Examples of org.apache.lucene.document.Document

org.apache.lucene.document.Document
Documents are the unit of indexing and search. A Document is a set of fields. Each field has a name and a textual value. A field may be {@link Fieldable#isStored() stored} with the document, in whichcase it is returned with search hits on the document. Thus each document should typically contain one or more stored fields which uniquely identify it.
Note that fields which are not {@link Fieldable#isStored() stored} arenot available in documents retrieved from the index, e.g. with {@link ScoreDoc#doc}, {@link Searcher#doc(int)} or {@link IndexReader#document(int)}.


    /**
     * ��������
     */
    protected static int addIndex() throws IOException {
    Document doc = new Document();
    doc.add(new Field("id", "1", Field.Store.YES, Field.Index.UN_TOKENIZED));
    doc.add(new Field("author", "����IBM OSIһһ����", Field.Store.YES, Field.Index.TOKENIZED));
    doc.add(new Field("time", Long.toString(System.currentTimeMillis()), Field.Store.YES, Field.Index.UN_TOKENIZED));
    doc.add(new Field("content", "��֪����ʲôʱ��ʼ����ʲô�������涼�и����ڣ��ﵶ�����ڣ����ͷ����ڣ�������ֽ������ڣ��ҿ�ʼ���ɣ�����������ϣ�����ʲô�����ǲ�����ڵģ�", Field.Store.NO, Field.Index.TOKENIZED));
    IndexWriter writer = getWriter();
    try {
        writer.addDocument(doc);
        writer.optimize();
    }finally {

View Full Code Here

   */
  public static synchronized void add(SearchEnabled doc) throws Exception {
    if(doc == null)
      return ;


    Document lucene_doc = new Document();
    
    //Set keyword field
    String key = getField(doc, doc.getKeywordField());
    lucene_doc.add(Keyword(doc.getKeywordField(), key));
    
    //Set identity(classname) of object
    lucene_doc.add(Keyword(CLASSNAME_FIELD, doc.getClass().getName()));
    
    //Set storage field
    String[] storeFields = doc.getStoreFields();
    for(int i=0;storeFields!=null && i<storeFields.length;i++){
      String propertyValue = getField(doc, storeFields[i]);
      if(propertyValue!=null)
        lucene_doc.add(Keyword(storeFields[i], propertyValue));
    }
    //Set indexed field
    String[] indexFields = doc.getIndexFields();
    for(int i=0;indexFields!=null && i<indexFields.length;i++){
      String propertyValue = getField(doc, indexFields[i]);
      lucene_doc.add(UnStored(indexFields[i], propertyValue));
    }
    //Write document
    IndexWriter writer = getWriter(doc.name());
    try {
        writer.addDocument(lucene_doc);

View Full Code Here

    int numResults = hits.length();
    //System.out.println(numResults + " found............................");
    int result_count = Math.min(numResults, MAX_RESULT_COUNT);
    List results = new ArrayList(result_count);
    for(int i=0;i<result_count;i++){
      Document doc = (Document)hits.doc(i);
      //ӳ���ĵ����Ե�Java������
      Object result = params.getSearchObject().newInstance();
      Enumeration fields = doc.fields();
      while(fields.hasMoreElements()){
        Field field = (Field)fields.nextElement();
        //System.out.println(field.name()+" -- "+field.stringValue());
        if(CLASSNAME_FIELD.equals(field.name()))
          continue;

View Full Code Here

            }
            for (int i = 0, len = docs.scoreDocs.length;
                    i < limit && i + offset < docs.totalHits
                    && i + offset < len; i++) {
                ScoreDoc sd = docs.scoreDocs[i + offset];
                Document doc = searcher.doc(sd.doc);
                float score = sd.score;
                //## LUCENE3 end ##
                String q = doc.get(LUCENE_FIELD_QUERY);
                if (data) {
                    int idx = q.indexOf(" WHERE ");
                    JdbcConnection c = (JdbcConnection) conn;
                    Session session = (Session) c.getSession();
                    Parser p = new Parser(session);

