SELECT * FROM table1 LEFT JOIN (CASE WHEN column1 = 'value1' THEN table2 WHEN column1 = 'value2' THEN table3 ELSE table4 END) ON table1.id = table2.id OR table1.id = table3.id OR table1.id = table4.id 语法不对

你需要使用子查询来实现你的逻辑，如下所示：

SELECT *
FROM table1
LEFT JOIN (
  SELECT *
  FROM table2
  WHERE column1 = 'value1'
  UNION ALL
  SELECT *
  FROM table3
  WHERE column1 = 'value2'
  UNION ALL
  SELECT *
  FROM table4
  WHERE column1 NOT IN ('value1', 'value2')
) AS subquery
ON table1.id = subquery.id

在这个查询中，我们使用了三个子查询，每个子查询都对应一个表，并且使用 UNION ALL 将这三个表组合成一个虚拟表。然后，我们将虚拟表作为一个子查询，与 table1 进行 LEFT JOIN 操作。这样就可以根据 column1 的值来选择不同的表，并且通过 OR 连接起来，实现了你想要的逻辑。

相关问题

你能把pg视图改为sqlserver的视图吗 SELECT c.relname AS table_name, a.attname AS column_name, d.description AS column_comment, CASE WHEN a.attnotnull AND con.conname IS NULL THEN 1 ELSE 0 END AS is_required, CASE WHEN con.conname IS NOT NULL THEN 1 ELSE 0 END AS is_pk, a.attnum AS sort, CASE WHEN "position"(pg_get_expr(ad.adbin, ad.adrelid), ((c.relname::text || '_'::text) || a.attname::text) || '_seq'::text) > 0 THEN 1 ELSE 0 END AS is_increment, btrim( CASE WHEN t.typelem <> 0::oid AND t.typlen = '-1'::integer THEN 'ARRAY'::text ELSE CASE WHEN t.typtype = 'd'::"char" THEN format_type(t.typbasetype, NULL::integer) ELSE format_type(a.atttypid, NULL::integer) END END, '"'::text) AS column_type FROM pg_attribute a JOIN (pg_class c JOIN pg_namespace n ON c.relnamespace = n.oid) ON a.attrelid = c.oid LEFT JOIN pg_description d ON d.objoid = c.oid AND a.attnum = d.objsubid LEFT JOIN pg_constraint con ON con.conrelid = c.oid AND (a.attnum = ANY (con.conkey)) LEFT JOIN pg_attrdef ad ON a.attrelid = ad.adrelid AND a.attnum = ad.adnum LEFT JOIN pg_type t ON a.atttypid = t.oid WHERE (c.relkind = ANY (ARRAY['r'::"char", 'p'::"char"])) AND a.attnum > 0 AND n.nspname = 'public'::name ORDER BY c.relname, a.attnum

抱歉，我无法将此查询转换为SQL Server的视图。这是因为该查询涉及到了一些PostgreSQL特定的函数和表达式，这些在SQL Server中并不存在。你可能需要手动重新编写查询以适应SQL Server的语法和函数。以下是一个可能的SQL Server等效查询的示例，供参考：

SELECT 
    t.name AS table_name,
    c.name AS column_name,
    CAST(ep.value AS NVARCHAR(MAX)) AS column_comment,
    CASE
        WHEN c.is_nullable = 0 AND pk.constraint_column_id IS NULL THEN 1
        ELSE 0
    END AS is_required,
    CASE
        WHEN pk.constraint_column_id IS NOT NULL THEN 1
        ELSE 0
    END AS is_pk,
    c.column_id AS sort,
    CASE
        WHEN COLUMNPROPERTY(c.object_id, c.name, 'IsIdentity') = 1 THEN 1
        ELSE 0
    END AS is_increment,
    CASE
        WHEN t.name = 'varchar' AND c.max_length <> -1 THEN t.name + '(' + CAST(c.max_length AS NVARCHAR(MAX)) + ')'
        WHEN t.name = 'nvarchar' AND c.max_length <> -1 THEN t.name + '(' + CAST(c.max_length / 2 AS NVARCHAR(MAX)) + ')'
        ELSE t.name
    END AS column_type
FROM sys.tables t
INNER JOIN sys.columns c ON t.object_id = c.object_id
LEFT JOIN sys.extended_properties ep ON ep.major_id = t.object_id AND ep.minor_id = c.column_id AND ep.name = 'MS_Description'
LEFT JOIN sys.indexes i ON t.object_id = i.object_id AND i.is_primary_key = 1
LEFT JOIN sys.index_columns ic ON i.object_id = ic.object_id AND i.index_id = ic.index_id AND c.column_id = ic.column_id
LEFT JOIN sys.key_constraints pk ON t.object_id = pk.parent_object_id AND ic.index_column_id = pk.unique_index_id
WHERE t.type = 'U'
AND SCHEMA_NAME(t.schema_id) = 'dbo'
ORDER BY t.name, c.column_id

请注意，这只是一个示例查询，具体取决于你的数据库结构和需求，你可能需要进行一些调整和修改。建议在转换之前备份你的数据库，以防出现意外情况。

sql join中能否使用case when_SQL---多表查询

是的，可以在 SQL JOIN 中使用 CASE WHEN 语句。可以在 JOIN 语句中使用 CASE WHEN 语句来根据一些条件连接不同的表或筛选不同的行。以下是一个使用 CASE WHEN 语句的多表查询的示例：

SELECT
  t1.column1,
  t2.column2,
  CASE WHEN t1.column1 = 'some_value' THEN t3.column3 ELSE t4.column4 END AS new_column
FROM table1 t1
JOIN table2 t2 ON t1.id = t2.id
LEFT JOIN table3 t3 ON t1.id = t3.id
RIGHT JOIN table4 t4 ON t2.id = t4.id

在上面的示例中，我们使用了 CASE WHEN 语句来根据条件选择要连接的表，以及选择要显示的值。需要注意的是，CASE WHEN 语句必须放在 SELECT 子句中，并且必须分配一个别名。