BigQuery如何获取JSON结构中的值之和?

下面是一个使用 REGEXP_EXTRACT_ALL :

WITH T AS (
  SELECT '{"Weights":{"blue":1.0,"purple":0.0,"yellow":1.0,"green":1.0}}' AS json
)
SELECT
  (
    SELECT SUM(CAST(val AS FLOAT64))
    FROM UNNEST(
      REGEXP_EXTRACT_ALL(
        JSON_EXTRACT(json, '$.Weights'),
        r':([^,}]+)')
    ) AS val
  )
FROM T;

为了探索其他选择-

下面是BigQuery标准SQL

第一个示例是为每行提取键:值对

#standardSQL
WITH `project.dataset.yourTbale` AS (
  SELECT 1 AS id, '{"Weights":{"blue":1.0,"purple":0.0,"yellow":1.0,"green":1.0}}' AS json 
  UNION ALL SELECT 2, '{"Weights":{"blue":1.0,"red":2.0,"yellow":1.0,"orange":3.0}}'
)
SELECT id,
  REPLACE(SPLIT(pair, ':')[OFFSET (0)], '"', '') color, 
  SAFE_CAST(SPLIT(pair, ':')[OFFSET (1)] AS FLOAT64) value
FROM `project.dataset.yourTbale`, 
UNNEST(SPLIT(REGEXP_REPLACE(JSON_EXTRACT(json, '$.Weights'), r'{|}', ''))) pair

这将给出以下结果

id  color   value    
1   blue    1.0  
1   purple  0.0  
1   yellow  1.0  
1   green   1.0  
2   blue    1.0  
2   red     2.0  
2   yellow  1.0  
2   orange  3.0  

现在很容易把上面的问题推广到 if there is a way to sum up all the values of the colors 甚至可以通过对特定颜色的潜在过滤来扩展它-参见下面的示例

#standardSQL
WITH `project.dataset.yourTbale` AS (
  SELECT 1 AS id, '{"Weights":{"blue":1.0,"purple":0.0,"yellow":1.0,"green":1.0}}' AS json 
  UNION ALL SELECT 2, '{"Weights":{"blue":1.0,"red":2.0,"yellow":1.0,"orange":3.0}}'
)
SELECT id,
  SUM(SAFE_CAST(SPLIT(pair, ':')[OFFSET (1)] AS FLOAT64)) AS total
FROM `project.dataset.yourTbale`, 
UNNEST(SPLIT(REGEXP_REPLACE(JSON_EXTRACT(json, '$.Weights'), r'{|}', ''))) pair
WHERE REPLACE(SPLIT(pair, ':')[OFFSET (0)], '"', '') != 'blue'
GROUP BY id

结果如下(不包括计算中的颜色=蓝色)

id  total    
1   2.0  
2   6.0