datax读取Parquet格式文件总列数

pom引用

org.apache.parquet
parquet-avro
1.12.0



org.apache.parquet
parquet-hadoop
1.12.0


org.apache.hadoop
hadoop-common
2.7.1

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.parquet.hadoop.ParquetFileReader;
import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData;
import org.apache.parquet.hadoop.metadata.ParquetMetadata;

public class ParquetColumnCountReader {
    public static void main(String[] args) {
        String parquetFilePath = "path/to/parquet/file.parquet";

        Configuration configuration = new Configuration();
        Path path = new Path(parquetFilePath);
        try {
            ParquetMetadata metadata = ParquetFileReader.readFooter(configuration, path);
            List columns = metadata.getBlocks().get(0).getColumns();
            int columnCount = columns.size();
            System.out.println("Total column count: " + columnCount);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}