Initial commit

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala

@@ -1177,8 +1177,7 @@ class CodegenContext {
     // be extremely expensive in certain cases, such as deeply-nested expressions which operate over
     // inputs with wide schemas. For more details on the performance issues that motivated this
     // flat, see SPARK-15680.
-    if (force ||
-      SparkEnv.get != null && SparkEnv.get.conf.getBoolean("spark.sql.codegen.comments", false)) {
+    if (force || SQLConf.get.codegenComments) {
       val name = if (placeholderId != "") {
         assert(!placeHolderToComments.contains(placeholderId))
         placeholderId

sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala

@@ -751,6 +751,19 @@ object SQLConf {
     .booleanConf
     .createWithDefault(true)
 
+  val MAX_CASES_BRANCHES = buildConf("spark.sql.codegen.maxCaseBranches")
+    .internal()
+    .doc("The maximum number of switches supported with codegen.")
+    .intConf
+    .createWithDefault(20)
+
+  val CODEGEN_COMMENTS = buildConf("spark.sql.codegen.comments")
+    .internal()
+    .doc("When true, put comment in the generated code. Since computing huge comments " +
+      "can be extremely expensive in certain cases, default is false.")
+    .booleanConf
+    .createWithDefault(false)
+
   val CODEGEN_LOGGING_MAX_LINES = buildConf("spark.sql.codegen.logging.maxLines")
     .internal()
     .doc("The maximum number of codegen lines to log when errors occur. Use -1 for unlimited.")
@@ -1539,6 +1552,10 @@ class SQLConf extends Serializable with Logging {
 
   def codegenFallback: Boolean = getConf(CODEGEN_FALLBACK)
 
+  def maxCaseBranchesForCodegen: Int = getConf(MAX_CASES_BRANCHES)
+
+  def codegenComments: Boolean = getConf(CODEGEN_COMMENTS)
+
   def loggingMaxLinesForCodegen: Int = getConf(CODEGEN_LOGGING_MAX_LINES)
 
   def hugeMethodLimit: Int = getConf(WHOLESTAGE_HUGE_METHOD_LIMIT)

sql/core/src/test/scala/org/apache/spark/sql/execution/debug/DebuggingSuite.scala

@@ -48,4 +48,20 @@ class DebuggingSuite extends SparkFunSuite with SharedSQLContext {
     assert(res.forall{ case (subtree, code) =>
       subtree.contains("Range") && code.contains("Object[]")})
   }
+
+  test("check to generate comment") {
+    withSQLConf("spark.sql.codegen.comments" -> "false") {
+      val res = codegenStringSeq(spark.range(10).groupBy("id").count().queryExecution.executedPlan)
+      assert(res.length == 2)
+      assert(res.forall{ case (_, code) =>
+        !code.contains("* Codegend pipeline") && !code.contains("// input[")})
+    }
+
+    withSQLConf("spark.sql.codegen.comments" -> "true") {
+      val res = codegenStringSeq(spark.range(10).groupBy("id").count().queryExecution.executedPlan)
+      assert(res.length == 2)
+      assert(res.forall{ case (_, code) =>
+        code.contains("* Codegend pipeline") && code.contains("// input[")})
+    }
+  }
 }