You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hbase.apache.org by mi...@apache.org on 2016/02/06 02:34:16 UTC

[05/17] hbase-site git commit: Published site at 9c832109458ced70d0db701e7f58ef41b1df0fc7.

http://git-wip-us.apache.org/repos/asf/hbase-site/blob/9bc06f81/testdevapidocs/src-html/org/apache/hadoop/hbase/mapreduce/TestImportTsv.html
----------------------------------------------------------------------
diff --git a/testdevapidocs/src-html/org/apache/hadoop/hbase/mapreduce/TestImportTsv.html b/testdevapidocs/src-html/org/apache/hadoop/hbase/mapreduce/TestImportTsv.html
index 4d1025b..ead7bbb 100644
--- a/testdevapidocs/src-html/org/apache/hadoop/hbase/mapreduce/TestImportTsv.html
+++ b/testdevapidocs/src-html/org/apache/hadoop/hbase/mapreduce/TestImportTsv.html
@@ -371,199 +371,212 @@
 <span class="sourceLineNo">363</span>    doMROnTableTest(util, tn, FAMILY, data, args, 1, 4);<a name="line.363"></a>
 <span class="sourceLineNo">364</span>    util.deleteTable(tn);<a name="line.364"></a>
 <span class="sourceLineNo">365</span>  }<a name="line.365"></a>
-<span class="sourceLineNo">366</span><a name="line.366"></a>
-<span class="sourceLineNo">367</span>  private Tool doMROnTableTest(String data, int valueMultiplier) throws Exception {<a name="line.367"></a>
-<span class="sourceLineNo">368</span>    return doMROnTableTest(util, tn, FAMILY, data, args, valueMultiplier,-1);<a name="line.368"></a>
-<span class="sourceLineNo">369</span>  }<a name="line.369"></a>
-<span class="sourceLineNo">370</span><a name="line.370"></a>
-<span class="sourceLineNo">371</span>  protected static Tool doMROnTableTest(HBaseTestingUtility util, TableName table,<a name="line.371"></a>
-<span class="sourceLineNo">372</span>      String family, String data, Map&lt;String, String&gt; args) throws Exception {<a name="line.372"></a>
-<span class="sourceLineNo">373</span>    return doMROnTableTest(util, table, family, data, args, 1,-1);<a name="line.373"></a>
-<span class="sourceLineNo">374</span>  }<a name="line.374"></a>
-<span class="sourceLineNo">375</span><a name="line.375"></a>
-<span class="sourceLineNo">376</span>  /**<a name="line.376"></a>
-<span class="sourceLineNo">377</span>   * Run an ImportTsv job and perform basic validation on the results.<a name="line.377"></a>
-<span class="sourceLineNo">378</span>   * Returns the ImportTsv &lt;code&gt;Tool&lt;/code&gt; instance so that other tests can<a name="line.378"></a>
-<span class="sourceLineNo">379</span>   * inspect it for further validation as necessary. This method is static to<a name="line.379"></a>
-<span class="sourceLineNo">380</span>   * insure non-reliance on instance's util/conf facilities.<a name="line.380"></a>
-<span class="sourceLineNo">381</span>   * @param args Any arguments to pass BEFORE inputFile path is appended.<a name="line.381"></a>
-<span class="sourceLineNo">382</span>   * @return The Tool instance used to run the test.<a name="line.382"></a>
-<span class="sourceLineNo">383</span>   */<a name="line.383"></a>
+<span class="sourceLineNo">366</span>  <a name="line.366"></a>
+<span class="sourceLineNo">367</span>  @Test<a name="line.367"></a>
+<span class="sourceLineNo">368</span>  public void testSkipEmptyColumns() throws Exception {<a name="line.368"></a>
+<span class="sourceLineNo">369</span>    Path bulkOutputPath = new Path(util.getDataTestDirOnTestFS(tn.getNameAsString()), "hfiles");<a name="line.369"></a>
+<span class="sourceLineNo">370</span>    args.put(ImportTsv.BULK_OUTPUT_CONF_KEY, bulkOutputPath.toString());<a name="line.370"></a>
+<span class="sourceLineNo">371</span>    args.put(ImportTsv.COLUMNS_CONF_KEY, "HBASE_ROW_KEY,HBASE_TS_KEY,FAM:A,FAM:B");<a name="line.371"></a>
+<span class="sourceLineNo">372</span>    args.put(ImportTsv.SEPARATOR_CONF_KEY, ",");<a name="line.372"></a>
+<span class="sourceLineNo">373</span>    args.put(ImportTsv.SKIP_EMPTY_COLUMNS, "true");<a name="line.373"></a>
+<span class="sourceLineNo">374</span>    // 2 Rows of data as input. Both rows are valid and only 3 columns are no-empty among 4<a name="line.374"></a>
+<span class="sourceLineNo">375</span>    String data = "KEY,1234,VALUE1,VALUE2\nKEY,1235,,VALUE2\n";<a name="line.375"></a>
+<span class="sourceLineNo">376</span>    doMROnTableTest(util, tn, FAMILY, data, args, 1, 3);<a name="line.376"></a>
+<span class="sourceLineNo">377</span>    util.deleteTable(tn);<a name="line.377"></a>
+<span class="sourceLineNo">378</span>  }<a name="line.378"></a>
+<span class="sourceLineNo">379</span><a name="line.379"></a>
+<span class="sourceLineNo">380</span>  private Tool doMROnTableTest(String data, int valueMultiplier) throws Exception {<a name="line.380"></a>
+<span class="sourceLineNo">381</span>    return doMROnTableTest(util, tn, FAMILY, data, args, valueMultiplier,-1);<a name="line.381"></a>
+<span class="sourceLineNo">382</span>  }<a name="line.382"></a>
+<span class="sourceLineNo">383</span><a name="line.383"></a>
 <span class="sourceLineNo">384</span>  protected static Tool doMROnTableTest(HBaseTestingUtility util, TableName table,<a name="line.384"></a>
