[SPARK-35253][SQL][BUILD] Bump up the janino version to v3.1.4

maropu · srowen · commit 101b0cc313cb · 2021-05-12T08:57:57.000-05:00
### What changes were proposed in this pull request? This PR proposes to bump up the janino version from 3.0.16 to v3.1.4. The major changes of this upgrade are as follows: - Fixed issue apache#131: Janino 3.1.2 is 10x slower than 3.0.11: The Compiler's IClassLoader was initialized way too eagerly, thus lots of classes were loaded from the class path, which is very slow. - Improved the encoding of stack map frames according to JVMS11 4.7.4: Previously, only "full_frame"s were generated. - Fixed issue apache#107: Janino requires "org.codehaus.commons.compiler.io", but commons-compiler does not export this package - Fixed the promotion of the array access index expression (see JLS7 15.13 Array Access Expressions). For all the changes, please see the change log: http://janino-compiler.github.io/janino/changelog.html NOTE1: I've checked that there is no obvious performance regression. For all the data, see a link: https://docs.google.com/spreadsheets/d/1srxT9CioGQg1fLKM3Uo8z1sTzgCsMj4pg6JzpdcG6VU/edit?usp=sharing NOTE2: We upgraded janino to 3.1.2 (apache#27860) once before, but the commit had been reverted in apache#29495 because of the correctness issue. Recently, apache#32374 had checked if Spark could land on v3.1.3 or not, but a new bug was found there. These known issues has been fixed in v3.1.4 by following PRs: - janino-compiler/janino#145 - janino-compiler/janino#146 ### Why are the changes needed? janino v3.0.X is no longer maintained. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? GA passed. Closes apache#32455 from maropu/janino_v3.1.4. Authored-by: Takeshi Yamamuro <yamamuro@apache.org> Signed-off-by: Sean Owen <srowen@gmail.com>
diff --git a/dev/deps/spark-deps-hadoop-2.7-hive-2.3 b/dev/deps/spark-deps-hadoop-2.7-hive-2.3
@@ -37,7 +37,7 @@ commons-beanutils/1.9.4//commons-beanutils-1.9.4.jar
 commons-cli/1.2//commons-cli-1.2.jar
 commons-codec/1.15//commons-codec-1.15.jar
 commons-collections/3.2.2//commons-collections-3.2.2.jar
-commons-compiler/3.0.16//commons-compiler-3.0.16.jar
+commons-compiler/3.1.4//commons-compiler-3.1.4.jar
 commons-compress/1.20//commons-compress-1.20.jar
 commons-configuration/1.6//commons-configuration-1.6.jar
 commons-crypto/1.1.0//commons-crypto-1.1.0.jar
@@ -122,7 +122,7 @@ jakarta.servlet-api/4.0.3//jakarta.servlet-api-4.0.3.jar
 jakarta.validation-api/2.0.2//jakarta.validation-api-2.0.2.jar
 jakarta.ws.rs-api/2.1.6//jakarta.ws.rs-api-2.1.6.jar
 jakarta.xml.bind-api/2.3.2//jakarta.xml.bind-api-2.3.2.jar
-janino/3.0.16//janino-3.0.16.jar
+janino/3.1.4//janino-3.1.4.jar
 javassist/3.25.0-GA//javassist-3.25.0-GA.jar
 javax.inject/1//javax.inject-1.jar
 javax.jdo/3.2.0-m3//javax.jdo-3.2.0-m3.jar
diff --git a/dev/deps/spark-deps-hadoop-3.2-hive-2.3 b/dev/deps/spark-deps-hadoop-3.2-hive-2.3
@@ -31,7 +31,7 @@ chill_2.12/0.9.5//chill_2.12-0.9.5.jar
 commons-cli/1.2//commons-cli-1.2.jar
 commons-codec/1.15//commons-codec-1.15.jar
 commons-collections/3.2.2//commons-collections-3.2.2.jar
-commons-compiler/3.0.16//commons-compiler-3.0.16.jar
+commons-compiler/3.1.4//commons-compiler-3.1.4.jar
 commons-compress/1.20//commons-compress-1.20.jar
 commons-crypto/1.1.0//commons-crypto-1.1.0.jar
 commons-dbcp/1.4//commons-dbcp-1.4.jar
@@ -98,7 +98,7 @@ jakarta.servlet-api/4.0.3//jakarta.servlet-api-4.0.3.jar
 jakarta.validation-api/2.0.2//jakarta.validation-api-2.0.2.jar
 jakarta.ws.rs-api/2.1.6//jakarta.ws.rs-api-2.1.6.jar
 jakarta.xml.bind-api/2.3.2//jakarta.xml.bind-api-2.3.2.jar
-janino/3.0.16//janino-3.0.16.jar
+janino/3.1.4//janino-3.1.4.jar
 javassist/3.25.0-GA//javassist-3.25.0-GA.jar
 javax.jdo/3.2.0-m3//javax.jdo-3.2.0-m3.jar
 javolution/5.5.1//javolution-5.5.1.jar
diff --git a/pom.xml b/pom.xml
@@ -184,7 +184,7 @@
     <commons-pool2.version>2.6.2</commons-pool2.version>
     <datanucleus-core.version>4.1.17</datanucleus-core.version>
     <guava.version>14.0.1</guava.version>
-    <janino.version>3.0.16</janino.version>
+    <janino.version>3.1.4</janino.version>
     <jersey.version>2.34</jersey.version>
     <joda.version>2.10.5</joda.version>
     <jodd.version>3.5.2</jodd.version>
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala
@@ -27,8 +27,9 @@ import scala.util.control.NonFatal
 
