我有一个较大的查询，其中包含几个通过WITH子句构造的窗口函数。 该查询对使用Pandas SQL连接器或任何SQL浏览器从Python脚本执行的amazon-rds和amazon-redshift数据库运行得很好。 但是，如果我通过Spark（来自Pyspark）jdbs连接器运行此查询，它将失败。 而且我找不到任何提示，为什么Spark不吃这个查询。 任何提示欢迎。 谢谢 亚历克斯
我尝试了sql fron Pandas和几个SQL Browser->效果很好 我在没有WITH子句语法的情况下尝试了带有其他SQL语句的spark SQL连接器->效果很好
下面是简化的代码示例：
mysql_test="""
WITH my_raw_table AS
(
SELECT
created_utc || '@' || sub_order_nr AS order_column,
operation_type,
id_in,
id_type_in,
created_utc
FROM sample.table
)
SELECT DISTINCT
operation_type
,ROW_NUMBER() OVER window_desc AS row_number
,FIRST_VALUE(created_utc) OVER window_desc AS created_utc_first
,FIRST_VALUE(created_utc) OVER window_desc AS created_utc_last
,FIRST_VALUE(order_column) OVER window_desc AS order_column_first
,FIRST_VALUE(order_column) OVER window_desc AS order_column_last
FROM my_raw_table
WINDOW
window_desc AS (
PARTITION BY operation_type,id_type_in,id_in
ORDER BY order_column DESC
),
window_asc AS (
PARTITION BY operation_type,id_type_in,id_in
ORDER BY order_column ASC
)
ORDER BY
operation_type
,order_column_last
"""
conn=my_modul.get_my_connection()
my_result = pd.read_sql(mysql_test,conn)
conn.close()
my_result.head()
conn=my_modul.get_my_connection()
my_result = spark.read.jdbc(url=conn['url'], table=mysql_test, properties= conn['properties'])
my_result.show()
主要问题是它声称WITH为语法错误
Py4JJavaError: An error occurred while calling o551.jdbc.
: org.postgresql.util.PSQLException: ERROR: syntax error at or near "WITH"
我不明白为什么。
完整的错误消息是：
---------------------------------------------------------------------------
Py4JJavaError Traceback (most recent call last)
<ipython-input-40-353e32a024e8> in <module>
11
12
---> 13 verbauwege_spark_sql = spark.read.jdbc(url=conn['url'], table=mysql_test, properties= conn['properties'])
14
15 row_count=verbauwege_spark_sql.count()
~/anaconda3/envs/Spark_Python3/lib/python3.7/site-packages/pyspark/sql/readwriter.py in jdbc(self, url, table, column, lowerBound, upperBound, numPartitions, predicates, properties)
554 jpredicates = utils.toJArray(gateway, gateway.jvm.java.lang.String, predicates)
555 return self._df(self._jreader.jdbc(url, table, jpredicates, jprop))
--> 556 return self._df(self._jreader.jdbc(url, table, jprop))
557
558
~/anaconda3/envs/Spark_Python3/lib/python3.7/site-packages/py4j/java_gateway.py in __call__(self, *args)
1255 answer = self.gateway_client.send_command(command)
1256 return_value = get_return_value(
-> 1257 answer, self.gateway_client, self.target_id, self.name)
1258
1259 for temp_arg in temp_args:
~/anaconda3/envs/Spark_Python3/lib/python3.7/site-packages/pyspark/sql/utils.py in deco(*a, **kw)
61 def deco(*a, **kw):
62 try:
---> 63 return f(*a, **kw)
64 except py4j.protocol.Py4JJavaError as e:
65 s = e.java_exception.toString()
~/anaconda3/envs/Spark_Python3/lib/python3.7/site-packages/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
326 raise Py4JJavaError(
327 "An error occurred while calling {0}{1}{2}.\n".
--> 328 format(target_id, ".", name), value)
329 else:
330 raise Py4JError(
Py4JJavaError: An error occurred while calling o551.jdbc.
: org.postgresql.util.PSQLException: ERROR: syntax error at or near "WITH"
Position: 15
at org.postgresql.core.v3.QueryExecutorImpl.receiveErrorResponse(QueryExecutorImpl.java:2468)
at org.postgresql.core.v3.QueryExecutorImpl.processResults(QueryExecutorImpl.java:2211)
at org.postgresql.core.v3.QueryExecutorImpl.execute(QueryExecutorImpl.java:309)
at org.postgresql.jdbc.PgStatement.executeInternal(PgStatement.java:446)
at org.postgresql.jdbc.PgStatement.execute(PgStatement.java:370)
at org.postgresql.jdbc.PgPreparedStatement.executeWithFlags(PgPreparedStatement.java:149)
at org.postgresql.jdbc.PgPreparedStatement.executeQuery(PgPreparedStatement.java:108)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRDD$.resolveTable(JDBCRDD.scala:61)
at org.apache.spark.sql.execution.datasources.jdbc.JDBCRelation$.getSchema(JDBCRelation.scala:210)
at org.apache.spark.sql.execution.datasources.jdbc.JdbcRelationProvider.createRelation(JdbcRelationProvider.scala:35)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:318)
at org.apache.spark.sql.DataFrameReader.loadV1Source(DataFrameReader.scala:223)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:211)
at org.apache.spark.sql.DataFrameReader.load(DataFrameReader.scala:167)
at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:238)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:483)
at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244)
at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357)
at py4j.Gateway.invoke(Gateway.java:282)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:745)
答案 0 :(得分：0)
解决方案是将完整的sql括在大括号中，并为其提供别名，以便spark jdbc可以处理它。
mysql_test="""
(
WITH my_raw_table AS
(
SELECT
created_utc || '@' || sub_order_nr AS order_column,
operation_type,
id_in,
id_type_in,
created_utc
FROM sample.table
)
SELECT DISTINCT
operation_type
,ROW_NUMBER() OVER window_desc AS row_number
,FIRST_VALUE(created_utc) OVER window_desc AS created_utc_first
,FIRST_VALUE(created_utc) OVER window_desc AS created_utc_last
,FIRST_VALUE(order_column) OVER window_desc AS order_column_first
,FIRST_VALUE(order_column) OVER window_desc AS order_column_last
FROM my_raw_table
WINDOW
window_desc AS (
PARTITION BY operation_type,id_type_in,id_in
ORDER BY order_column DESC
),
window_asc AS (
PARTITION BY operation_type,id_type_in,id_in
ORDER BY order_column ASC
)
ORDER BY
operation_type
,order_column_last
) as my_redshift_result
"""