huaxingao commented on a change in pull request #29939:
URL: https://github.com/apache/spark/pull/29939#discussion_r500021925
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/DataFrameReader.scala
##########
@@ -333,9 +333,26 @@ class DataFrameReader private[sql](sparkSession:
SparkSession) extends Logging {
assertNoSpecifiedSchema("jdbc")
// properties should override settings in extraOptions.
this.extraOptions ++= properties.asScala
- // explicit url and dbtable should override all
- this.extraOptions ++= Seq(JDBCOptions.JDBC_URL -> url,
JDBCOptions.JDBC_TABLE_NAME -> table)
- format("jdbc").load()
+ // explicit url should override all
+ this.extraOptions ++= Seq(JDBCOptions.JDBC_URL -> url)
+
+ import sparkSession.sessionState.analyzer.NonSessionCatalogAndIdentifier
+
+ this.source = "jdbc"
+ if (table.contains(" ")) { // if table is not a table name, e.g. a SELECT
statement
Review comment:
`JDBCWriteSuite.test("SPARK-10849: create table using user specified
column type and verify on target table")` will fail.
```
val query =
"""
|(SELECT column_name, type_name, character_maximum_length
| FROM information_schema.columns WHERE table_name =
'DBCOLTYPETEST')
""".stripMargin
val rows = spark.read.jdbc(url1, query, properties).collect()
```
Error message:
```
extraneous input '(' expecting {'ADD', 'AFTER', 'ALL', 'ALTER', 'ANALYZE',
'AND', 'ANTI', 'ANY', 'ARCHIVE', 'ARRAY', 'AS', 'ASC', 'AT', 'AUTHORIZATION',
'BETWEEN', 'BOTH', 'BUCKET', 'BUCKETS', 'BY', 'CACHE', 'CASCADE', 'CASE',
'CAST', 'CHANGE', 'CHECK', 'CLEAR', 'CLUSTER', 'CLUSTERED', 'CODEGEN',
'COLLATE', 'COLLECTION', 'COLUMN', 'COLUMNS', 'COMMENT', 'COMMIT', 'COMPACT',
'COMPACTIONS', 'COMPUTE', 'CONCATENATE', 'CONSTRAINT', 'COST', 'CREATE',
'CROSS', 'CUBE', 'CURRENT', 'CURRENT_DATE', 'CURRENT_TIME',
'CURRENT_TIMESTAMP', 'CURRENT_USER', 'DATA', 'DATABASE', DATABASES,
'DBPROPERTIES', 'DEFINED', 'DELETE', 'DELIMITED', 'DESC', 'DESCRIBE', 'DFS',
'DIRECTORIES', 'DIRECTORY', 'DISTINCT', 'DISTRIBUTE', 'DIV', 'DROP', 'ELSE',
'END', 'ESCAPE', 'ESCAPED', 'EXCEPT', 'EXCHANGE', 'EXISTS', 'EXPLAIN',
'EXPORT', 'EXTENDED', 'EXTERNAL', 'EXTRACT', 'FALSE', 'FETCH', 'FIELDS',
'FILTER', 'FILEFORMAT', 'FIRST', 'FOLLOWING', 'FOR', 'FOREIGN', 'FORMAT',
'FORMATTED', 'FROM', 'FULL', 'FUNCTION', 'FUNC
TIONS', 'GLOBAL', 'GRANT', 'GROUP', 'GROUPING', 'HAVING', 'IF', 'IGNORE',
'IMPORT', 'IN', 'INDEX', 'INDEXES', 'INNER', 'INPATH', 'INPUTFORMAT', 'INSERT',