-<span class="sourceLineNo">385</span>      String family, String data, Map&lt;String, String&gt; args, int valueMultiplier,int expectedKVCount)<a name="line.385"></a>
-<span class="sourceLineNo">386</span>  throws Exception {<a name="line.386"></a>
-<span class="sourceLineNo">387</span>    Configuration conf = new Configuration(util.getConfiguration());<a name="line.387"></a>
+<span class="sourceLineNo">385</span>      String family, String data, Map&lt;String, String&gt; args) throws Exception {<a name="line.385"></a>
+<span class="sourceLineNo">386</span>    return doMROnTableTest(util, table, family, data, args, 1,-1);<a name="line.386"></a>
+<span class="sourceLineNo">387</span>  }<a name="line.387"></a>
 <span class="sourceLineNo">388</span><a name="line.388"></a>
-<span class="sourceLineNo">389</span>    // populate input file<a name="line.389"></a>
-<span class="sourceLineNo">390</span>    FileSystem fs = FileSystem.get(conf);<a name="line.390"></a>
-<span class="sourceLineNo">391</span>    Path inputPath = fs.makeQualified(<a name="line.391"></a>
-<span class="sourceLineNo">392</span>            new Path(util.getDataTestDirOnTestFS(table.getNameAsString()), "input.dat"));<a name="line.392"></a>
-<span class="sourceLineNo">393</span>    FSDataOutputStream op = fs.create(inputPath, true);<a name="line.393"></a>
-<span class="sourceLineNo">394</span>    if (data == null) {<a name="line.394"></a>
-<span class="sourceLineNo">395</span>      data = "KEY\u001bVALUE1\u001bVALUE2\n";<a name="line.395"></a>
-<span class="sourceLineNo">396</span>    }<a name="line.396"></a>
-<span class="sourceLineNo">397</span>    op.write(Bytes.toBytes(data));<a name="line.397"></a>
-<span class="sourceLineNo">398</span>    op.close();<a name="line.398"></a>
-<span class="sourceLineNo">399</span>    LOG.debug(String.format("Wrote test data to file: %s", inputPath));<a name="line.399"></a>
-<span class="sourceLineNo">400</span><a name="line.400"></a>
-<span class="sourceLineNo">401</span>    if (conf.getBoolean(FORCE_COMBINER_CONF, true)) {<a name="line.401"></a>
-<span class="sourceLineNo">402</span>      LOG.debug("Forcing combiner.");<a name="line.402"></a>
-<span class="sourceLineNo">403</span>      conf.setInt("mapreduce.map.combine.minspills", 1);<a name="line.403"></a>
-<span class="sourceLineNo">404</span>    }<a name="line.404"></a>
-<span class="sourceLineNo">405</span><a name="line.405"></a>
-<span class="sourceLineNo">406</span>    // Build args array.<a name="line.406"></a>
-<span class="sourceLineNo">407</span>    String[] argsArray = new String[args.size() + 2];<a name="line.407"></a>
-<span class="sourceLineNo">408</span>    Iterator it = args.entrySet().iterator();<a name="line.408"></a>
-<span class="sourceLineNo">409</span>    int i = 0;<a name="line.409"></a>
-<span class="sourceLineNo">410</span>    while (it.hasNext()) {<a name="line.410"></a>
-<span class="sourceLineNo">411</span>      Map.Entry pair = (Map.Entry) it.next();<a name="line.411"></a>
-<span class="sourceLineNo">412</span>      argsArray[i] = "-D" + pair.getKey() + "=" + pair.getValue();<a name="line.412"></a>
-<span class="sourceLineNo">413</span>      i++;<a name="line.413"></a>
-<span class="sourceLineNo">414</span>    }<a name="line.414"></a>
-<span class="sourceLineNo">415</span>    argsArray[i] = table.getNameAsString();<a name="line.415"></a>
-<span class="sourceLineNo">416</span>    argsArray[i + 1] = inputPath.toString();<a name="line.416"></a>
-<span class="sourceLineNo">417</span><a name="line.417"></a>
-<span class="sourceLineNo">418</span>    // run the import<a name="line.418"></a>
-<span class="sourceLineNo">419</span>    Tool tool = new ImportTsv();<a name="line.419"></a>
-<span class="sourceLineNo">420</span>    LOG.debug("Running ImportTsv with arguments: " + argsArray);<a name="line.420"></a>
-<span class="sourceLineNo">421</span>    assertEquals(0, ToolRunner.run(conf, tool, argsArray));<a name="line.421"></a>
-<span class="sourceLineNo">422</span><a name="line.422"></a>
-<span class="sourceLineNo">423</span>    // Perform basic validation. If the input args did not include<a name="line.423"></a>
-<span class="sourceLineNo">424</span>    // ImportTsv.BULK_OUTPUT_CONF_KEY then validate data in the table.<a name="line.424"></a>
-<span class="sourceLineNo">425</span>    // Otherwise, validate presence of hfiles.<a name="line.425"></a>
-<span class="sourceLineNo">426</span>    boolean isDryRun = args.containsKey(ImportTsv.DRY_RUN_CONF_KEY) &amp;&amp;<a name="line.426"></a>
-<span class="sourceLineNo">427</span>        "true".equalsIgnoreCase(args.get(ImportTsv.DRY_RUN_CONF_KEY));<a name="line.427"></a>
-<span class="sourceLineNo">428</span>    if (args.containsKey(ImportTsv.BULK_OUTPUT_CONF_KEY)) {<a name="line.428"></a>
-<span class="sourceLineNo">429</span>      if (isDryRun) {<a name="line.429"></a>
-<span class="sourceLineNo">430</span>        assertFalse(String.format("Dry run mode, %s should not have been created.",<a name="line.430"></a>
-<span class="sourceLineNo">431</span>                 ImportTsv.BULK_OUTPUT_CONF_KEY),<a name="line.431"></a>
