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

Introduction

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

Prototype

public long addDocument(Iterable<? extends IndexableField> doc) throws IOException 

Source Link

Document

Adds a document to this index.

Usage

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexSites(IndexWriter writer) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {//  ww  w.  ja v  a2s . com
        pst = con.prepareStatement(INDEX_SITES_SQL);
        ResultSet rs = pst.executeQuery();
        int count = 0;
        while (rs.next()) {
            SiteSearchData data = new SiteSearchData();
            getSearchData(data, rs);
            data.setDoc();
            writer.addDocument(data.getDoc());
            count++;
            if ((count % 100) == 0) {
                writer.commit();
            }
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing " + count + " sites");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexSite(IndexWriter writer, int id) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {/*from w  w  w .j a  va2 s  .c  o  m*/
        pst = con.prepareStatement(INDEX_NODE_SQL);
        pst.setInt(1, id);
        ResultSet rs = pst.executeQuery();
        if (rs.next()) {
            SiteSearchData data = new SiteSearchData();
            getSearchData(data, rs);
            data.setDoc();
            writer.addDocument(data.getDoc());
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing site");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexPages(IndexWriter writer) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {//from   w  w  w  . ja v  a2 s.co m
        pst = con.prepareStatement(INDEX_PAGES_SQL);
        ResultSet rs = pst.executeQuery();
        int count = 0;
        while (rs.next()) {
            PageSearchData data = new PageSearchData();
            getSearchData(data, rs);
            data.setDoc();
            writer.addDocument(data.getDoc());
            count++;
            if ((count % 100) == 0) {
                writer.commit();
            }
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing " + count + " pages");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexPage(IndexWriter writer, int id) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {/*from   w ww  .  j  a v  a2s . c om*/
        pst = con.prepareStatement(INDEX_NODE_SQL);
        pst.setInt(1, id);
        ResultSet rs = pst.executeQuery();
        if (rs.next()) {
            PageSearchData data = new PageSearchData();
            getSearchData(data, rs);
            //todo read parts
            data.setDoc();
            writer.addDocument(data.getDoc());
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing page");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexFiles(IndexWriter writer) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {/*from   w ww  .  j  av a 2  s .co  m*/
        pst = con.prepareStatement(INDEX_FILES_SQL);
        ResultSet rs = pst.executeQuery();
        int count = 0;
        while (rs.next()) {
            FileSearchData data = new FileSearchData();
            getSearchData(data, rs);
            data.setDoc();
            writer.addDocument(data.getDoc());
            count++;
            if ((count % 100) == 0) {
                writer.commit();
            }
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing " + count + " files");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexFile(IndexWriter writer, int id) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {// w  ww.j a  v a  2 s  .co  m
        pst = con.prepareStatement(INDEX_NODE_SQL);
        pst.setInt(1, id);
        ResultSet rs = pst.executeQuery();
        if (rs.next()) {
            FileSearchData data = new FileSearchData();
            getSearchData(data, rs);
            data.setDoc();
            writer.addDocument(data.getDoc());
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing file");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexUsers(IndexWriter writer) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {/* w w w. j  av a 2 s  .c om*/
        int count = 0;
        pst = con.prepareStatement(INDEX_USERS_SQL);
        ResultSet rs = pst.executeQuery();
        while (rs.next()) {
            SearchData data = getUserSearchData(rs);
            writer.addDocument(data.getDoc());
            count++;
            if ((count % 100) == 0) {
                writer.commit();
            }
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing " + count + " users");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.elbe5.cms.search.SearchBean.java

License:Open Source License

protected void indexUser(IndexWriter writer, int id) throws Exception {
    Connection con = getConnection();
    PreparedStatement pst = null;
    try {/*from  www .j av  a2s.  c  o m*/
        pst = con.prepareStatement(INDEX_USER_SQL);
        pst.setInt(1, id);
        ResultSet rs = pst.executeQuery();
        while (rs.next()) {
            SearchData data = getUserSearchData(rs);
            writer.addDocument(data.getDoc());
        }
        rs.close();
        writer.commit();
        Log.log("finished indexing user");
    } catch (SQLException se) {
        se.printStackTrace();
    } finally {
        closeStatement(pst);
        closeConnection(con);
    }
}