'INTERSECT', 'INTERVAL', 'INTO', 'IS', 'ITEMS', 'JOIN', 'KEYS', 'LAST',
'LATERAL', 'LAZY', 'LEADING', 'LEFT', 'LIKE', 'LIMIT', 'LINES', 'LIST', 'LOAD',
'LOCAL', 'LOCATION', 'LOCK', 'LOCKS', 'LOGICAL', 'MACRO', 'MAP', 'MATCHED',
'MERGE', 'MSCK', 'NAMESPACE', 'NAMESPACES', 'NATURAL', 'NO', NOT, 'NULL',
'NULLS', 'OF', 'ON', 'ONLY', 'OPTION', 'OPTIONS', 'OR', 'ORDER', 'OUT',
'OUTER', 'OUTPUTFORMAT', 'OVER', 'OVERLAPS', 'OVERLAY', 'OVERWRITE',
'PARTITION', 'PARTITIONED', 'PARTITIONS', 'PERCENT', 'PIVOT', 'PLACING',
'POSITION', 'PRECEDING', 'PRIMARY', 'PRINCIPALS', 'PROPERTIES', 'PURGE',
'QUERY', 'RANGE', 'RECORDREADER', 'RECORDWRITER', 'RECOVER', 'REDUCE',
'REFERENCES', 'REFRESH', 'RENAME', 'REPAIR', 'REPLACE', 'RESET', 'RESTRICT',
'REVOKE', 'RIGHT', RLIKE, 'ROLE', 'ROLES', 'ROLLBACK', 'ROLLUP', 'ROW', 'ROWS',
'SCHEMA', 'SELECT', 'SEMI'
, 'SEPARATED', 'SERDE', 'SERDEPROPERTIES', 'SESSION_USER', 'SET', 'MINUS',
'SETS', 'SHOW', 'SKEWED', 'SOME', 'SORT', 'SORTED', 'START', 'STATISTICS',
'STORED', 'STRATIFY', 'STRUCT', 'SUBSTR', 'SUBSTRING', 'TABLE', 'TABLES',
'TABLESAMPLE', 'TBLPROPERTIES', TEMPORARY, 'TERMINATED', 'THEN', 'TIME', 'TO',
'TOUCH', 'TRAILING', 'TRANSACTION', 'TRANSACTIONS', 'TRANSFORM', 'TRIM',
'TRUE', 'TRUNCATE', 'TYPE', 'UNARCHIVE', 'UNBOUNDED', 'UNCACHE', 'UNION',
'UNIQUE', 'UNKNOWN', 'UNLOCK', 'UNSET', 'UPDATE', 'USE', 'USER', 'USING',
'VALUES', 'VIEW', 'VIEWS', 'WHEN', 'WHERE', 'WINDOW', 'WITH', 'ZONE',
IDENTIFIER, BACKQUOTED_IDENTIFIER}(line 2, pos 0)
== SQL ==
(SELECT column_name, type_name, character_maximum_length
^^^
FROM information_schema.columns WHERE table_name = 'DBCOLTYPETEST')
org.apache.spark.sql.catalyst.parser.ParseException:
extraneous input '(' expecting {'ADD', 'AFTER', 'ALL', 'ALTER', 'ANALYZE',
'AND', 'ANTI', 'ANY', 'ARCHIVE', 'ARRAY', 'AS', 'ASC', 'AT', 'AUTHORIZATION',
'BETWEEN', 'BOTH', 'BUCKET', 'BUCKETS', 'BY', 'CACHE', 'CASCADE', 'CASE',
'CAST', 'CHANGE', 'CHECK', 'CLEAR', 'CLUSTER', 'CLUSTERED', 'CODEGEN',
'COLLATE', 'COLLECTION', 'COLUMN', 'COLUMNS', 'COMMENT', 'COMMIT', 'COMPACT',
'COMPACTIONS', 'COMPUTE', 'CONCATENATE', 'CONSTRAINT', 'COST', 'CREATE',
'CROSS', 'CUBE', 'CURRENT', 'CURRENT_DATE', 'CURRENT_TIME',
'CURRENT_TIMESTAMP', 'CURRENT_USER', 'DATA', 'DATABASE', DATABASES,
'DBPROPERTIES', 'DEFINED', 'DELETE', 'DELIMITED', 'DESC', 'DESCRIBE', 'DFS',
'DIRECTORIES', 'DIRECTORY', 'DISTINCT', 'DISTRIBUTE', 'DIV', 'DROP', 'ELSE',
