* 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()){