }
    } else if ("search".equals(cmd)) {
        check(idx.exists(), "Index dir not found");
        check(arg.length > 3, "Not enough arguments");
        String field = arg[2];
        String value = arg[3];
        IndexSearcher searcher = new IndexSearcher(IndexReader.open(idx));
        ScorelessHitCollector collector = new HashSetScorelessHitCollector();
        searcher.search(new TermQuery(new Term(field, value)), collector);
        Set<Integer> docIds = collector.getMatchingDocuments();
        System.out.println("\nNumber of hits: " + docIds.size() + "\n");
        for (Integer docId : docIds) {
            Document doc = searcher.doc(docId);
            List flds = doc.getFields();
            Iterator iter = flds.iterator();
            while (iter.hasNext()) {
                Field fld = (Field) iter.next();
                System.out.println(fld.name() + ": " + fld.stringValue());
            }
        }
        searcher.close();
        System.out.println();
    } else if ("delete".equals(cmd)) {
        check(idx.exists(), "Index dir not found");
        check(arg.length > 3, "Not enough arguments");
        String field = arg[2];
        String value = arg[3];
        IndexReader reader = IndexReader.open(idx);
        reader.deleteDocuments(new Term(field, value));
        reader.close();
    } else if ("optimize".equals(cmd)) {
        IndexWriter writer = new IndexWriter(idx, new StandardAnalyzer(), false,
                IndexWriter.MaxFieldLength.UNLIMITED);
        writer.optimize();
        writer.close();
    } else if ("merge".equals(cmd)) {
        check(arg.length == 3, "not enough parameters");
        File idx2 = new File(arg[2]);
        check(idx.exists(), "Index dir 1 not found");
        check(idx2.exists(), "Index dir 2 not found");
        IndexReader reader = IndexReader.open(idx2);
        IndexWriter writer = new IndexWriter(idx, new StandardAnalyzer(), false,
                IndexWriter.MaxFieldLength.UNLIMITED);
        writer.addIndexes(new IndexReader[] { reader });
        writer.close();
        reader.close();
    } else if ("term-count".equals(cmd)) {
        check(arg.length == 3, "not enough parameters");
        check(idx.exists(), "Index dir not found");
        IndexReader reader = IndexReader.open(idx);
        String field = arg[2];
        int count = 0;
        TermEnum terms = reader.terms();
        while (terms.next()) {
            Term term = terms.term();
            if (term.field().equals(field))
                count++;
        }
        terms.close();
        reader.close();
        System.out.println("Found " + count + " different values for field " + field);
    } else if ("hit-count".equals(cmd)) {
        check(arg.length > 3, "Not enough arguments");
        check(idx.exists(), "Index dir not found");
        String field = arg[2];
        String value = arg[3];
        IndexSearcher searcher = new IndexSearcher(IndexReader.open(idx));
        CountingHitCollector collector = new CountingHitCollector();
        searcher.search(new TermQuery(new Term(field, value)), collector);
        System.out.println("\nNumber of hits: " + collector.getDocCount() + "\n");
        searcher.close();
    } else if ("uncompound".equals(cmd)) {
        IndexWriter writer = new IndexWriter(idx, new StandardAnalyzer(), false,
                IndexWriter.MaxFieldLength.UNLIMITED);
        writer.setUseCompoundFile(false);
        writer.optimize();
        writer.close();
    } else if ("compound".equals(cmd)) {
        IndexWriter writer = new IndexWriter(idx, new StandardAnalyzer(), false,
                IndexWriter.MaxFieldLength.UNLIMITED);
        writer.setUseCompoundFile(true);
        writer.optimize();
        writer.close();
    } else if ("terms".equals(cmd)) {
        check(arg.length == 3, "not enough parameters");
        check(idx.exists(), "Index dir not found");
        String field = arg[2];
        IndexReader reader = IndexReader.open(idx);
        TermEnum terms = reader.terms();
        while (terms.next()) {
            Term t = terms.term();
            if (t.field().equals(field)) {
                System.out.println(t.text());
            }
        }

    }

}

From source file:com.flycode.CRIBSearch.SearchEngine.Demo.IndexFiles.java

License:Apache License

/**
 * Index all text files under a directory.
 *///from  www .j a  v  a 2  s.co  m
public static void main(String[] args) {
    String usage = "java com.flycode.CRIBSearch.demo.IndexFiles"
            + " [-index INDEX_PATH] [-docs DOCS_PATH] [-update]\n\n"
            + "This indexes the documents in DOCS_PATH, creating a Lucene index"
            + "in INDEX_PATH that can be searched with SearchFiles class";
    String indexPath = "index";
    String docsPath = null;
    boolean create = true;
    for (int i = 0; i < args.length; i++) {
        if ("-index".equals(args[i])) {
            indexPath = args[i + 1];
            i++;
        } else if ("-docs".equals(args[i])) {
            docsPath = args[i + 1];
            i++;
        } else if ("-update".equals(args[i])) {
            create = false;
        }
    }

    if (docsPath == null) {
        System.err.println("Usage: " + usage);
        System.exit(1);
    }

    final Path docDir = Paths.get(docsPath);
    if (!Files.isReadable(docDir)) {
        System.out.println("Document directory '" + docDir.toAbsolutePath()
                + "' does not exist or is not readable, please check the path");
        System.exit(1);
    }

    Date start = new Date();
    try {
        System.out.println("Indexing to directory '" + indexPath + "'...");

