Github user jackylk commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1995#discussion_r170408142
--- Diff:
hadoop/src/main/java/org/apache/carbondata/hadoop/api/CarbonFileInputFormat.java
---
@@ -0,0 +1,940 @@
+/*
+ * 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.File;
+import java.io.IOException;
+import java.io.Serializable;
+import java.lang.reflect.Constructor;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.BitSet;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.LinkedList;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+import org.apache.carbondata.core.constants.CarbonCommonConstants;
+import org.apache.carbondata.core.datamap.DataMapStoreManager;
+import org.apache.carbondata.core.datamap.DataMapType;
+import org.apache.carbondata.core.datamap.TableDataMap;
+import org.apache.carbondata.core.datastore.filesystem.CarbonFile;
+import org.apache.carbondata.core.datastore.impl.FileFactory;
+import org.apache.carbondata.core.exception.InvalidConfigurationException;
+import org.apache.carbondata.core.indexstore.ExtendedBlocklet;
+import org.apache.carbondata.core.indexstore.blockletindex.BlockletDataMap;
+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.CarbonUpdateUtil;
+import org.apache.carbondata.core.mutate.SegmentUpdateDetails;
+import org.apache.carbondata.core.mutate.UpdateVO;
+import org.apache.carbondata.core.mutate.data.BlockMappingVO;
+import org.apache.carbondata.core.reader.CarbonIndexFileReader;
+import org.apache.carbondata.core.scan.expression.Expression;
+import org.apache.carbondata.core.scan.filter.FilterExpressionProcessor;
+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.statusmanager.FileFormat;
+import org.apache.carbondata.core.statusmanager.SegmentStatusManager;
+import org.apache.carbondata.core.statusmanager.SegmentUpdateStatusManager;
+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.format.BlockIndex;
+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.carbondata.hadoop.util.SchemaReader;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.BlockLocation;
+import org.apache.hadoop.fs.FileStatus;
+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.Job;
+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.
+ *
+ * @param <T>
+ */
+public class CarbonFileInputFormat<T> extends FileInputFormat<Void, T>
implements Serializable {
--- End diff --
Use InterfaceAudience and InterfaceStability to annotation all newly added
public class
Please follow this in the future
---