-<span class="sourceLineNo">432</span>            fs.exists(new Path(ImportTsv.BULK_OUTPUT_CONF_KEY)));<a name="line.432"></a>
-<span class="sourceLineNo">433</span>      } else {<a name="line.433"></a>
-<span class="sourceLineNo">434</span>        validateHFiles(fs, args.get(ImportTsv.BULK_OUTPUT_CONF_KEY), family,expectedKVCount);<a name="line.434"></a>
-<span class="sourceLineNo">435</span>      }<a name="line.435"></a>
-<span class="sourceLineNo">436</span>    } else {<a name="line.436"></a>
-<span class="sourceLineNo">437</span>      validateTable(conf, table, family, valueMultiplier, isDryRun);<a name="line.437"></a>
-<span class="sourceLineNo">438</span>    }<a name="line.438"></a>
-<span class="sourceLineNo">439</span><a name="line.439"></a>
-<span class="sourceLineNo">440</span>    if (conf.getBoolean(DELETE_AFTER_LOAD_CONF, true)) {<a name="line.440"></a>
-<span class="sourceLineNo">441</span>      LOG.debug("Deleting test subdirectory");<a name="line.441"></a>
-<span class="sourceLineNo">442</span>      util.cleanupDataTestDirOnTestFS(table.getNameAsString());<a name="line.442"></a>
-<span class="sourceLineNo">443</span>    }<a name="line.443"></a>
-<span class="sourceLineNo">444</span>    return tool;<a name="line.444"></a>
-<span class="sourceLineNo">445</span>  }<a name="line.445"></a>
-<span class="sourceLineNo">446</span><a name="line.446"></a>
-<span class="sourceLineNo">447</span>  /**<a name="line.447"></a>
-<span class="sourceLineNo">448</span>   * Confirm ImportTsv via data in online table.<a name="line.448"></a>
-<span class="sourceLineNo">449</span>   */<a name="line.449"></a>
-<span class="sourceLineNo">450</span>  private static void validateTable(Configuration conf, TableName tableName,<a name="line.450"></a>
-<span class="sourceLineNo">451</span>      String family, int valueMultiplier, boolean isDryRun) throws IOException {<a name="line.451"></a>
+<span class="sourceLineNo">389</span>  /**<a name="line.389"></a>
+<span class="sourceLineNo">390</span>   * Run an ImportTsv job and perform basic validation on the results.<a name="line.390"></a>
+<span class="sourceLineNo">391</span>   * Returns the ImportTsv &lt;code&gt;Tool&lt;/code&gt; instance so that other tests can<a name="line.391"></a>
+<span class="sourceLineNo">392</span>   * inspect it for further validation as necessary. This method is static to<a name="line.392"></a>
+<span class="sourceLineNo">393</span>   * insure non-reliance on instance's util/conf facilities.<a name="line.393"></a>
+<span class="sourceLineNo">394</span>   * @param args Any arguments to pass BEFORE inputFile path is appended.<a name="line.394"></a>
+<span class="sourceLineNo">395</span>   * @return The Tool instance used to run the test.<a name="line.395"></a>
+<span class="sourceLineNo">396</span>   */<a name="line.396"></a>
+<span class="sourceLineNo">397</span>  protected static Tool doMROnTableTest(HBaseTestingUtility util, TableName table,<a name="line.397"></a>
+<span class="sourceLineNo">398</span>      String family, String data, Map&lt;String, String&gt; args, int valueMultiplier,int expectedKVCount)<a name="line.398"></a>
+<span class="sourceLineNo">399</span>  throws Exception {<a name="line.399"></a>
+<span class="sourceLineNo">400</span>    Configuration conf = new Configuration(util.getConfiguration());<a name="line.400"></a>
+<span class="sourceLineNo">401</span><a name="line.401"></a>
+<span class="sourceLineNo">402</span>    // populate input file<a name="line.402"></a>
+<span class="sourceLineNo">403</span>    FileSystem fs = FileSystem.get(conf);<a name="line.403"></a>
+<span class="sourceLineNo">404</span>    Path inputPath = fs.makeQualified(<a name="line.404"></a>
+<span class="sourceLineNo">405</span>            new Path(util.getDataTestDirOnTestFS(table.getNameAsString()), "input.dat"));<a name="line.405"></a>
+<span class="sourceLineNo">406</span>    FSDataOutputStream op = fs.create(inputPath, true);<a name="line.406"></a>
+<span class="sourceLineNo">407</span>    if (data == null) {<a name="line.407"></a>
+<span class="sourceLineNo">408</span>      data = "KEY\u001bVALUE1\u001bVALUE2\n";<a name="line.408"></a>
+<span class="sourceLineNo">409</span>    }<a name="line.409"></a>
+<span class="sourceLineNo">410</span>    op.write(Bytes.toBytes(data));<a name="line.410"></a>
+<span class="sourceLineNo">411</span>    op.close();<a name="line.411"></a>
+<span class="sourceLineNo">412</span>    LOG.debug(String.format("Wrote test data to file: %s", inputPath));<a name="line.412"></a>
+<span class="sourceLineNo">413</span><a name="line.413"></a>
+<span class="sourceLineNo">414</span>    if (conf.getBoolean(FORCE_COMBINER_CONF, true)) {<a name="line.414"></a>
+<span class="sourceLineNo">415</span>      LOG.debug("Forcing combiner.");<a name="line.415"></a>
+<span class="sourceLineNo">416</span>      conf.setInt("mapreduce.map.combine.minspills", 1);<a name="line.416"></a>
+<span class="sourceLineNo">417</span>    }<a name="line.417"></a>
+<span class="sourceLineNo">418</span><a name="line.418"></a>
+<span class="sourceLineNo">419</span>    // Build args array.<a name="line.419"></a>
