parquet - Apache 的 Parquet Java API 的文档？

Question

我想使用 Apache 的 parquet-mr 项目通过 Java 以编程方式读取/写入 Parquet 文件。我似乎找不到任何有关如何使用此 API 的文档(除了查看源代码并查看它的使用方式)——只是想知道是否存在任何此类文档？

Answer 1

我写了一篇关于读取 Parquet 文件 ( http://www.jofre.de/?p=1459 ) 的博客文章，并提出了以下解决方案，它甚至能够读取 INT96 字段。

您需要以下 Maven 依赖项:

<dependencies>
  <dependency>
    <groupId>org.apache.parquet</groupId>
    <artifactId>parquet-hadoop</artifactId>
    <version>1.9.0</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.7.0</version>
  </dependency>
</dependencies>

代码基本上是:

public class Main {

    private static Path path = new Path("file:\\C:\\Users\\file.snappy.parquet");

    private static void printGroup(Group g) {

        int fieldCount = g.getType().getFieldCount();
        for (int field = 0; field < fieldCount; field++) {
            int valueCount = g.getFieldRepetitionCount(field);

            Type fieldType = g.getType().getType(field);
            String fieldName = fieldType.getName();

            for (int index = 0; index < valueCount; index++) {
                if (fieldType.isPrimitive()) {
                    System.out.println(fieldName + " " + g.getValueToString(field, index));
                }
            }
        }

    }

    public static void main(String[] args) throws IllegalArgumentException {

        Configuration conf = new Configuration();

        try {
            ParquetMetadata readFooter = ParquetFileReader.readFooter(conf, path, ParquetMetadataConverter.NO_FILTER);
            MessageType schema = readFooter.getFileMetaData().getSchema();
            ParquetFileReader r = new ParquetFileReader(conf, path, readFooter);

            PageReadStore pages = null;
            try {
                while (null != (pages = r.readNextRowGroup())) {
                    final long rows = pages.getRowCount();
                    System.out.println("Number of rows: " + rows);

                    final MessageColumnIO columnIO = new ColumnIOFactory().getColumnIO(schema);
                    final RecordReader<Group> recordReader = columnIO.getRecordReader(pages, new GroupRecordConverter(schema));
                    for (int i = 0; i < rows; i++) {
                        final Group g = recordReader.read();
                        printGroup(g);

                        // TODO Compare to System.out.println(g);
                    }
                }
            } finally {
                r.close();
            }
        } catch (IOException e) {
            System.out.println("Error reading parquet file.");
            e.printStackTrace();
        }

    }
}