From e52499ea9c32326b399b50bf0e3f26278da3feb2 Mon Sep 17 00:00:00 2001 From: windpiger Date: Mon, 6 Mar 2017 22:36:43 -0800 Subject: [SPARK-19832][SQL] DynamicPartitionWriteTask get partitionPath should escape the partition name ## What changes were proposed in this pull request? Currently in DynamicPartitionWriteTask, when we get the paritionPath of a parition, we just escape the partition value, not escape the partition name. this will cause some problems for some special partition name situation, for example : 1) if the partition name contains '%' etc, there will be two partition path created in the filesytem, one is for escaped path like '/path/a%25b=1', another is for unescaped path like '/path/a%b=1'. and the data inserted stored in unescaped path, while the show partitions table will return 'a%25b=1' which the partition name is escaped. So here it is not consist. And I think the data should be stored in the escaped path in filesystem, which Hive2.0.0 also have the same action. 2) if the partition name contains ':', there will throw exception that new Path("/path","a:b"), this is illegal which has a colon in the relative path. ``` java.lang.IllegalArgumentException: java.net.URISyntaxException: Relative path in absolute URI: a:b at org.apache.hadoop.fs.Path.initialize(Path.java:205) at org.apache.hadoop.fs.Path.(Path.java:171) at org.apache.hadoop.fs.Path.(Path.java:88) ... 48 elided Caused by: java.net.URISyntaxException: Relative path in absolute URI: a:b at java.net.URI.checkPath(URI.java:1823) at java.net.URI.(URI.java:745) at org.apache.hadoop.fs.Path.initialize(Path.java:202) ... 50 more ``` ## How was this patch tested? unit test added Author: windpiger Closes #17173 from windpiger/fixDatasourceSpecialCharPartitionName. --- .../org/apache/spark/sql/execution/datasources/FileFormatWriter.scala | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'sql/core/src/main') diff --git a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala index 950e5ca0d6..30a09a9ad3 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala @@ -341,7 +341,7 @@ object FileFormatWriter extends Logging { Seq(Cast(c, StringType, Option(desc.timeZoneId))), Seq(StringType)) val str = If(IsNull(c), Literal(ExternalCatalogUtils.DEFAULT_PARTITION_NAME), escaped) - val partitionName = Literal(c.name + "=") :: str :: Nil + val partitionName = Literal(ExternalCatalogUtils.escapePathName(c.name) + "=") :: str :: Nil if (i == 0) partitionName else Literal(Path.SEPARATOR) :: partitionName } } -- cgit v1.2.3