SELECT partition_nameFROM information_schema.partitionsWHERE table_name = 'my_table' AND partition_name IS NOT NULL AND (partition_description = CONCAT('{"created_date": "', DATE_FORMAT(created_date, '%Y-%m-%d'), '"}') OR partition_description = CONCAT('{"created_date": "', DATE_FORMAT(created_date - INTERVAL 1 DAY, '%Y-%m-%d'), '"}')) AND id = <your_id>;我用的不是DATE类型的列

如果你使用的不是 `DATE` 类型的列，你可以使用相应类型的函数来格式化分区描述中的值。例如，如果你使用的是 `DATETIME` 类型的列，你可以使用 `DATE_FORMAT()` 函数来格式化分区描述中的日期时间值。以下是一个示例查询：

SELECT partition_name
FROM information_schema.partitions
WHERE table_name = 'my_table'
  AND partition_name IS NOT NULL
  AND (partition_description = CONCAT('{"created_datetime": "', DATE_FORMAT(created_datetime, '%Y-%m-%d %H:%i:%s'), '"}')
       OR partition_description = CONCAT('{"created_datetime": "', DATE_FORMAT(created_datetime - INTERVAL 1 DAY, '%Y-%m-%d %H:%i:%s'), '"}'))
  AND id = <your_id>;

在上面的查询中，我假设你使用的是 `created_datetime` 列来存储日期时间值，并且使用了 `DATE_FORMAT()` 函数来格式化分区描述中的日期时间值。你需要根据实际情况进行调整。

相关问题

SELECT PARTITION_name part, PARTITION_expression expr, PARTITION_description descr, TABLE_rows FROM information_schema.PARTITIONS WHERE TABLE_schema=SCHEMA() AND TABLE_name = `借阅表`; 改正

在 SQL 语句中，如果要引用一个表名或列名，应该使用反引号（`）将其括起来。同时，SCHEMA() 函数用于返回当前数据库的名称，应该直接使用函数名即可，不需要加括号。

因此，正确的 SQL 语句应该是：

SELECT PARTITION_name AS part, PARTITION_expression AS expr, PARTITION_description AS descr, TABLE_rows
FROM information_schema.PARTITIONS
WHERE TABLE_schema = SCHEMA() AND TABLE_name = `借阅表`;

这个语句的作用是查询名为“借阅表”的表的分区信息，其中 PARTITION_name、PARTITION_expression 和 PARTITION_description 分别表示分区名称、分区表达式和分区描述，TABLE_rows 表示每个分区中的行数。注意，AS 关键字可以用于为列取别名，方便查询结果的阅读。

new_df_cols = new_df.columns old_df_cols = older_df.columns total = set(new_df_cols + old_df_cols) new_df = new_df.select(*self.fill_empty_colums(new_df_cols, total)).withColumn("row_priority",F.lit(0)) older_df = older_df.select(*self.fill_empty_colums(old_df_cols, total)).withColumn("row_priority",F.lit(1)) key_column = [F.col(column_name) for column_name in key_columns] merge_spec = Window.partitionBy(key_column).orderBy("row_priority") ranked_df=new_df.unionByName(older_df).withColumn("rank", F.rank().over(merge_spec)) return self.update_audit_created_column(ranked_df,key_column).where(F.col("rank") == 1).drop("rank", "row_priority")

这段代码用 PySpark 实现了对两个 DataFrame 进行合并和去重的操作，并添加了一些元数据信息。下面是使用 SQL 实现的代码：

-- 选取需要合并的列名
WITH new_cols AS (
  SELECT COLUMN_NAME
  FROM INFORMATION_SCHEMA.COLUMNS
  WHERE TABLE_NAME = 'new_df'
),
old_cols AS (
  SELECT COLUMN_NAME
  FROM INFORMATION_SCHEMA.COLUMNS
  WHERE TABLE_NAME = 'older_df'
),
cols AS (
  SELECT DISTINCT COLUMN_NAME
  FROM (
    SELECT COLUMN_NAME FROM new_cols
    UNION ALL
    SELECT COLUMN_NAME FROM old_cols
  )
),
-- 对 new_df 填充空缺的列，并添加 "row_priority" 列
new_df_filled AS (
  SELECT COALESCE(col1, '') AS col1, COALESCE(col2, '') AS col2, ..., COALESCE(colN, '') AS colN, 0 AS row_priority
  FROM new_df
),
new_df_selected AS (
  SELECT *, ROW_NUMBER() OVER (PARTITION BY key_column ORDER BY row_priority) AS rank
  FROM (
    -- 选取 new_df 中的列，包括填充空缺的列和 "row_priority" 列
    SELECT col1, col2, ..., colN, row_priority
    FROM new_df_filled
    -- 生成 key_column 列，用于分组
    CROSS JOIN (SELECT col1 AS key_column FROM new_df_filled) key_columns
  )
),
-- 对 older_df 填充空缺的列，并添加 "row_priority" 列
old_df_filled AS (
  SELECT COALESCE(col1, '') AS col1, COALESCE(col2, '') AS col2, ..., COALESCE(colN, '') AS colN, 1 AS row_priority
  FROM older_df
),
old_df_selected AS (
  SELECT *, ROW_NUMBER() OVER (PARTITION BY key_column ORDER BY row_priority) AS rank
  FROM (
    -- 选取 older_df 中的列，包括填充空缺的列和 "row_priority" 列
    SELECT col1, col2, ..., colN, row_priority
    FROM old_df_filled
    -- 生成 key_column 列，用于分组
    CROSS JOIN (SELECT col1 AS key_column FROM old_df_filled) key_columns
  )
),
-- 合并两个 DataFrame，并去重
merged_df AS (
  SELECT * FROM new_df_selected
  UNION ALL
  SELECT * FROM old_df_selected
),
-- 选取合并后的第一行
final_df AS (
  SELECT *, ROW_NUMBER() OVER (PARTITION BY key_column ORDER BY rank) AS row_num
  FROM merged_df
)
SELECT col1, col2, ..., colN
FROM final_df
WHERE row_num = 1

这段 SQL 代码的实现原理与 PySpark 代码相同，主要分为以下几个步骤：

1. 获取需要合并的列名。
2. 对 new_df 和 older_df 分别进行填充空缺列、添加 "row_priority" 列和选取列的操作，生成 new_df_selected 和 old_df_selected 两个数据集。
3. 将 two_df_selected 进行合并，并添加 rank 列，用于去重。
4. 选取合并后的第一行，得到最终的去重结果。