diff options
| author | Rajesh Balamohan <rbalamohan@apache.org> | 2016-03-04 10:59:40 +0000 |
|---|---|---|
| committer | Sean Owen <sowen@cloudera.com> | 2016-03-04 10:59:40 +0000 |
| commit | 204b02b56afe358b7f2d403fb6e2b9e8a7122798 (patch) | |
| tree | b04f7f3caeddf1a84568c6f1da6ac80d3892f1bc /sql | |
| parent | c04dc27cedd3d75781fda4c24da16b6ada44d3e4 (diff) | |
| download | spark-204b02b56afe358b7f2d403fb6e2b9e8a7122798.tar.gz spark-204b02b56afe358b7f2d403fb6e2b9e8a7122798.tar.bz2 spark-204b02b56afe358b7f2d403fb6e2b9e8a7122798.zip | |
[SPARK-12925] Improve HiveInspectors.unwrap for StringObjectInspector.…
Earlier fix did not copy the bytes and it is possible for higher level to reuse Text object. This was causing issues. Proposed fix now copies the bytes from Text. This still avoids the expensive encoding/decoding
Author: Rajesh Balamohan <rbalamohan@apache.org>
Closes #11477 from rajeshbalamohan/SPARK-12925.2.
Diffstat (limited to 'sql')
| -rw-r--r-- | sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala index 3e91569109..589862c7c0 100644 --- a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala +++ b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveInspectors.scala @@ -320,9 +320,10 @@ private[hive] trait HiveInspectors { case hvoi: HiveCharObjectInspector => UTF8String.fromString(hvoi.getPrimitiveJavaObject(data).getValue) case x: StringObjectInspector if x.preferWritable() => - // Text is in UTF-8 already. No need to convert again via fromString + // Text is in UTF-8 already. No need to convert again via fromString. Copy bytes val wObj = x.getPrimitiveWritableObject(data) - UTF8String.fromBytes(wObj.getBytes, 0, wObj.getLength) + val result = wObj.copyBytes() + UTF8String.fromBytes(result, 0, result.length) case x: StringObjectInspector => UTF8String.fromString(x.getPrimitiveJavaObject(data)) case x: IntObjectInspector if x.preferWritable() => x.get(data) |