tedyu commented on a change in pull request #30984:
URL: https://github.com/apache/spark/pull/30984#discussion_r553712976
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/DataSourceStrategy.scala
##########
@@ -737,6 +737,10 @@ abstract class PushableColumnBase {
}
case s: GetStructField if nestedPredicatePushdownEnabled =>
helper(s.child).map(_ :+ s.childSchema(s.ordinal).name)
+ case GetJsonObject(col, field) =>
+ val colName = col.toString.split("#")(0)
+ val fieldName = field.toString.split("\\.").last
+ Some(Seq("GetJsonObject(" + col + "," + field + ")"))
Review comment:
```
scala> spark.sql("CREATE TABLE IF NOT EXISTS
t1(`GetJsonObject(phone,'$.code')`)")
org.apache.spark.sql.catalyst.parser.ParseException:
mismatched 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', 'RESPECT',
'RESTRICT', 'REVOKE', 'RIGHT', RLIKE, 'ROLE', 'ROLES', 'ROLLBACK', 'ROLLUP',
'ROW', 'ROWS', 'SCHEMA', 'SELE
CT', '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 1, pos 61)
== SQL ==
CREATE TABLE IF NOT EXISTS t1(`GetJsonObject(phone,'$.code')`)
-------------------------------------------------------------^^^
at
org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:255)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:124)
at
org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:50)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parsePlan(ParseDriver.scala:75)
at org.apache.spark.sql.SparkSession.$anonfun$sql$2(SparkSession.scala:613)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:613)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
```
----------------------------------------------------------------
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]
