[jira] [Commented] (TAJO-1131) Supports Inserting or Creating table into the HBase mapped table.

[ASF GitHub Bot (JIRA)]

    [ 
https://issues.apache.org/jira/browse/TAJO-1131?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14211837#comment-14211837
 ] 

ASF GitHub Bot commented on TAJO-1131:
--------------------------------------

Github user babokim commented on a diff in the pull request:

    https://github.com/apache/tajo/pull/232#discussion_r20343234
  
    --- Diff: 
tajo-storage/src/main/java/org/apache/tajo/storage/hbase/HBaseScanner.java ---
    @@ -0,0 +1,445 @@
    +/**
    + * Licensed to the Apache Software Foundation (ASF) under one
    + * or more contributor license agreements.  See the NOTICE file
    + * distributed with this work for additional information
    + * regarding copyright ownership.  The ASF licenses this file
    + * to you under the Apache License, Version 2.0 (the
    + * "License"); you may not use this file except in compliance
    + * with the License.  You may obtain a copy of the License at
    + *
    + *     http://www.apache.org/licenses/LICENSE-2.0
    + *
    + * Unless required by applicable law or agreed to in writing, software
    + * distributed under the License is distributed on an "AS IS" BASIS,
    + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    + * See the License for the specific language governing permissions and
    + * limitations under the License.
    + */
    +
    +package org.apache.tajo.storage.hbase;
    +
    +import org.apache.commons.logging.Log;
    +import org.apache.commons.logging.LogFactory;
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.hbase.client.*;
    +import org.apache.hadoop.hbase.filter.*;
    +import org.apache.tajo.catalog.Column;
    +import org.apache.tajo.catalog.Schema;
    +import org.apache.tajo.catalog.TableMeta;
    +import org.apache.tajo.catalog.proto.CatalogProtos.StoreType;
    +import org.apache.tajo.catalog.statistics.ColumnStats;
    +import org.apache.tajo.catalog.statistics.TableStats;
    +import org.apache.tajo.conf.TajoConf;
    +import org.apache.tajo.datum.Datum;
    +import org.apache.tajo.datum.NullDatum;
    +import org.apache.tajo.datum.TextDatum;
    +import org.apache.tajo.storage.Scanner;
    +import org.apache.tajo.storage.StorageManager;
    +import org.apache.tajo.storage.Tuple;
    +import org.apache.tajo.storage.VTuple;
    +import org.apache.tajo.storage.fragment.Fragment;
    +import org.apache.tajo.util.BytesUtils;
    +
    +import java.io.IOException;
    +import java.util.Collection;
    +import java.util.NavigableMap;
    +import java.util.Set;
    +import java.util.concurrent.atomic.AtomicBoolean;
    +
    +public class HBaseScanner implements Scanner {
    +  private static final Log LOG = LogFactory.getLog(HBaseScanner.class);
    +  private static final int DEFAULT_FETCH_SIZE = 1000;
    +  private static final int MAX_LIST_SIZE = 100;
    +
    +  protected boolean inited = false;
    +  private TajoConf conf;
    +  private Schema schema;
    +  private TableMeta meta;
    +  private HBaseFragment fragment;
    +  private Scan scan;
    +  private HTableInterface htable;
    +  private Configuration hbaseConf;
    +  private Column[] targets;
    +  private TableStats tableStats;
    +  private ResultScanner scanner;
    +  private AtomicBoolean finished = new AtomicBoolean(false);
    +  private float progress = 0.0f;
    +  private int scanFetchSize;
    +  private Result[] scanResults;
    +  private int scanResultIndex = -1;
    +  private Column[] schemaColumns;
    +
    +  private ColumnMapping columnMapping;
    +  private int[] targetIndexes;
    +
    +  private int numRows = 0;
    +
    +  private byte[][][] mappingColumnFamilies;
    +  private boolean[] isRowKeyMappings;
    +  private boolean[] isBinaryColumns;
    +  private boolean[] isColumnKeys;
    +  private boolean[] isColumnValues;
    +
    +  private int[] rowKeyFieldIndexes;
    +  private char rowKeyDelimiter;
    +
    +  public HBaseScanner (Configuration conf, Schema schema, TableMeta meta, 
Fragment fragment) throws IOException {
    +    this.conf = (TajoConf)conf;
    +    this.schema = schema;
    +    this.meta = meta;
    +    this.fragment = (HBaseFragment)fragment;
    +    this.tableStats = new TableStats();
    +  }
    +
    +  @Override
    +  public void init() throws IOException {
    +    inited = true;
    +    schemaColumns = schema.toArray();
    +    if (fragment != null) {
    +      tableStats.setNumBytes(0);
    +      tableStats.setNumBlocks(1);
    +    }
    +    if (schema != null) {
    +      for(Column eachColumn: schema.getColumns()) {
    +        ColumnStats columnStats = new ColumnStats(eachColumn);
    +        tableStats.addColumnStat(columnStats);
    +      }
    +    }
    +
    +    scanFetchSize = 
Integer.parseInt(meta.getOption("hbase.scanner.fetch,size", "" + 
DEFAULT_FETCH_SIZE));
    --- End diff --
    
    I will change constant value. And all constant variables for HBase storage 
are placed in HBaseStorageConstants class.


> Supports Inserting or Creating table into the HBase mapped table.
> -----------------------------------------------------------------
>
>                 Key: TAJO-1131
>                 URL: https://issues.apache.org/jira/browse/TAJO-1131
>             Project: Tajo
>          Issue Type: Sub-task
>            Reporter: Hyoungjun Kim
>            Assignee: Hyoungjun Kim
>            Priority: Minor
>
> Tajo should support inserting or creating table into the HBase mapped table.
> HBase supports bulk uploading. For using  this tool the query result should 
> be range partitioned and sorted by a region split range. 
> See the following HBase reference.
> http://hbase.apache.org/book/arch.bulk.load.html



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)