[GitHub] carbondata pull request #2069: [WIP][CARBONDATA-2224][File Level Reader Supp...

[jackylk <gi...@git.apache.org>]

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

    https://github.com/apache/carbondata/pull/2069#discussion_r175339069
  
    --- Diff: hadoop/src/main/java/org/apache/carbondata/hadoop/api/CarbonInputFormat.java ---
    @@ -0,0 +1,530 @@
    +/*
    + * 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.carbondata.hadoop.api;
    +
    +import java.io.ByteArrayInputStream;
    +import java.io.DataInputStream;
    +import java.io.IOException;
    +import java.lang.reflect.Constructor;
    +import java.util.ArrayList;
    +import java.util.BitSet;
    +import java.util.List;
    +
    +import org.apache.carbondata.core.constants.CarbonCommonConstants;
    +import org.apache.carbondata.core.datamap.DataMapChooser;
    +import org.apache.carbondata.core.datamap.DataMapLevel;
    +import org.apache.carbondata.core.datamap.Segment;
    +import org.apache.carbondata.core.datamap.dev.expr.DataMapExprWrapper;
    +import org.apache.carbondata.core.exception.InvalidConfigurationException;
    +import org.apache.carbondata.core.indexstore.ExtendedBlocklet;
    +import org.apache.carbondata.core.indexstore.PartitionSpec;
    +import org.apache.carbondata.core.indexstore.blockletindex.BlockletDataMapFactory;
    +import org.apache.carbondata.core.metadata.AbsoluteTableIdentifier;
    +import org.apache.carbondata.core.metadata.ColumnarFormatVersion;
    +import org.apache.carbondata.core.metadata.schema.PartitionInfo;
    +import org.apache.carbondata.core.metadata.schema.partition.PartitionType;
    +import org.apache.carbondata.core.metadata.schema.table.CarbonTable;
    +import org.apache.carbondata.core.metadata.schema.table.TableInfo;
    +import org.apache.carbondata.core.mutate.UpdateVO;
    +import org.apache.carbondata.core.scan.expression.Expression;
    +import org.apache.carbondata.core.scan.filter.SingleTableProvider;
    +import org.apache.carbondata.core.scan.filter.TableProvider;
    +import org.apache.carbondata.core.scan.filter.resolver.FilterResolverIntf;
    +import org.apache.carbondata.core.scan.model.QueryModel;
    +import org.apache.carbondata.core.stats.QueryStatistic;
    +import org.apache.carbondata.core.stats.QueryStatisticsConstants;
    +import org.apache.carbondata.core.stats.QueryStatisticsRecorder;
    +import org.apache.carbondata.core.util.CarbonProperties;
    +import org.apache.carbondata.core.util.CarbonTimeStatisticsFactory;
    +import org.apache.carbondata.core.util.CarbonUtil;
    +import org.apache.carbondata.core.util.DataTypeConverter;
    +import org.apache.carbondata.core.util.DataTypeConverterImpl;
    +import org.apache.carbondata.core.util.path.CarbonTablePath;
    +import org.apache.carbondata.hadoop.CarbonInputSplit;
    +import org.apache.carbondata.hadoop.CarbonMultiBlockSplit;
    +import org.apache.carbondata.hadoop.CarbonProjection;
    +import org.apache.carbondata.hadoop.CarbonRecordReader;
    +import org.apache.carbondata.hadoop.readsupport.CarbonReadSupport;
    +import org.apache.carbondata.hadoop.readsupport.impl.DictionaryDecodeReadSupport;
    +import org.apache.carbondata.hadoop.util.CarbonInputFormatUtil;
    +import org.apache.carbondata.hadoop.util.ObjectSerializationUtil;
    +
    +import org.apache.commons.logging.Log;
    +import org.apache.commons.logging.LogFactory;
    +import org.apache.hadoop.conf.Configuration;
    +import org.apache.hadoop.fs.FileSystem;
    +import org.apache.hadoop.fs.LocalFileSystem;
    +import org.apache.hadoop.fs.Path;
    +import org.apache.hadoop.mapreduce.InputSplit;
    +import org.apache.hadoop.mapreduce.JobContext;
    +import org.apache.hadoop.mapreduce.RecordReader;
    +import org.apache.hadoop.mapreduce.TaskAttemptContext;
    +import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
    +import org.apache.hadoop.mapreduce.lib.input.FileSplit;
    +import org.apache.hadoop.mapreduce.security.TokenCache;
    +
    +/**
    + * Input format of CarbonData file.
    --- End diff --
    
    change comment: 
    `Base class for carbondata input format, there are two input format implementation:
    1. CarbonFileInputFormat: describe this format
    2. CarbonTableInputFormat: describe this format
    `


---