Example usage for org.apache.hadoop.io Text readString

Introduction

In this page you can find the example usage for org.apache.hadoop.io Text readString.

Prototype

public static String readString(DataInput in) throws IOException

Source Link

Document

Read a UTF8 encoded string from in

Usage

From source file:com.marklogic.mapreduce.LargeBinaryDocument.java

License:Apache License

@Override
public void readFields(DataInput in) throws IOException {
    super.readFields(in);
    path = new Path(Text.readString(in));
    offset = in.readLong();/* w  ww . ja v a2s.  c  o  m*/
    size = in.readLong();
    binaryOrigLen = in.readLong();
    conf = new Configuration();
    conf.readFields(in);
}

From source file:com.marklogic.mapreduce.MarkLogicInputSplit.java

License:Apache License

@Override
public void readFields(DataInput in) throws IOException {
    start = in.readLong();/* ww w  . j a v  a  2  s .co  m*/
    length = in.readLong();
    Text forestIdText = new Text();
    forestIdText.readFields(in);
    forestId = new BigInteger(forestIdText.getBytes());
    hostName = new String[1];
    hostName[0] = Text.readString(in);
    isLastSplit = in.readBoolean();
}

From source file:com.marklogic.mapreduce.MarkLogicNode.java

License:Apache License

public void readFields(DataInput in) throws IOException {
    int type = in.readInt();
    DocumentBuilder docBuilder = builderLocal.get();
    String val = Text.readString(in);
    try {/*from   ww  w.ja  v  a 2s .c  o m*/
        if (type == Node.ATTRIBUTE_NODE) {
            AttributeImpl attr = new AttributeImpl(Text.readString(in), Text.readString(in));
            node = attr.asW3cNode(docBuilder);
        } else {
            node = DomUtil.readXml(IOHelper.newStream(val));
        }
    } catch (SAXException e) {
        LOG.error("error parsing input", e);
        throw new IOException(e);
    } catch (ParserConfigurationException e) {
        LOG.error("error parsing input", e);
        throw new IOException(e);
    }
}

From source file:com.marklogic.mapreduce.NodePath.java

License:Apache License

@Override
public void readFields(DataInput in) throws IOException {
    docUri = Text.readString(in);
    path = Text.readString(in);
}

From source file:com.marklogic.mapreduce.StreamLocator.java

License:Apache License

@Override
public void readFields(DataInput in) throws IOException {
    path = new Path(Text.readString(in));
    codec = WritableUtils.readEnum(in, CompressionCodec.class);
}

From source file:com.marklogic.mapreduce.utilities.ForestInfo.java

License:Apache License

public void readFields(DataInput in) throws IOException {
    hostName = Text.readString(in);
    frangmentCount = in.readLong();
    updatable = in.readBoolean();
}

From source file:com.pivotal.hawq.mapreduce.ao.file.HAWQAOSplit.java

License:Apache License

@Override
public void readFields(DataInput in) throws IOException {
    super.readFields(in);
    checksum = in.readBoolean();/*from   www  . j  a va  2s .co  m*/
    compressType = Text.readString(in);
    blockSize = in.readInt();
}

From source file:com.scaleoutsoftware.soss.hserver.hadoop.SubmittedJob.java

License:Apache License

@SuppressWarnings("unchecked")
private static <T> T getSplitDetails(FSDataInputStream inFile, long offset, Configuration configuration)
        throws IOException {
    inFile.seek(offset);//from   w w w .ja  v  a  2s  .  c om
    String className = StringInterner.weakIntern(Text.readString(inFile));
    Class<T> cls;
    try {
        cls = (Class<T>) configuration.getClassByName(className);
    } catch (ClassNotFoundException ce) {
        IOException wrap = new IOException("Split class " + className + " not found");
        wrap.initCause(ce);
        throw wrap;
    }
    SerializationFactory factory = new SerializationFactory(configuration);
    Deserializer<T> deserializer = (Deserializer<T>) factory.getDeserializer(cls);
    deserializer.open(inFile);
    T split = deserializer.deserialize(null);
    return split;
}

From source file:com.sensei.indexing.hadoop.keyvalueformat.Shard.java

License:Apache License

public void readFields(DataInput in) throws IOException {
    version = in.readLong();
    dir = Text.readString(in);
    gen = in.readLong();
}

From source file:com.sensei.indexing.hadoop.reduce.RAMDirectoryUtil.java

License:Apache License

/**
 * Read a number of files from a data input to a ram directory.
 * @param in  the data input//from   w  w  w.  j av  a2  s .c om
 * @param dir  the ram directory
 * @throws IOException
 */
public static void readRAMFiles(DataInput in, RAMDirectory dir) throws IOException {
    int numFiles = in.readInt();

    for (int i = 0; i < numFiles; i++) {
        String name = Text.readString(in);
        long length = in.readLong();

        if (length > 0) {
            // can we avoid the extra copy?
            IndexOutput output = null;
            try {
                output = dir.createOutput(name);

                int position = 0;
                byte[] buffer = new byte[BUFFER_SIZE];

                while (position < length) {
                    int len = position + BUFFER_SIZE <= length ? BUFFER_SIZE : (int) (length - position);
                    in.readFully(buffer, 0, len);
                    output.writeBytes(buffer, 0, len);
                    position += len;
                }
            } finally {
                if (output != null) {
                    output.close();
                }
            }
        }
    }
}