List of usage examples for org.apache.commons.cli2.builder ArgumentBuilder ArgumentBuilder
public ArgumentBuilder()
From source file:imageClassify.Describe.java
public static void main(String[] args) throws IOException, DescriptorException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option pathOpt = obuilder.withLongName("path").withShortName("p").withRequired(true) .withArgument(abuilder.withName("path").withMinimum(1).withMaximum(1).create()) .withDescription("Data path").create(); Option descriptorOpt = obuilder.withLongName("descriptor").withShortName("d").withRequired(true) .withArgument(abuilder.withName("descriptor").withMinimum(1).create()) .withDescription("data descriptor").create(); Option descPathOpt = obuilder.withLongName("file").withShortName("f").withRequired(true) .withArgument(abuilder.withName("file").withMinimum(1).withMaximum(1).create()) .withDescription("Path to generated descriptor file").create(); Option regOpt = obuilder.withLongName("regression").withDescription("Regression Problem").withShortName("r") .create();//from ww w .ja v a 2 s .com Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(pathOpt).withOption(descPathOpt) .withOption(descriptorOpt).withOption(regOpt).withOption(helpOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } String dataPath = cmdLine.getValue(pathOpt).toString(); String descPath = cmdLine.getValue(descPathOpt).toString(); List<String> descriptor = convert(cmdLine.getValues(descriptorOpt)); boolean regression = cmdLine.hasOption(regOpt); log.debug("Data path : {}", dataPath); log.debug("Descriptor path : {}", descPath); log.debug("Descriptor : {}", descriptor); log.debug("Regression : {}", regression); runTool(dataPath, descriptor, descPath, regression); } catch (OptionException e) { log.warn(e.toString()); CommandLineUtil.printHelp(group); } }
From source file:com.tamingtext.tagging.LuceneTagExtractor.java
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(false) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output directory").withShortName("o").create(); Option maxOpt = obuilder.withLongName("max").withRequired(false) .withArgument(abuilder.withName("max").withMinimum(1).withMaximum(1).create()) .withDescription(//from ww w. j a v a 2s . c om "The maximum number of vectors to output. If not specified, then it will loop over all docs") .withShortName("m").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 helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(maxOpt) .withOption(fieldOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } File file = new File(cmdLine.getValue(inputOpt).toString()); if (!file.isDirectory()) { throw new IllegalArgumentException(file + " does not exist or is not a directory"); } long maxDocs = Long.MAX_VALUE; if (cmdLine.hasOption(maxOpt)) { maxDocs = Long.parseLong(cmdLine.getValue(maxOpt).toString()); } if (maxDocs < 0) { throw new IllegalArgumentException("maxDocs must be >= 0"); } String field = cmdLine.getValue(fieldOpt).toString(); PrintWriter out = null; if (cmdLine.hasOption(outputOpt)) { out = new PrintWriter(new FileWriter(cmdLine.getValue(outputOpt).toString())); } else { out = new PrintWriter(new OutputStreamWriter(System.out, "UTF-8")); } File output = new File("/home/drew/taming-text/delicious/training"); output.mkdirs(); emitTextForTags(file, output); IOUtils.close(Collections.singleton(out)); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:com.tamingtext.tagging.LuceneCategoryExtractor.java
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(false) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output directory").withShortName("o").create(); Option maxOpt = obuilder.withLongName("max").withRequired(false) .withArgument(abuilder.withName("max").withMinimum(1).withMaximum(1).create()) .withDescription(// w w w . j a va 2 s . c o m "The maximum number of documents to analyze. If not specified, then it will loop over all docs") .withShortName("m").