parquetinputformat是fileinputformat的子级，它支持多个文件输入。所以，简而言之，您不需要combileparquetfileinputformat
只需使用fileinputformat.addinputpaths来指定输入。
parquetinputformat的来源https://github.com/parquet/parquet-mr/blob/master/parquet-hadoop/src/main/java/parquet/hadoop/parquetinputformat.java
p、 如果你有很多小Parquet文件，很可能你做错了什么。

import org.apache.hadoop.mapreduce.InputSplit; 
import org.apache.hadoop.mapreduce.RecordReader; 
import org.apache.hadoop.mapreduce.TaskAttemptContext; 
import org.apache.hadoop.mapreduce.lib.input.CombineFileInputFormat; 
import org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader; 
import org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReaderWrapper; import org.apache.hadoop.mapreduce.lib.input.CombineFileSplit; 
import parquet.avro.AvroReadSupport; 
import parquet.hadoop.ParquetInputFormat;
    import java.io.IOException;
    public class CombineParquetInputFormat<T> extends CombineFileInputFormat<Void, T> {
        @Override
        public RecordReader<Void, T> createRecordReader(InputSplit split, TaskAttemptContext
                context) throws IOException {
            CombineFileSplit combineSplit = (CombineFileSplit) split;
            return new CombineFileRecordReader(combineSplit, context, CombineParquetrecordReader.class);
        }
        private static class CombineParquetrecordReader<T> extends CombineFileRecordReaderWrapper<Void, T> {
            public  CombineParquetrecordReader(CombineFileSplit split, TaskAttemptContext context, Integer idx) throws
                    IOException, InterruptedException {
                super(new ParquetInputFormat<T>(AvroReadSupport.class), split, context, idx);
            }
        } }

一个很棒的关于集成测试的博客http://bytepadding.com/big-data/spark/combineparquetfileinputformat/