+<span class="sourceLineNo">420</span>    String[] argsArray = new String[args.size() + 2];<a name="line.420"></a>
+<span class="sourceLineNo">421</span>    Iterator it = args.entrySet().iterator();<a name="line.421"></a>
+<span class="sourceLineNo">422</span>    int i = 0;<a name="line.422"></a>
+<span class="sourceLineNo">423</span>    while (it.hasNext()) {<a name="line.423"></a>
+<span class="sourceLineNo">424</span>      Map.Entry pair = (Map.Entry) it.next();<a name="line.424"></a>
+<span class="sourceLineNo">425</span>      argsArray[i] = "-D" + pair.getKey() + "=" + pair.getValue();<a name="line.425"></a>
+<span class="sourceLineNo">426</span>      i++;<a name="line.426"></a>
+<span class="sourceLineNo">427</span>    }<a name="line.427"></a>
+<span class="sourceLineNo">428</span>    argsArray[i] = table.getNameAsString();<a name="line.428"></a>
+<span class="sourceLineNo">429</span>    argsArray[i + 1] = inputPath.toString();<a name="line.429"></a>
+<span class="sourceLineNo">430</span><a name="line.430"></a>
+<span class="sourceLineNo">431</span>    // run the import<a name="line.431"></a>
+<span class="sourceLineNo">432</span>    Tool tool = new ImportTsv();<a name="line.432"></a>
+<span class="sourceLineNo">433</span>    LOG.debug("Running ImportTsv with arguments: " + argsArray);<a name="line.433"></a>
+<span class="sourceLineNo">434</span>    assertEquals(0, ToolRunner.run(conf, tool, argsArray));<a name="line.434"></a>
+<span class="sourceLineNo">435</span><a name="line.435"></a>
+<span class="sourceLineNo">436</span>    // Perform basic validation. If the input args did not include<a name="line.436"></a>
+<span class="sourceLineNo">437</span>    // ImportTsv.BULK_OUTPUT_CONF_KEY then validate data in the table.<a name="line.437"></a>
+<span class="sourceLineNo">438</span>    // Otherwise, validate presence of hfiles.<a name="line.438"></a>
+<span class="sourceLineNo">439</span>    boolean isDryRun = args.containsKey(ImportTsv.DRY_RUN_CONF_KEY) &amp;&amp;<a name="line.439"></a>
+<span class="sourceLineNo">440</span>        "true".equalsIgnoreCase(args.get(ImportTsv.DRY_RUN_CONF_KEY));<a name="line.440"></a>
+<span class="sourceLineNo">441</span>    if (args.containsKey(ImportTsv.BULK_OUTPUT_CONF_KEY)) {<a name="line.441"></a>
+<span class="sourceLineNo">442</span>      if (isDryRun) {<a name="line.442"></a>
+<span class="sourceLineNo">443</span>        assertFalse(String.format("Dry run mode, %s should not have been created.",<a name="line.443"></a>
+<span class="sourceLineNo">444</span>                 ImportTsv.BULK_OUTPUT_CONF_KEY),<a name="line.444"></a>
+<span class="sourceLineNo">445</span>            fs.exists(new Path(ImportTsv.BULK_OUTPUT_CONF_KEY)));<a name="line.445"></a>
+<span class="sourceLineNo">446</span>      } else {<a name="line.446"></a>
+<span class="sourceLineNo">447</span>        validateHFiles(fs, args.get(ImportTsv.BULK_OUTPUT_CONF_KEY), family,expectedKVCount);<a name="line.447"></a>
+<span class="sourceLineNo">448</span>      }<a name="line.448"></a>
+<span class="sourceLineNo">449</span>    } else {<a name="line.449"></a>
+<span class="sourceLineNo">450</span>      validateTable(conf, table, family, valueMultiplier, isDryRun);<a name="line.450"></a>
+<span class="sourceLineNo">451</span>    }<a name="line.451"></a>
 <span class="sourceLineNo">452</span><a name="line.452"></a>
-<span class="sourceLineNo">453</span>    LOG.debug("Validating table.");<a name="line.453"></a>
-<span class="sourceLineNo">454</span>    Connection connection = ConnectionFactory.createConnection(conf);<a name="line.454"></a>
-<span class="sourceLineNo">455</span>    Table table = connection.getTable(tableName);<a name="line.455"></a>
-<span class="sourceLineNo">456</span>    boolean verified = false;<a name="line.456"></a>
-<span class="sourceLineNo">457</span>    long pause = conf.getLong("hbase.client.pause", 5 * 1000);<a name="line.457"></a>
-<span class="sourceLineNo">458</span>    int numRetries = conf.getInt(HConstants.HBASE_CLIENT_RETRIES_NUMBER, 5);<a name="line.458"></a>
-<span class="sourceLineNo">459</span>    for (int i = 0; i &lt; numRetries; i++) {<a name="line.459"></a>
-<span class="sourceLineNo">460</span>      try {<a name="line.460"></a>
-<span class="sourceLineNo">461</span>        Scan scan = new Scan();<a name="line.461"></a>
-<span class="sourceLineNo">462</span>        // Scan entire family.<a name="line.462"></a>
-<span class="sourceLineNo">463</span>        scan.addFamily(Bytes.toBytes(family));<a name="line.463"></a>
-<span class="sourceLineNo">464</span>        ResultScanner resScanner = table.getScanner(scan);<a name="line.464"></a>
-<span class="sourceLineNo">465</span>        int numRows = 0;<a name="line.465"></a>
-<span class="sourceLineNo">466</span>        for (Result res : resScanner) {<a name="line.466"></a>
-<span class="sourceLineNo">467</span>          numRows++;<a name="line.467"></a>
-<span class="sourceLineNo">468</span>          assertEquals(2, res.size());<a name="line.468"></a>
-<span class="sourceLineNo">469</span>          List&lt;Cell&gt; kvs = res.listCells();<a name="line.469"></a>
