BigQuery - 相关子查询取消嵌套数组不起作用

Question

我正在尝试在 BigQuery 中加入数组元素，但收到以下错误消息：Correlated subqueries that reference other tables are not supported unless they can be de-correlated, such as by transforming them into an efficient JOIN.

假设我有两个映射表：

CREATE OR REPLACE TABLE `test.field_id_name` (
  id STRING,
  name STRING
) AS (
  SELECT * FROM UNNEST(
     [STRUCT("s1", "string1"),
     STRUCT("s2", "string2"),
     STRUCT("s3", "string3")]
  )
)

CREATE OR REPLACE TABLE `test.field_values` (
  id STRING,
  name STRING
) AS (
  SELECT * FROM UNNEST(
     [STRUCT("v1", "val1"),
     STRUCT("v2", "val2"),
     STRUCT("v3", "val3")]
  )
)

我有以下输入：

CREATE OR REPLACE TABLE `test.input` AS
  SELECT [
    STRUCT<id STRING, value ARRAY<STRING>>("s1", ["v1"]),
    STRUCT("s2", ["v1"]),
    STRUCT("s3", ["v1"])
  ] records
  UNION ALL
  SELECT [
    STRUCT("s1", ["v1", "v2"]),
    STRUCT("s2", ["v1", "v2"]),
    STRUCT("s3", ["v1", "v2"])
  ]
  UNION ALL
  SELECT [
    STRUCT("s1", ["v1", "v2", "v3"]),
    STRUCT("s2", ["v1", "v2", "v3"]),
    STRUCT("s3", ["v1", "v2", "v3"])
  ]

我正在尝试产生这个输出：

SELECT [
  STRUCT<id_mapped STRING, value_mapped ARRAY<STRING>>("string1", ["val1"]),
  STRUCT("string2", ["val1"]),
  STRUCT("string3", ["val1"])
] records
UNION ALL
SELECT [
  STRUCT("string1", ["val1", "val2"]),
  STRUCT("string2", ["val1", "val2"]),
  STRUCT("string3", ["val1", "val2"])
]
UNION ALL
SELECT [
  STRUCT("string1", ["val1", "val2", "val3"]),
  STRUCT("string2", ["val1", "val2", "val3"]),
  STRUCT("string3", ["val1", "val2", "val3"])
]

但是，以下查询因相关子查询错误而失败。

SELECT
  ARRAY(
    SELECT
      STRUCT(fin.name, ARRAY(SELECT fv.name FROM UNNEST(value) v JOIN test.field_values fv ON (v = fv.id)))
    FROM UNNEST(records) r
    JOIN test.field_id_name fin ON (fin.id = r.id)
  )
FROM test.input

Answer 1

以下是 BigQuery 标准 SQL

#standardSQL
SELECT ARRAY_AGG(STRUCT(id AS id_mapped, val AS value_mapped)) AS records
FROM (
  SELECT fin.name AS id, ARRAY_AGG(fv.name) AS val, FORMAT('%t', t) id1, FORMAT('%t', RECORD) id2
  FROM `test.input` t,
  UNNEST(records) record,
  UNNEST(value) val
  JOIN `test.field_id_name` fin ON record.id = fin.id
  JOIN `test.field_values` fv ON val = fv.id
  GROUP BY id, id1, id2
)
GROUP BY id1   

如果应用于您问题的样本数据 - 返回您期望的准确输出