'END', 'ESCAPE', 'ESCAPED', 'EXCEPT', 'EXCHANGE', 'EXISTS', 'EXPLAIN',
'EXPORT', 'EXTENDED', 'EXTERNAL', 'EXTRACT', 'FALSE', 'FETCH', 'FIELDS',
'FILTER', 'FILEFORMAT', 'FIRST', 'FOLLOWING', 'FOR', 'FOREIGN', 'FORMAT',
'FORMATTED', 'FROM', 'FULL', 'FUNCTION', 'FUNC
TIONS', 'GLOBAL', 'GRANT', 'GROUP', 'GROUPING', 'HAVING', 'IF', 'IGNORE',
'IMPORT', 'IN', 'INDEX', 'INDEXES', 'INNER', 'INPATH', 'INPUTFORMAT', 'INSERT',
'INTERSECT', 'INTERVAL', 'INTO', 'IS', 'ITEMS', 'JOIN', 'KEYS', 'LAST',
'LATERAL', 'LAZY', 'LEADING', 'LEFT', 'LIKE', 'LIMIT', 'LINES', 'LIST', 'LOAD',
'LOCAL', 'LOCATION', 'LOCK', 'LOCKS', 'LOGICAL', 'MACRO', 'MAP', 'MATCHED',
'MERGE', 'MSCK', 'NAMESPACE', 'NAMESPACES', 'NATURAL', 'NO', NOT, 'NULL',
'NULLS', 'OF', 'ON', 'ONLY', 'OPTION', 'OPTIONS', 'OR', 'ORDER', 'OUT',
'OUTER', 'OUTPUTFORMAT', 'OVER', 'OVERLAPS', 'OVERLAY', 'OVERWRITE',
'PARTITION', 'PARTITIONED', 'PARTITIONS', 'PERCENT', 'PIVOT', 'PLACING',
'POSITION', 'PRECEDING', 'PRIMARY', 'PRINCIPALS', 'PROPERTIES', 'PURGE',
'QUERY', 'RANGE', 'RECORDREADER', 'RECORDWRITER', 'RECOVER', 'REDUCE',
'REFERENCES', 'REFRESH', 'RENAME', 'REPAIR', 'REPLACE', 'RESET', 'RESTRICT',
'REVOKE', 'RIGHT', RLIKE, 'ROLE', 'ROLES', 'ROLLBACK', 'ROLLUP', 'ROW', 'ROWS',
'SCHEMA', 'SELECT', 'SEMI'
, 'SEPARATED', 'SERDE', 'SERDEPROPERTIES', 'SESSION_USER', 'SET', 'MINUS',
'SETS', 'SHOW', 'SKEWED', 'SOME', 'SORT', 'SORTED', 'START', 'STATISTICS',
'STORED', 'STRATIFY', 'STRUCT', 'SUBSTR', 'SUBSTRING', 'TABLE', 'TABLES',
'TABLESAMPLE', 'TBLPROPERTIES', TEMPORARY, 'TERMINATED', 'THEN', 'TIME', 'TO',
'TOUCH', 'TRAILING', 'TRANSACTION', 'TRANSACTIONS', 'TRANSFORM', 'TRIM',
'TRUE', 'TRUNCATE', 'TYPE', 'UNARCHIVE', 'UNBOUNDED', 'UNCACHE', 'UNION',
'UNIQUE', 'UNKNOWN', 'UNLOCK', 'UNSET', 'UPDATE', 'USE', 'USER', 'USING',
'VALUES', 'VIEW', 'VIEWS', 'WHEN', 'WHERE', 'WINDOW', 'WITH', 'ZONE',
IDENTIFIER, BACKQUOTED_IDENTIFIER}(line 2, pos 0)
== SQL ==
(SELECT column_name, type_name, character_maximum_length
^^^
FROM information_schema.columns WHERE table_name = 'DBCOLTYPETEST')
at
org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:263)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:130)
at
org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:51)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parseMultipartIdentifier(ParseDriver.scala:67)
at org.apache.spark.sql.DataFrameReader.jdbc(DataFrameReader.scala:347)
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