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 helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(maxOpt) .withOption(fieldOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } File inputDir = new File(cmdLine.getValue(inputOpt).toString()); if (!inputDir.isDirectory()) { throw new IllegalArgumentException(inputDir + " does not exist or is not a directory"); } long maxDocs = Long.MAX_VALUE; if (cmdLine.hasOption(maxOpt)) { maxDocs = Long.parseLong(cmdLine.getValue(maxOpt).toString()); } if (maxDocs < 0) { throw new IllegalArgumentException("maxDocs must be >= 0"); } String field = cmdLine.getValue(fieldOpt).toString(); PrintWriter out = null; if (cmdLine.hasOption(outputOpt)) { out = new PrintWriter(new FileWriter(cmdLine.getValue(outputOpt).toString())); } else { out = new PrintWriter(new OutputStreamWriter(System.out, "UTF-8")); } dumpDocumentFields(inputDir, field, maxDocs, out); IOUtils.close(Collections.singleton(out)); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } }
From source file:hack.VectorScan.java
public static void main(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option seqOpt = obuilder.withLongName("seqFile").withRequired(false) .withArgument(abuilder.withName("seqFile").withMinimum(1).withMaximum(1).create()) .withDescription("The Sequence File containing the Clusters").withShortName("s").create(); Option outputOpt = obuilder.withLongName("output").withRequired(false) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output file. If not specified, dumps to the console").withShortName("o") .create();/*from www .j a v a 2s. c o m*/ Option substringOpt = obuilder.withLongName("substring").withRequired(false) .withArgument(abuilder.withName("substring").withMinimum(1).withMaximum(1).create()) .withDescription("The number of chars of the asFormatString() to print").withShortName("b") .create(); Option countOpt = obuilder.withLongName("count").withRequired(false) .withDescription("Report the count only").withShortName("c").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(seqOpt).withOption(outputOpt).withOption(substringOpt) .withOption(countOpt).withOption(helpOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { printHelp(group); return; } boolean doCount = false; if (cmdLine.hasOption(countOpt)) doCount = true; if (cmdLine.hasOption(seqOpt)) { Path path = new Path(cmdLine.getValue(seqOpt).toString()); Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(path.toUri(), conf); SequenceFile.Reader reader = new SequenceFile.Reader(fs, path, conf); int start = 4; int end = 5; int samples = 1000; SimplexSpace<String>[] spaces = makeSpaces(start, end, doCount); try { int sub = Integer.MAX_VALUE; if (cmdLine.hasOption(substringOpt)) { sub = Integer.parseInt(cmdLine.getValue(substringOpt).toString()); } Text key = (Text) reader.getKeyClass().asSubclass(Writable.class).newInstance(); VectorWritable value = (VectorWritable) reader.getValueClass().asSubclass(Writable.class) .newInstance(); int count = 0; while (reader.next(key, value)) { String text = key.toString(); Vector v = value.get(); // int size = v.size(); // int density = v.getNumNondefaultElements(); // System.out.println(size + "," + density); addSpaces(spaces, start, text, v); count++; if (count % 1000 == 0) System.out.print("."); if (count == samples) break; } if (doCount) printSpacesCounts(spaces, start, samples); else printSpacesFull(spaces, start, samples); } finally { } } } catch (OptionException e) { log.error("Exception", e); printHelp(group); } }
From source file:chapter7.src.InputDriver.java
public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = DefaultOptionCreator.inputOption().withRequired(false).create(); Option outputOpt = DefaultOptionCreator.outputOption().withRequired(false).create(); Option vectorOpt = obuilder.withLongName("vector").withRequired(false) .withArgument(abuilder.withName("v").withMinimum(1).withMaximum(1).create()) .withDescription("The vector implementation to use.").withShortName("v").create(); Option helpOpt = DefaultOptionCreator.helpOption(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(outputOpt).withOption(vectorOpt) .withOption(helpOpt).create(); try {/*from w w w .j a va2s .c o m*/ Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } Path input = new Path(cmdLine.getValue(inputOpt, "testdata").toString()); Path output = new Path(cmdLine.getValue(outputOpt, "output").toString()); String vectorClassName = cmdLine.getValue(vectorOpt, "org.apache.mahout.math.RandomAccessSparseVector") .toString(); //runJob(input, output, vectorClassName); } catch (OptionException e) { InputDriver.log.error("Exception parsing command line: ", e); CommandLineUtil.printHelp(group); } }