-<span class="sourceLineNo">470</span>          assertTrue(CellUtil.matchingRow(kvs.get(0), Bytes.toBytes("KEY")));<a name="line.470"></a>
-<span class="sourceLineNo">471</span>          assertTrue(CellUtil.matchingRow(kvs.get(1), Bytes.toBytes("KEY")));<a name="line.471"></a>
-<span class="sourceLineNo">472</span>          assertTrue(CellUtil.matchingValue(kvs.get(0), Bytes.toBytes("VALUE" + valueMultiplier)));<a name="line.472"></a>
-<span class="sourceLineNo">473</span>          assertTrue(CellUtil.matchingValue(kvs.get(1), Bytes.toBytes("VALUE" + 2 * valueMultiplier)));<a name="line.473"></a>
-<span class="sourceLineNo">474</span>          // Only one result set is expected, so let it loop.<a name="line.474"></a>
-<span class="sourceLineNo">475</span>        }<a name="line.475"></a>
-<span class="sourceLineNo">476</span>        if (isDryRun) {<a name="line.476"></a>
-<span class="sourceLineNo">477</span>          assertEquals(0, numRows);<a name="line.477"></a>
-<span class="sourceLineNo">478</span>        } else {<a name="line.478"></a>
-<span class="sourceLineNo">479</span>          assertEquals(1, numRows);<a name="line.479"></a>
-<span class="sourceLineNo">480</span>        }<a name="line.480"></a>
-<span class="sourceLineNo">481</span>        verified = true;<a name="line.481"></a>
-<span class="sourceLineNo">482</span>        break;<a name="line.482"></a>
-<span class="sourceLineNo">483</span>      } catch (NullPointerException e) {<a name="line.483"></a>
-<span class="sourceLineNo">484</span>        // If here, a cell was empty. Presume its because updates came in<a name="line.484"></a>
-<span class="sourceLineNo">485</span>        // after the scanner had been opened. Wait a while and retry.<a name="line.485"></a>
-<span class="sourceLineNo">486</span>      }<a name="line.486"></a>
-<span class="sourceLineNo">487</span>      try {<a name="line.487"></a>
-<span class="sourceLineNo">488</span>        Thread.sleep(pause);<a name="line.488"></a>
-<span class="sourceLineNo">489</span>      } catch (InterruptedException e) {<a name="line.489"></a>
-<span class="sourceLineNo">490</span>        // continue<a name="line.490"></a>
-<span class="sourceLineNo">491</span>      }<a name="line.491"></a>
-<span class="sourceLineNo">492</span>    }<a name="line.492"></a>
-<span class="sourceLineNo">493</span>    table.close();<a name="line.493"></a>
-<span class="sourceLineNo">494</span>    connection.close();<a name="line.494"></a>
-<span class="sourceLineNo">495</span>    assertTrue(verified);<a name="line.495"></a>
-<span class="sourceLineNo">496</span>  }<a name="line.496"></a>
-<span class="sourceLineNo">497</span><a name="line.497"></a>
-<span class="sourceLineNo">498</span>  /**<a name="line.498"></a>
-<span class="sourceLineNo">499</span>   * Confirm ImportTsv via HFiles on fs.<a name="line.499"></a>
-<span class="sourceLineNo">500</span>   */<a name="line.500"></a>
-<span class="sourceLineNo">501</span>  private static void validateHFiles(FileSystem fs, String outputPath, String family,<a name="line.501"></a>
-<span class="sourceLineNo">502</span>      int expectedKVCount) throws IOException {<a name="line.502"></a>
-<span class="sourceLineNo">503</span>    // validate number and content of output columns<a name="line.503"></a>
-<span class="sourceLineNo">504</span>    LOG.debug("Validating HFiles.");<a name="line.504"></a>
-<span class="sourceLineNo">505</span>    Set&lt;String&gt; configFamilies = new HashSet&lt;String&gt;();<a name="line.505"></a>
-<span class="sourceLineNo">506</span>    configFamilies.add(family);<a name="line.506"></a>
-<span class="sourceLineNo">507</span>    Set&lt;String&gt; foundFamilies = new HashSet&lt;String&gt;();<a name="line.507"></a>
-<span class="sourceLineNo">508</span>    int actualKVCount = 0;<a name="line.508"></a>
-<span class="sourceLineNo">509</span>    for (FileStatus cfStatus : fs.listStatus(new Path(outputPath), new OutputFilesFilter())) {<a name="line.509"></a>
-<span class="sourceLineNo">510</span>      String[] elements = cfStatus.getPath().toString().split(Path.SEPARATOR);<a name="line.510"></a>
-<span class="sourceLineNo">511</span>      String cf = elements[elements.length - 1];<a name="line.511"></a>
-<span class="sourceLineNo">512</span>      foundFamilies.add(cf);<a name="line.512"></a>
-<span class="sourceLineNo">513</span>      assertTrue(<a name="line.513"></a>
-<span class="sourceLineNo">514</span>        String.format(<a name="line.514"></a>
-<span class="sourceLineNo">515</span>          "HFile output contains a column family (%s) not present in input families (%s)",<a name="line.515"></a>
-<span class="sourceLineNo">516</span>          cf, configFamilies),<a name="line.516"></a>
-<span class="sourceLineNo">517</span>          configFamilies.contains(cf));<a name="line.517"></a>
-<span class="sourceLineNo">518</span>      for (FileStatus hfile : fs.listStatus(cfStatus.getPath())) {<a name="line.518"></a>
-<span class="sourceLineNo">519</span>        assertTrue(<a name="line.519"></a>
