From 157840d1b14502a4f25cff53633c927998c6ada1 Mon Sep 17 00:00:00 2001
From: Hossein <hossein@databricks.com>
Date: Thu, 30 Jul 2015 16:16:17 -0700
Subject: [SPARK-8742] [SPARKR] Improve SparkR error messages for DataFrame API

This patch improves SparkR error message reporting, especially with DataFrame API. When there is a user error (e.g., malformed SQL query), the message of the cause is sent back through the RPC and the R client reads it and returns it back to user.

cc shivaram

Author: Hossein <hossein@databricks.com>

Closes #7742 from falaki/SPARK-8742 and squashes the following commits:

4f643c9 [Hossein] Not logging exceptions in RBackendHandler
4a8005c [Hossein] Returning stack track of causing exception from RBackendHandler
5cf17f0 [Hossein] Adding unit test for error messages from SQLContext
2af75d5 [Hossein] Reading error message in case of failure and stoping with that message
f479c99 [Hossein] Wrting exception cause message in JVM
---
 R/pkg/R/backend.R                                              |  4 +++-
 R/pkg/inst/tests/test_sparkSQL.R                               |  5 +++++
 .../main/scala/org/apache/spark/api/r/RBackendHandler.scala    | 10 ++++++++--
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/R/pkg/R/backend.R b/R/pkg/R/backend.R
index 2fb6fae55f..49162838b8 100644
--- a/R/pkg/R/backend.R
+++ b/R/pkg/R/backend.R
@@ -110,6 +110,8 @@ invokeJava <- function(isStatic, objId, methodName, ...) {
 
   # TODO: check the status code to output error information
   returnStatus <- readInt(conn)
-  stopifnot(returnStatus == 0)
+  if (returnStatus != 0) {
+    stop(readString(conn))
+  }
   readObject(conn)
 }
diff --git a/R/pkg/inst/tests/test_sparkSQL.R b/R/pkg/inst/tests/test_sparkSQL.R
index d5db97248c..61c8a7ec7d 100644
--- a/R/pkg/inst/tests/test_sparkSQL.R
+++ b/R/pkg/inst/tests/test_sparkSQL.R
@@ -1002,6 +1002,11 @@ test_that("crosstab() on a DataFrame", {
   expect_identical(expected, ordered)
 })
 
+test_that("SQL error message is returned from JVM", {
+  retError <- tryCatch(sql(sqlContext, "select * from blah"), error = function(e) e)
+  expect_equal(grepl("Table Not Found: blah", retError), TRUE)
+})
+
 unlink(parquetPath)
 unlink(jsonPath)
 unlink(jsonPathNa)
diff --git a/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala b/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala
index a5de10fe89..14dac4ed28 100644
--- a/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala
+++ b/core/src/main/scala/org/apache/spark/api/r/RBackendHandler.scala
@@ -69,8 +69,11 @@ private[r] class RBackendHandler(server: RBackend)
             case e: Exception =>
               logError(s"Removing $objId failed", e)
               writeInt(dos, -1)
+              writeString(dos, s"Removing $objId failed: ${e.getMessage}")
           }
-        case _ => dos.writeInt(-1)
+        case _ =>
+          dos.writeInt(-1)
+          writeString(dos, s"Error: unknown method $methodName")
       }
     } else {
       handleMethodCall(isStatic, objId, methodName, numArgs, dis, dos)
@@ -146,8 +149,11 @@ private[r] class RBackendHandler(server: RBackend)
       }
     } catch {
       case e: Exception =>
-        logError(s"$methodName on $objId failed", e)
+        logError(s"$methodName on $objId failed")
         writeInt(dos, -1)
+        // Writing the error message of the cause for the exception. This will be returned
+        // to user in the R process.
+        writeString(dos, Utils.exceptionString(e.getCause))
     }
   }
 
-- 
cgit v1.2.3