Github user ravipesala commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/2384#discussion_r197347008
--- Diff:
processing/src/main/java/org/apache/carbondata/processing/loading/jsoninput/JsonInputFormat.java
---
@@ -0,0 +1,285 @@
+/*
+ * 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.processing.loading.jsoninput;
+
+import java.io.BufferedInputStream;
+import java.io.IOException;
+import java.security.InvalidParameterException;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.Job;
+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.lib.input.LineRecordReader;
+import org.apache.log4j.Logger;
+import org.codehaus.jackson.JsonFactory;
+import org.codehaus.jackson.JsonNode;
+import org.codehaus.jackson.JsonParseException;
+import org.codehaus.jackson.map.JsonMappingException;
+import org.codehaus.jackson.map.ObjectMapper;
+
+/**
+ * Code ported from Hydra-Spark {package com.pluralsight.hydra.hadoop.io}
package
+ * The JsonInputFormat will read two types of JSON formatted data. The
default
+ * expectation is each JSON record is newline delimited. This method is
+ * generally faster and is backed by the {@link LineRecordReader} you are
likely
+ * familiar with. The other method is 'pretty print' of JSON records, where
+ * records span multiple lines and often have some type of root
identifier. This
+ * method is likely slower, but respects record boundaries much like the
+ * LineRecordReader.<br>
+ * <br>
+ * Use of the 'pretty print' reader requires a record identifier.
+ */
+public class JsonInputFormat extends FileInputFormat<LongWritable, Text> {
+
+ private static JsonFactory factory = new JsonFactory();
+
+ private static ObjectMapper mapper = new ObjectMapper(factory);
+
+ public static final String ONE_RECORD_PER_LINE =
"json.input.format.one.record.per.line";
+
+ public static final String RECORD_IDENTIFIER =
"json.input.format.record.identifier";
+
+ @Override public RecordReader<LongWritable, Text>
createRecordReader(InputSplit split,
+ TaskAttemptContext context) throws IOException, InterruptedException
{
+ RecordReader<LongWritable, Text> rdr;
+ if (context.getConfiguration().getBoolean(ONE_RECORD_PER_LINE, false))
{
--- End diff --
use `getOneRecordPerLine` method here
---
