本帖最后由 pig2 于 2014-2-4 00:25 编辑
1、例子一 import java.io.IOException;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Scanner;
import org.apache.hadoop.hbase.io.BatchUpdate;
import org.apache.hadoop.hbase.io.Cell;
import org.apache.hadoop.hbase.io.RowResult; public class MyClient { public static void main(String args[]) throws IOException {
// You need a configuration object to tell the client where to connect.
// But don't worry, the defaults are pulled from the local config file.
HBaseConfiguration config = new HBaseConfiguration(); // This instantiates an HTable object that connects you to the "myTable"
// table.
HTable table = new HTable(config, "myTable"); // To do any sort of update on a row, you use an instance of the BatchUpdate
// class. A BatchUpdate takes a row and optionally a timestamp which your
// updates will affect.
BatchUpdate batchUpdate = new BatchUpdate("myRow"); // The BatchUpdate#put method takes a Text that describes what cell you want
// to put a value into, and a byte array that is the value you want to
// store. Note that if you want to store strings, you have to getBytes()
// from the string for HBase to understand how to store it. (The same goes
// for primitives like ints and longs and user-defined classes - you must
// find a way to reduce it to bytes.)
batchUpdate.put("myColumnFamily:columnQualifier1",
"columnQualifier1 value!".getBytes()); // Deletes are batch operations in HBase as well.
batchUpdate.delete("myColumnFamily:cellIWantDeleted"); // Once you've done all the puts you want, you need to commit the results.
// The HTable#commit method takes the BatchUpdate instance you've been
// building and pushes the batch of changes you made into HBase.
table.commit(batchUpdate); // Now, to retrieve the data we just wrote. The values that come back are
// Cell instances. A Cell is a combination of the value as a byte array and
// the timestamp the value was stored with. If you happen to know that the
// value contained is a string and want an actual string, then you must
// convert it yourself.
Cell cell = table.get("myRow", "myColumnFamily:columnQualifier1");
String valueStr = new String(cell.getValue());
// Sometimes, you won't know the row you're looking for. In this case, you
// use a Scanner. This will give you cursor-like interface to the contents
// of the table.
Scanner scanner =
// we want to get back only "myColumnFamily:columnQualifier1" when we iterate
table.getScanner(new String[]{"myColumnFamily:columnQualifier1"});
// Scanners in HBase 0.2 return RowResult instances. A RowResult is like the
// row key and the columns all wrapped up in a single interface.
// RowResult#getRow gives you the row key. RowResult also implements
// Map, so you can get to your column results easily.
// Now, for the actual iteration. One way is to use a while loop like so:
RowResult rowResult = scanner.next();
while(rowResult != null) {
// print out the row we found and the columns we were looking for
System.out.println("Found row: " + new String(rowResult.getRow()) + " with value: " +
rowResult.get("myColumnFamily:columnQualifier1".getBytes()));
rowResult = scanner.next();
}
// The other approach is to use a foreach loop. Scanners are iterable!
for (RowResult result : scanner) {
// print out the row we found and the columns we were looking for
System.out.println("Found row: " + new String(result.getRow()) + " with value: " +
result.get("myColumnFamily:columnQualifier1".getBytes()));
}
// Make sure you close your scanners when you are done!
scanner.close();
}
} 在这个例子中,使用了HBase中的很多概念,包括:
HBaseConfiguration: 用于告诉client如何连接,连接到哪个HBase的服务器上。
HTable:代表一个HBase表格。
BatchUpdate:用于表格中一行的更新。包括添加某个列,修改某列的值,删除某列等。
commit:table的一个方法。代表某个BatchUpdate操作可以生效了。类似于数据库中的commit操作。 Cell:table中对应某个(行key, 列值,时间戳)下的单元格值。
获取Cell的方法。For example:
table.get("myRow", "myColumnFamily:columnQualifier1"); scanner:用于遍历表格。
