[jira] [Created] (SPARK-31065) Empty string values cause schema_of_json() to return a schema not usable by from_json()

["Nicholas Chammas (Jira)" <ji...@apache.org>]

Nicholas Chammas created SPARK-31065:
----------------------------------------

             Summary: Empty string values cause schema_of_json() to return a schema not usable by from_json()
                 Key: SPARK-31065
                 URL: https://issues.apache.org/jira/browse/SPARK-31065
             Project: Spark
          Issue Type: Bug
          Components: SQL
    Affects Versions: 2.4.5
            Reporter: Nicholas Chammas


Here's a reproduction:
  
{code:python}
from pyspark.sql.functions import from_json, schema_of_json
json = '{"a": ""}'

df = spark.createDataFrame([(json,)], schema=['json'])
df.show()

# chokes with org.apache.spark.sql.catalyst.parser.ParseException
json_schema = schema_of_json(json)
df.select(from_json('json', json_schema))

# works fine
json_schema = spark.read.json(df.rdd.map(lambda x: x[0])).schema
df.select(from_json('json', json_schema))
{code}
The output:
{code:java}
>>> from pyspark.sql.functions import from_json, schema_of_json
>>> json = '{"a": ""}'
>>> 
>>> df = spark.createDataFrame([(json,)], schema=['json'])
>>> df.show()
+---------+
|     json|
+---------+
|{"a": ""}|
+---------+

>>> 
>>> # chokes with org.apache.spark.sql.catalyst.parser.ParseException
>>> json_schema = schema_of_json(json)
>>> df.select(from_json('json', json_schema))
Traceback (most recent call last):
  File ".../site-packages/pyspark/sql/utils.py", line 63, in deco
    return f(*a, **kw)
  File ".../site-packages/pyspark/python/lib/py4j-0.10.7-src.zip/py4j/protocol.py", line 328, in get_return_value
py4j.protocol.Py4JJavaError: An error occurred while calling z:org.apache.spark.sql.functions.from_json.
: org.apache.spark.sql.catalyst.parser.ParseException: 