---

From source file:de.hsmannheim.ss15.alr.searchengine.DefaultLuceneController.java

/**
 * Indexes a single document/* w ww.jav a  2s .c  om*/
 */
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try (InputStream stream = Files.newInputStream(file)) {
        // make a new, empty document
        org.apache.lucene.document.Document doc = new org.apache.lucene.document.Document();

        // Add the path of the file as a field named "path".  Use a
        // field that is indexed (i.e. searchable), but don't tokenize 
        // the field into separate words and don't index term frequency
        // or positional information:
        Field pathField = new StringField("path", file.toString(), Field.Store.YES);
        doc.add(pathField);

        // Add the last modified date of the file a field named "modified".
        // Use a LongField that is indexed (i.e. efficiently filterable with
        // NumericRangeFilter).  This indexes to milli-second resolution, which
        // is often too fine.  You could instead create a number based on
        // year/month/day/hour/minutes/seconds, down the resolution you require.
        // For example the long value 2011021714 would mean
        // February 17, 2011, 2-3 PM.
        doc.add(new LongField("modified", lastModified, Field.Store.NO));

        // Add the contents of the file to a field named "contents".  Specify a Reader,
        // so that the text of the file is tokenized and indexed, but not stored.
        // Note that FileReader expects the file to be in UTF-8 encoding.
        // If that's not the case searching for special characters will fail.
        BufferedReader reader = new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8));

        List<String> lines = new ArrayList<>();
        while (reader.ready()) {
            lines.add(reader.readLine());
        }
        if (lines.size() > 0) {
            String urlLine = lines.remove(0);
            if (urlLine != null && urlLine.startsWith("URL:")) {
                urlLine = urlLine.substring(4);
                doc.add(new TextField("URL", urlLine, Field.Store.YES));
            }
        }
        if (lines.size() > 0) {
            String dataType = lines.remove(0);
            if (dataType != null && dataType.startsWith("DataType:")) {
                dataType = dataType.substring(9);
                doc.add(new TextField("DataType", dataType, Field.Store.YES));
            }
        }
        if (lines.size() > 0) {
            String title = lines.remove(0);
            if (title != null && title.startsWith("Title:")) {
                title = title.substring(6);
                doc.add(new TextField("title", title, Field.Store.YES));
            }
        }
        String content = "";
        for (String s : lines) {
            content = content + s;
        }
        doc.add(new TextField("contents", content, Field.Store.NO));

        if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) {
            // New index, so we just add the document (no old document can be there):
            writer.addDocument(doc);
        } else {
            // Existing index (an old copy of this document may have been indexed) so 
            // we use updateDocument instead to replace the old one matching the exact 
            // path, if present:
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
    }
}

---

From source file:de.hybris.platform.lucenesearch.jalo.LuceneTest.java

License:Open Source License

@Before
public void setUp() throws Exception {
    directory = new RAMDirectory();
    final IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_40,
            new StandardAnalyzer(Version.LUCENE_40)).setOpenMode(OpenMode.CREATE_OR_APPEND);
    final IndexWriter writer = new IndexWriter(directory, indexWriterConfig);
    docA = new Document();
    docA.add(new Field("key", "a", Field.Store.YES, Field.Index.NOT_ANALYZED));
    docA.add(new Field("text", "text zum ersten document", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(docA);
    docB = new Document();
    docB.add(new Field("key", "b", Field.Store.YES, Field.Index.NOT_ANALYZED));
    docB.add(new Field("text", "text zum zweiten document", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(docB);//from   w w  w .j a  va  2 s .c  o m
    docC = new Document();
    docC.add(new Field("key", "c", Field.Store.YES, Field.Index.NOT_ANALYZED));
    docC.add(new Field("text", "text zum dritten document", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(docC);
    //writer.optimize();
    writer.close();
}

---

• «
• 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
• 49
• 50
• »