        Directory dir = FSDirectory.open(Paths.get(indexPath));
        Analyzer analyzer = new StandardAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);

        if (create) {
            // Create a new index in the directory, removing any
            // previously indexed documents:
            iwc.setOpenMode(OpenMode.CREATE);
        } else {
            // Add new documents to an existing index:
            iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        }

        // Optional: for better indexing performance, if you
        // are indexing many documents, increase the RAM
        // buffer.  But if you do this, increase the max heap
        // size to the JVM (eg add -Xmx512m or -Xmx1g):
        //
        // iwc.setRAMBufferSizeMB(256.0);

        IndexWriter writer = new IndexWriter(dir, iwc);
        indexDocs(writer, docDir);

        // NOTE: if you want to maximize search performance,
        // you can optionally call forceMerge here.  This can be
        // a terribly costly operation, so generally it's only
        // worth it when your index is relatively static (ie
        // you're done adding documents to it):
        //
        // writer.forceMerge(1);

        writer.close();

        Date end = new Date();
        System.out.println(end.getTime() - start.getTime() + " total milliseconds");

    } catch (IOException e) {
        System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage());
    }
}

From source file:com.FormBasedXmlQueryDemo.java

License:Apache License

private void openExampleIndex() throws IOException {
    //Create a RAM-based index from our test data file
    RAMDirectory rd = new RAMDirectory();
    IndexWriterConfig iwConfig = new IndexWriterConfig(Version.LUCENE_40, analyzer);
    IndexWriter writer = new IndexWriter(rd, iwConfig);
    InputStream dataIn = getServletContext().getResourceAsStream("/WEB-INF/data.tsv");
    BufferedReader br = new BufferedReader(new InputStreamReader(dataIn, IOUtils.CHARSET_UTF_8));
    String line = br.readLine();/*ww w .  j a  va 2  s  .c o  m*/
    final FieldType textNoNorms = new FieldType(TextField.TYPE_STORED);
    textNoNorms.setOmitNorms(true);
    while (line != null) {
        line = line.trim();
        if (line.length() > 0) {
            //parse row and create a document
            StringTokenizer st = new StringTokenizer(line, "\t");
            Document doc = new Document();
            doc.add(new Field("location", st.nextToken(), textNoNorms));
            doc.add(new Field("salary", st.nextToken(), textNoNorms));
            doc.add(new Field("type", st.nextToken(), textNoNorms));
            doc.add(new Field("description", st.nextToken(), textNoNorms));
            writer.addDocument(doc);
        }
        line = br.readLine();
    }
    writer.close();

    //open searcher
    // this example never closes it reader!
    IndexReader reader = DirectoryReader.open(rd);
    searcher = new IndexSearcher(reader);
}

From source file:com.foundationdb.lucene.SimpleTest.java

License:Open Source License

@Test
public void indexBasic() throws Exception {
    StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_44, analyzer);
    // recreate the index on each execution
    config.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
    config.setCodec(new FDBCodec());
    FDBDirectory dir = createDirectoryForMethod();
    IndexWriter writer = new IndexWriter(dir, config);
    try {/*from   www  .j ava2  s .  c  o  m*/
        writer.addDocument(Arrays.asList(new TextField("title", "The title of my first document", Store.YES),
                new TextField("content", "The content of the first document", Store.NO)));

        writer.addDocument(Arrays.asList(new TextField("title", "The title of the second document", Store.YES),
                new TextField("content", "And this is the content", Store.NO)));
    } finally {
        writer.close();
    }
    assertDocumentsAreThere(dir, 2);
}

From source file:com.fuerve.villageelder.actions.results.SearchResultItemTest.java

License:Apache License

private void buildDummyIndex(final Directory indexDirectory, final Directory taxonomyDirectory)
        throws IOException {
    IndexWriterConfig iwc = new IndexWriterConfig(Lucene.LUCENE_VERSION, Lucene.getPerFieldAnalyzer());
    iwc.setOpenMode(OpenMode.CREATE);/*  w w  w  .  ja v a2  s .c o  m*/
    IndexWriter iw = new IndexWriter(indexDirectory, iwc);
    TaxonomyWriter tw = new DirectoryTaxonomyWriter(taxonomyDirectory, OpenMode.CREATE);
    List<CategoryPath> categories = new ArrayList<CategoryPath>();
    FacetFields facetFields = new FacetFields(tw);

    Document doc = new Document();
    categories.clear();
    doc.add(new StringField("Author", "foo", Store.YES));
    categories.add(new CategoryPath("Author", "foo"));
    doc.add(new LongField("RevisionNumber", 50L, Store.YES));
    doc.add(new StringField("Revision", "50", Store.YES));
    doc.add(new TextField("Message", "stuff", Store.YES));
    iw.addDocument(doc);
    facetFields.addFields(doc, categories);

    doc = new Document();
    facetFields = new FacetFields(tw);
    categories.clear();
    doc.add(new StringField("Author", "bar", Store.YES));
    categories.add(new CategoryPath("Author", "bar"));
    doc.add(new LongField("RevisionNumber", 5000L, Store.YES));
    doc.add(new StringField("Revision", "5000", Store.YES));
    doc.add(new TextField("Message", "stuff", Store.YES));
    iw.addDocument(doc);
    facetFields.addFields(doc, categories);

    tw.commit();
    tw.close();
    iw.commit();
    iw.close();
}