rowResult:遍历过程当中保存某行信息。 2、例子二 通过编码(java)的形式对HBase进行一系列的管理涉及到对表的管理、数据的操作等。 1、 对表的创建、删除、显示以及修改等,可以用HBaseAdmin,一旦创建了表,那么可以通过HTable的实例来访问表,每次可以往表里增加数据。 2、 插入数据 创建一个Put对象,在这个Put对象里可以指定要给哪个列增加数据,以及当前的时间戳等值,然后通过调用HTable.put(Put)来提交操作,子猴在这里提请注意的是:在创建Put对象的时候,你必须指定一个行(Row)值,在构造Put对象的时候作为参数传入。 3、 获取数据 要获取数据,使用Get对象,Get对象同Put对象一样有好几个构造函数,通常在构造的时候传入行值,表示取第几行的数据,通过HTable.get(Get)来调用。 4、 浏览每一行 通过Scan可以对表中的行进行浏览,得到每一行的信息,比如列名,时间戳等,Scan 相当于一个游标,通过next()来浏览下一个,通过调用HTable.getScanner(Scan) 来返回一个ResultScanner对象。HTable.get(Get)和HTable.getScanner(Scan) 都是返回一个Result。Result是一个KeyValue的链表, 5、 删除 使用Delete来删除记录,通过调用HTable.delete(Delete)来执行删除操作。(注:删除这里有些特别,也就是删除并不是马上将数据从表中删除。) 6、 锁 7、 新增、获取、删除在操作过程中会对所操作的行加一个锁,而浏览却不会。 8、 簇(cluster)的访问 客户端代码通过ZooKeeper来访问找到簇,也就是说ZooKeeper quorum将被使用,那么相关的类(包)应该在客户端的类(classes)目录下,即客户端一定要找到文件hbase-site.xml。 下面是一个例子,假定你已经创建了一个表:myTable,还有一个column family(这个找不到合适的翻译词语):myColumnFamily: import java.io.IOException; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.client.Get; import org.apache.hadoop.hbase.client.HTable; import org.apache.hadoop.hbase.client.Put; import org.apache.hadoop.hbase.client.Result; import org.apache.hadoop.hbase.client.ResultScanner; import org.apache.hadoop.hbase.client.Scan; import org.apache.hadoop.hbase.util.Bytes; // Class that has nothing but a main. // Does a Put, Get and a Scan against an hbase table. public class MyLittleHBaseClient { public static void main(String[] args) throws IOException { // You need a configuration object to tell the client where to connect. // When you create a HBaseConfiguration, it reads in whatever you've set // into your hbase-site.xml and in hbase-default.xml, as long as these can // be found on the CLASSPATH HBaseConfiguration config = new HBaseConfiguration(); // This instantiates an HTable object that connects you to // the "myLittleHBaseTable" table. HTable table = new HTable(config, "myLittleHBaseTable"); // To add to a row, use Put. A Put constructor takes the name of the row // you want to insert into as a byte array. In HBase, the Bytes class has // utility for converting all kinds of java types to byte arrays. In the // below, we are converting the String "myLittleRow" into a byte array to // use as a row key for our update. Once you have a Put instance, you can // adorn it by setting the names of columns you want to update on the row, // the timestamp to use in your update, etc.If no timestamp, the server // applies current time to the edits. Put p = new Put(Bytes.toBytes("myLittleRow")); // To set the value you'd like to update in the row 'myLittleRow', specify // the column family, column qualifier, and value of the table cell you'd // like to update. The column family must already exist in your table // schema. The qualifier can be anything. All must be specified as byte // arrays as hbase is all about byte arrays. Lets pretend the table // 'myLittleHBaseTable' was created with a family 'myLittleFamily'. p.add(Bytes.toBytes("myLittleFamily"), Bytes.toBytes("someQualifier"), Bytes.toBytes("Some Value")); // Once you've adorned your Put instance with all the updates you want to // make, to commit it do the following (The HTable#put method takes the // Put instance you've been building and pushes the changes you made into // hbase) table.put(p); // Now, to retrieve the data we just wrote. The values that come back are // Result instances. Generally, a Result is an object that will package up // the hbase return into the form you find most palatable. Get g = new Get(Bytes.toBytes("myLittleRow")); Result r = table.get(g); byte [] value = r.getValue(Bytes.toBytes("myLittleFamily"), Bytes.toBytes("someQualifier")); // If we convert the value bytes, we should get back 'Some Value', the // value we inserted at this location. String valueStr = Bytes.toString(value); System.out.println("GET: " + valueStr); // Sometimes, you won't know the row you're looking for. In this case, you // use a Scanner. This will give you cursor-like interface to the contents // of the table. To set up a Scanner, do like you did above making a Put // and a Get, create a Scan. Adorn it with column names, etc. Scan s = new Scan(); s.addColumn(Bytes.toBytes("myLittleFamily"), Bytes.toBytes("someQualifier")); ResultScanner scanner = table.getScanner(s); try { // Scanners return Result instances. // Now, for the actual iteration. One way is to use a while loop like so: for (Result rr = scanner.next(); rr != null; rr = scanner.next()) { // print out the row we found and the columns we were looking for System.out.println("Found row: " + rr); } // The other approach is to use a foreach loop. Scanners are iterable! // for (Result rr : scanner) { // System.out.println("Found row: " + rr); // } } finally { // Make sure you close your scanners when you are done! // Thats why we have it inside a try/finally clause scanner.close(); } } } |