extraneous input '<' expecting {'SELECT', 'FROM', 'ADD', 'AS', 'ALL', 'ANY', 'DISTINCT', 'WHERE', 'GROUP', 'BY', 'GROUPING', 'SETS', 'CUBE', 'ROLLUP', 'ORDER', 'HAVING', 'LIMIT', 'AT', 'OR', 'AND', 'IN', NOT, 'NO', 'EXISTS', 'BETWEEN', 'LIKE', RLIKE, 'IS', 'NULL', 'TRUE', 'FALSE', 'NULLS', 'ASC', 'DESC', 'FOR', 'INTERVAL', 'CASE', 'WHEN', 'THEN', 'ELSE', 'END', 'JOIN', 'CROSS', 'OUTER', 'INNER', 'LEFT', 'SEMI', 'RIGHT', 'FULL', 'NATURAL', 'ON', 'PIVOT', 'LATERAL', 'WINDOW', 'OVER', 'PARTITION', 'RANGE', 'ROWS', 'UNBOUNDED', 'PRECEDING', 'FOLLOWING', 'CURRENT', 'FIRST', 'AFTER', 'LAST', 'ROW', 'WITH', 'VALUES', 'CREATE', 'TABLE', 'DIRECTORY', 'VIEW', 'REPLACE', 'INSERT', 'DELETE', 'INTO', 'DESCRIBE', 'EXPLAIN', 'FORMAT', 'LOGICAL', 'CODEGEN', 'COST', 'CAST', 'SHOW', 'TABLES', 'COLUMNS', 'COLUMN', 'USE', 'PARTITIONS', 'FUNCTIONS', 'DROP', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'TO', 'TABLESAMPLE', 'STRATIFY', 'ALTER', 'RENAME', 'ARRAY', 'MAP', 'STRUCT', 'COMMENT', 'SET', 'RESET', 'DATA', 'START', 'TRANSACTION', 'COMMIT', 'ROLLBACK', 'MACRO', 'IGNORE', 'BOTH', 'LEADING', 'TRAILING', 'IF', 'POSITION', 'EXTRACT', 'DIV', 'PERCENT', 'BUCKET', 'OUT', 'OF', 'SORT', 'CLUSTER', 'DISTRIBUTE', 'OVERWRITE', 'TRANSFORM', 'REDUCE', 'SERDE', 'SERDEPROPERTIES', 'RECORDREADER', 'RECORDWRITER', 'DELIMITED', 'FIELDS', 'TERMINATED', 'COLLECTION', 'ITEMS', 'KEYS', 'ESCAPED', 'LINES', 'SEPARATED', 'FUNCTION', 'EXTENDED', 'REFRESH', 'CLEAR', 'CACHE', 'UNCACHE', 'LAZY', 'FORMATTED', 'GLOBAL', TEMPORARY, 'OPTIONS', 'UNSET', 'TBLPROPERTIES', 'DBPROPERTIES', 'BUCKETS', 'SKEWED', 'STORED', 'DIRECTORIES', 'LOCATION', 'EXCHANGE', 'ARCHIVE', 'UNARCHIVE', 'FILEFORMAT', 'TOUCH', 'COMPACT', 'CONCATENATE', 'CHANGE', 'CASCADE', 'RESTRICT', 'CLUSTERED', 'SORTED', 'PURGE', 'INPUTFORMAT', 'OUTPUTFORMAT', DATABASE, DATABASES, 'DFS', 'TRUNCATE', 'ANALYZE', 'COMPUTE', 'LIST', 'STATISTICS', 'PARTITIONED', 'EXTERNAL', 'DEFINED', 'REVOKE', 'GRANT', 'LOCK', 'UNLOCK', 'MSCK', 'REPAIR', 'RECOVER', 'EXPORT', 'IMPORT', 'LOAD', 'ROLE', 'ROLES', 'COMPACTIONS', 'PRINCIPALS', 'TRANSACTIONS', 'INDEX', 'INDEXES', 'LOCKS', 'OPTION', 'ANTI', 'LOCAL', 'INPATH', IDENTIFIER, BACKQUOTED_IDENTIFIER}(line 1, pos 6)

