我正在阅读 Snowflake 的文档，但还没有找到解决方案，所以我来找你。我在 Snowflake 中有一个表，其中包含一个用于存储 JSON 数据的变体列。您知道一种将变体列上的查询结果动态转换为表格格式的方法吗？
例如我有一个像
这样的查询select json_data from database.schema.table limit 2
哪个会返回类似
| JSON_DATA |
|---|
| {"EventName": "Test", "EventValue": 100} |
| {"EventName": "Test", "EventValue": 200} |
有没有办法将它作为表返回而不必引用键？我知道我能做到
select
json_data['EventName'] EventName,
json_data['EventValue'] EventValue
from
database.schema.table
但我正在寻找更动态的东西
select * from table(json_to_table(select json_data from database.schema.table)) limit 2
那可能会回来
| 事件名称 | 事件值 |
|---|---|
| 测试 | 100 |
| 测试 | 200 |
我正在寻找任何内部解决方案（例如我可能遗漏的存储过程、udf、雪花函数......除了外部函数之外的任何东西）
答案 0 :(得分：1)
虽然目前无法创建动态列列表，但如注释中所述，您可以运行存储过程来构建（和重建）视图。这将避免必须手动输入和维护一长列列。
在底部创建 SP 后，您可以像这样使用它：
create or replace table MY_TABLE(JSON_DATA variant);
insert into MY_TABLE select parse_json('{"EventName": "Test", "EventValue": 100}');
insert into MY_TABLE select parse_json('{"EventName": "Test", "EventValue": 200}');
call create_view_over_json('MY_TABLE', 'JSON_DATA', 'MY_VIEW');
select * from MY_VIEW;
这是创建视图的存储过程。请注意，如果表非常大，则需要使用 Snowflake 的 TYPEOF() 函数一段时间才能确定列类型。如果已知它是一致的，您可以将其指向示例表或创建的限制为 1000 的表。
create or replace procedure create_view_over_json (TABLE_NAME varchar, COL_NAME varchar, VIEW_NAME varchar)
returns varchar
language javascript
as
$$
/****************************************************************************************************************
* *
* CREATE_VIEW_OVER_JSON - Craig Warman, Alan Eldridge and Greg Pavlik Snowflake Computing, 2019, 2020, 2021 *
* *
* This stored procedure creates a view on a table that contains JSON data in a column. *
* of type VARIANT. It can be used for easily generating views that enable access to *
* this data for BI tools without the need for manual view creation based on the underlying *
* JSON document structure. *
* *
* Parameters: *
* TABLE_NAME - Name of table that contains the semi-structured data. *
* COL_NAME - Name of VARIANT column in the aforementioned table. *
* VIEW_NAME - Name of view to be created by this stored procedure. *
* *
* Usage Example: *
* call create_view_over_json('db.schema.semistruct_data', 'variant_col', 'db.schema.semistruct_data_vw'); *
* *
* Important notes: *
* - This is the "basic" version of a more sophisticated procedure. Its primary purpose *
* is to illustrate the view generation concept. *
* - This version of the procedure does not support: *
* - Column case preservation (all view column names will be case-insensitive). *
* - JSON document attributes that are SQL reserved words (like TYPE or NUMBER). *
* - "Exploding" arrays into separate view columns - instead, arrays are simply *
* materialized as view columns of type ARRAY. *
* - Execution of this procedure may take an extended period of time for very *
* large datasets, or for datasets with a wide variety of document attributes *
* (since the view will have a large number of columns). *
* *
* Attribution: *
* I leveraged code developed by Alan Eldridge as the basis for this stored procedure. *
* *
****************************************************************************************************************/
var currentActivity;
try{
currentActivity = "building the query for column types";
var elementQuery = GetElementQuery(TABLE_NAME, COL_NAME);
currentActivity = "running the query to get column names";
var elementRS = GetResultSet(elementQuery);
currentActivity = "building the column list";
var colList = GetColumnList(elementRS);
currentActivity = "building the view's DDL";
var viewDDL = GetViewDDL(VIEW_NAME, colList, TABLE_NAME);
currentActivity = "creating the view";
return ExecuteSingleValueQuery("status", viewDDL);
}
catch(err){
return "ERROR: Encountered an error while " + currentActivity + ".\n" + err.message;
}
/****************************************************************************************************************
* *
* End of main function. Helper functions below. *
* *
****************************************************************************************************************/
function GetElementQuery(tableName, columnName){
// Build a query that returns a list of elements which will be used to build the column list for the CREATE VIEW statement
sql =
`
SELECT DISTINCT regexp_replace(regexp_replace(f.path,'\\\\[(.+)\\\\]'),'(\\\\w+)','\"\\\\1\"') AS path_name, -- This generates paths with levels enclosed by double quotes (ex: "path"."to"."element"). It also strips any bracket-enclosed array element references (like "[0]")
DECODE (substr(typeof(f.value),1,1),'A','ARRAY','B','BOOLEAN','I','FLOAT','D','FLOAT','STRING') AS attribute_type, -- This generates column datatypes of ARRAY, BOOLEAN, FLOAT, and STRING only
REGEXP_REPLACE(REGEXP_REPLACE(f.path, '\\\\[(.+)\\\\]'),'[^a-zA-Z0-9]','_') AS alias_name -- This generates column aliases based on the path
FROM
@~TABLE_NAME~@,
LATERAL FLATTEN(@~COL_NAME~@, RECURSIVE=>true) f
WHERE TYPEOF(f.value) != 'OBJECT'
AND NOT contains(f.path, '['); -- This prevents traversal down into arrays
`;
sql = sql.replace(/@~TABLE_NAME~@/g, tableName);
sql = sql.replace(/@~COL_NAME~@/g, columnName);
return sql;
}
function GetColumnList(elementRS){
/*
Add elements and datatypes to the column list
They will look something like this when added:
col_name:"name"."first"::STRING as name_first,
col_name:"name"."last"::STRING as name_last
*/
var col_list = "";
while (elementRS.next()) {
if (col_list != "") {
col_list += ", \n";
}
col_list += COL_NAME + ":" + elementRS.getColumnValue("PATH_NAME"); // Start with the element path name
col_list += "::" + elementRS.getColumnValue("ATTRIBUTE_TYPE"); // Add the datatype
col_list += " as " + elementRS.getColumnValue("ALIAS_NAME"); // And finally the element alias
}
return col_list;
}
function GetViewDDL(viewName, columnList, tableName){
sql =
`
create or replace view @~VIEW_NAME~@ as
select
@~COLUMN_LIST~@
from @~TABLE_NAME~@;
`;
sql = sql.replace(/@~VIEW_NAME~@/g, viewName);
sql = sql.replace(/@~COLUMN_LIST~@/g, columnList);
sql = sql.replace(/@~TABLE_NAME~@/g, tableName);
return sql;
}
/****************************************************************************************************************
* *
* Library functions *
* *
****************************************************************************************************************/
function ExecuteSingleValueQuery(columnName, queryString) {
var out;
cmd1 = {sqlText: queryString};
stmt = snowflake.createStatement(cmd1);
var rs;
try{
rs = stmt.execute();
rs.next();
return rs.getColumnValue(columnName);
}
catch(err) {
throw err;
}
return out;
}
function GetResultSet(sql){
try{
cmd1 = {sqlText: sql};
stmt = snowflake.createStatement(cmd1);
var rs;
rs = stmt.execute();
return rs;
}
catch(err) {
throw err;
}
}
$$;