Suhas Nalapure created PHOENIX-2547:
---------------------------------------
Summary: Spark Data Source API: Filter operation doesn't work for
column names containing a white space
Key: PHOENIX-2547
URL: https://issues.apache.org/jira/browse/PHOENIX-2547
Project: Phoenix
Issue Type: Bug
Affects Versions: 4.6.0
Reporter: Suhas Nalapure
Priority: Critical
Dataframe.filter() results in
"org.apache.phoenix.exception.PhoenixParserException: ERROR 604 (42P00): Syntax
error. Mismatched input. Expecting "LPAREN", got "first" at line 1, column 52."
when a column name has a white space in it.
Steps to Reproduce
--------------------------
1. Create a test table & insert a row as below
create table "space" ("key" varchar primary key, "first name" varchar);
upsert into "space" values ('key1', 'xyz');
2. Java code that leads to the error:
//omitting the DataFrame creation part
df = df.filter(df.col("first name").equalTo("xyz"));
System.out.println(df.collectAsList());
Exception Stack Trace:
------------------------------
java.lang.RuntimeException:
org.apache.phoenix.exception.PhoenixParserException: ERROR 604 (42P00): Syntax
error. Mismatched input. Expecting "LPAREN", got "first" at line 1, column 52.
at
org.apache.phoenix.mapreduce.PhoenixInputFormat.getQueryPlan(PhoenixInputFormat.java:125)
at
org.apache.phoenix.mapreduce.PhoenixInputFormat.getSplits(PhoenixInputFormat.java:80)
at
org.apache.spark.rdd.NewHadoopRDD.getPartitions(NewHadoopRDD.scala:95)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.phoenix.spark.PhoenixRDD.getPartitions(PhoenixRDD.scala:48)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at
org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:239)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:237)
at scala.Option.getOrElse(Option.scala:120)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:237)
at org.apache.spark.SparkContext.runJob(SparkContext.scala:1910)
at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:905)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:306)
at org.apache.spark.rdd.RDD.collect(RDD.scala:904)
at
org.apache.spark.sql.DataFrame$$anonfun$collectAsList$1.apply(DataFrame.scala:1395)
at
org.apache.spark.sql.DataFrame$$anonfun$collectAsList$1.apply(DataFrame.scala:1395)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:56)
at
org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:1904)
at org.apache.spark.sql.DataFrame.collectAsList(DataFrame.scala:1394)
at
com.dataken.dataframe.dao.DataFrameDAOTest.testPhoenixGetDataFrame(DataFrameDAOTest.java:167)
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:497)
at
org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
at
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
at
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
at
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
at
org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
at
org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
at
org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
at
org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:86)
at
org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:675)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382)
at
org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192)
Caused by: org.apache.phoenix.exception.PhoenixParserException: ERROR 604
(42P00): Syntax error. Mismatched input. Expecting "LPAREN", got "first" at
line 1, column 52.
at
org.apache.phoenix.exception.PhoenixParserException.newException(PhoenixParserException.java:33)
at org.apache.phoenix.parse.SQLParser.parseStatement(SQLParser.java:111)
at
org.apache.phoenix.jdbc.PhoenixStatement$PhoenixStatementParser.parseStatement(PhoenixStatement.java:1229)
at
org.apache.phoenix.jdbc.PhoenixStatement.parseStatement(PhoenixStatement.java:1310)
at
org.apache.phoenix.jdbc.PhoenixStatement.compileQuery(PhoenixStatement.java:1320)
at
org.apache.phoenix.jdbc.PhoenixStatement.optimizeQuery(PhoenixStatement.java:1315)
at
org.apache.phoenix.mapreduce.PhoenixInputFormat.getQueryPlan(PhoenixInputFormat.java:118)
... 78 more
Caused by: MismatchedTokenException(60!=90)
at
org.apache.phoenix.parse.PhoenixSQLParser.recoverFromMismatchedToken(PhoenixSQLParser.java:351)
at org.antlr.runtime.BaseRecognizer.match(BaseRecognizer.java:115)
at
org.apache.phoenix.parse.PhoenixSQLParser.not_expression(PhoenixSQLParser.java:6403)
at
org.apache.phoenix.parse.PhoenixSQLParser.and_expression(PhoenixSQLParser.java:6223)
at
org.apache.phoenix.parse.PhoenixSQLParser.or_expression(PhoenixSQLParser.java:6160)
at
org.apache.phoenix.parse.PhoenixSQLParser.expression(PhoenixSQLParser.java:6125)
at
org.apache.phoenix.parse.PhoenixSQLParser.not_expression(PhoenixSQLParser.java:6405)
at
org.apache.phoenix.parse.PhoenixSQLParser.and_expression(PhoenixSQLParser.java:6223)
at
org.apache.phoenix.parse.PhoenixSQLParser.or_expression(PhoenixSQLParser.java:6160)
at
org.apache.phoenix.parse.PhoenixSQLParser.expression(PhoenixSQLParser.java:6125)
at
org.apache.phoenix.parse.PhoenixSQLParser.single_select(PhoenixSQLParser.java:4328)
at
org.apache.phoenix.parse.PhoenixSQLParser.unioned_selects(PhoenixSQLParser.java:4410)
at
org.apache.phoenix.parse.PhoenixSQLParser.select_node(PhoenixSQLParser.java:4475)
at
org.apache.phoenix.parse.PhoenixSQLParser.oneStatement(PhoenixSQLParser.java:757)
at
org.apache.phoenix.parse.PhoenixSQLParser.statement(PhoenixSQLParser.java:499)
at org.apache.phoenix.parse.SQLParser.parseStatement(SQLParser.java:108)
... 83 more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
