SQOOP-1429: Fix native characters usage for SqlServer object names

(Venkat Ranganathan via Jarek Jarcec Cecho)

src/java/org/apache/sqoop/manager/SQLServerManager.java

@@ -38,6 +38,7 @@
 import com.cloudera.sqoop.mapreduce.JdbcUpdateExportJob;
 import com.cloudera.sqoop.util.ExportException;
 import com.cloudera.sqoop.util.ImportException;
+
 import org.apache.sqoop.cli.RelatedOptions;
 import org.apache.sqoop.mapreduce.sqlserver.SqlServerExportBatchOutputFormat;
 import org.apache.sqoop.mapreduce.sqlserver.SqlServerInputFormat;
@@ -226,14 +227,30 @@ protected String getSchemaQuery() {
 
     return "'" + schema + "'";
   }
-
   @Override
   protected String getListColumnsQuery(String tableName) {
     return
-      super.getListColumnsQuery(tableName)
+      "SELECT COLUMN_NAME FROM INFORMATION_SCHEMA.COLUMNS "
+    + "WHERE TABLE_SCHEMA = (" + getSchemaQuery() + ") "
+    + "  AND TABLE_NAME = N'" + tableName + "' "
     + "  ORDER BY ORDINAL_POSITION";
   }
 
+  @Override
+  protected String getPrimaryKeyQuery(String tableName) {
+    return
+      "SELECT kcu.COLUMN_NAME FROM INFORMATION_SCHEMA.TABLE_CONSTRAINTS tc, "
+    + "  INFORMATION_SCHEMA.KEY_COLUMN_USAGE kcu "
+    + "WHERE tc.TABLE_SCHEMA = kcu.TABLE_SCHEMA "
+    + "  AND tc.TABLE_NAME = kcu.TABLE_NAME "
+    + "  AND tc.CONSTRAINT_SCHEMA = kcu.CONSTRAINT_SCHEMA "
+    + "  AND tc.CONSTRAINT_NAME = kcu.CONSTRAINT_NAME "
+    + "  AND tc.TABLE_SCHEMA = (" + getSchemaQuery() + ") "
+    + "  AND tc.TABLE_NAME = N'" + tableName + "' "
+    + "  AND tc.CONSTRAINT_TYPE = 'PRIMARY KEY'";
+  }
+
+
   @Override
   public String escapeColName(String colName) {
     return escapeObjectName(colName);

src/java/org/apache/sqoop/mapreduce/db/DataDrivenDBInputFormat.java

@@ -97,10 +97,12 @@ protected DBSplitter getSplitter(int sqlDataType) {
     case Types.DOUBLE:
       return new FloatSplitter();
 
-    case Types.CHAR:
-    case Types.NCHAR:
-    case Types.VARCHAR:
     case Types.NVARCHAR:
+    case Types.NCHAR:
+      return new NTextSplitter();
+
+    case Types.CHAR:
+    case Types.VARCHAR:
     case Types.LONGVARCHAR:
       return new TextSplitter();
 

src/java/org/apache/sqoop/mapreduce/db/NTextSplitter.java

@@ -0,0 +1,28 @@
+/**
+ * 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;
+
+/**
+ * Implement DBSplitter over native text strings.
+ */
+public class NTextSplitter extends TextSplitter {
+
+  public NTextSplitter() {
+    setUseNCharStrings(true);
+  }
+}

src/java/org/apache/sqoop/mapreduce/db/TextSplitter.java

@@ -39,6 +39,8 @@ public class TextSplitter extends BigDecimalSplitter {
 
   private static final Log LOG = LogFactory.getLog(TextSplitter.class);
 
+  private boolean useNCharStrings = false;
+
   /**
    * This method needs to determine the splits between two user-provided
    * strings.  In the case where the user's strings are 'A' and 'Z', this is
@@ -90,8 +92,8 @@ public List<InputSplit> split(Configuration conf, ResultSet results,
     // divide cleanly.
     int numSplits = ConfigurationHelper.getConfNumMaps(conf);
 
-    String lowClausePrefix = colName + " >= '";
-    String highClausePrefix = colName + " < '";
+    String lowClausePrefix = colName + " >= " + (useNCharStrings ? "N'" : "'");
+    String highClausePrefix = colName + " < " + (useNCharStrings ? "N'" : "'");
 
     // If there is a common prefix between minString and maxString, establish
     // it and pull it out of minString and maxString.
@@ -123,7 +125,8 @@ public List<InputSplit> split(Configuration conf, ResultSet results,
       if (i == splitStrings.size() - 1) {
         // This is the last one; use a closed interval.
         splits.add(new DataDrivenDBInputFormat.DataDrivenDBInputSplit(
-            lowClausePrefix + start + "'", colName + " <= '" + end + "'"));
+            lowClausePrefix + start + "'", colName
+            + " <= " + (useNCharStrings ? "N'" : "'") + end + "'"));
       } else {
         // Normal open-interval case.
         splits.add(new DataDrivenDBInputFormat.DataDrivenDBInputSplit(
@@ -225,4 +228,12 @@ public String bigDecimalToString(BigDecimal bd) {
 
     return sb.toString();
   }
+
+  public void setUseNCharStrings(boolean use) {
+    useNCharStrings = use;
+  }
+
+  public boolean isUseNCharStrings() {
+    return useNCharStrings;
+  }
 }

src/test/org/apache/sqoop/mapreduce/db/TestTextSplitter.java

@@ -134,4 +134,13 @@ public void testCommonPrefix() throws SQLException {
     assertEquals("Hardy", splits.get(splits.size() -1));
     assertEquals(6, splits.size());
   }
+
+  public void testNChar() throws SQLException {
+    // Splits between 'Hand' and 'Hardy'
+    NTextSplitter splitter = new NTextSplitter();
+    assertEquals(true, splitter.isUseNCharStrings());
+    TextSplitter splitter2 = new TextSplitter();
+    assertEquals(false, splitter2.isUseNCharStrings());
+  }
+
 }