This is an automated email from the ASF dual-hosted git repository.
JingsongLi pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/paimon.git
The following commit(s) were added to refs/heads/master by this push:
new 023883e56e [e2e] Strip any trailing Spark error log from spark-sql
output before comparison (#9971)
023883e56e is described below
commit 023883e56e4dba77ec2b2c1a377d3971571b2278
Author: Eunbin Son <[email protected]>
AuthorDate: Sat Sep 19 23:02:53 2026 +0900
[e2e] Strip any trailing Spark error log from spark-sql output before
comparison (#9971)
---
.../apache/paimon/tests/SparkE2eOutputTest.java | 73 ++++++++++++++++++++++
.../java/org/apache/paimon/tests/SparkE2eTest.java | 36 +++++++----
2 files changed, 97 insertions(+), 12 deletions(-)
diff --git
a/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eOutputTest.java
b/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eOutputTest.java
new file mode 100644
index 0000000000..6bf2fcf94f
--- /dev/null
+++
b/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eOutputTest.java
@@ -0,0 +1,73 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.paimon.tests;
+
+import org.junit.jupiter.api.Test;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+/** Tests for {@link SparkE2eTest#stripTrailingSparkErrorLogs(String)}. Does
not need Docker. */
+public class SparkE2eOutputTest {
+
+ private static final String ROWS =
"1\t10\tHi\n2\t20\tHello\n3\t30\tTable\n";
+
+ private static final String COARSE_GRAINED_SCHEDULER_ERROR =
+ "26/07/29 04:25:43 ERROR Utils: Uncaught exception in thread
dispatcher-CoarseGrainedScheduler\n"
+ + "org.apache.spark.SparkException: Could not find
CoarseGrainedScheduler.\n"
+ + "\tat
org.apache.spark.rpc.netty.Dispatcher.postMessage(Dispatcher.scala:178)\n";
+
+ private static final String TRANSPORT_REQUEST_HANDLER_ERROR =
+ "26/08/30 07:28:25 ERROR TransportRequestHandler: Error while
invoking RpcHandler#receive() for one-way message.\n"
+ + "org.apache.spark.SparkException: Could not find
AppClient.\n"
+ + "\tat
org.apache.spark.rpc.netty.Dispatcher.postMessage(Dispatcher.scala:178)\n"
+ + "\tat java.lang.Thread.run(Thread.java:748)\n";
+
+ @Test
+ public void testNoErrorLogIsUnchanged() {
+
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(ROWS)).isEqualTo(ROWS);
+ }
+
+ @Test
+ public void testStripsCoarseGrainedSchedulerError() {
+ assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(ROWS +
COARSE_GRAINED_SCHEDULER_ERROR))
+ .isEqualTo(ROWS);
+ }
+
+ @Test
+ public void testStripsRepeatedTransportRequestHandlerErrors() {
+ assertThat(
+ SparkE2eTest.stripTrailingSparkErrorLogs(
+ ROWS
+ + TRANSPORT_REQUEST_HANDLER_ERROR
+ + TRANSPORT_REQUEST_HANDLER_ERROR))
+ .isEqualTo(ROWS);
+ }
+
+ @Test
+ public void testErrorOnFirstLineYieldsEmptyOutput() {
+
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(TRANSPORT_REQUEST_HANDLER_ERROR))
+ .isEmpty();
+ }
+
+ @Test
+ public void testErrorWordInsideResultRowIsKept() {
+ String rows = "1\t10\tsome ERROR text\n2\t20\tERROR Foo\n";
+
assertThat(SparkE2eTest.stripTrailingSparkErrorLogs(rows)).isEqualTo(rows);
+ }
+}
diff --git
a/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eTest.java
b/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eTest.java
index e78b82e607..ad2e577041 100644
--- a/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eTest.java
+++ b/paimon-e2e-tests/src/test/java/org/apache/paimon/tests/SparkE2eTest.java
@@ -18,6 +18,8 @@
package org.apache.paimon.tests;
+import org.apache.paimon.annotation.VisibleForTesting;
+
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.condition.DisabledOnJre;
import org.slf4j.Logger;
@@ -27,6 +29,8 @@ import org.testcontainers.containers.ContainerState;
import java.util.Arrays;
import java.util.UUID;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
import java.util.stream.Collectors;
import static org.junit.jupiter.api.condition.JRE.JAVA_11;
@@ -36,8 +40,14 @@ import static org.junit.jupiter.api.condition.JRE.JAVA_11;
public class SparkE2eTest extends E2eReaderTestBase {
private static final Logger LOG =
LoggerFactory.getLogger(SparkE2eTest.class);
- private static final String COARSE_GRAINED_SCHEDULER_SHUTDOWN_ERROR =
- "ERROR Utils: Uncaught exception in thread
dispatcher-CoarseGrainedScheduler";
+
+ /**
+ * Start of a Spark ERROR log line in the default log4j2 pattern ({@code
%d{yy/MM/dd HH:mm:ss}
+ * %p %c{1}: %m%n%ex}), which spark-sql writes to stdout. Anchoring on the
timestamp prefix
+ * avoids matching an "ERROR" word inside a result row.
+ */
+ private static final Pattern SPARK_ERROR_LOG_LINE =
+ Pattern.compile("(?m)^\\d{2}/\\d{2}/\\d{2} \\d{2}:\\d{2}:\\d{2}
ERROR ");
public SparkE2eTest() {
super(false, false, true);
@@ -77,8 +87,7 @@ public class SparkE2eTest extends E2eReaderTestBase {
LOG.info(execResult.getStderr());
throw new AssertionError("Failed when running spark
sql.");
}
- String stdout =
-
stripCoarseGrainedSchedulerShutdownError(execResult.getStdout());
+ String stdout =
stripTrailingSparkErrorLogs(execResult.getStdout());
return Arrays.stream(stdout.split("\n"))
.filter(s -> !s.contains("WARN"))
.collect(Collectors.joining("\n"))
@@ -86,14 +95,17 @@ public class SparkE2eTest extends E2eReaderTestBase {
});
}
- private static String stripCoarseGrainedSchedulerShutdownError(String
stdout) {
- int errorIndex =
stdout.indexOf(COARSE_GRAINED_SCHEDULER_SHUTDOWN_ERROR);
- if (errorIndex < 0) {
- return stdout;
- }
-
- int errorLineStart = stdout.lastIndexOf('\n', errorIndex);
- return errorLineStart < 0 ? "" : stdout.substring(0, errorLineStart);
+ /**
+ * Drops everything from the first Spark ERROR log line onwards. When
spark-sql exits, the
+ * driver shutdown races with RPC dispatch and may log after the query
result, with exit code 0,
+ * e.g. {@code ERROR Utils: Uncaught exception in thread
dispatcher-CoarseGrainedScheduler} or
+ * {@code ERROR TransportRequestHandler: Error while invoking
RpcHandler#receive() for one-way
+ * message.} followed by a stack trace.
+ */
+ @VisibleForTesting
+ static String stripTrailingSparkErrorLogs(String stdout) {
+ Matcher matcher = SPARK_ERROR_LOG_LINE.matcher(stdout);
+ return matcher.find() ? stdout.substring(0, matcher.start()) : stdout;
}
private ContainerState getSpark() {
