From 9ce12aaf283a2793e719bdc956dd858922636e8d Mon Sep 17 00:00:00 2001 From: q00251598 Date: Mon, 2 Mar 2015 10:13:11 -0800 Subject: [SPARK-5741][SQL] Support the path contains comma in HiveContext When run ```select * from nzhang_part where hr = 'file,';```, it throws exception ```java.lang.IllegalArgumentException: Can not create a Path from an empty string``` . Because the path of hdfs contains comma, and FileInputFormat.setInputPaths will split path by comma. ### SQL ``` set hive.merge.mapfiles=true; set hive.merge.mapredfiles=true; set hive.input.format=org.apache.hadoop.hive.ql.io.HiveInputFormat; set hive.exec.dynamic.partition=true; set hive.exec.dynamic.partition.mode=nonstrict; create table nzhang_part like srcpart; insert overwrite table nzhang_part partition (ds='2010-08-15', hr) select key, value, hr from srcpart where ds='2008-04-08'; insert overwrite table nzhang_part partition (ds='2010-08-15', hr=11) select key, value from srcpart where ds='2008-04-08'; insert overwrite table nzhang_part partition (ds='2010-08-15', hr) select * from ( select key, value, hr from srcpart where ds='2008-04-08' union all select '1' as key, '1' as value, 'file,' as hr from src limit 1) s; select * from nzhang_part where hr = 'file,'; ``` ### Error Log ``` 15/02/10 14:33:16 ERROR SparkSQLDriver: Failed in [select * from nzhang_part where hr = 'file,'] java.lang.IllegalArgumentException: Can not create a Path from an empty string at org.apache.hadoop.fs.Path.checkPathArg(Path.java:127) at org.apache.hadoop.fs.Path.(Path.java:135) at org.apache.hadoop.util.StringUtils.stringToPath(StringUtils.java:241) at org.apache.hadoop.mapred.FileInputFormat.setInputPaths(FileInputFormat.java:400) at org.apache.spark.sql.hive.HadoopTableReader$.initializeLocalJobConfFunc(TableReader.scala:251) at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$11.apply(TableReader.scala:229) at org.apache.spark.sql.hive.HadoopTableReader$$anonfun$11.apply(TableReader.scala:229) at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:172) at org.apache.spark.rdd.HadoopRDD$$anonfun$getJobConf$6.apply(HadoopRDD.scala:172) at scala.Option.map(Option.scala:145) at org.apache.spark.rdd.HadoopRDD.getJobConf(HadoopRDD.scala:172) at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:196) Author: q00251598 Closes #4532 from watermen/SPARK-5741 and squashes the following commits: 9758ab1 [q00251598] fix bug 1db1a1c [q00251598] use setInputPaths(Job job, Path... inputPaths) b788a72 [q00251598] change FileInputFormat.setInputPaths to jobConf.set and add test suite --- .../src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a | 1 + 1 file changed, 1 insertion(+) create mode 100644 sql/hive/src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a (limited to 'sql/hive/src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a') diff --git a/sql/hive/src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a b/sql/hive/src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a new file mode 100644 index 0000000000..573541ac97 --- /dev/null +++ b/sql/hive/src/test/resources/golden/merge4-0-b12e5c70d6d29757471b900b6160fa8a @@ -0,0 +1 @@ +0 -- cgit v1.2.3