PHOENIX-1523 Make it easy to provide a tab literal as separator for C…

…SV imports(Sergey Soldatov)
apache · Mar 31, 2016 · 9e767ff · 9e767ff
1 parent b988050
commit 9e767ff
Show file tree

Hide file tree

Showing 3 changed files with 39 additions and 4 deletions.
diff --git a/phoenix-core/src/it/java/org/apache/phoenix/end2end/CsvBulkLoadToolIT.java b/phoenix-core/src/it/java/org/apache/phoenix/end2end/CsvBulkLoadToolIT.java
@@ -100,6 +100,38 @@ public void testBasicImport() throws Exception {
         stmt.close();
     }
 
+    @Test
+    public void testImportWithTabs() throws Exception {
+
+        Statement stmt = conn.createStatement();
+        stmt.execute("CREATE TABLE TABLE8 (ID INTEGER NOT NULL PRIMARY KEY, " +
+                "NAME1 VARCHAR, NAME2 VARCHAR)");
+
+        FileSystem fs = FileSystem.get(getUtility().getConfiguration());
+        FSDataOutputStream outputStream = fs.create(new Path("/tmp/input8.csv"));
+        PrintWriter printWriter = new PrintWriter(outputStream);
+        printWriter.println("1\tName 1a\tName 2a");
+        printWriter.println("2\tName 2a\tName 2b");
+        printWriter.close();
+
+        CsvBulkLoadTool csvBulkLoadTool = new CsvBulkLoadTool();
+        csvBulkLoadTool.setConf(getUtility().getConfiguration());
+        int exitCode = csvBulkLoadTool.run(new String[] {
+                "--input", "/tmp/input8.csv",
+                "--table", "table8",
+                "--zookeeper", zkQuorum,
+                "--delimiter", "\\t"});
+        assertEquals(0, exitCode);
+
+        ResultSet rs = stmt.executeQuery("SELECT id, name1, name2 FROM table8 ORDER BY id");
+        assertTrue(rs.next());
+        assertEquals(1, rs.getInt(1));
+        assertEquals("Name 1a", rs.getString(2));
+
+        rs.close();
+        stmt.close();
+    }
+
     @Test
     public void testFullOptionImport() throws Exception {
 

diff --git a/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/CsvBulkLoadTool.java b/phoenix-core/src/main/java/org/apache/phoenix/mapreduce/CsvBulkLoadTool.java
@@ -23,6 +23,7 @@
 import org.apache.commons.cli.CommandLine;
 import org.apache.commons.cli.Option;
 import org.apache.commons.cli.Options;
+import org.apache.commons.lang.StringEscapeUtils;
 import org.apache.hadoop.conf.Configuration;
 import org.apache.hadoop.mapreduce.Job;
 import org.apache.hadoop.util.ToolRunner;
@@ -54,7 +55,7 @@ protected void configureOptions(CommandLine cmdLine, List<ColumnInfo> importColu
 
         char delimiterChar = ',';
         if (cmdLine.hasOption(DELIMITER_OPT.getOpt())) {
-            String delimString = cmdLine.getOptionValue(DELIMITER_OPT.getOpt());
+            String delimString = StringEscapeUtils.unescapeJava(cmdLine.getOptionValue(DELIMITER_OPT.getOpt()));
             if (delimString.length() != 1) {
                 throw new IllegalArgumentException("Illegal delimiter character: " + delimString);
             }

diff --git a/phoenix-core/src/main/java/org/apache/phoenix/util/PhoenixRuntime.java b/phoenix-core/src/main/java/org/apache/phoenix/util/PhoenixRuntime.java
@@ -49,6 +49,7 @@
 import org.apache.commons.cli.Options;
 import org.apache.commons.cli.ParseException;
 import org.apache.commons.cli.PosixParser;
+import org.apache.commons.lang.StringEscapeUtils;
 import org.apache.hadoop.hbase.Cell;
 import org.apache.hadoop.hbase.KeyValue;
 import org.apache.hadoop.hbase.client.Mutation;
@@ -633,10 +634,11 @@ public static ExecutionCommand parseArgs(String[] args) {
         }
 
         private static char getCharacter(String s) {
-            if (s.length() > 1) {
-                throw new IllegalArgumentException("Invalid single character: '" + s + "'");
+            String unescaped = StringEscapeUtils.unescapeJava(s);
+            if (unescaped.length() > 1) {
+                throw new IllegalArgumentException("Invalid single character: '" + unescaped + "'");
             }
-            return s.charAt(0);
+            return unescaped.charAt(0);
         }
 
         private static void usageError(String errorMsg, Options options) {