-<span class="sourceLineNo">520</span>          String.format("HFile %s appears to contain no data.", hfile.getPath()),<a name="line.520"></a>
-<span class="sourceLineNo">521</span>          hfile.getLen() &gt; 0);<a name="line.521"></a>
-<span class="sourceLineNo">522</span>        // count the number of KVs from all the hfiles<a name="line.522"></a>
-<span class="sourceLineNo">523</span>        if (expectedKVCount &gt; -1) {<a name="line.523"></a>
-<span class="sourceLineNo">524</span>          actualKVCount += getKVCountFromHfile(fs, hfile.getPath());<a name="line.524"></a>
-<span class="sourceLineNo">525</span>        }<a name="line.525"></a>
-<span class="sourceLineNo">526</span>      }<a name="line.526"></a>
-<span class="sourceLineNo">527</span>    }<a name="line.527"></a>
-<span class="sourceLineNo">528</span>    assertTrue(String.format("HFile output does not contain the input family '%s'.", family),<a name="line.528"></a>
-<span class="sourceLineNo">529</span>        foundFamilies.contains(family));<a name="line.529"></a>
-<span class="sourceLineNo">530</span>    if (expectedKVCount &gt; -1) {<a name="line.530"></a>
-<span class="sourceLineNo">531</span>      assertTrue(String.format(<a name="line.531"></a>
-<span class="sourceLineNo">532</span>        "KV count in ouput hfile=&lt;%d&gt; doesn't match with expected KV count=&lt;%d&gt;", actualKVCount,<a name="line.532"></a>
-<span class="sourceLineNo">533</span>        expectedKVCount), actualKVCount == expectedKVCount);<a name="line.533"></a>
-<span class="sourceLineNo">534</span>    }<a name="line.534"></a>
-<span class="sourceLineNo">535</span>  }<a name="line.535"></a>
-<span class="sourceLineNo">536</span><a name="line.536"></a>
-<span class="sourceLineNo">537</span>  /**<a name="line.537"></a>
-<span class="sourceLineNo">538</span>   * Method returns the total KVs in given hfile<a name="line.538"></a>
-<span class="sourceLineNo">539</span>   * @param fs File System<a name="line.539"></a>
-<span class="sourceLineNo">540</span>   * @param p HFile path<a name="line.540"></a>
-<span class="sourceLineNo">541</span>   * @return KV count in the given hfile<a name="line.541"></a>
-<span class="sourceLineNo">542</span>   * @throws IOException<a name="line.542"></a>
-<span class="sourceLineNo">543</span>   */<a name="line.543"></a>
-<span class="sourceLineNo">544</span>  private static int getKVCountFromHfile(FileSystem fs, Path p) throws IOException {<a name="line.544"></a>
-<span class="sourceLineNo">545</span>    Configuration conf = util.getConfiguration();<a name="line.545"></a>
-<span class="sourceLineNo">546</span>    HFile.Reader reader = HFile.createReader(fs, p, new CacheConfig(conf), conf);<a name="line.546"></a>
-<span class="sourceLineNo">547</span>    reader.loadFileInfo();<a name="line.547"></a>
-<span class="sourceLineNo">548</span>    HFileScanner scanner = reader.getScanner(false, false);<a name="line.548"></a>
-<span class="sourceLineNo">549</span>    scanner.seekTo();<a name="line.549"></a>
-<span class="sourceLineNo">550</span>    int count = 0;<a name="line.550"></a>
-<span class="sourceLineNo">551</span>    do {<a name="line.551"></a>
-<span class="sourceLineNo">552</span>      count++;<a name="line.552"></a>
-<span class="sourceLineNo">553</span>    } while (scanner.next());<a name="line.553"></a>
-<span class="sourceLineNo">554</span>    reader.close();<a name="line.554"></a>
-<span class="sourceLineNo">555</span>    return count;<a name="line.555"></a>
-<span class="sourceLineNo">556</span>  }<a name="line.556"></a>
-<span class="sourceLineNo">557</span>}<a name="line.557"></a>
-<span class="sourceLineNo">558</span><a name="line.558"></a>
+<span class="sourceLineNo">453</span>    if (conf.getBoolean(DELETE_AFTER_LOAD_CONF, true)) {<a name="line.453"></a>
+<span class="sourceLineNo">454</span>      LOG.debug("Deleting test subdirectory");<a name="line.454"></a>
+<span class="sourceLineNo">455</span>      util.cleanupDataTestDirOnTestFS(table.getNameAsString());<a name="line.455"></a>
+<span class="sourceLineNo">456</span>    }<a name="line.456"></a>
+<span class="sourceLineNo">457</span>    return tool;<a name="line.457"></a>
+<span class="sourceLineNo">458</span>  }<a name="line.458"></a>
+<span class="sourceLineNo">459</span><a name="line.459"></a>
+<span class="sourceLineNo">460</span>  /**<a name="line.460"></a>
+<span class="sourceLineNo">461</span>   * Confirm ImportTsv via data in online table.<a name="line.461"></a>
+<span class="sourceLineNo">462</span>   */<a name="line.462"></a>
+<span class="sourceLineNo">463</span>  private static void validateTable(Configuration conf, TableName tableName,<a name="line.463"></a>
+<span class="sourceLineNo">464</span>      String family, int valueMultiplier, boolean isDryRun) throws IOException {<a name="line.464"></a>
+<span class="sourceLineNo">465</span><a name="line.465"></a>
+<span class="sourceLineNo">466</span>    LOG.debug("Validating table.");<a name="line.466"></a>
+<span class="sourceLineNo">467</span>    Connection connection = ConnectionFactory.createConnection(conf);<a name="line.467"></a>
