如何更改存储在 Postgres 中的 jsonb 数据的结构

Question

我在 Postgres 中有 jsonb 数据，如下所示：-

{"DestinationLists": [{"name": "TV3/TVNZ/CHOICE", "destinations": [183, 165]}]}

我正在尝试编写脚本/查询以将 Postgres 中此 json 的结构更改为：-

{
  "DestinationLists": [
    {"name": "TV3/TVNZ/CHOICE", "destinations": [{"Id":183}{"Id":165}]}
   ]
}

有可能吗？我如何做到这一点？

编辑：我正在尝试使用新结构更新表中存在的每一行数据

这就是表格的样子：-

Id  JsonValue
1   {"DestinationLists": [{"name": "TV3/TVNZ/CHOICE", "destinations": [183, 165]}]}

Answer 1

您可以使用 postgresql 中的一些 json functions 来实现这一点。

在下面使用 db-fiddle 的示例中，我包含了一些额外的测试数据。

架构 (PostgreSQL v13)

CREATE TABLE my_table (
  "dest" json
);

INSERT INTO my_table
  ("dest")
VALUES
  ('{"DestinationLists": [{"name": "TV3/TVNZ/CHOICE", "destinations": [183, 165]}]}'),
  ('{"DestinationLists": [{"name": "SecondTest", "destinations": [103, 105]},{"name": "ThirdTest", "destinations": [3, 5]}]}');

---

查询 #1

WITH expanded_data AS (
    SELECT
        dest::text, 
        json_build_object(
            'name',
             dl->>'name',
             'destinations',
             json_agg(
               json_build_object('Id',dld::text::int)
             )
        ) as dest_list_item
    FROM
        my_table, 
        json_array_elements(dest->'DestinationLists') dl,
        json_array_elements(dl->'destinations') dld
    GROUP BY
        dest::text,dl->>'name'
)
SELECT
    json_build_object(
        'DestinationLists',
        json_agg(dest_list_item)
    ) as new_dest
FROM
    expanded_data
GROUP BY
    dest::text;

new_dest
{"DestinationLists":[{"name":"ThirdTest","destinations":[{"Id":3},{"Id":5}]},{"name":"SecondTest","destinations":[{"Id":103},{"Id":105}]}]}
{"DestinationLists":[{"name":"TV3/TVNZ/CHOICE","destinations":[{"Id":183},{"Id":165}]}]}

---

View on DB Fiddle

编辑 1

为响应您的编辑，下面的代码可用作语句的更新。注意。 CTE 也可以重写为子查询。请看下面的例子：

架构 (PostgreSQL v13)

CREATE TABLE my_table (
  id bigserial,
  "dest" jsonb
);

INSERT INTO my_table
  ("dest")
VALUES
  ('{"DestinationLists": [{"name": "TV3/TVNZ/CHOICE", "destinations": [183, 165]}]}'),
  ('{"DestinationLists": [{"name": "SecondTest", "destinations": [103, 105]},{"name": "ThirdTest", "destinations": [3, 5]}]}');

---

WITH expanded_data AS (
    SELECT
        id, 
        json_build_object(
            'name',
             dl->>'name',
             'destinations',
             json_agg(
               json_build_object('Id',dld::text::int)
             )
        ) as dest_list_item
    FROM
        my_table, 
        jsonb_array_elements(dest->'DestinationLists') dl,
        jsonb_array_elements(dl->'destinations') dld
    GROUP BY
        id,dl->>'name'
), 
new_json AS (
    SELECT
        id,
        json_build_object(
            'DestinationLists',
            json_agg(dest_list_item)
        ) as new_dest
    FROM
        expanded_data
    GROUP BY
        id
)
UPDATE my_table
SET dest = new_json.new_dest
FROM new_json
WHERE my_table.id = new_json.id;

之后

SELECT * FROM my_table;

id	dest
1	{"DestinationLists":[{"name":"TV3/TVNZ/CHOICE","destinations":[{"Id":183},{"Id":165}]}]}
2	{"DestinationLists":[{"name":"SecondTest","destinations":[{"Id":103},{"Id":105}]},{"name":"ThirdTest","destinations":[{"Id":3},{"Id":5}]}]}

---

View on DB Fiddle

编辑 2

此编辑响应某些目的地可能没有目的地并且因此可能不会更新的边缘情况。

为了进行测试，添加了两条额外的记录，示例记录提供了两个命名的目的地列表，但只有一个有目的地，另一个有一个命名的目的地列表但没有目的地。

更新确保如果没有更改，即存在没有目的地的命名目的地列表，这些目的地保持不变。它通过检查命名目标列表项的数量是否与空目标列表项的数量相同来确保这一点。由于所有内容都是空的，因此它会从更新中过滤掉这条记录，并减少数据库所需的更新次数。这方面的一个例子是记录号4

修改了初始查询以适应这些空列表，因为它们正在使用之前的方法进行过滤。

架构 (PostgreSQL v13)

CREATE TABLE my_table (
  id bigserial,
  "dest" jsonb
);

