用于缓冲或字节流的 Parquet Writer

java bufferedreader parquet

2022-09-03 15:53:31

我有一个java应用程序，可以将json消息转换为镶木地板格式。有没有在java中写入缓冲区或字节流的镶木地板编写器？大多数例子，我都见过写入文件。

答案 1

TLDR;您将需要实现，例如，类似以下内容的内容：OutputFile

import org.apache.parquet.io.OutputFile;
import org.apache.parquet.io.PositionOutputStream;

import java.io.BufferedOutputStream;
import java.io.IOException;

public class ParquetBufferedWriter implements OutputFile {

    private final BufferedOutputStream out;

    public ParquetBufferedWriter(BufferedOutputStream out) {
        this.out = out;
    }

    @Override
    public PositionOutputStream create(long blockSizeHint) throws IOException {
        return createPositionOutputstream();
    }

    private PositionOutputStream createPositionOutputstream() {
        return new PositionOutputStream() {
            @Override
            public long getPos() throws IOException {
                return 0;
            }

            @Override
            public void write(int b) throws IOException {
                out.write(b);
            }
        };
    }

    @Override
    public PositionOutputStream createOrOverwrite(long blockSizeHint) throws IOException {
        return createPositionOutputstream();
    }

    @Override
    public boolean supportsBlockSize() {
        return false;
    }

    @Override
    public long defaultBlockSize() {
        return 0;
    }

}

你的作家会是这样的：

    ParquetBufferedWriter out = new ParquetBufferedWriter();
        try (ParquetWriter<Record> writer = AvroParquetWriter.
                <Record>builder(out)
                .withRowGroupSize(DEFAULT_BLOCK_SIZE)
                .withPageSize(DEFAULT_PAGE_SIZE)
                .withSchema(SCHEMA)
                .build()) {

            for (Record record : records) {
                writer.write(record);
            }
        } catch (IOException e) {
            throw new IllegalStateException(e);
        }

答案 2

我只需要写入流，所以我完成了naimdjon给出的示例。以下内容对我来说完全没问题。

class ParquetBufferedWriter implements OutputFile {
    
    private final BufferedOutputStream out;

    public ParquetBufferedWriter(BufferedOutputStream out) {
        this.out = out;
    }

    @Override
    public PositionOutputStream create(long blockSizeHint) throws IOException {
        return createPositionOutputstream();
    }

    private PositionOutputStream createPositionOutputstream() {
        return new PositionOutputStream() {
            
            int pos = 0;

            @Override
            public long getPos() throws IOException {
                return pos;
            }

            @Override
            public void flush() throws IOException {
                out.flush();
            };

            @Override
            public void close() throws IOException {
                out.close();
            };

            @Override
            public void write(int b) throws IOException {
                out.write(b);
                pos++;
            }

            @Override
            public void write(byte[] b, int off, int len) throws IOException {
                out.write(b, off, len);
                pos += len;
            }
        };
    }

    @Override
    public PositionOutputStream createOrOverwrite(long blockSizeHint) throws IOException {
        return createPositionOutputstream();
    }

    @Override
    public boolean supportsBlockSize() {
        return false;
    }

    @Override
    public long defaultBlockSize() {
        return 0;
    }
}