Configuration conf = new Configuration();
conf.set("fs.defaultFS", "hdfs://localhost:9000");
TableSchema schema = new Schema(
Optional.of(1),
new SchemaField("id", Types.IntegerType.get()),
new SchemaField("name", Types.StringType.get())
);
Table table = new HadoopTables(conf).create(schema, "hdfs://localhost:9000/data/my_table");
table.newAppend()
.appendFile(Paths.get("hdfs://localhost:9000/data/data.csv"))
.commit();
table.updateSpec()
.addFieldPartitionStrategy("name", "hash", 4)
.commit();
table.newRewrite()
.rewriteDataFiles()
.clusterBy("id")
.build();
Iterable<Row> rows = table.newScan()
.filter(Expressions.equal("name", "John"))
.select("id", "name")
.execute();
for (Row row : rows) {
System.out.println(row);
}