 import com.google.common.cache.{CacheBuilder, CacheLoader}
 import com.google.common.util.concurrent.{ExecutionError, UncheckedExecutionException}
-import org.codehaus.commons.compiler.CompileException
-import org.codehaus.janino.{ByteArrayClassLoader, ClassBodyEvaluator, InternalCompilerException, SimpleCompiler}
+import org.codehaus.commons.compiler.{CompileException, InternalCompilerException}
+import org.codehaus.commons.compiler.util.reflect.ByteArrayClassLoader
+import org.codehaus.janino.{ClassBodyEvaluator, SimpleCompiler}
 import org.codehaus.janino.util.ClassFile
 
 import org.apache.spark.{TaskContext, TaskKilledException}
@@ -1434,9 +1435,10 @@ object CodeGenerator extends Logging {
   private def updateAndGetCompilationStats(evaluator: ClassBodyEvaluator): ByteCodeStats = {
     // First retrieve the generated classes.
     val classes = {
-      val resultField = classOf[SimpleCompiler].getDeclaredField("result")
-      resultField.setAccessible(true)
-      val loader = resultField.get(evaluator).asInstanceOf[ByteArrayClassLoader]
+      val scField = classOf[ClassBodyEvaluator].getDeclaredField("sc")
+      scField.setAccessible(true)
+      val compiler = scField.get(evaluator).asInstanceOf[SimpleCompiler]
+      val loader = compiler.getClassLoader.asInstanceOf[ByteArrayClassLoader]
       val classesField = loader.getClass.getDeclaredField("classes")
       classesField.setAccessible(true)
       classesField.get(loader).asInstanceOf[JavaMap[String, Array[Byte]]].asScala
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/errors/QueryExecutionErrors.scala
@@ -24,8 +24,7 @@ import java.time.{DateTimeException, LocalDate}
 import java.time.temporal.ChronoField
 
 import org.apache.hadoop.fs.{FileStatus, Path}
-import org.codehaus.commons.compiler.CompileException
-import org.codehaus.janino.InternalCompilerException
+import org.codehaus.commons.compiler.{CompileException, InternalCompilerException}
 
 import org.apache.spark.{Partition, SparkException, SparkUpgradeException}
 import org.apache.spark.executor.CommitDeniedException