View Full Code Here

                throw convertException(e);
            }
            ## LUCENE2 end ##*/
            //## LUCENE3 begin ##
            String query = getQuery(row);
            Document doc = new Document();
            doc.add(new Field(LUCENE_FIELD_QUERY, query,
                    Field.Store.YES, Field.Index.NOT_ANALYZED));
            long time = System.currentTimeMillis();
            doc.add(new Field(LUCENE_FIELD_MODIFIED,
                    DateTools.timeToString(time, DateTools.Resolution.SECOND),
                    Field.Store.YES, Field.Index.NOT_ANALYZED));
            StatementBuilder buff = new StatementBuilder();
            for (int index : indexColumns) {
                String columnName = columns[index];
                String data = asString(row[index], columnTypes[index]);
                // column names that start with _
                // must be escaped to avoid conflicts
                // with internal field names (_DATA, _QUERY, _modified)
                if (columnName.startsWith(LUCENE_FIELD_COLUMN_PREFIX)) {
                    columnName = LUCENE_FIELD_COLUMN_PREFIX + columnName;
                }
                doc.add(new Field(columnName, data,
                        Field.Store.NO, Field.Index.ANALYZED));
                buff.appendExceptFirst(" ");
                buff.append(data);
            }
            Field.Store storeText = STORE_DOCUMENT_TEXT_IN_INDEX ?
                    Field.Store.YES : Field.Store.NO;
            doc.add(new Field(LUCENE_FIELD_DATA, buff.toString(), storeText,
                    Field.Index.ANALYZED));
            try {
                indexAccess.writer.addDocument(doc);
                indexAccess.writer.commit();
                // recreate Searcher with the IndexWriter's reader.

View Full Code Here

          {
            // handle partial full pages
            break;
          }


          Document doc = hits.doc(i);


          // pull in our values
          String   nickname = doc.getField("nickname").stringValue();
          String   message = doc.getField("message").stringValue();
          String   channelname = doc.getField("channel").stringValue();
          String   botname = doc.getField("botname").stringValue();
          String   servername = doc.getField("servername").stringValue();
          Date   moment = DateField.stringToDate(doc.getField("moment").stringValue());
          String   day = mOutputDateFormat.format(moment);
          String   time = mOutputTimeFormat.format(moment);
          String   outputday = mDateFormat.format(moment);


          // stolen directly from ChannelLog

View Full Code Here

              {
                String       servername = resultSet.getString("servername").toLowerCase();
                String       botname = resultSet.getString("botname").toLowerCase();
                String       channel = resultSet.getString("channel").substring(1).toLowerCase();
                String       key = getIndexName(botname, servername, channel);
                Document     doc = new Document();
                Timestamp     moment = resultSet.getTimestamp("moment");
                IndexWriter   writer = (IndexWriter)index_writer_cache.get(key);


                if (writer == null)
                {
                  writer = getIndexWriter(key, true);


                  index_writer_cache.put(key, writer);
                }


                beginningOfDay.setTime(moment);
                beginningOfDay.setTimeZone(TimeZone.getTimeZone(DroneConfig.getTimezone()));
                beginningOfDay.set(Calendar.HOUR, 0);
                beginningOfDay.set(Calendar.MINUTE, 0);
                beginningOfDay.set(Calendar.SECOND, 0);
                beginningOfDay.set(Calendar.MILLISECOND, 0);


                long dayInMillis = beginningOfDay.getTimeInMillis();
                long timeInMillis = moment.getTime() - dayInMillis;