From source file:com.tamingtext.classifier.maxent.TestMaxent.java
/** * @param args//from w w w . ja v a2 s . c o m */ public static void main(String[] args) throws IOException { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option helpOpt = DefaultOptionCreator.helpOption(); Option inputDirOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription("The input directory").withShortName("i").create(); Option modelOpt = obuilder.withLongName("model").withRequired(true) .withArgument(abuilder.withName("index").withMinimum(1).withMaximum(1).create()) .withDescription("The directory containing the index model").withShortName("m").create(); Group group = gbuilder.withName("Options").withOption(helpOpt).withOption(inputDirOpt).withOption(modelOpt) .create(); try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } String inputPath = (String) cmdLine.getValue(inputDirOpt); File f = new File(inputPath); if (!f.isDirectory()) { throw new IllegalArgumentException(f + " is not a directory or does not exit"); } File[] inputFiles = FileUtil.buildFileList(f); File modelDir = new File((String) cmdLine.getValue(modelOpt)); execute(inputFiles, modelDir); } catch (OptionException e) { log.error("Error while parsing options", e); } }
From source file:com.tamingtext.classifier.mlt.TestMoreLikeThis.java
public static void main(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option helpOpt = DefaultOptionCreator.helpOption(); Option inputDirOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription("The input directory").withShortName("i").create(); Option modelOpt = obuilder.withLongName("model").withRequired(true) .withArgument(abuilder.withName("index").withMinimum(1).withMaximum(1).create()) .withDescription("The directory containing the index model").withShortName("m").create(); Option categoryFieldOpt = obuilder.withLongName("categoryField").withRequired(true) .withArgument(abuilder.withName("index").withMinimum(1).withMaximum(1).create()) .withDescription("Name of the field containing category information").withShortName("catf") .create();/*from w ww. j a v a 2 s. c o m*/ Option contentFieldOpt = obuilder.withLongName("contentField").withRequired(true) .withArgument(abuilder.withName("index").withMinimum(1).withMaximum(1).create()) .withDescription("Name of the field containing content information").withShortName("contf") .create(); Option maxResultsOpt = obuilder.withLongName("maxResults").withRequired(false) .withArgument(abuilder.withName("gramSize").withMinimum(1).withMaximum(1).create()) .withDescription("Number of results to retrive, default: 10 ").withShortName("r").create(); Option gramSizeOpt = obuilder.withLongName("gramSize").withRequired(false) .withArgument(abuilder.withName("gramSize").withMinimum(1).withMaximum(1).create()) .withDescription("Size of the n-gram. Default Value: 1 ").withShortName("ng").create(); Option typeOpt = obuilder.withLongName("classifierType").withRequired(false) .withArgument(abuilder.withName("classifierType").withMinimum(1).withMaximum(1).create()) .withDescription("Type of classifier: knn|tfidf. Default: bayes").withShortName("type").create(); Group group = gbuilder.withName("Options").withOption(gramSizeOpt).withOption(helpOpt) .withOption(inputDirOpt).withOption(modelOpt).withOption(typeOpt).withOption(contentFieldOpt) .withOption(categoryFieldOpt).withOption(maxResultsOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } String classifierType = (String) cmdLine.getValue(typeOpt); int gramSize = 1; if (cmdLine.hasOption(gramSizeOpt)) { gramSize = Integer.parseInt((String) cmdLine.getValue(gramSizeOpt)); } int maxResults = 10; if (cmdLine.hasOption(maxResultsOpt)) { maxResults = Integer.parseInt((String) cmdLine.getValue(maxResultsOpt)); } String inputPath = (String) cmdLine.getValue(inputDirOpt); String modelPath = (String) cmdLine.getValue(modelOpt); String categoryField = (String) cmdLine.getValue(categoryFieldOpt); String