in community/mahout-mr/integration/src/main/java/org/apache/mahout/utils/vectors/lucene/Driver.java [146:284]
public static void main(String[] args) throws IOException {
DefaultOptionBuilder obuilder = new DefaultOptionBuilder();
ArgumentBuilder abuilder = new ArgumentBuilder();
GroupBuilder gbuilder = new GroupBuilder();
Option inputOpt = obuilder.withLongName("dir").withRequired(true).withArgument(
abuilder.withName("dir").withMinimum(1).withMaximum(1).create())
.withDescription("The Lucene directory").withShortName("d").create();
Option outputOpt = obuilder.withLongName("output").withRequired(true).withArgument(
abuilder.withName("output").withMinimum(1).withMaximum(1).create()).withDescription("The output file")
.withShortName("o").create();
Option fieldOpt = obuilder.withLongName("field").withRequired(true).withArgument(
abuilder.withName("field").withMinimum(1).withMaximum(1).create()).withDescription(
"The field in the index").withShortName("f").create();
Option idFieldOpt = obuilder.withLongName("idField").withRequired(false).withArgument(
abuilder.withName("idField").withMinimum(1).withMaximum(1).create()).withDescription(
"The field in the index containing the index. If null, then the Lucene internal doc "
+ "id is used which is prone to error if the underlying index changes").create();
Option dictOutOpt = obuilder.withLongName("dictOut").withRequired(true).withArgument(
abuilder.withName("dictOut").withMinimum(1).withMaximum(1).create()).withDescription(
"The output of the dictionary").withShortName("t").create();
Option seqDictOutOpt = obuilder.withLongName("seqDictOut").withRequired(false).withArgument(
abuilder.withName("seqDictOut").withMinimum(1).withMaximum(1).create()).withDescription(
"The output of the dictionary as sequence file").withShortName("st").create();
Option weightOpt = obuilder.withLongName("weight").withRequired(false).withArgument(
abuilder.withName("weight").withMinimum(1).withMaximum(1).create()).withDescription(
"The kind of weight to use. Currently TF or TFIDF").withShortName("w").create();
Option delimiterOpt = obuilder.withLongName("delimiter").withRequired(false).withArgument(
abuilder.withName("delimiter").withMinimum(1).withMaximum(1).create()).withDescription(
"The delimiter for outputting the dictionary").withShortName("l").create();
Option powerOpt = obuilder.withLongName("norm").withRequired(false).withArgument(
abuilder.withName("norm").withMinimum(1).withMaximum(1).create()).withDescription(
"The norm to use, expressed as either a double or \"INF\" if you want to use the Infinite norm. "
+ "Must be greater or equal to 0. The default is not to normalize").withShortName("n").create();
Option maxOpt = obuilder.withLongName("max").withRequired(false).withArgument(
abuilder.withName("max").withMinimum(1).withMaximum(1).create()).withDescription(
"The maximum number of vectors to output. If not specified, then it will loop over all docs")
.withShortName("m").create();
Option minDFOpt = obuilder.withLongName("minDF").withRequired(false).withArgument(
abuilder.withName("minDF").withMinimum(1).withMaximum(1).create()).withDescription(
"The minimum document frequency. Default is 1").withShortName("md").create();
Option maxDFPercentOpt = obuilder.withLongName("maxDFPercent").withRequired(false).withArgument(
abuilder.withName("maxDFPercent").withMinimum(1).withMaximum(1).create()).withDescription(
"The max percentage of docs for the DF. Can be used to remove really high frequency terms."
+ " Expressed as an integer between 0 and 100. Default is 99.").withShortName("x").create();
Option maxPercentErrorDocsOpt = obuilder.withLongName("maxPercentErrorDocs").withRequired(false).withArgument(
abuilder.withName("maxPercentErrorDocs").withMinimum(1).withMaximum(1).create()).withDescription(
"The max percentage of docs that can have a null term vector. These are noise document and can occur if the "
+ "analyzer used strips out all terms in the target field. This percentage is expressed as a value "
+ "between 0 and 1. The default is 0.").withShortName("err").create();
Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h")
.create();
Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(idFieldOpt).withOption(
outputOpt).withOption(delimiterOpt).withOption(helpOpt).withOption(fieldOpt).withOption(maxOpt)
.withOption(dictOutOpt).withOption(seqDictOutOpt).withOption(powerOpt).withOption(maxDFPercentOpt)
.withOption(weightOpt).withOption(minDFOpt).withOption(maxPercentErrorDocsOpt).create();
try {
Parser parser = new Parser();
parser.setGroup(group);
CommandLine cmdLine = parser.parse(args);
if (cmdLine.hasOption(helpOpt)) {
CommandLineUtil.printHelp(group);
return;
}
if (cmdLine.hasOption(inputOpt)) { // Lucene case
Driver luceneDriver = new Driver();
luceneDriver.setLuceneDir(cmdLine.getValue(inputOpt).toString());
if (cmdLine.hasOption(maxOpt)) {
luceneDriver.setMaxDocs(Long.parseLong(cmdLine.getValue(maxOpt).toString()));
}
if (cmdLine.hasOption(weightOpt)) {
luceneDriver.setWeightType(cmdLine.getValue(weightOpt).toString());
}
luceneDriver.setField(cmdLine.getValue(fieldOpt).toString());
if (cmdLine.hasOption(minDFOpt)) {
luceneDriver.setMinDf(Integer.parseInt(cmdLine.getValue(minDFOpt).toString()));
}
if (cmdLine.hasOption(maxDFPercentOpt)) {
luceneDriver.setMaxDFPercent(Integer.parseInt(cmdLine.getValue(maxDFPercentOpt).toString()));
}
if (cmdLine.hasOption(powerOpt)) {
String power = cmdLine.getValue(powerOpt).toString();
if ("INF".equals(power)) {
luceneDriver.setNorm(Double.POSITIVE_INFINITY);
} else {
luceneDriver.setNorm(Double.parseDouble(power));
}
}
if (cmdLine.hasOption(idFieldOpt)) {
luceneDriver.setIdField(cmdLine.getValue(idFieldOpt).toString());
}
if (cmdLine.hasOption(maxPercentErrorDocsOpt)) {
luceneDriver.setMaxPercentErrorDocs(Double.parseDouble(cmdLine.getValue(maxPercentErrorDocsOpt).toString()));
}
luceneDriver.setOutFile(cmdLine.getValue(outputOpt).toString());
luceneDriver.setDelimiter(cmdLine.hasOption(delimiterOpt) ? cmdLine.getValue(delimiterOpt).toString() : "\t");
luceneDriver.setDictOut(cmdLine.getValue(dictOutOpt).toString());
if (cmdLine.hasOption(seqDictOutOpt)) {
luceneDriver.setSeqDictOut(cmdLine.getValue(seqDictOutOpt).toString());
}
luceneDriver.dumpVectors();
}
} catch (OptionException e) {
log.error("Exception", e);
CommandLineUtil.printHelp(group);
}
}