+<span class="sourceLineNo">468</span>    Table table = connection.getTable(tableName);<a name="line.468"></a>
+<span class="sourceLineNo">469</span>    boolean verified = false;<a name="line.469"></a>
+<span class="sourceLineNo">470</span>    long pause = conf.getLong("hbase.client.pause", 5 * 1000);<a name="line.470"></a>
+<span class="sourceLineNo">471</span>    int numRetries = conf.getInt(HConstants.HBASE_CLIENT_RETRIES_NUMBER, 5);<a name="line.471"></a>
+<span class="sourceLineNo">472</span>    for (int i = 0; i &lt; numRetries; i++) {<a name="line.472"></a>
+<span class="sourceLineNo">473</span>      try {<a name="line.473"></a>
+<span class="sourceLineNo">474</span>        Scan scan = new Scan();<a name="line.474"></a>
+<span class="sourceLineNo">475</span>        // Scan entire family.<a name="line.475"></a>
+<span class="sourceLineNo">476</span>        scan.addFamily(Bytes.toBytes(family));<a name="line.476"></a>
+<span class="sourceLineNo">477</span>        ResultScanner resScanner = table.getScanner(scan);<a name="line.477"></a>
+<span class="sourceLineNo">478</span>        int numRows = 0;<a name="line.478"></a>
+<span class="sourceLineNo">479</span>        for (Result res : resScanner) {<a name="line.479"></a>
+<span class="sourceLineNo">480</span>          numRows++;<a name="line.480"></a>
+<span class="sourceLineNo">481</span>          assertEquals(2, res.size());<a name="line.481"></a>
+<span class="sourceLineNo">482</span>          List&lt;Cell&gt; kvs = res.listCells();<a name="line.482"></a>
+<span class="sourceLineNo">483</span>          assertTrue(CellUtil.matchingRow(kvs.get(0), Bytes.toBytes("KEY")));<a name="line.483"></a>
+<span class="sourceLineNo">484</span>          assertTrue(CellUtil.matchingRow(kvs.get(1), Bytes.toBytes("KEY")));<a name="line.484"></a>
+<span class="sourceLineNo">485</span>          assertTrue(CellUtil.matchingValue(kvs.get(0), Bytes.toBytes("VALUE" + valueMultiplier)));<a name="line.485"></a>
+<span class="sourceLineNo">486</span>          assertTrue(CellUtil.matchingValue(kvs.get(1), Bytes.toBytes("VALUE" + 2 * valueMultiplier)));<a name="line.486"></a>
+<span class="sourceLineNo">487</span>          // Only one result set is expected, so let it loop.<a name="line.487"></a>
+<span class="sourceLineNo">488</span>        }<a name="line.488"></a>
+<span class="sourceLineNo">489</span>        if (isDryRun) {<a name="line.489"></a>
+<span class="sourceLineNo">490</span>          assertEquals(0, numRows);<a name="line.490"></a>
+<span class="sourceLineNo">491</span>        } else {<a name="line.491"></a>
+<span class="sourceLineNo">492</span>          assertEquals(1, numRows);<a name="line.492"></a>
+<span class="sourceLineNo">493</span>        }<a name="line.493"></a>
+<span class="sourceLineNo">494</span>        verified = true;<a name="line.494"></a>
+<span class="sourceLineNo">495</span>        break;<a name="line.495"></a>
+<span class="sourceLineNo">496</span>      } catch (NullPointerException e) {<a name="line.496"></a>
+<span class="sourceLineNo">497</span>        // If here, a cell was empty. Presume its because updates came in<a name="line.497"></a>
+<span class="sourceLineNo">498</span>        // after the scanner had been opened. Wait a while and retry.<a name="line.498"></a>
+<span class="sourceLineNo">499</span>      }<a name="line.499"></a>
+<span class="sourceLineNo">500</span>      try {<a name="line.500"></a>
+<span class="sourceLineNo">501</span>        Thread.sleep(pause);<a name="line.501"></a>
+<span class="sourceLineNo">502</span>      } catch (InterruptedException e) {<a name="line.502"></a>
+<span class="sourceLineNo">503</span>        // continue<a name="line.503"></a>
+<span class="sourceLineNo">504</span>      }<a name="line.504"></a>
+<span class="sourceLineNo">505</span>    }<a name="line.505"></a>
+<span class="sourceLineNo">506</span>    table.close();<a name="line.506"></a>
+<span class="sourceLineNo">507</span>    connection.close();<a name="line.507"></a>
+<span class="sourceLineNo">508</span>    assertTrue(verified);<a name="line.508"></a>
+<span class="sourceLineNo">509</span>  }<a name="line.509"></a>
+<span class="sourceLineNo">510</span><a name="line.510"></a>
+<span class="sourceLineNo">511</span>  /**<a name="line.511"></a>
+<span class="sourceLineNo">512</span>   * Confirm ImportTsv via HFiles on fs.<a name="line.512"></a>
+<span class="sourceLineNo">513</span>   */<a name="line.513"></a>
+<span class="sourceLineNo">514</span>  private static void validateHFiles(FileSystem fs, String outputPath, String family,<a name="line.514"></a>
+<span class="sourceLineNo">515</span>      int expectedKVCount) throws IOException {<a name="line.515"></a>
+<span class="sourceLineNo">516</span>    // validate number and content of output columns<a name="line.516"></a>
+<span class="sourceLineNo">517</span>    LOG.debug("Validating HFiles.");<a name="line.517"></a>
+<span class="sourceLineNo">518</span>    Set&lt;String&gt; configFamilies = new HashSet&lt;String&gt;();<a name="line.518"></a>
+<span class="sourceLineNo">519</span>    configFamilies.add(family);<a name="line.519"></a>
