/**
* Serializations are found by reading the <code>io.serializations</code> property from <code>conf
* </code>, which is a comma-delimited list of classnames.
*/
public SerializationFactory(Configuration conf) {
super(conf);
for (String serializerName :
conf.getStrings(
"io.serializations",
new String[] {"org.apache.hadoop.io.serializer.WritableSerialization"})) {
add(conf, serializerName);
}
}
@SuppressWarnings("unchecked")
private void add(Configuration conf, String serializationName) {
try {
Class<? extends Serialization> serializionClass =
(Class<? extends Serialization>) conf.getClassByName(serializationName);
serializations.add(ReflectionUtils.newInstance(serializionClass, getConf()));
} catch (ClassNotFoundException e) {
LOG.warn("Serilization class not found: " + StringUtils.stringifyException(e));
}
}
@Override
public void setConf(Configuration conf) {
super.setConf(conf);
if (conf.get(NUM_ATTRIBUTES) != null) numAttributes = conf.getInt(NUM_ATTRIBUTES, -1);
}
@Override
public void initialize(Configuration conf, InputSplit split)
throws IOException, InterruptedException {
super.initialize(conf, split);
if (conf.get(NUM_ATTRIBUTES) != null) numAttributes = conf.getInt(NUM_ATTRIBUTES, -1);
}
@Override
public void initialize(Configuration conf) {
minWordFrequency = conf.getInt(TextVectorizer.MIN_WORD_FREQUENCY, 5);
}