Github user andrewor14 commented on a diff in the pull request:
https://github.com/apache/spark/pull/3916#discussion_r25305725
--- Diff:
launcher/src/main/java/org/apache/spark/launcher/SparkSubmitCommandBuilder.java
---
@@ -0,0 +1,335 @@
+/*
+ * 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.spark.launcher;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+
+import static org.apache.spark.launcher.CommandBuilderUtils.*;
+
+/**
+ * Special launcher for handling a CLI invocation of SparkSubmit.
+ * <p/>
+ * This launcher extends SparkLauncher to add command line parsing
compatible with
+ * SparkSubmit. It handles setting driver-side options and special parsing
needed
+ * for the different specialClasses.
+ * <p/>
+ * This class has also some special features to aid PySparkLauncher.
+ */
+class SparkSubmitCommandBuilder extends AbstractCommandBuilder {
+
+ /**
+ * Name of the app resource used to identify the PySpark shell. The
command line parser expects
+ * the resource name to be the very first argument to spark-submit in
this case.
+ *
+ * NOTE: this cannot be "pyspark-shell" since that identifies the
PySpark shell to SparkSubmit
+ * (see java_gateway.py), and can cause this code to enter into an
infinite loop.
+ */
+ static final String PYSPARK_SHELL = "pyspark-shell-main";
+
+ /**
+ * This is the actual resource name that identifies the PySpark shell to
SparkSubmit.
+ */
+ static final String PYSPARK_SHELL_RESOURCE = "pyspark-shell";
+
+ /**
+ * This map must match the class names for available special classes,
since this modifies the way
+ * command line parsing works. This maps the class name to the resource
to use when calling
+ * spark-submit.
+ */
+ private static final Map<String, String> specialClasses = new
HashMap<String, String>();
+ static {
+ specialClasses.put("org.apache.spark.repl.Main", "spark-shell");
+
specialClasses.put("org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver",
+ "spark-internal");
+ }
+
+ private final List<String> sparkArgs;
+ private boolean hasMixedArguments;
+
+ SparkSubmitCommandBuilder() {
+ this.sparkArgs = new ArrayList<String>();
+ }
+
+ SparkSubmitCommandBuilder(List<String> args) {
+ this(false, args);
+ }
+
+ SparkSubmitCommandBuilder(boolean hasMixedArguments, List<String> args) {
--- End diff --
I don't really see how `hasMixedArguments` should be a constructor
argument. Shouldn't we only allow mixing arguments for special classes like the
spark REPL or the hive thrift server? When else do we want to mix arguments?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
