过滤器查询
引言：过滤器的类型很多，但是可以分为两大类——比较过滤器，专用过滤器
过滤器的作用是在服务端判断数据是否满足条件，然后只将满足条件的数据返回给客户端；
hbase过滤器的比较运算符：
| LESS < LESS_OR_EQUAL <= EQUAL = NOT_EQUAL <> GREATER_OR_EQUAL >= GREATER > NO_OP 排除所有 |
Hbase过滤器的比较器（指定比较机制）：
| BinaryComparator 按字节索引顺序比较指定字节数组，采用Bytes.compareTo(byte[]) BinaryPrefixComparator 跟前面相同，只是比较左端的数据是否相同 NullComparator 判断给定的是否为空 BitComparator 按位比较 RegexStringComparator 提供一个正则的比较器，仅支持 EQUAL 和非EQUAL SubstringComparator 判断提供的子串是否出现在value中。 |
Hbase的过滤器分类
- 比较过滤器
1.1 行键过滤器RowFilter
| Filter filter1 = new RowFilter(CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("row-22"))); scan.setFilter(filter1); |
1.2 列族过滤器FamilyFilter
| Filter filter1 = new FamilyFilter(CompareFilter.CompareOp.LESS, new BinaryComparator(Bytes.toBytes("colfam3"))); scan.setFilter(filter1); |
1.3 列过滤器QualifierFilter
| filter = new QualifierFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("col-2"))); scan.setFilter(filter1); |
1.4 值过滤器 ValueFilter
| Filter filter = new ValueFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator(".4") ); scan.setFilter(filter1); |
- 专用过滤器
2.1 单列值过滤器 SingleColumnValueFilter ----会返回满足条件的整行
| SingleColumnValueFilter filter = new SingleColumnValueFilter( Bytes.toBytes("colfam1"), Bytes.toBytes("col-5"), CompareFilter.CompareOp.NOT_EQUAL, new SubstringComparator("val-5")); filter.setFilterIfMissing(true); //如果不设置为true，则那些不包含指定column的行也会返回 scan.setFilter(filter1); |
2.2 SingleColumnValueExcludeFilter
与上相反
2.3 前缀过滤器 PrefixFilter----针对行键
| Filter filter = new PrefixFilter(Bytes.toBytes("row1")); scan.setFilter(filter1); |
2.4 列前缀过滤器 ColumnPrefixFilter
| Filter filter = new ColumnPrefixFilter(Bytes.toBytes("qual2")); scan.setFilter(filter1); |
2.4分页过滤器 PageFilter
| public static void main(String[] args) throws Exception { Configuration conf = HBaseConfiguration.create(); conf.set("hbase.zookeeper.quorum", "spark01:2181,spark02:2181,spark03:2181");
String tableName = "testfilter"; String cfName = "f1"; final byte[] POSTFIX = new byte[] { 0x00 }; HTable table = new HTable(conf, tableName); Filter filter = new PageFilter(3); byte[] lastRow = null; int totalRows = 0; while (true) { Scan scan = new Scan(); scan.setFilter(filter); if(lastRow != null){ //注意这里添加了POSTFIX操作，用来重置扫描边界 byte[] startRow = Bytes.add(lastRow,POSTFIX); scan.setStartRow(startRow); } ResultScanner scanner = table.getScanner(scan); int localRows = 0; Result result; while((result = scanner.next()) != null){ System.out.println(localRows++ + ":" + result); totalRows ++; lastRow = result.getRow(); } scanner.close(); if(localRows == 0) break; } System.out.println("total rows:" + totalRows); } |
| /** * 多种过滤条件的使用方法 * @throws Exception */ @Test public void testScan() throws Exception{ HTable table = new HTable(conf, "person_info".getBytes()); Scan scan = new Scan(Bytes.toBytes("person_rk_bj_zhang_000001"), Bytes.toBytes("person_rk_bj_zhang_000002"));
//前缀过滤器----针对行键 Filter filter = new PrefixFilter(Bytes.toBytes("rk"));
//行过滤器 ---针对行键 ByteArrayComparable rowComparator = new BinaryComparator(Bytes.toBytes("person_rk_bj_zhang_000001")); RowFilter rf = new RowFilter(CompareOp.LESS_OR_EQUAL, rowComparator);
/** * 假设rowkey格式为：创建日期_发布日期_ID_TITLE * 目标：查找 发布日期 为 2014-12-21 的数据 * sc.textFile("path").flatMap(line=>line.split("\t")).map(x=>(x,1)).reduceByKey(_+_).map((_(2),_(1))).sortByKey().map((_(2),_(1))).saveAsTextFile("") * * */ rf = new RowFilter(CompareOp.EQUAL , new SubstringComparator("_2014-12-21_"));
//单值过滤器1完整匹配字节数组 new SingleColumnValueFilter("base_info".getBytes(), "name".getBytes(), CompareOp.EQUAL, "zhangsan".getBytes()); //单值过滤器2 匹配正则表达式 ByteArrayComparable comparator = new RegexStringComparator("zhang."); new SingleColumnValueFilter("info".getBytes(), "NAME".getBytes(), CompareOp.EQUAL, comparator);
//单值过滤器3匹配是否包含子串,大小写不敏感 comparator = new SubstringComparator("wu"); new SingleColumnValueFilter("info".getBytes(), "NAME".getBytes(), CompareOp.EQUAL, comparator);
//键值对元数据过滤-----family过滤----字节数组完整匹配 FamilyFilter ff = new FamilyFilter( CompareOp.EQUAL , new BinaryComparator(Bytes.toBytes("base_info")) //表中不存在inf列族，过滤结果为空 ); //键值对元数据过滤-----family过滤----字节数组前缀匹配 ff = new FamilyFilter( CompareOp.EQUAL , new BinaryPrefixComparator(Bytes.toBytes("inf")) //表中存在以inf打头的列族info，过滤结果为该列族所有行 );
//键值对元数据过滤-----qualifier过滤----字节数组完整匹配
filter = new QualifierFilter( CompareOp.EQUAL , new BinaryComparator(Bytes.toBytes("na")) //表中不存在na列，过滤结果为空 ); filter = new QualifierFilter( CompareOp.EQUAL , new BinaryPrefixComparator(Bytes.toBytes("na")) //表中存在以na打头的列name，过滤结果为所有行的该列数据 );
//基于列名(即Qualifier)前缀过滤数据的ColumnPrefixFilter filter = new ColumnPrefixFilter("na".getBytes());
//基于列名(即Qualifier)多个前缀过滤数据的MultipleColumnPrefixFilter byte[][] prefixes = new byte[][] {Bytes.toBytes("na"), Bytes.toBytes("me")}; filter = new MultipleColumnPrefixFilter(prefixes);
//为查询设置过滤条件 scan.setFilter(filter);
scan.addFamily(Bytes.toBytes("base_info")); //一行 // Result result = table.get(get); //多行的数据 ResultScanner scanner = table.getScanner(scan); for(Result r : scanner){ /** for(KeyValue kv : r.list()){ String family = new String(kv.getFamily()); System.out.println(family); String qualifier = new String(kv.getQualifier()); System.out.println(qualifier); System.out.println(new String(kv.getValue())); } */ //直接从result中取到某个特定的value byte[] value = r.getValue(Bytes.toBytes("base_info"), Bytes.toBytes("name")); System.out.println(new String(value)); } table.close(); } |