Hadoop學習記錄(五、hadoop IO操作)
阿新 • • 發佈:2018-12-06
1.壓縮從標準輸入讀取的資料,然後將其寫到標準輸出
通過GzipCodec的StreamCompressor物件對字串“Text”進行壓縮,再使用gunzip從標準輸出中對它進行讀取並解壓縮
public class StreamCompressor { public static void main(String[] args) throws Exception { String codecClassname = args[0]; Class<?> codecClass = Class.forName(codecClassname); Configuration conf = new Configuration(); CompressionCodec codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); CompressionOutputStream out = codec.createOutputStream(System.out); IOUtils.copyBytes(System.in, out, 4096, false); out.finish(); } }
2.根據副檔名選取codec解壓縮檔案
public class FileDecompressor { public static void main(String[] args) throws Exception { String uri = args[0]; Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(URI.create(uri), conf); Path inputPath = new Path(uri); CompressionCodecFactory factory = new CompressionCodecFactory(conf); CompressionCodec codec = factory.getCodec(inputPath); if (codec == null) { System.err.println("No codec found for " + uri); System.exit(1); } String outputUri = CompressionCodecFactory.removeSuffix(uri, codec.getDefaultExtension()); InputStream in = null; OutputStream out = null; try { in = codec.createInputStream(fs.open(inputPath)); out = fs.create(new Path(outputUri)); IOUtils.copyBytes(in, out, conf); } finally { IOUtils.closeStream(in); IOUtils.closeStream(out); } } }
3. 使用壓縮池對讀取自標準輸入資料進行壓縮,然後將其寫在標準輸出裡
public class PooledStreamCompressor { public static void main(String[] args) throws Exception { String codecClassname = args[0]; Class<?> codecClass = Class.forName(codecClassname); Configuration conf = new Configuration(); CompressionCodec codec = (CompressionCodec) ReflectionUtils.newInstance(codecClass, conf); Compressor compressor = null; try { compressor = CodecPool.getCompressor(codec); CompressionOutputStream out = codec.createOutputStream(System.out, compressor); IOUtils.copyBytes(System.in, out, 4096, false); out.finish(); } finally { CodecPool.returnCompressor(compressor); } } }
4.在MapReduce中使用壓縮
對輸出進行壓縮
./hadoop jar /tmp/hadoop-1.0-SNAPSHOT.jar HotSearch /input/IAMSinger.txt /output/
5.使用SequenceFile對小檔案進行讀取
public class SequenceFileWriteDemo {
private static final String[] DATA = {
"One, two, buckle my shoe",
"Three, four, shut the door",
"Five, six, pick up sticks",
"Seven, eight, lay them straight",
"Nine, ten, a big fat hen"
};
public static void main(String[] args) throws IOException {
String uri = args[0];
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(uri), conf);
Path path = new Path(uri);
IntWritable key = new IntWritable();
Text value = new Text();
SequenceFile.Writer writer = null;
try {
writer = SequenceFile.createWriter(fs, conf, path,
key.getClass(), value.getClass());
for (int i = 0; i < 100; i++) {
key.set(100 - i);
value.set(DATA[i % DATA.length]);
System.out.printf("[%s]\t%s\t%s\n", writer.getLength(), key, value);
writer.append(key, value);
}
} finally {
IOUtils.closeStream(writer);
}
}
}
public class SequenceFileReadDemo {
public static void main(String[] args) throws IOException {
String uri = args[0];
Configuration conf = new Configuration();
FileSystem fs = FileSystem.get(URI.create(uri), conf);
Path path = new Path(uri);
SequenceFile.Reader reader = null;
try {
reader = new SequenceFile.Reader(fs, path, conf);
Writable key = (Writable)
ReflectionUtils.newInstance(reader.getKeyClass(), conf);
Writable value = (Writable)
ReflectionUtils.newInstance(reader.getValueClass(), conf);
long position = reader.getPosition();
while (reader.next(key, value)) {
String syncSeen = reader.syncSeen() ? "*" : "";
System.out.printf("[%s%s]\t%s\t%s\n", position, syncSeen, key, value);
position = reader.getPosition(); // beginning of next record
}
} finally {
IOUtils.closeStream(reader);
}
}
}