数据湖解决方案关键一环，IceBerg会不会脱颖而出？

Apache Iceberg is an open table format for huge analytic datasets. Iceberg adds tables to Trino and Spark that use a high-performance format that works just like a SQL table.
Iceberg是一个为大规模数据集设计的通用的表格形式。并且适配Trino(原PrestoSQL)和Spark适，提供SQL化解决方案。

import org.apache.iceberg.catalog.TableIdentifier
import org.apache.iceberg.spark.SparkSchemaUtil
val catalog = new HiveCatalog(spark.sparkContext.hadoopConfiguration)
val data = Seq((1, "a"), (2, "b"), (3, "c")).toDF("id", "data")
val schema = SparkSchemaUtil.convert(data.schema)
val name = TableIdentifier.of("default", "test_table")
val table = catalog.createTable(name, schema)

// write the dataset to the table
data.write.format("iceberg").mode("append").save("default.test_table")

// read the table
spark.read.format("iceberg").load("default.test_table")

spark.read.format("iceberg").load("default.test_table").createOrReplaceTempView("test_table")
spark.sql("""SELECT count(1) FROM test_table""")

// Configurate catalog
org.apache.hadoop.conf.Configuration hadoopConf =
    new org.apache.hadoop.conf.Configuration();
hadoopConf.set(
    org.apache.hadoop.hive.conf.HiveConf.ConfVars.METASTOREURIS.varname,
    META_STORE_URIS);
hadoopConf.set(
    org.apache.hadoop.hive.conf.HiveConf.ConfVars.METASTOREWAREHOUSE.varname,
    META_STORE_WAREHOUSE);

Catalog icebergCatalog = new HiveCatalog(hadoopConf);

// Create Iceberg table
Schema schema = new Schema(
   ...
);
PartitionSpec partitionSpec = builderFor(schema)...
TableIdentifier tableIdentifier =
    TableIdentifier.of(DATABASE_NAME, TABLE_NAME);
// If needed, check the existence of table by loadTable() and drop it
// before creating it
icebergCatalog.createTable(tableIdentifier, schema, partitionSpec);

// Obtain an execution environment
StreamExecutionEnvironment env = 
    StreamExecutionEnvironment.getExecutionEnvironment();

// Enable checkpointing
env.enableCheckpointing(...);

// Add Source
DataStream<Map<String, Object>> dataStream =
    env.addSource(source, typeInformation);

// Configure Ieberg sink
Configuration conf = new Configuration();
conf.setString(
    org.apache.hadoop.hive.conf.HiveConf.ConfVars.METASTOREWAREHOUSE.varname,
    META_STORE_URIS);
conf.setString(IcebergConnectorConstant.DATABASE, DATABASE_NAME);
conf.setString(IcebergConnectorConstant.TABLE, TABLE_NAME);

// Append Iceberg sink to data stream
IcebergSinkAppender<Map<String, Object>> appender =
   new IcebergSinkAppender<Map<String, Object>>(conf, "test")
       .withSerializer(MapAvroSerializer.getInstance())
       .withWriterParallelism(1);
appender.append(dataStream);

// Trigger the execution
env.execute("Sink Test");