使用分区投影功能并以 Apache Parquet 格式为流日志创建表

以下用于 VPC 流日志的分区投影 CREATE TABLE 语句采用 Apache Parquet 格式，不兼容 Hive，按小时和日期而不是按天分区。将示例中的表名称 test_table_vpclogs_parquet 替换为您的表名称。编辑 LOCATION 子句以指定包含 Amazon VPC 日志数据的 Amazon S3 存储桶。

CREATE EXTERNAL TABLE IF NOT EXISTS test_table_vpclogs_parquet (
  version int,
  account_id string,
  interface_id string,
  srcaddr string,
  dstaddr string,
  srcport int,
  dstport int,
  protocol bigint,
  packets bigint,
  bytes bigint,
  start bigint,
  `end` bigint,
  action string,
  log_status string,
  vpc_id string,
  subnet_id string,
  instance_id string,
  tcp_flags int,
  type string,
  pkt_srcaddr string,
  pkt_dstaddr string,
  az_id string,
  sublocation_type string,
  sublocation_id string,
  pkt_src_aws_service string,
  pkt_dst_aws_service string,
  flow_direction string,
  traffic_path int
)
PARTITIONED BY (region string, date string, hour string)
ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
STORED AS INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
LOCATION 's3://amzn-s3-demo-bucket/prefix/AWSLogs/{account_id}/vpcflowlogs/'
TBLPROPERTIES (
"EXTERNAL"="true",
"skip.header.line.count" = "1",
"projection.enabled" = "true",
"projection.region.type" = "enum",
"projection.region.values" = "us-east-1,us-west-2,ap-south-1,eu-west-1",
"projection.date.type" = "date",
"projection.date.range" = "2021/01/01,NOW",
"projection.date.format" = "yyyy/MM/dd",
"projection.hour.type" = "integer",
"projection.hour.range" = "00,23",
"projection.hour.digits" = "2",
"storage.location.template" = "s3://amzn-s3-demo-bucket/prefix/AWSLogs/${account_id}/vpcflowlogs/${region}/${date}/${hour}"
)