(spark) branch master updated: [SPARK-46954][SQL] XML: Wrap InputStreamReader with BufferedReader

[gu...@apache.org]

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

gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git


The following commit(s) were added to refs/heads/master by this push:
     new 10439902b6dd [SPARK-46954][SQL] XML: Wrap InputStreamReader with BufferedReader
10439902b6dd is described below

commit 10439902b6ddc2d5826ed16f855a8429d9a15466
Author: Sandip Agarwala <13...@users.noreply.github.com>
AuthorDate: Tue Feb 6 16:11:23 2024 +0900

    [SPARK-46954][SQL] XML: Wrap InputStreamReader with BufferedReader
    
    ### What changes were proposed in this pull request?
    Wrap InputStreamReader with BufferedReader
    
    ### Why are the changes needed?
    More than doubles the performance.
    
    ### Does this PR introduce _any_ user-facing change?
    Yes, performance improvement.
    
    ### How was this patch tested?
    Existing unit tests and manual perf testing
    
    ### Was this patch authored or co-authored using generative AI tooling?
    No
    
    Closes #45041 from sandip-db/xml_buffered_reader.
    
    Authored-by: Sandip Agarwala <13...@users.noreply.github.com>
    Signed-off-by: Hyukjin Kwon <gu...@apache.org>
---
 .../spark/sql/catalyst/xml/StaxXmlParser.scala       | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala
index 74413bb8cbb2..66ec636d1a65 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/xml/StaxXmlParser.scala
@@ -16,7 +16,7 @@
  */
 package org.apache.spark.sql.catalyst.xml
 
-import java.io.{CharConversionException, FileNotFoundException, InputStream, InputStreamReader, IOException, StringReader}
+import java.io.{BufferedReader, CharConversionException, FileNotFoundException, InputStream, InputStreamReader, IOException, StringReader}
 import java.nio.charset.{Charset, MalformedInputException}
 import java.text.NumberFormat
 import java.util.Locale
@@ -37,20 +37,7 @@ import org.apache.spark.SparkUpgradeException
 import org.apache.spark.internal.Logging
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.expressions.ExprUtils
-import org.apache.spark.sql.catalyst.util.{
-  ArrayBasedMapData,
-  BadRecordException,
-  DateFormatter,
-  DropMalformedMode,
-  FailureSafeParser,
-  GenericArrayData,
-  MapData,
-  ParseMode,
-  PartialResultArrayException,
-  PartialResultException,
-  PermissiveMode,
-  TimestampFormatter
-}
+import org.apache.spark.sql.catalyst.util.{ArrayBasedMapData, BadRecordException, DateFormatter, DropMalformedMode, FailureSafeParser, GenericArrayData, MapData, ParseMode, PartialResultArrayException, PartialResultException, PermissiveMode, TimestampFormatter}
 import org.apache.spark.sql.catalyst.util.LegacyDateFormats.FAST_DATE_FORMAT
 import org.apache.spark.sql.catalyst.xml.StaxXmlParser.convertStream
 import org.apache.spark.sql.errors.QueryExecutionErrors
@@ -623,7 +610,8 @@ class StaxXmlParser(
 class XmlTokenizer(
   inputStream: InputStream,
   options: XmlOptions) extends Logging {
-  private var reader = new InputStreamReader(inputStream, Charset.forName(options.charset))
+  private var reader = new BufferedReader(
+    new InputStreamReader(inputStream, Charset.forName(options.charset)))
   private var currentStartTag: String = _
   private var buffer = new StringBuilder()
   private val startTag = s"<${options.rowTag}>"


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org