+<span class="sourceLineNo">520</span>    Set&lt;String&gt; foundFamilies = new HashSet&lt;String&gt;();<a name="line.520"></a>
+<span class="sourceLineNo">521</span>    int actualKVCount = 0;<a name="line.521"></a>
+<span class="sourceLineNo">522</span>    for (FileStatus cfStatus : fs.listStatus(new Path(outputPath), new OutputFilesFilter())) {<a name="line.522"></a>
+<span class="sourceLineNo">523</span>      String[] elements = cfStatus.getPath().toString().split(Path.SEPARATOR);<a name="line.523"></a>
+<span class="sourceLineNo">524</span>      String cf = elements[elements.length - 1];<a name="line.524"></a>
+<span class="sourceLineNo">525</span>      foundFamilies.add(cf);<a name="line.525"></a>
+<span class="sourceLineNo">526</span>      assertTrue(<a name="line.526"></a>
+<span class="sourceLineNo">527</span>        String.format(<a name="line.527"></a>
+<span class="sourceLineNo">528</span>          "HFile output contains a column family (%s) not present in input families (%s)",<a name="line.528"></a>
+<span class="sourceLineNo">529</span>          cf, configFamilies),<a name="line.529"></a>
+<span class="sourceLineNo">530</span>          configFamilies.contains(cf));<a name="line.530"></a>
+<span class="sourceLineNo">531</span>      for (FileStatus hfile : fs.listStatus(cfStatus.getPath())) {<a name="line.531"></a>
+<span class="sourceLineNo">532</span>        assertTrue(<a name="line.532"></a>
+<span class="sourceLineNo">533</span>          String.format("HFile %s appears to contain no data.", hfile.getPath()),<a name="line.533"></a>
+<span class="sourceLineNo">534</span>          hfile.getLen() &gt; 0);<a name="line.534"></a>
+<span class="sourceLineNo">535</span>        // count the number of KVs from all the hfiles<a name="line.535"></a>
+<span class="sourceLineNo">536</span>        if (expectedKVCount &gt; -1) {<a name="line.536"></a>
+<span class="sourceLineNo">537</span>          actualKVCount += getKVCountFromHfile(fs, hfile.getPath());<a name="line.537"></a>
+<span class="sourceLineNo">538</span>        }<a name="line.538"></a>
+<span class="sourceLineNo">539</span>      }<a name="line.539"></a>
+<span class="sourceLineNo">540</span>    }<a name="line.540"></a>
+<span class="sourceLineNo">541</span>    assertTrue(String.format("HFile output does not contain the input family '%s'.", family),<a name="line.541"></a>
+<span class="sourceLineNo">542</span>        foundFamilies.contains(family));<a name="line.542"></a>
+<span class="sourceLineNo">543</span>    if (expectedKVCount &gt; -1) {<a name="line.543"></a>
+<span class="sourceLineNo">544</span>      assertTrue(String.format(<a name="line.544"></a>
+<span class="sourceLineNo">545</span>        "KV count in ouput hfile=&lt;%d&gt; doesn't match with expected KV count=&lt;%d&gt;", actualKVCount,<a name="line.545"></a>
+<span class="sourceLineNo">546</span>        expectedKVCount), actualKVCount == expectedKVCount);<a name="line.546"></a>
+<span class="sourceLineNo">547</span>    }<a name="line.547"></a>
+<span class="sourceLineNo">548</span>  }<a name="line.548"></a>
+<span class="sourceLineNo">549</span><a name="line.549"></a>
+<span class="sourceLineNo">550</span>  /**<a name="line.550"></a>
+<span class="sourceLineNo">551</span>   * Method returns the total KVs in given hfile<a name="line.551"></a>
+<span class="sourceLineNo">552</span>   * @param fs File System<a name="line.552"></a>
+<span class="sourceLineNo">553</span>   * @param p HFile path<a name="line.553"></a>
+<span class="sourceLineNo">554</span>   * @return KV count in the given hfile<a name="line.554"></a>
+<span class="sourceLineNo">555</span>   * @throws IOException<a name="line.555"></a>
+<span class="sourceLineNo">556</span>   */<a name="line.556"></a>
+<span class="sourceLineNo">557</span>  private static int getKVCountFromHfile(FileSystem fs, Path p) throws IOException {<a name="line.557"></a>
+<span class="sourceLineNo">558</span>    Configuration conf = util.getConfiguration();<a name="line.558"></a>
+<span class="sourceLineNo">559</span>    HFile.Reader reader = HFile.createReader(fs, p, new CacheConfig(conf), conf);<a name="line.559"></a>
+<span class="sourceLineNo">560</span>    reader.loadFileInfo();<a name="line.560"></a>
+<span class="sourceLineNo">561</span>    HFileScanner scanner = reader.getScanner(false, false);<a name="line.561"></a>
+<span class="sourceLineNo">562</span>    scanner.seekTo();<a name="line.562"></a>
+<span class="sourceLineNo">563</span>    int count = 0;<a name="line.563"></a>
+<span class="sourceLineNo">564</span>    do {<a name="line.564"></a>
+<span class="sourceLineNo">565</span>      count++;<a name="line.565"></a>
+<span class="sourceLineNo">566</span>    } while (scanner.next());<a name="line.566"></a>
+<span class="sourceLineNo">567</span>    reader.close();<a name="line.567"></a>
+<span class="sourceLineNo">568</span>    return count;<a name="line.568"></a>
+<span class="sourceLineNo">569</span>  }<a name="line.569"></a>
+<span class="sourceLineNo">570</span>}<a name="line.570"></a>
+<span class="sourceLineNo">571</span><a name="line.571"></a>