SQOOP-2910: Add capability to Sqoop to require an explicit option to be specified with --split-by for a String column
(Attila Szabo via Jarek Jarcec Cecho)
diff --git a/src/java/org/apache/sqoop/mapreduce/db/TextSplitter.java b/src/java/org/apache/sqoop/mapreduce/db/TextSplitter.java
index 9896d95..8c98d14 100644
--- a/src/java/org/apache/sqoop/mapreduce/db/TextSplitter.java
+++ b/src/java/org/apache/sqoop/mapreduce/db/TextSplitter.java
@@ -38,6 +38,8 @@
*/
public class TextSplitter extends BigDecimalSplitter {
+ public static final String ALLOW_TEXT_SPLITTER_PROPERTY = "org.apache.sqoop.splitter.allow_text_splitter";
+
private static final Log LOG = LogFactory.getLog(TextSplitter.class);
private boolean useNCharStrings = false;
@@ -61,6 +63,10 @@
*/
public List<InputSplit> split(Configuration conf, ResultSet results,
String colName) throws SQLException, ValidationException {
+ if (!conf.getBoolean(ALLOW_TEXT_SPLITTER_PROPERTY, false)) {
+ throw new ValidationException("Generating splits for a textual index column " + "allowed only in case of \"-D"
+ + ALLOW_TEXT_SPLITTER_PROPERTY + "=true\" property " + "passed as a parameter");
+ }
LOG.warn("Generating splits for a textual index column.");
LOG.warn("If your database sorts in a case-insensitive order, "
diff --git a/src/test/org/apache/sqoop/mapreduce/db/TextSplitterHadoopConfIntegrationTest.java b/src/test/org/apache/sqoop/mapreduce/db/TextSplitterHadoopConfIntegrationTest.java
new file mode 100644
index 0000000..043130e
--- /dev/null
+++ b/src/test/org/apache/sqoop/mapreduce/db/TextSplitterHadoopConfIntegrationTest.java
@@ -0,0 +1,59 @@
+/**
+ * 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.sqoop.mapreduce.db;
+
+import java.sql.ResultSet;
+import java.util.List;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.sqoop.validation.ValidationException;
+
+import com.cloudera.sqoop.Sqoop;
+import com.cloudera.sqoop.testutil.MockResultSet;
+
+import junit.framework.TestCase;
+
+public class TextSplitterHadoopConfIntegrationTest extends TestCase {
+ private static final String TEXT_COL_NAME = "text_col_name";
+
+ public void testDefaultValueOfUnsetBooleanParam() throws Exception {
+ Configuration conf = Job.getInstance().getConfiguration();
+ TextSplitter splitter = new TextSplitter();
+ ResultSet rs = new MockResultSet();
+ try {
+ splitter.split(conf, rs, TEXT_COL_NAME);
+ fail();
+ } catch (ValidationException e) {
+ // expected to throw ValidationException with the a message about the
+ // "i-know-what-i-am-doing" prop
+ assertTrue(e.getMessage().contains(TextSplitter.ALLOW_TEXT_SPLITTER_PROPERTY));
+ }
+ }
+
+ public void testBooleanParamValue() throws Exception {
+ Configuration conf = Job.getInstance().getConfiguration();
+ conf.set(TextSplitter.ALLOW_TEXT_SPLITTER_PROPERTY, "true");
+ TextSplitter splitter = new TextSplitter();
+ ResultSet rs = new MockResultSet();
+ List<InputSplit> splits = splitter.split(conf, rs, TEXT_COL_NAME);
+ assertFalse(splits.isEmpty());
+ }
+}
+
