Java Scan.setFilter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
public static void QueryByCondition2(String tableName) {

        try {
            HTablePool pool = new HTablePool(configuration, 1000);
            HTable table = (HTable) pool.getTable(tableName);
            Filter filter = new SingleColumnValueFilter(Bytes
                    .toBytes("column1"), null, CompareOp.EQUAL, Bytes
                    .toBytes("aaa")); // 当列column1的值为aaa时进行查询
            Scan s = new Scan();
            s.setFilter(filter);
            ResultScanner rs = table.getScanner(s);
            for (Result r : rs) {
                System.out.println("获得到rowkey:" + new String(r.getRow()));
                for (KeyValue keyValue : r.raw()) {
                    System.out.println("列：" + new String(keyValue.getFamily())
                            + "====值:" + new String(keyValue.getValue()));
                }
            }
        } catch (Exception e) {
            e.printStackTrace();
        }

    }
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * Tests the the {@link WhileMatchFilter} works in combination with a
 * {@link Filter} that uses the
 * {@link Filter#filterKeyValue(org.apache.hadoop.hbase.KeyValue)} method.
 *
 * See HBASE-2258.
 *
 * @throws Exception
 */
@Test
public void testWhileMatchFilterWithFilterKeyValue() throws Exception {
  Scan s = new Scan();
  WhileMatchFilter filter = new WhileMatchFilter(
      new SingleColumnValueFilter(FAMILIES[0], QUALIFIERS_ONE[0], CompareOp.EQUAL, Bytes.toBytes("foo"))
  );
  s.setFilter(filter);

  InternalScanner scanner = this.region.getScanner(s);
  while (true) {
    ArrayList<Cell> values = new ArrayList<Cell>();
    boolean isMoreResults = scanner.next(values);
    assertTrue("The WhileMatchFilter should now filter all remaining", filter.filterAllRemaining());
    if (!isMoreResults) {
      break;
    }
  }
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test
public void testMultiRowRangeFilterWithoutRangeOverlap() throws IOException {
  tableName = Bytes.toBytes("testMultiRowRangeFilterWithoutRangeOverlap");
  HTable ht = TEST_UTIL.createTable(tableName, family, Integer.MAX_VALUE);
  generateRows(numRows, ht, family, qf, value);

  Scan scan = new Scan();
  scan.setMaxVersions();

  List<RowRange> ranges = new ArrayList<RowRange>();
  ranges.add(new RowRange(Bytes.toBytes(30), true, Bytes.toBytes(40), false));
  ranges.add(new RowRange(Bytes.toBytes(10), true, Bytes.toBytes(20), false));
  ranges.add(new RowRange(Bytes.toBytes(60), true, Bytes.toBytes(70), false));

  MultiRowRangeFilter filter = new MultiRowRangeFilter(ranges);
  scan.setFilter(filter);
  int resultsSize = getResultsSize(ht, scan);
  LOG.info("found " + resultsSize + " results");
  List<Cell> results1 = getScanResult(Bytes.toBytes(10), Bytes.toBytes(20), ht);
  List<Cell> results2 = getScanResult(Bytes.toBytes(30), Bytes.toBytes(40), ht);
  List<Cell> results3 = getScanResult(Bytes.toBytes(60), Bytes.toBytes(70), ht);

  assertEquals(results1.size() + results2.size() + results3.size(), resultsSize);