contentField = (String) cmdLine.getValue(contentFieldOpt); MatchMode mode; if ("knn".equalsIgnoreCase(classifierType)) { mode = MatchMode.KNN; } else if ("tfidf".equalsIgnoreCase(classifierType)) { mode = MatchMode.TFIDF; } else { throw new IllegalArgumentException("Unkown classifierType: " + classifierType); } Directory directory = FSDirectory.open(new File(modelPath)); IndexReader indexReader = IndexReader.open(directory); Analyzer analyzer //<co id="mlt.analyzersetup"/> = new EnglishAnalyzer(Version.LUCENE_36); MoreLikeThisCategorizer categorizer = new MoreLikeThisCategorizer(indexReader, categoryField); categorizer.setAnalyzer(analyzer); categorizer.setMatchMode(mode); categorizer.setFieldNames(new String[] { contentField }); categorizer.setMaxResults(maxResults); categorizer.setNgramSize(gramSize); File f = new File(inputPath); if (!f.isDirectory()) { throw new IllegalArgumentException(f + " is not a directory or does not exit"); } File[] inputFiles = FileUtil.buildFileList(f); String line = null; //<start id="lucene.examples.mlt.test"/> final ClassifierResult UNKNOWN = new ClassifierResult("unknown", 1.0); ResultAnalyzer resultAnalyzer = //<co id="co.mlt.ra"/> new ResultAnalyzer(categorizer.getCategories(), UNKNOWN.getLabel()); for (File ff : inputFiles) { //<co id="co.mlt.read"/> BufferedReader in = new BufferedReader(new InputStreamReader(new FileInputStream(ff), "UTF-8")); while ((line = in.readLine()) != null) { String[] parts = line.split("\t"); if (parts.length != 2) { continue; } CategoryHits[] hits //<co id="co.mlt.cat"/> = categorizer.categorize(new StringReader(parts[1])); ClassifierResult result = hits.length > 0 ? hits[0] : UNKNOWN; resultAnalyzer.addInstance(parts[0], result); //<co id="co.mlt.an"/> } in.close(); } System.out.println(resultAnalyzer.toString());//<co id="co.mlt.print"/> /* <calloutlist> <callout arearefs="co.mlt.ra">Create <classname>ResultAnalyzer</classname></callout> <callout arearefs="co.mlt.read">Read Test data</callout> <callout arearefs="co.mlt.cat">Categorize</callout> <callout arearefs="co.mlt.an">Collect Results</callout> <callout arearefs="co.mlt.print">Display Results</callout> </calloutlist> */ //<end id="lucene.examples.mlt.test"/> } catch (OptionException e) { log.error("Error while parsing options", e); } }
From source file:com.tamingtext.classifier.bayes.ClassifyDocument.java
public static void main(String[] args) { log.info("Command-line arguments: " + Arrays.toString(args)); DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option inputOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription("Input file").withShortName("i").create(); Option modelOpt = obuilder.withLongName("model").withRequired(true) .withArgument(abuilder.withName("model").withMinimum(1).withMaximum(1).create()) .withDescription("Model to use when classifying data").withShortName("m").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create();// w ww . j a va 2 s. c o m Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(modelOpt).withOption(helpOpt) .create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } File inputFile = new File(cmdLine.getValue(inputOpt).toString()); if (!inputFile.isFile()) { throw new IllegalArgumentException(inputFile + " does not exist or is not a file"); } File modelDir = new File(cmdLine.getValue(modelOpt).toString()); if (!modelDir.isDirectory()) { throw new IllegalArgumentException(modelDir + " does not exist or is not a directory"); } BayesParameters p = new BayesParameters(); p.set("basePath", modelDir.getCanonicalPath()); Datastore ds = new InMemoryBayesDatastore(p); Algorithm a = new BayesAlgorithm(); ClassifierContext ctx = new ClassifierContext(a, ds); ctx.initialize(); //TODO: make the analyzer configurable StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_36); TokenStream ts = analyzer.tokenStream(null, new InputStreamReader(new FileInputStream(inputFile), "UTF-8")); ArrayList<String> tokens = new ArrayList<String>(1000); while (ts.incrementToken()) { tokens.add(ts.getAttribute(CharTermAttribute.class).toString()); } String[] document = tokens.toArray(new String[tokens.size()]); ClassifierResult[] cr = ctx.classifyDocument(document, "unknown", 5); for (ClassifierResult r : cr) { System.err.println(r.getLabel() + "\t" + r.getScore()); } } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } catch (IOException e) { log.error("IOException", e); } catch (InvalidDatastoreException e) { log.error("InvalidDataStoreException", e); } finally { } }
