Java Scan.addFamily方法代码示例

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Override
public void configure(JobConf job) {
  try {
    Connection connection = ConnectionFactory.createConnection(HBaseConfiguration.create(job));
    TableName tableName = TableName.valueOf("exampleJobConfigurableTable");
    // mandatory
    initializeTable(connection, tableName);
    byte[][] inputColumns = new byte [][] { Bytes.toBytes("columnA"),
      Bytes.toBytes("columnB") };
    //optional
    Scan scan = new Scan();
    for (byte[] family : inputColumns) {
      scan.addFamily(family);
    }
    Filter exampleFilter = new RowFilter(CompareOp.EQUAL, new RegexStringComparator("aa.*"));
    scan.setFilter(exampleFilter);
    setScan(scan);
  } catch (IOException exception) {
    throw new RuntimeException("Failed to initialize.", exception);
  }
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testMinWithInvalidRange2() {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setStartRow(ROWS[6]);
  scan.setStopRow(ROWS[6]);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  BigDecimal min = null;
  try {
    min = aClient.min(TEST_TABLE, ci, scan);
  } catch (Throwable e) {
  }
  assertEquals(null, min);// control should go to the catch block
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testMinWithInvalidRange2() {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setStartRow(ROWS[6]);
  scan.setStopRow(ROWS[6]);
  final ColumnInterpreter<Long, Long, EmptyMsg, LongMsg, LongMsg> ci =
      new LongColumnInterpreter();
  Long min = null;
  try {
    min = aClient.min(TEST_TABLE, ci, scan);
  } catch (Throwable e) {
  }
  assertEquals(null, min);// control should go to the catch block
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Override
protected void initialize(JobContext job) throws IOException {
  Connection connection = ConnectionFactory.createConnection(HBaseConfiguration.create(
      job.getConfiguration()));
  TableName tableName = TableName.valueOf("exampleTable");
  // mandatory
  initializeTable(connection, tableName);
  byte[][] inputColumns = new byte [][] { Bytes.toBytes("columnA"),
    Bytes.toBytes("columnB") };
  //optional
  Scan scan = new Scan();
  for (byte[] family : inputColumns) {
    scan.addFamily(family);
  }
  Filter exampleFilter = new RowFilter(CompareOp.EQUAL, new RegexStringComparator("aa.*"));
  scan.setFilter(exampleFilter);
  setScan(scan);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * Tests a MR scan using data skew auto-balance
 *
 * @throws IOException
 * @throws ClassNotFoundException
 * @throws InterruptedException
 */
public void testNumOfSplits(String ratio, int expectedNumOfSplits) throws IOException,
        InterruptedException,
        ClassNotFoundException {
  String jobName = "TestJobForNumOfSplits";
  LOG.info("Before map/reduce startup - job " + jobName);
  Configuration c = new Configuration(TEST_UTIL.getConfiguration());
  Scan scan = new Scan();
  scan.addFamily(INPUT_FAMILY);
  c.set("hbase.mapreduce.input.autobalance", "true");
  c.set("hbase.mapreduce.input.autobalance.maxskewratio", ratio);
  c.set(KEY_STARTROW, "");
  c.set(KEY_LASTROW, "");
  Job job = new Job(c, jobName);
  TableMapReduceUtil.initTableMapperJob(Bytes.toString(TABLE_NAME), scan, ScanMapper.class,
          ImmutableBytesWritable.class, ImmutableBytesWritable.class, job);
  TableInputFormat tif = new TableInputFormat();
  tif.setConf(job.getConfiguration());
  Assert.assertEquals(new String(TABLE_NAME), new String(table.getTableName()));
  List<InputSplit> splits = tif.getSplits(job);
  Assert.assertEquals(expectedNumOfSplits, splits.size());
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testSumWithInvalidRange() {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setStartRow(ROWS[6]);
  scan.setStopRow(ROWS[2]);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  BigDecimal sum = null;
  try {
    sum = aClient.sum(TEST_TABLE, ci, scan);
  } catch (Throwable e) {
  }
  assertEquals(null, sum);// control should go to the catch block
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
public Result getRowOrBefore(Table table, byte[] row, byte[] family) throws IOException {
  long start = System.currentTimeMillis();
  Scan scan = new Scan();
  scan.addFamily(family);
  scan.setReversed(true);
  scan.setStartRow(row);
  scan.setCacheBlocks(false);
  scan.setCaching(1);
  scan.setSmall(true);
  ResultScanner scanner = table.getScanner(scan);
  Result ret = scanner.next();
  scanner.close();
  prevRowTotalTime += System.currentTimeMillis() - start;
  prevRowTotalCount++;
  return ret;
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testStdWithInvalidRange() {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setStartRow(ROWS[6]);
  scan.setStopRow(ROWS[1]);
  final ColumnInterpreter<Long, Long, EmptyMsg, LongMsg, LongMsg> ci =
      new LongColumnInterpreter();
  Double std = null;
  try {
    std = aClient.std(TEST_TABLE, ci, scan);
  } catch (Throwable e) {
  }
  assertEquals(null, std);// control should go to the catch block
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
public void testBulkDeleteFamily() throws Throwable {
  TableName tableName = TableName.valueOf("testBulkDeleteFamily");
  HTableDescriptor htd = new HTableDescriptor(tableName);
  htd.addFamily(new HColumnDescriptor(FAMILY1));
  htd.addFamily(new HColumnDescriptor(FAMILY2));
  TEST_UTIL.getHBaseAdmin().createTable(htd, Bytes.toBytes(0), Bytes.toBytes(120), 5);
  Table ht = new HTable(TEST_UTIL.getConfiguration(), tableName);
  List<Put> puts = new ArrayList<Put>(100);
  for (int j = 0; j < 100; j++) {
    Put put = new Put(Bytes.toBytes(j));
    put.add(FAMILY1, QUALIFIER1, "v1".getBytes());
    put.add(FAMILY2, QUALIFIER2, "v2".getBytes());
    puts.add(put);
  }
  ht.put(puts);
  Scan scan = new Scan();
  scan.addFamily(FAMILY1);
  // Delete the column family cf1
  long noOfRowsDeleted = invokeBulkDeleteProtocol(tableName, scan, 500, DeleteType.FAMILY, null);
  assertEquals(100, noOfRowsDeleted);
  int rows = 0;
  for (Result result : ht.getScanner(new Scan())) {
    assertTrue(result.getFamilyMap(FAMILY1).isEmpty());
    assertEquals(1, result.getColumnCells(FAMILY2, QUALIFIER2).size());
    rows++;
  }
  assertEquals(100, rows);
  ht.close();
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
private InternalScanner buildScanner(String keyPrefix, String value, HRegion r)
    throws IOException {
  // Defaults FilterList.Operator.MUST_PASS_ALL.
  FilterList allFilters = new FilterList();
  allFilters.addFilter(new PrefixFilter(Bytes.toBytes(keyPrefix)));
  // Only return rows where this column value exists in the row.
  SingleColumnValueFilter filter = new SingleColumnValueFilter(Bytes.toBytes("trans-tags"),
      Bytes.toBytes("qual2"), CompareOp.EQUAL, Bytes.toBytes(value));
  filter.setFilterIfMissing(true);
  allFilters.addFilter(filter);
  Scan scan = new Scan();
  scan.addFamily(Bytes.toBytes("trans-blob"));
  scan.addFamily(Bytes.toBytes("trans-type"));
  scan.addFamily(Bytes.toBytes("trans-date"));
  scan.addFamily(Bytes.toBytes("trans-tags"));
  scan.addFamily(Bytes.toBytes("trans-group"));
  scan.setFilter(allFilters);
  return r.getScanner(scan);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testAvgWithValidRangeWithNoCQ() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  double avg = aClient.avg(TEST_TABLE, ci, scan);
  assertEquals(10.45, avg, 0.01);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test
public void testReverseScanWithPadding() throws Exception {
  byte[] terminator = new byte[] { -1 };
  byte[] row1 = Bytes.add(invert(Bytes.toBytes("a")), terminator);
  byte[] row2 = Bytes.add(invert(Bytes.toBytes("ab")), terminator);
  byte[] row3 = Bytes.add(invert(Bytes.toBytes("b")), terminator);