  ht.close();
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * 参考列过滤器(获取相同时间戳的列)
 *
 * @param tableName    表名
 * @param columnFamily 列族
 * @param qualifier    列限定符
 * @param columnValue  列值
 * @param count        数量
 */
public void dependentColumnFilter(String tableName, String columnFamily, String qualifier, String columnValue, int count) {
    HBaseConfiguration hBaseConfiguration = new HBaseConfiguration();
    Table table = hBaseConfiguration.table(tableName);
    Scan scan = new Scan();
    scan.setFilter(new PrefixFilter(Bytes.toBytes("")));
    scan.setCaching(10);
    scan.setBatch(10);
    try {
        ResultScanner scanner = table.getScanner(scan);
        Result[] results = scanner.next(count);
        HBaseResultUtil.print(results);
    } catch (IOException e) {
        e.printStackTrace();
    }
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * 单列排除过滤器（返回的列 不包含参考列）
 *
 * @param tableName    表名
 * @param columnFamily 列族
 * @param qualifier    列限定符
 * @param columnValue  列值
 * @param count        数量
 */
public void SingleColumnValueExcludeFilter(String tableName, String columnFamily, String qualifier, String columnValue, int count) {
    HBaseConfiguration hBaseConfiguration = new HBaseConfiguration();
    Table table = hBaseConfiguration.table(tableName);
    Scan scan = new Scan();
    SingleColumnValueExcludeFilter singleColumnValueFilter = new SingleColumnValueExcludeFilter(Bytes.toBytes(columnFamily), Bytes.toBytes(qualifier), CompareFilter.CompareOp.EQUAL, Bytes.toBytes(columnValue));
    //singleColumnValueFilter.setFilterIfMissing(true);//当不存在这列的行 默认不过滤
    singleColumnValueFilter.setLatestVersionOnly(true);//获取最新版本
    scan.setFilter(singleColumnValueFilter);
    scan.setCaching(10);
    //scan.setBatch(10);
    try {
        ResultScanner scanner = table.getScanner(scan);
        Result[] results = scanner.next(count);
        HBaseResultUtil.print(results);
    } catch (IOException e) {
        e.printStackTrace();
    }
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test
public void testMultiRowRangeFilterWithEmptyStopRow() throws IOException {
  tableName = Bytes.toBytes("testMultiRowRangeFilterWithEmptyStopRow");
  HTable ht = TEST_UTIL.createTable(tableName, family, Integer.MAX_VALUE);
  generateRows(numRows, ht, family, qf, value);
  Scan scan = new Scan();
  scan.setMaxVersions();

  List<RowRange> ranges = new ArrayList<RowRange>();
  ranges.add(new RowRange(Bytes.toBytes(10), true, Bytes.toBytes(""), false));
  ranges.add(new RowRange(Bytes.toBytes(30), true, Bytes.toBytes(40), false));

  MultiRowRangeFilter filter = new MultiRowRangeFilter(ranges);
  scan.setFilter(filter);
  int resultsSize = getResultsSize(ht, scan);
  List<Cell> results1 = getScanResult(Bytes.toBytes(10), Bytes.toBytes(""), ht);
  assertEquals(results1.size(), resultsSize);