                // need to store channel without the '#'
                doc.add(new Field("moment", DateField.dateToString(resultSet.getTimestamp("moment")), true, true, true));
                doc.add(new Field("momentDateSort", String.valueOf(dayInMillis), false, true, false));
                doc.add(new Field("momentTimeSort", String.valueOf(timeInMillis), false, true, false));
                doc.add(new Field("botname", botname, true, true, true));
                doc.add(new Field("channel", channel, true, true, true));
                doc.add(new Field("servername", servername, true, true, true));
                doc.add(new Field("nickname", resultSet.getString("nickname"), true, true, true));
                doc.add(new Field("username", resultSet.getString("username"), true, true, true));
                doc.add(new Field("hostname", resultSet.getString("hostname"), true, true, true));
                doc.add(new Field("message", resultSet.getString("message"), true, true, true));


                try
                {
                  writer.addDocument(doc, getAnalyzer());
                }

View Full Code Here

  {
    String botname = bot.getName();
    String channelname = channel.getName().substring(1);
    String servername = channel.getServer().getServerName();


    Document doc = new Document();
    Calendar beginningOfDay = Calendar.getInstance();


    beginningOfDay.setTime(moment);
    beginningOfDay.setTimeZone(TimeZone.getTimeZone(DroneConfig.getTimezone()));
    beginningOfDay.set(Calendar.HOUR, 0);
    beginningOfDay.set(Calendar.MINUTE, 0);
    beginningOfDay.set(Calendar.SECOND, 0);
    beginningOfDay.set(Calendar.MILLISECOND, 0);


    long dayInMillis = beginningOfDay.getTimeInMillis();
    long timeInMillis = moment.getTime() - dayInMillis;


    doc.add(new Field("moment", DateField.dateToString(moment), true, true, true));
    doc.add(new Field("momentDateSort", String.valueOf(dayInMillis), false, true, false));
    doc.add(new Field("momentTimeSort", String.valueOf(timeInMillis), false, true, false));
    doc.add(new Field("botname", botname, true, true, true));
    doc.add(new Field("channel", channelname, true, true, true));
    doc.add(new Field("servername", servername, true, true, true));
    doc.add(new Field("nickname", message.getPrefix().getNickName(), true, true, true));
    doc.add(new Field("username", message.getPrefix().getUser(), true, true, true));
    doc.add(new Field("hostname", message.getPrefix().getHost(), true, true, true));
    doc.add(new Field("message", message.getTrailing(), true, true, true));


    addDocumentToQueue(getIndexName(botname, servername, channelname), doc);
  }

View Full Code Here

        }
        indexArticle( article );
    }


    private void indexArticle(Article article) throws IOException {
        Document doc = article.getOveriewDocument();
        IndexWriter writer = new IndexWriter( forum.getArticleOverview(), ws, true );
        writer.addDocument( doc );
        writer.close();
    }

View Full Code Here

    public String getLines() {
        return headers.get("Lines", "");
    }


    public Document getOveriewDocument() {
        Document doc = new Document();
        doc.add( Field.Keyword("article.message-id", getMessageId()) );
        doc.add( Field.Text("article.subject", getSubject()) );
        doc.add( Field.Keyword("article.from", getFrom()) );
        try {
            doc.add( Field.Keyword("article.date", getDate()) );
        } catch( ParseException e ) {
        }
        doc.add( Field.Text("article.references", getReferences()) );
        doc.add( Field.UnIndexed("article.bytes", String.valueOf(getBody().length()) ) );
        doc.add( Field.UnIndexed("article.lines", getLines()) );
        doc.add( Field.UnIndexed("article.xref", getXRef()) );
        addNewsgroupArticleNumbers(doc);
        return doc;
    }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.document.Document

com.bericotech.clavin.gazetteer.query.LuceneGazetteer

com.browseengine.bobo.test.BasicIndexingTest

com.browseengine.bobo.test.BoboTestCase

com.browseengine.bobo.test.FacetNotValuesTest

com.gentics.cr.lucene.autocomplete.Autocompleter

com.gentics.cr.lucene.indexer.index.CRLuceneIndexJob

com.gentics.cr.lucene.indexer.index.LuceneIndexUpdateChecker

com.gentics.cr.lucene.search.CRSearcher

com.gentics.cr.lucene.search.query.mocks.SimpleLucene

com.tamingtext.classifier.mlt.TrainMoreLikeThis

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.