  Put put1 = new Put(row1);
  put1.addColumn(cfName, cqName, HConstants.EMPTY_BYTE_ARRAY);
  Put put2 = new Put(row2);
  put2.addColumn(cfName, cqName, HConstants.EMPTY_BYTE_ARRAY);
  Put put3 = new Put(row3);
  put3.addColumn(cfName, cqName, HConstants.EMPTY_BYTE_ARRAY);

  region.put(put1);
  region.put(put2);
  region.put(put3);
  region.flush(true);
  Scan scan = new Scan();
  scan.setCacheBlocks(false);
  scan.setReversed(true);
  scan.setFilter(new FirstKeyOnlyFilter());
  scan.addFamily(cfName);
  RegionScanner scanner = region.getScanner(scan);
  List<Cell> res = new ArrayList<Cell>();
  int count = 1;
  while (scanner.next(res)) {
    count++;
  }
  assertEquals(3, count);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testMinWithValidRangeWithNoCQ() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setStartRow(HConstants.EMPTY_START_ROW);
  scan.setStopRow(HConstants.EMPTY_END_ROW);
  final ColumnInterpreter<Long, Long, EmptyMsg, LongMsg, LongMsg> ci =
      new LongColumnInterpreter();
  long min = aClient.min(TEST_TABLE, ci,
      scan);
  assertEquals(0, min);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * Test the filter by adding all columns of family A in the scan. (OK)
 */
@Test
public void scanWithAllQualifiersOfFamiliyA() throws IOException {
  /* Given */
  Scan scan = new Scan();
  scan.addFamily(FAMILY_A);
  scan.setFilter(scanFilter);

  verify(scan);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testSumWithValidRangeWithNoCQ() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  BigDecimal sum = aClient.sum(TEST_TABLE, ci, scan);
  assertEquals(new BigDecimal("209.00"), sum); // 190 + 19
}