  ht.close();
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
public static Scan getScan(String fileName) throws IOException {
  BufferedReader br = new BufferedReader(new FileReader(fileName));
  String line;
  Scan scan = new Scan();
  System.out.println("winter for scan ******");
  FilterList filterList = new FilterList();
  while ((line = br.readLine()) != null) {
    System.out.println("winter for scan : " + line);
    if (line.startsWith("#")) continue;
    // family, qualifier, type, >=, 10, <=, 1000
    // family, qualifier, type, >=, 10
    String[] splits = line.split("\t");
    byte[] family = Bytes.toBytes(splits[0]);
    byte[] qualifier = Bytes.toBytes(splits[1]);
    DataType type = DataType.valueOf(splits[2].toUpperCase());
    CompareFilter.CompareOp firstOp = parseOp(splits[3]);
    byte[] firstValue = DataType.stringToBytes(type, splits[4]);
    filterList.addFilter(new SingleColumnValueFilter(family, qualifier, firstOp, firstValue));
    if (splits.length >= 6) {
      CompareFilter.CompareOp secondOp = parseOp(splits[5].toUpperCase());
      byte[] secondValue = DataType.stringToBytes(type, splits[6]);
      filterList
          .addFilter(new SingleColumnValueFilter(family, qualifier, secondOp, secondValue));
    }
  }
  scan.setFilter(filterList);
  ScanRangeList scanRangeList = ScanRangeList.getScanRangeList(fileName);
  if (scanRangeList.getRanges().size() > 0) {
    scan.setAttribute(ScanRange.SCAN_RANGE_ATTRIBUTE_STR, scanRangeList.toBytesAttribute());
  }
  return scan;
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Override
void testRow(final int i) throws IOException {
  Scan scan = new Scan(getRandomRow(this.rand, this.totalRows));
  scan.addColumn(FAMILY_NAME, QUALIFIER_NAME);
  scan.setFilter(new WhileMatchFilter(new PageFilter(120)));
  ResultScanner s = this.table.getScanner(scan);
  s.close();
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
/**
 * Test the filter by adding 1 column of family A (the one used in the filter) and 1 column of
 * family B in the scan. (OK)
 */
@Test
public void scanWithSpecificQualifiers2() throws IOException {
  /* When */
  Scan scan = new Scan();
  scan.addColumn(FAMILY_A, QUALIFIER_FOO);
  scan.addColumn(FAMILY_B, QUALIFIER_BAR);
  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 testMinWithFilter() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addColumn(TEST_FAMILY, TEST_QUALIFIER);
  Filter f = new PrefixFilter(Bytes.toBytes("foo:bar"));
  scan.setFilter(f);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  BigDecimal min = null;
  min = aClient.min(TEST_TABLE, ci, scan);
  assertEquals(null, min);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
protected Scan constructScan(byte[] valuePrefix) throws IOException {
  Filter filter = new SingleColumnValueFilter(
      FAMILY_NAME, QUALIFIER_NAME, CompareFilter.CompareOp.EQUAL,
      new BinaryComparator(valuePrefix)
  );
  Scan scan = new Scan();
  scan.addColumn(FAMILY_NAME, QUALIFIER_NAME);
  scan.setFilter(filter);
  return scan;
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test (timeout=300000)
public void testAvgWithFilter() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Scan scan = new Scan();
  scan.addColumn(TEST_FAMILY, TEST_QUALIFIER);
  Filter f = new PrefixFilter(Bytes.toBytes("foo:bar"));
  scan.setFilter(f);
  final ColumnInterpreter<BigDecimal, BigDecimal, EmptyMsg, BigDecimalMsg, BigDecimalMsg> ci =
    new BigDecimalColumnInterpreter();
  Double avg = null;
  avg = aClient.avg(TEST_TABLE, ci, scan);
  assertEquals(Double.NaN, avg, 0);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Test(timeout = 300000)
public void testSumWithFilter() throws Throwable {
  AggregationClient aClient = new AggregationClient(conf);
  Filter f = new PrefixFilter(Bytes.toBytes("foo:bar"));
  Scan scan = new Scan();
  scan.addFamily(TEST_FAMILY);
  scan.setFilter(f);
  final ColumnInterpreter<Double, Double, EmptyMsg, DoubleMsg, DoubleMsg> ci = 
      new DoubleColumnInterpreter();
  Double sum = null;
  sum = aClient.sum(TEST_TABLE, ci, scan);
  assertEquals(null, sum);
}
 

import org.apache.hadoop.hbase.client.Scan; //导入方法依赖的package包/类
@Override
public List<String> getUserAuths(byte[] user, boolean systemCall)
    throws IOException {
  assert (labelsRegion != null || systemCall);
  if (systemCall || labelsRegion == null) {
    return this.labelsCache.getUserAuths(Bytes.toString(user));
  }
  Scan s = new Scan();
  if (user != null && user.length > 0) {
    s.addColumn(LABELS_TABLE_FAMILY, user);
  }
  Filter filter = VisibilityUtils.createVisibilityLabelFilter(this.labelsRegion,
    new Authorizations(SYSTEM_LABEL));
  s.setFilter(filter);
  ArrayList<String> auths = new ArrayList<String>();
  RegionScanner scanner = this.labelsRegion.getScanner(s);
  try {
    List<Cell> results = new ArrayList<Cell>(1);
    while (true) {
      scanner.next(results);
      if (results.isEmpty()) break;
      Cell cell = results.get(0);
      int ordinal = Bytes.toInt(cell.getRowArray(), cell.getRowOffset(), cell.getRowLength());
      String label = this.labelsCache.getLabel(ordinal);
      if (label != null) {
        auths.add(label);
      }
      results.clear();
    }
  } finally {
    scanner.close();
  }
  return auths;
}