private static void createMapReduceJob(
String tableNameToIndex, Configuration conf, int caching, int versions)
throws IOException, InterruptedException, ClassNotFoundException {
// Set the details to TableInputFormat
Scan s = new Scan();
s.setCaching(caching);
s.setMaxVersions(versions);
conf.set(TableInputFormat.INPUT_TABLE, tableNameToIndex);
Set<Entry<String, List<String>>> entrySet = cfs.entrySet();
for (Entry<String, List<String>> entry : entrySet) {
List<String> quals = entry.getValue();
addColumn(quals, Bytes.toBytes(entry.getKey()), s);
}
Job job = new Job(conf, "CreateIndex");
String hfileOutPath = conf.get(BULK_OUTPUT_CONF_KEY);
TableMapReduceUtil.initTableMapperJob(
tableNameToIndex, // input table
s, // Scan instance to control CF and attribute selection
IndexCreationMapper.class, // mapper class
ImmutableBytesWritable.class, // mapper output key
Put.class, // mapper output value
job);
TableMapReduceUtil.initTableReducerJob(
IndexUtils.getIndexTableName(tableNameToIndex), // output
// table
null, // reducer class
job);
if (hfileOutPath != null) {
HTable table = new HTable(conf, tableNameToIndex);
job.setReducerClass(KeyValueSortReducer.class);
Path outputDir = new Path(hfileOutPath);
FileOutputFormat.setOutputPath(job, outputDir);
HFileOutputFormat.configureIncrementalLoad(job, table);
} else {
job.setNumReduceTasks(0);
}
TableMapReduceUtil.addDependencyJars(
job.getConfiguration(), com.google.common.base.Preconditions.class);
job.waitForCompletion(true);
assert job.isComplete() == true;
}
public static void main(String[] args) throws Exception {
Configuration conf = HBaseConfiguration.create();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length < 2) {
System.out.println("Caching and Versions not specified");
System.exit(-1);
}
int caching = -1;
int versions = -1;
try {
caching = Integer.parseInt(otherArgs[0]);
} catch (NumberFormatException nfe) {
caching = DEFAULT_CACHING;
}
try {
versions = Integer.parseInt(otherArgs[1]);
} catch (NumberFormatException nfe) {
versions = DEFAULT_VERSIONS;
}
String[] tableName = conf.getStrings(TABLE_NAME_TO_INDEX);
if (tableName == null) {
System.out.println(
"Wrong usage. Usage is pass the table -Dindex.tablename='table1' "
+ "-Dtable.columns.index='IDX1=>cf1:[q1->datatype& length],[q2],"
+ "[q3];cf2:[q1->datatype&length],[q2->datatype&length],[q3->datatype& lenght]#IDX2=>cf1:q5,q5'");
System.out.println("The format used here is: ");
System.out.println("IDX1 - Index name");
System.out.println("cf1 - Columnfamilyname");
System.out.println("q1 - qualifier");
System.out.println("datatype - datatype (Int, String, Double, Float)");
System.out.println("length - length of the value");
System.out.println("The columnfamily should be seperated by ';'");
System.out.println(
"The qualifier and the datatype and its length should be enclosed in '[]'."
+ " The qualifier details are specified using '->' following qualifer name and the details are seperated by '&'");
System.out.println("If the qualifier details are not specified default values are used.");
System.out.println("# is used to seperate between two index details");
System.out.println("Pass the scanner caching and maxversions as arguments.");
System.exit(-1);
}
String tableNameToIndex = tableName[0];
IndexUtils.createIndexTable(tableNameToIndex, conf, cfs);
createMapReduceJob(tableNameToIndex, conf, caching, versions);
}