根据来自另一个 table 的数据在 FOR 循环中执行 Snowflake SQL 查询

Question

在 Snowflake 中，我正在尝试创建一个带有 for 循环的 SQL 脚本，该脚本根据 data_type 列

将结果输出到新的 table ]

我有一个名为 PROFILE_TABLE_LIST 的 table，其中的列带有 table名称和列名，以及数据类型如下所示：

TABLENAME	COLUMN_NAME	DATA_TYPE
Table1	PLANTS	TEXT
Table1	HEIGHT	FLOAT
Table2	COLOR	TEXT
Table2	SMELL	TEXT

我目前正在尝试使用游标执行 for 循环并对每一行执行查询以根据列类型分析 table 看起来像这样：

TABLENAME	COLUMN_NAME	DATA_TYPE	COUNT	MAX_LENGTH	MAX_VALUE
Table1	PLANTS	TEXT	10	82	NULL
Table1	HEIGHT	FLOAT	10	NULL	58.6
Table2	COLOR	TEXT	20	56	NULL
Table2	SMELL	TEXT	20	23	NULL

最终，我想运行不同的 select 语句以 data_type 为条件，但在这个阶段，我只关注计数。这是我的当前循环。但是，select 语句未正确执行，因为 table 名称作为字符串传递，如果我使用 TABLE(tablename) 我会收到语法错误（我在下面注释掉了该行：

declare
    tablename string;
    column_name string;
    row_count integer;
    table_schema string;
    table_catalog string;
    name string;
    
    tmp_array ARRAY default ARRAY_CONSTRUCT();

    res resultset default (select * from PROFILE_TABLE_LIST);
    c1 cursor for res;
    rs_output RESULTSET;
begin

  for record in c1 do
    tablename := record.TABLENAME;
    column_name := record.column_name;
    table_schema := record.table_schema;
    table_catalog := record.table_catalog;
   
   
    
    tmp_array := array_append(:tmp_array, OBJECT_CONSTRUCT('tmp_tables', record.TABLENAME, 'COUNT', (SELECT COUNT(column_name) FROM tablename)));
    -- tmp_array := array_append(:tmp_array, OBJECT_CONSTRUCT('tmp_tables', record.TABLENAME, 'COUNT', (SELECT COUNT(column_name) FROM TABLE(tablename))));
 
     
    
  end for;

  rs_output := (select value:tmp_tables, value:COUNT from table(flatten(:tmp_array)));
  return table(rs_output);
end;

Answer 1

我会在最后构建一个 SQL 和运行的块。

使用简单的 SELECT 作为模式来显示构建过程的初始化，您可以编写自己的动态 sql 来自：

WITH table_list as (
    SELECT * FROM VALUES
    ('Table1', 'PLANTS', 'TEXT'),
    ('Table1', 'HEIGHT', 'FLOAT'),
    ('Table2', 'COLOR', 'TEXT'),
    ('Table2', 'SMELL', 'TEXT')
    v(tablename, column_name, data_type)
), to_rows as (
    SELECT
        tablename
        ,CASE data_type
            WHEN 'TEXT' THEN 'SELECT ''tablename'' as TABLENAME, ''column_name'' as COLUMN_NAME, ''data_type'' as DATA_TYPE, count(column_name) as count, MAX(LEN(column_name)) as max_length, null as max_value FROM tablename '
            WHEN 'FLOAT' THEN 'SELECT ''tablename'' as TABLENAME, ''column_name'' as COLUMN_NAME, ''data_type'' as DATA_TYPE, count(column_name) as count, null as max_length, MAX(column_name) as max_value FROM tablename '
        END as sql
        ,REPLACE(REPLACE(REPLACE(sql, 'data_type', data_type), 'column_name', column_name), 'tablename', tablename) as final_sql
    FROM table_list
)
SELECT
    listagg (final_sql, ' UNION ALL ') within group(order by tablename) as the_big_sql
FROM to_rows;

给出：

THE_BIG_SQL

SELECT 'Table1' as TABLENAME, 'PLANTS' as COLUMN_NAME, 'TEXT' as DATA_TYPE, count(PLANTS) as count, MAX(LEN(PLANTS)) as max_length, null as max_value FROM Table1 UNION ALL SELECT 'Table1' as TABLENAME, 'HEIGHT' as COLUMN_NAME, 'FLOAT' as DATA_TYPE, count(HEIGHT) as count, null as max_length, MAX(HEIGHT) as max_value FROM Table1 UNION ALL SELECT 'Table2' as TABLENAME, 'COLOR' as COLUMN_NAME, 'TEXT' as DATA_TYPE, count(COLOR) as count, MAX(LEN(COLOR)) as max_length, null as max_value FROM Table2 UNION ALL SELECT 'Table2' as TABLENAME, 'SMELL' as COLUMN_NAME, 'TEXT' as DATA_TYPE, count(SMELL) as count, MAX(LEN(SMELL)) as max_length, null as max_value FROM Table2

如果运行针对这些表：

create table table1(plants text, height float);
create table table2(color text, smell text);

insert into table1 values ('big plant', 10.1),('medium plant', 5.3),('tiny', 1.0);
insert into table2 values ('red', 'bold'), ('blue', 'weak');

给出：

TABLENAME	COLUMN_NAME	DATA_TYPE	COUNT	MAX_LENGTH	MAX_VALUE
Table1	PLANTS	TEXT	3	12
Table1	HEIGHT	FLOAT	3		10.1
Table2	COLOR	TEXT	2	4
Table2	SMELL	TEXT	2	4

但这里是为您完整编写的动态答案：

首先制作 TABLE 待完成的工作：

CREATE TABLE PROFILE_TABLE_LIST AS 
SELECT * FROM VALUES
    ('Table1', 'PLANTS', 'TEXT'),
    ('Table1', 'HEIGHT', 'FLOAT'),
    ('Table2', 'COLOR', 'TEXT'),
    ('Table2', 'SMELL', 'TEXT')
    v(tablename, column_name, data_type);

并使用之前创建的“真实数据表”我们可以使用：

declare
    sql string;
    final_sql string;
    c1 cursor for (select * from PROFILE_TABLE_LIST);
    res resultset;
begin
  final_sql := '';
  
  for record in c1 do
    if(record.data_type = 'TEXT') THEN
        sql := 'SELECT '''||record.tablename||''' as TABLENAME, '''||record.column_name||''' as COLUMN_NAME, '''||record.data_type||''' as DATA_TYPE, count('||record.column_name||') as count, MAX(LEN('||record.column_name||')) as max_length, null as max_value FROM '||record.tablename||' ';
    else
        sql := 'SELECT '''||record.tablename||''' as TABLENAME, '''||record.column_name||''' as COLUMN_NAME, ''data_type'' as DATA_TYPE, count('||record.column_name||') as count, null as max_length, MAX('||record.column_name||') as max_value FROM '||record.tablename||' ';
    end if;
    if(final_sql<>'')then 
        final_sql := final_sql || ' UNION ALL ';
    end if;
    final_sql := final_sql || sql;
        
  end for;

  res := (execute immediate :final_sql);
  return table(res);
end;

给出：

TABLENAME	COLUMN_NAME	DATA_TYPE	COUNT	MAX_LENGTH	MAX_VALUE
Table1	PLANTS	TEXT	3	12
Table1	HEIGHT	data_type	3		10.1
Table2	COLOR	TEXT	2	4
Table2	SMELL	TEXT	2	4

根据来自另一个 table 的数据在 FOR 循环中执行 Snowflake SQL 查询

Perform Snowflake SQL queries in FOR LOOP based on data from another table

sql

for-loop

snowflake-cloud-data-platform