SQL Error Message with PySpark

[cpatte7372]

Hello community,

I've nearly figured this out for myself.

I had to change the code as follows:

results7 = spark.sql("SELECT\
appl_stock.[Open]\
,appl_stock.[Close]\
FROM dbo.appl_stock\
WHERE appl_stock.[Close] < 500")

However, that still produced the following error:

Py4JJavaError                             Traceback (most recent call last)
~/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
     62         try:
---> 63             return f(*a, **kw)
     64         except py4j.protocol.Py4JJavaError as e:

~/spark-2.1.0-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip/py4j/protocol.py in get_return_value(answer, gateway_client, target_id, name)
    318                     "An error occurred while calling {0}{1}{2}.\n".
--> 319                     format(target_id, ".", name), value)
    320             else:

Py4JJavaError: An error occurred while calling o19.sql.
: org.apache.spark.sql.catalyst.parser.ParseException: 
mismatched input '.' expecting {<EOF>, ',', 'FROM', 'WHERE', 'GROUP', 'ORDER', 'HAVING', 'LIMIT', 'LATERAL', 'WINDOW', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'SORT', 'CLUSTER', 'DISTRIBUTE'}(line 1, pos 35)

== SQL ==
SELECT  appl_stock.Open  appl_stock.CloseFROM appl_stockWHERE appl_stock.Close < 500
-----------------------------------^^^

	at org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:197)
	at org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:99)
	at org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:45)
	at org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parsePlan(ParseDriver.scala:53)
	at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
	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:280)
	at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
	at py4j.commands.CallCommand.execute(CallCommand.java:79)
	at py4j.GatewayConnection.run(GatewayConnection.java:214)
	at java.lang.Thread.run(Thread.java:748)


During handling of the above exception, another exception occurred:

ParseException                            Traceback (most recent call last)
<ipython-input-37-4920f7e68c0e> in <module>()
----> 1 results5 = spark.sql("SELECT  appl_stock.Open  appl_stock.CloseFROM appl_stockWHERE appl_stock.Close < 500")

~/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/session.py in sql(self, sqlQuery)
    539         [Row(f1=1, f2=u'row1'), Row(f1=2, f2=u'row2'), Row(f1=3, f2=u'row3')]
    540         """
--> 541         return DataFrame(self._jsparkSession.sql(sqlQuery), self._wrapped)
    542 
    543     @since(2.0)

~/spark-2.1.0-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py in __call__(self, *args)
   1131         answer = self.gateway_client.send_command(command)
   1132         return_value = get_return_value(
-> 1133             answer, self.gateway_client, self.target_id, self.name)
   1134 
   1135         for temp_arg in temp_args:

~/spark-2.1.0-bin-hadoop2.7/python/pyspark/sql/utils.py in deco(*a, **kw)
     71                 raise AnalysisException(s.split(': ', 1)[1], stackTrace)
     72             if s.startswith('org.apache.spark.sql.catalyst.parser.ParseException: '):
---> 73                 raise ParseException(s.split(': ', 1)[1], stackTrace)
     74             if s.startswith('org.apache.spark.sql.streaming.StreamingQueryException: '):
     75                 raise StreamingQueryException(s.split(': ', 1)[1], stackTrace)

ParseException: "\nmismatched input '.' expecting {<EOF>, ',', 'FROM', 'WHERE', 'GROUP', 'ORDER', 'HAVING', 'LIMIT', 'LATERAL', 'WINDOW', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'SORT', 'CLUSTER', 'DISTRIBUTE'}(line 1, pos 35)\n\n== SQL ==\nSELECT  appl_stock.Open  appl_stock.CloseFROM appl_stockWHERE appl_stock.Close < 500\n-----------------------------------^^^\n"

However, when I executed the command the following code, (same code but all on one line) it was a success:

results7 = spark.sql("SELECT appl_stock.Open ,appl_stock.Close FROM appl_stock WHERE appl_stock.Close < 500")

Can someone shed some light on why the prior code produces the error?

Cheers

Carlton