List of usage examples for org.apache.hadoop.io DefaultStringifier loadArray
public static <K> K[] loadArray(Configuration conf, String keyName, Class<K> itemClass) throws IOException
From source file:RandIntPartSamplerMapper.java
License:Apache License
@Override public void configure(JobConf conf) { id = conf.getInt("mapred.task.partition", -1); reducersNum = conf.getInt("PARMM.reducersNum", 1000); try {// ww w . j a va 2 s . c o m int id = conf.getInt("mapred.task.partition", -1); System.out.println("id: " + id); IntWritable[] toSampleArr = DefaultStringifier.loadArray(conf, "PARMM.toSampleArr_" + id, IntWritable.class); toSample = 0; for (IntWritable toSampleRed : toSampleArr) { toSample += toSampleRed.get(); } System.out.println("toSample: " + toSample); sampleDestinations = new IntWritable[toSample]; int i = 0; for (int k = 0; k < toSampleArr.length; k++) { for (int j = 0; j < toSampleArr[k].get(); j++) { sampleDestinations[i++] = new IntWritable(k); } } Collections.shuffle(Arrays.asList(sampleDestinations)); } catch (IOException e) { } }
From source file:org.apache.sqoop.mapreduce.hcat.SqoopHCatImportHelper.java
License:Apache License
public SqoopHCatImportHelper(Configuration conf) throws IOException, InterruptedException { String inputJobInfoStr = conf.get(HCatConstants.HCAT_KEY_JOB_INFO); jobInfo = (InputJobInfo) HCatUtil.deserialize(inputJobInfoStr); dataColsSchema = jobInfo.getTableInfo().getDataColumns(); partitionSchema = jobInfo.getTableInfo().getPartitionColumns(); StringBuilder storerInfoStr = new StringBuilder(1024); StorerInfo storerInfo = jobInfo.getTableInfo().getStorerInfo(); storerInfoStr.append("HCatalog Storer Info : ").append("\n\tHandler = ") .append(storerInfo.getStorageHandlerClass()).append("\n\tInput format class = ") .append(storerInfo.getIfClass()).append("\n\tOutput format class = ") .append(storerInfo.getOfClass()).append("\n\tSerde class = ").append(storerInfo.getSerdeClass()); Properties storerProperties = storerInfo.getProperties(); if (!storerProperties.isEmpty()) { storerInfoStr.append("\nStorer properties "); for (Map.Entry<Object, Object> entry : storerProperties.entrySet()) { String key = (String) entry.getKey(); Object val = entry.getValue(); storerInfoStr.append("\n\t").append(key).append('=').append(val); }//from w ww. ja v a 2 s . c o m } storerInfoStr.append("\n"); LOG.info(storerInfoStr); hCatFullTableSchema = new HCatSchema(dataColsSchema.getFields()); for (HCatFieldSchema hfs : partitionSchema.getFields()) { hCatFullTableSchema.append(hfs); } fieldCount = hCatFullTableSchema.size(); lobLoader = new LargeObjectLoader(conf, new Path(jobInfo.getTableInfo().getTableLocation())); bigDecimalFormatString = conf.getBoolean(ImportJobBase.PROPERTY_BIGDECIMAL_FORMAT, ImportJobBase.PROPERTY_BIGDECIMAL_FORMAT_DEFAULT); debugHCatImportMapper = conf.getBoolean(SqoopHCatUtilities.DEBUG_HCAT_IMPORT_MAPPER_PROP, false); IntWritable[] delimChars = DefaultStringifier.loadArray(conf, SqoopHCatUtilities.HIVE_DELIMITERS_TO_REPLACE_PROP, IntWritable.class); hiveDelimiters = new DelimiterSet((char) delimChars[0].get(), (char) delimChars[1].get(), (char) delimChars[2].get(), (char) delimChars[3].get(), delimChars[4].get() == 1 ? true : false); hiveDelimsReplacement = conf.get(SqoopHCatUtilities.HIVE_DELIMITERS_REPLACEMENT_PROP); if (hiveDelimsReplacement == null) { hiveDelimsReplacement = ""; } doHiveDelimsReplacement = Boolean .valueOf(conf.get(SqoopHCatUtilities.HIVE_DELIMITERS_REPLACEMENT_ENABLED_PROP)); IntWritable[] fPos = DefaultStringifier.loadArray(conf, SqoopHCatUtilities.HCAT_FIELD_POSITIONS_PROP, IntWritable.class); hCatFieldPositions = new int[fPos.length]; for (int i = 0; i < fPos.length; ++i) { hCatFieldPositions[i] = fPos[i].get(); } LOG.debug("Hive delims replacement enabled : " + doHiveDelimsReplacement); LOG.debug("Hive Delimiters : " + hiveDelimiters.toString()); LOG.debug("Hive delimiters replacement : " + hiveDelimsReplacement); staticPartitionKey = conf.get(SqoopHCatUtilities.HCAT_STATIC_PARTITION_KEY_PROP); LOG.debug("Static partition key used : " + staticPartitionKey); }