方法名称和描述 |
Public abstract ReaderContext prepareRead() throws HCatException
这应该在主节点上调用以获得 ReaderContext,然后将其序列化并发送给从节点。
|
Public abstract Iterator <HCatRecorder> read() throws HCaException
这应该在从节点上调用以读取 HCatRecords。
|
Public Configuration getConf()
它将返回配置类对象。
|
ReadEntity.Builder builder = new ReadEntity.Builder(); ReadEntity entity = builder.withDatabase("mydb").withTable("mytbl").build(); 10.
HCatReader reader = DataTransferFactory.getHCatReader(entity, config);
ReaderContext cntxt = reader.prepareRead();
方法名称和描述 |
Public abstract WriterContext prepareRead() throws HCatException
外部系统应该从主节点调用该方法一次。它返回一个
WriterContext。这应该被序列化并发送到从节点以在那里构建
HCatWriter。
|
Public abstract void write(Iterator<HCatRecord> recordItr) throws HCaException
这个方法应该在从节点上使用来执行写操作。 recordItr 是一个迭代器对象,包含要写入 HCatalog 的记录集合。
|
public abstract void abort(WriterContext cntxt) throws HCatException
这个方法应该在master节点调用。此方法的主要目的是在出现故障时进行清理。
|
public abstract void commit(WriterContext cntxt) throws HCatException
这个方法应该在master节点调用。这个方法的目的是做元数据提交。
|
WriteEntity.Builder builder = new WriteEntity.Builder(); WriteEntity entity = builder.withDatabase("mydb").withTable("mytbl").build();
entity
,可用于写入数据库
mydb中名为
mytbl的表。
HCatWriter writer = DataTransferFactory.getHCatWriter(entity, config); WriterContext info = writer.prepareWrite();
HCatWriter writer = DataTransferFactory.getHCatWriter(context);
write
方法的参数-
writer.write(hCatRecordItr);
import java.io.File; import java.io.FileInputStream; import java.io.FileOutputStream; import java.io.IOException; import java.io.ObjectInputStream; import java.io.ObjectOutputStream; import java.util.ArrayList; import java.util.HashMap; import java.util.Iterator; import java.util.List; import java.util.Map; import java.util.Map.Entry; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hive.metastore.api.MetaException; import org.apache.hadoop.hive.ql.CommandNeedRetryException; import org.apache.hadoop.mapreduce.InputSplit; import org.apache.hive.HCatalog.common.HCatException; import org.apache.hive.HCatalog.data.transfer.DataTransferFactory; import org.apache.hive.HCatalog.data.transfer.HCatReader; import org.apache.hive.HCatalog.data.transfer.HCatWriter; import org.apache.hive.HCatalog.data.transfer.ReadEntity; import org.apache.hive.HCatalog.data.transfer.ReaderContext; import org.apache.hive.HCatalog.data.transfer.WriteEntity; import org.apache.hive.HCatalog.data.transfer.WriterContext; import org.apache.hive.HCatalog.mapreduce.HCatBaseTest; import org.junit.Assert; import org.junit.Test; public class TestReaderWriter extends HCatBaseTest { @Test public void test() throws MetaException, CommandNeedRetryException, IOException, ClassNotFoundException { driver.run("drop table mytbl"); driver.run("create table mytbl (a string, b int)"); Iterator<Entry<String, String>> itr = hiveConf.iterator(); Map<String, String> map = new HashMap<String, String>(); while (itr.hasNext()) { Entry<String, String> kv = itr.next(); map.put(kv.getKey(), kv.getValue()); } WriterContext cntxt = runsInMaster(map); File writeCntxtFile = File.createTempFile("hcat-write", "temp"); writeCntxtFile.deleteOnExit(); // Serialize context. ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(writeCntxtFile)); oos.writeObject(cntxt); oos.flush(); oos.close(); // Now, deserialize it. ObjectInputStream ois = new ObjectInputStream(new FileInputStream(writeCntxtFile)); cntxt = (WriterContext) ois.readObject(); ois.close(); runsInSlave(cntxt); commit(map, true, cntxt); ReaderContext readCntxt = runsInMaster(map, false); File readCntxtFile = File.createTempFile("hcat-read", "temp"); readCntxtFile.deleteOnExit(); oos = new ObjectOutputStream(new FileOutputStream(readCntxtFile)); oos.writeObject(readCntxt); oos.flush(); oos.close(); ois = new ObjectInputStream(new FileInputStream(readCntxtFile)); readCntxt = (ReaderContext) ois.readObject(); ois.close(); for (int i = 0; i < readCntxt.numSplits(); i++) { runsInSlave(readCntxt, i); } } private WriterContext runsInMaster(Map<String, String> config) throws HCatException { WriteEntity.Builder builder = new WriteEntity.Builder(); WriteEntity entity = builder.withTable("mytbl").build(); HCatWriter writer = DataTransferFactory.getHCatWriter(entity, config); WriterContext info = writer.prepareWrite(); return info; } private ReaderContext runsInMaster(Map<String, String> config, boolean bogus) throws HCatException { ReadEntity entity = new ReadEntity.Builder().withTable("mytbl").build(); HCatReader reader = DataTransferFactory.getHCatReader(entity, config); ReaderContext cntxt = reader.prepareRead(); return cntxt; } private void runsInSlave(ReaderContext cntxt, int slaveNum) throws HCatException { HCatReader reader = DataTransferFactory.getHCatReader(cntxt, slaveNum); Iterator<HCatRecord> itr = reader.read(); int i = 1; while (itr.hasNext()) { HCatRecord read = itr.next(); HCatRecord written = getRecord(i++); // Argh, HCatRecord doesnt implement equals() Assert.assertTrue("Read: " + read.get(0) + "Written: " + written.get(0), written.get(0).equals(read.get(0))); Assert.assertTrue("Read: " + read.get(1) + "Written: " + written.get(1), written.get(1).equals(read.get(1))); Assert.assertEquals(2, read.size()); } //Assert.assertFalse(itr.hasNext()); } private void runsInSlave(WriterContext context) throws HCatException { HCatWriter writer = DataTransferFactory.getHCatWriter(context); writer.write(new HCatRecordItr()); } private void commit(Map<String, String> config, boolean status, WriterContext context) throws IOException { WriteEntity.Builder builder = new WriteEntity.Builder(); WriteEntity entity = builder.withTable("mytbl").build(); HCatWriter writer = DataTransferFactory.getHCatWriter(entity, config); if (status) { writer.commit(context); } else { writer.abort(context); } } private static HCatRecord getRecord(int i) { List<Object> list = new ArrayList<Object>(2); list.add("Row #: " + i); list.add(i); return new DefaultHCatRecord(list); } private static class HCatRecordItr implements Iterator<HCatRecord> { int i = 0; @Override public boolean hasNext() { return i++ < 100 ? true : false; } @Override public HCatRecord next() { return getRecord(i); } @Override public void remove() { throw new RuntimeException(); } } }