[hadoop2.7.1]I/O之序列化(WritableSerialization)示例
程序员文章站
2024-01-15 17:18:22
...
首先先引入hadoop2.7.1中的一个工具类GenericsUtil,顾名思义,是用来处理java泛型的一个工具类,这个类很简单,但很实用,不多说,直接上源码:
package org.apache.hadoop.util; import java.lang.reflect.Array; import java.util.List; import org.apache.hadoop.classification.InterfaceAudience; import org.apache.hadoop.classification.InterfaceStability; /** * Contains utility methods for dealing with Java Generics. */ @InterfaceAudience.Private @InterfaceStability.Unstable public class GenericsUtil { /** * Returns the Class object (of type <code>Class<T></code>) of the * argument of type <code>T</code>. * @param <T> The type of the argument * @param t the object to get it class * @return <code>Class<T></code> */ public static <T> Class<T> getClass(T t) { @SuppressWarnings("unchecked") Class<T> clazz = (Class<T>)t.getClass(); return clazz; } /** * Converts the given <code>List<T></code> to a an array of * <code>T[]</code>. * @param c the Class object of the items in the list * @param list the list to convert */ public static <T> T[] toArray(Class<T> c, List<T> list) { @SuppressWarnings("unchecked") T[] ta= (T[])Array.newInstance(c, list.size()); for (int i= 0; i<list.size(); i++) ta[i]= list.get(i); return ta; } /** * Converts the given <code>List<T></code> to a an array of * <code>T[]</code>. * @param list the list to convert * @throws ArrayIndexOutOfBoundsException if the list is empty. * Use {@link #toArray(Class, List)} if the list may be empty. */ public static <T> T[] toArray(List<T> list) { return toArray(getClass(list.get(0)), list); } }
利用上面的工具类,下面举一个TestWritableSerialization的一个示例,源码如下:
import java.io.Serializable; import java.util.EnumSet; import org.apache.hadoop.io.DataInputBuffer; import org.apache.hadoop.io.DataOutputBuffer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.io.ArrayWritable; import org.apache.hadoop.io.EnumSetWritable; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.BytesWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.Writable; import org.apache.hadoop.io.WritableComparator; import org.apache.hadoop.util.GenericsUtil; import org.junit.Test; import static org.junit.Assert.*; public class THT_TestWritableSerialization { private static final Configuration conf = new Configuration(); enum TestEnumSet { CREATE, OVERWRITE, APPEND; } @Test public void testWritableSerialization() throws Exception { IntWritable before1 = new IntWritable(123456789); byte[] hadoop = "hadoop".getBytes(); BytesWritable before2 = new BytesWritable(hadoop); String[] arraywr = { "zero", "one", "two" }; ArrayWritable arraywrA = new ArrayWritable(arraywr); Writable[] arraywrW = arraywrA.get(); Writable before3 = arraywrW[0]; EnumSetWritable<TestEnumSet> before4 = new EnumSetWritable<TestEnumSet>( EnumSet.of(TestEnumSet.APPEND)); Text before5=new Text("test for you"); IntWritable after1 = testSerialization(conf, before1); BytesWritable after2 = testSerialization(conf, before2); Writable after3 = testSerialization(conf, before3); EnumSetWritable<TestEnumSet> after4 = testSerialization(conf, before4); Text after5 = testSerialization(conf, before5); assertEquals(before1, after1); assertEquals(before2, after2); assertEquals(before3, after3); assertEquals(before4, after4); assertEquals(before5, after5); } public static <K> K testSerialization(Configuration conf, K before) throws Exception { SerializationFactory factory = new SerializationFactory(conf); Serializer<K> serializer = factory.getSerializer(GenericsUtil .getClass(before)); Deserializer<K> deserializer = factory.getDeserializer(GenericsUtil .getClass(before)); DataOutputBuffer out = new DataOutputBuffer(); serializer.open(out); serializer.serialize(before); serializer.close(); DataInputBuffer in = new DataInputBuffer(); in.reset(out.getData(), out.getLength()); deserializer.open(in); K after = deserializer.deserialize(null); deserializer.close(); return after; } }
上一篇: 软件测试推荐书目【转】
下一篇: 开博客 2012年9月16日