== SQL ==
struct<a:null>
------^^^

	at org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:241)
	at org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:117)
	at org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parseTableSchema(ParseDriver.scala:64)
	at org.apache.spark.sql.types.DataType$.fromDDL(DataType.scala:123)
	at org.apache.spark.sql.catalyst.expressions.JsonExprUtils$.evalSchemaExpr(jsonExpressions.scala:777)
	at org.apache.spark.sql.catalyst.expressions.JsonToStructs.<init>(jsonExpressions.scala:527)
	at org.apache.spark.sql.functions$.from_json(functions.scala:3606)
	at org.apache.spark.sql.functions.from_json(functions.scala)
	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:498)
	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:748)


During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File ".../site-packages/pyspark/sql/functions.py", line 2284, in from_json
    jc = sc._jvm.functions.from_json(_to_java_column(col), schema, options)
  File ".../site-packages/pyspark/python/lib/py4j-0.10.7-src.zip/py4j/java_gateway.py", line 1257, in __call__
  File ".../site-packages/pyspark/sql/utils.py", line 73, in deco
    raise ParseException(s.split(': ', 1)[1], stackTrace)
pyspark.sql.utils.ParseException: "\nextraneous input '<' expecting {'SELECT', 'FROM', 'ADD', 'AS', 'ALL', 'ANY', 'DISTINCT', 'WHERE', 'GROUP', 'BY', 'GROUPING', 'SETS', 'CUBE', 'ROLLUP', 'ORDER', 'HAVING', 'LIMIT', 'AT', 'OR', 'AND', 'IN', NOT, 'NO', 'EXISTS', 'BETWEEN', 'LIKE', RLIKE, 'IS', 'NULL', 'TRUE', 'FALSE', 'NULLS', 'ASC', 'DESC', 'FOR', 'INTERVAL', 'CASE', 'WHEN', 'THEN', 'ELSE', 'END', 'JOIN', 'CROSS', 'OUTER', 'INNER', 'LEFT', 'SEMI', 'RIGHT', 'FULL', 'NATURAL', 'ON', 'PIVOT', 'LATERAL', 'WINDOW', 'OVER', 'PARTITION', 'RANGE', 'ROWS', 'UNBOUNDED', 'PRECEDING', 'FOLLOWING', 'CURRENT', 'FIRST', 'AFTER', 'LAST', 'ROW', 'WITH', 'VALUES', 'CREATE', 'TABLE', 'DIRECTORY', 'VIEW', 'REPLACE', 'INSERT', 'DELETE', 'INTO', 'DESCRIBE', 'EXPLAIN', 'FORMAT', 'LOGICAL', 'CODEGEN', 'COST', 'CAST', 'SHOW', 'TABLES', 'COLUMNS', 'COLUMN', 'USE', 'PARTITIONS', 'FUNCTIONS', 'DROP', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'TO', 'TABLESAMPLE', 'STRATIFY', 'ALTER', 'RENAME', 'ARRAY', 'MAP', 'STRUCT', 'COMMENT', 'SET', 'RESET', 'DATA', 'START', 'TRANSACTION', 'COMMIT', 'ROLLBACK', 'MACRO', 'IGNORE', 'BOTH', 'LEADING', 'TRAILING', 'IF', 'POSITION', 'EXTRACT', 'DIV', 'PERCENT', 'BUCKET', 'OUT', 'OF', 'SORT', 'CLUSTER', 'DISTRIBUTE', 'OVERWRITE', 'TRANSFORM', 'REDUCE', 'SERDE', 'SERDEPROPERTIES', 'RECORDREADER', 'RECORDWRITER', 'DELIMITED', 'FIELDS', 'TERMINATED', 'COLLECTION', 'ITEMS', 'KEYS', 'ESCAPED', 'LINES', 'SEPARATED', 'FUNCTION', 'EXTENDED', 'REFRESH', 'CLEAR', 'CACHE', 'UNCACHE', 'LAZY', 'FORMATTED', 'GLOBAL', TEMPORARY, 'OPTIONS', 'UNSET', 'TBLPROPERTIES', 'DBPROPERTIES', 'BUCKETS', 'SKEWED', 'STORED', 'DIRECTORIES', 'LOCATION', 'EXCHANGE', 'ARCHIVE', 'UNARCHIVE', 'FILEFORMAT', 'TOUCH', 'COMPACT', 'CONCATENATE', 'CHANGE', 'CASCADE', 'RESTRICT', 'CLUSTERED', 'SORTED', 'PURGE', 'INPUTFORMAT', 'OUTPUTFORMAT', DATABASE, DATABASES, 'DFS', 'TRUNCATE', 'ANALYZE', 'COMPUTE', 'LIST', 'STATISTICS', 'PARTITIONED', 'EXTERNAL', 'DEFINED', 'REVOKE', 'GRANT', 'LOCK', 'UNLOCK', 'MSCK', 'REPAIR', 'RECOVER', 'EXPORT', 'IMPORT', 'LOAD', 'ROLE', 'ROLES', 'COMPACTIONS', 'PRINCIPALS', 'TRANSACTIONS', 'INDEX', 'INDEXES', 'LOCKS', 'OPTION', 'ANTI', 'LOCAL', 'INPATH', IDENTIFIER, BACKQUOTED_IDENTIFIER}(line 1, pos 6)\n\n== SQL ==\nstruct<a:null>\n------^^^\n"
>>> 
>>> # works fine
>>> json_schema = spark.read.json(df.rdd.map(lambda x: x[0])).schema
>>> df.select(from_json('json', json_schema))
DataFrame[jsontostructs(json): struct<a:string>]
{code}
I assumed that {{schema_of_json()}} would use the same code path that underlies {{spark.read.json()}}, but I guess there is something different that trips up the parser.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org