[orc] branch main updated: ORC-835: Cache TRUE/FALSE Bytes in StringGroupFromBooleanTreeReader (#741)

[do...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

dongjoon pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/orc.git


The following commit(s) were added to refs/heads/main by this push:
     new bc53cc3  ORC-835: Cache TRUE/FALSE Bytes in StringGroupFromBooleanTreeReader (#741)
bc53cc3 is described below

commit bc53cc33a3f61ecced87df91450264ea85f4b69d
Author: belugabehr <12...@users.noreply.github.com>
AuthorDate: Thu Jul 29 15:25:48 2021 -0400

    ORC-835: Cache TRUE/FALSE Bytes in StringGroupFromBooleanTreeReader (#741)
    
    ### What changes were proposed in this pull request?
    Cache byte value for TRUE and FALSE strings.
    
    
    ### Why are the changes needed?
    Performance.
    
    ### How was this patch tested?
    No change in functionality. Uses existing unit tests.
---
 java/core/src/java/org/apache/orc/impl/ConvertTreeReaderFactory.java | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/java/core/src/java/org/apache/orc/impl/ConvertTreeReaderFactory.java b/java/core/src/java/org/apache/orc/impl/ConvertTreeReaderFactory.java
index bfd51ea..86e90cc 100644
--- a/java/core/src/java/org/apache/orc/impl/ConvertTreeReaderFactory.java
+++ b/java/core/src/java/org/apache/orc/impl/ConvertTreeReaderFactory.java
@@ -1069,6 +1069,8 @@ public class ConvertTreeReaderFactory extends TreeReaderFactory {
   }
 
   public static class StringGroupFromBooleanTreeReader extends StringGroupFromAnyIntegerTreeReader {
+    private static final byte[] TRUE_BYTES = "TRUE".getBytes(StandardCharsets.US_ASCII);
+    private static final byte[] FALSE_BYTES = "FALSE".getBytes(StandardCharsets.US_ASCII);
 
     StringGroupFromBooleanTreeReader(int columnId, TypeDescription fileType,
                                      TypeDescription readerType,
@@ -1078,8 +1080,7 @@ public class ConvertTreeReaderFactory extends TreeReaderFactory {
 
     @Override
     public void setConvertVectorElement(int elementNum) {
-      byte[] bytes = (longColVector.vector[elementNum] != 0 ? "TRUE" : "FALSE")
-         .getBytes(StandardCharsets.UTF_8);
+      byte[] bytes = (longColVector.vector[elementNum] != 0 ? TRUE_BYTES : FALSE_BYTES);
       assignStringGroupVectorEntry(bytesColVector, elementNum, readerType, bytes);
     }
   }