feat: Define function signatures in CometFuzz (#2614)

Author: andygrove

fuzz-testing/README.md

@@ -61,7 +61,7 @@ Set appropriate values for `SPARK_HOME`, `SPARK_MASTER`, and `COMET_JAR` environ
 $SPARK_HOME/bin/spark-submit \
     --master $SPARK_MASTER \
     --class org.apache.comet.fuzz.Main \
-    target/comet-fuzz-spark3.4_2.12-0.7.0-SNAPSHOT-jar-with-dependencies.jar \
+    target/comet-fuzz-spark3.5_2.12-0.12.0-SNAPSHOT-jar-with-dependencies.jar \
     data --num-files=2 --num-rows=200 --exclude-negative-zero --generate-arrays --generate-structs --generate-maps
 ```
 
@@ -77,7 +77,7 @@ Generate random queries that are based on the available test files.
 $SPARK_HOME/bin/spark-submit \
     --master $SPARK_MASTER \
     --class org.apache.comet.fuzz.Main \
-    target/comet-fuzz-spark3.4_2.12-0.7.0-SNAPSHOT-jar-with-dependencies.jar \
+    target/comet-fuzz-spark3.5_2.12-0.12.0-SNAPSHOT-jar-with-dependencies.jar \
     queries --num-files=2 --num-queries=500
 ```
 
@@ -88,18 +88,17 @@ Note that the output filename is currently hard-coded as `queries.sql`
 ```shell
 $SPARK_HOME/bin/spark-submit \
     --master $SPARK_MASTER \
+    --conf spark.memory.offHeap.enabled=true \
+    --conf spark.memory.offHeap.size=16G \
     --conf spark.plugins=org.apache.spark.CometPlugin \
     --conf spark.comet.enabled=true \
-    --conf spark.comet.exec.enabled=true \
-    --conf spark.comet.exec.all.enabled=true \
     --conf spark.shuffle.manager=org.apache.spark.sql.comet.execution.shuffle.CometShuffleManager \
     --conf spark.comet.exec.shuffle.enabled=true \
-    --conf spark.comet.exec.shuffle.mode=auto \
     --jars $COMET_JAR \
     --conf spark.driver.extraClassPath=$COMET_JAR \
     --conf spark.executor.extraClassPath=$COMET_JAR \
     --class org.apache.comet.fuzz.Main \
-    target/comet-fuzz-spark3.4_2.12-0.7.0-SNAPSHOT-jar-with-dependencies.jar \
+    target/comet-fuzz-spark3.5_2.12-0.12.0-SNAPSHOT-jar-with-dependencies.jar \
     run --num-files=2 --filename=queries.sql
 ```
 

fuzz-testing/src/main/scala/org/apache/comet/fuzz/Main.scala

@@ -87,7 +87,11 @@ object Main {
             SchemaGenOptions(
               generateArray = conf.generateData.generateArrays(),
               generateStruct = conf.generateData.generateStructs(),
-              generateMap = conf.generateData.generateMaps()),
+              generateMap = conf.generateData.generateMaps(),
+              // create two columns of each primitive type so that they can be used in binary
+              // expressions such as `a + b` and `a <  b`
+              primitiveTypes = SchemaGenOptions.defaultPrimitiveTypes ++
+                SchemaGenOptions.defaultPrimitiveTypes),
             DataGenOptions(
               allowNull = true,
               generateNegativeZero = !conf.generateData.excludeNegativeZero()))