INSERT INTO my_table
  ("dest")
VALUES
  ('{"DestinationLists": [{"name": "TV3/TVNZ/CHOICE", "destinations": [183, 165]}]}'),
  ('{"DestinationLists": [{"name": "SecondTest", "destinations": [103, 105]},{"name": "ThirdTest", "destinations": [3, 5]}]}'),
  ('{"DestinationLists": [{"name": "TVNZ, Mediaworks, Choice", "destinations": []}, {"name": "TVNZ, Discovery", "destinations": [165, 183, 4155]}]}'),
  ('{"DestinationLists": [{"name": "Fourth Test", "destinations": []}]}');

---

查询 #1

SELECT '------ BEFORE -----';

?column?
------ BEFORE -----

---

查询 #2

SELECT * FROM my_table;

id	dest
1	{"DestinationLists":[{"name":"TV3/TVNZ/CHOICE","destinations":[183,165]}]}
2	{"DestinationLists":[{"name":"SecondTest","destinations":[103,105]},{"name":"ThirdTest","destinations":[3,5]}]}
3	{"DestinationLists":[{"name":"TVNZ, Mediaworks, Choice","destinations":[]},{"name":"TVNZ, Discovery","destinations":[165,183,4155]}]}
4	{"DestinationLists":[{"name":"Fourth Test","destinations":[]}]}

---

查询 #3

WITH expanded_data AS (
    SELECT
        id, 
        CASE
            WHEN COUNT(dld)=0 THEN 1
            ELSE 0
        END as name_has_empty_list_item,
        json_build_object(
            'name',
             dl->>'name',
             'destinations',
              CASE 
                  WHEN 
                       COUNT(dld)=0 
                  THEN 
                       to_json(array[]::json[])
                  ELSE
                       json_agg(
                           json_build_object('Id',dld::text::int )
                       )
              END
        ) as dest_list_item
    FROM
        my_table, 
        jsonb_array_elements(dest->'DestinationLists') dl
    LEFT JOIN
        jsonb_array_elements(dl->'destinations') dld ON 1=1
    GROUP BY
        id,dl->>'name'
), 
new_json AS (
    SELECT
        id,
        COUNT(dest_list_item) as no_list_item,
        SUM(name_has_empty_list_item) as no_empty_list_item,
        json_build_object(
            'DestinationLists',
            json_agg(dest_list_item)
        ) as new_dest
    FROM
        expanded_data
    GROUP BY
        id
    HAVING
        SUM(name_has_empty_list_item) <> COUNT(dest_list_item)
    
)
SELECT * FROM new_json;

id	no_list_item	no_empty_list_item	new_dest
1	1	0	{"DestinationLists":[{"name":"TV3/TVNZ/CHOICE","destinations":[{"Id":183},{"Id":165}]}]}
2	2	0	{"DestinationLists":[{"name":"SecondTest","destinations":[{"Id":103},{"Id":105}]},{"name":"ThirdTest","destinations":[{"Id":3},{"Id":5}]}]}
3	2	1	{"DestinationLists":[{"name":"TVNZ, Discovery","destinations":[{"Id":165},{"Id":183},{"Id":4155}]},{"name":"TVNZ, Mediaworks, Choice","destinations":[]}]}

---

查询 #4

WITH expanded_data AS (
    SELECT
        id, 
        CASE
            WHEN COUNT(dld)=0 THEN 1
            ELSE 0
        END as name_has_empty_list_item,
        json_build_object(
            'name',
             dl->>'name',
             'destinations',
              CASE 
                  WHEN 
                       COUNT(dld)=0 
                  THEN 
                       to_json(array[]::json[])
                  ELSE
                       json_agg(
                           json_build_object('Id',dld::text::int )
                       )
              END
        ) as dest_list_item
    FROM
        my_table, 
        jsonb_array_elements(dest->'DestinationLists') dl
    LEFT JOIN
        jsonb_array_elements(dl->'destinations') dld ON 1=1
    GROUP BY
        id,dl->>'name'
), 
new_json AS (
    SELECT
        id,
        json_build_object(
            'DestinationLists',
            json_agg(dest_list_item)
        ) as new_dest
    FROM
        expanded_data
    GROUP BY
        id
    HAVING
        SUM(name_has_empty_list_item) <> COUNT(dest_list_item)
)
UPDATE my_table
SET dest = new_json.new_dest
FROM new_json
WHERE my_table.id = new_json.id;

没有要显示的结果。

---

查询 #5

SELECT '------ AFTER -----';

?column?
------ AFTER -----

---

查询 #6

SELECT * FROM my_table;

id	dest
4	{"DestinationLists":[{"name":"Fourth Test","destinations":[]}]}
1	{"DestinationLists":[{"name":"TV3/TVNZ/CHOICE","destinations":[{"Id":183},{"Id":165}]}]}
2	{"DestinationLists":[{"name":"SecondTest","destinations":[{"Id":103},{"Id":105}]},{"name":"ThirdTest","destinations":[{"Id":3},{"Id":5}]}]}
3	{"DestinationLists":[{"name":"TVNZ, Discovery","destinations":[{"Id":165},{"Id":183},{"Id":4155}]},{"name":"TVNZ, Mediaworks, Choice","destinations":[]}]}

---

View on DB Fiddle

让我知道这是否适合你。