From source file:com.tamingtext.classifier.bayes.ExtractTrainingData.java
public static void main(String[] args) { log.info("Command-line arguments: " + Arrays.toString(args)); 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("Lucene index directory containing input data").withShortName("d").create(); Option categoryOpt = obuilder.withLongName("categories").withRequired(true) .withArgument(abuilder.withName("file").withMinimum(1).withMaximum(1).create()) .withDescription("File containing a list of categories").withShortName("c").create(); Option outputOpt = obuilder.withLongName("output").withRequired(false) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("Output directory").withShortName("o").create(); Option categoryFieldsOpt = obuilder.withLongName("category-fields").withRequired(true) .withArgument(abuilder.withName("fields").withMinimum(1).withMaximum(1).create()) .withDescription("Fields to match categories against (comma-delimited)").withShortName("cf") .create();// w w w . j a v a2 s .c om Option textFieldsOpt = obuilder.withLongName("text-fields").withRequired(true) .withArgument(abuilder.withName("fields").withMinimum(1).withMaximum(1).create()) .withDescription("Fields from which to extract training text (comma-delimited)").withShortName("tf") .create(); Option useTermVectorsOpt = obuilder.withLongName("use-term-vectors").withDescription( "Extract term vectors containing preprocessed data " + "instead of unprocessed, stored text values") .withShortName("tv").create(); Option helpOpt = obuilder.withLongName("help").withDescription("Print out help").withShortName("h") .create(); Group group = gbuilder.withName("Options").withOption(inputOpt).withOption(categoryOpt) .withOption(outputOpt).withOption(categoryFieldsOpt).withOption(textFieldsOpt) .withOption(useTermVectorsOpt).create(); try { Parser parser = new Parser(); parser.setGroup(group); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } File inputDir = new File(cmdLine.getValue(inputOpt).toString()); if (!inputDir.isDirectory()) { throw new IllegalArgumentException(inputDir + " does not exist or is not a directory"); } File categoryFile = new File(cmdLine.getValue(categoryOpt).toString()); if (!categoryFile.isFile()) { throw new IllegalArgumentException(categoryFile + " does not exist or is not a directory"); } File outputDir = new File(cmdLine.getValue(outputOpt).toString()); outputDir.mkdirs(); if (!outputDir.isDirectory()) { throw new IllegalArgumentException(outputDir + " is not a directory or could not be created"); } Collection<String> categoryFields = stringToList(cmdLine.getValue(categoryFieldsOpt).toString()); if (categoryFields.size() < 1) { throw new IllegalArgumentException("At least one category field must be spcified."); } Collection<String> textFields = stringToList(cmdLine.getValue(textFieldsOpt).toString()); if (categoryFields.size() < 1) { throw new IllegalArgumentException("At least one text field must be spcified."); } boolean useTermVectors = cmdLine.hasOption(useTermVectorsOpt); extractTraininingData(inputDir, categoryFile, categoryFields, textFields, outputDir, useTermVectors); } catch (OptionException e) { log.error("Exception", e); CommandLineUtil.printHelp(group); } catch (IOException e) { log.error("IOException", e); } finally { closeWriters(); } }
From source file:com.tamingtext.classifier.maxent.TrainMaxent.java
public static void main(String[] args) throws Exception { DefaultOptionBuilder obuilder = new DefaultOptionBuilder(); ArgumentBuilder abuilder = new ArgumentBuilder(); GroupBuilder gbuilder = new GroupBuilder(); Option helpOpt = DefaultOptionCreator.helpOption(); Option inputDirOpt = obuilder.withLongName("input").withRequired(true) .withArgument(abuilder.withName("input").withMinimum(1).withMaximum(1).create()) .withDescription("The input directory, containing properly formatted files: " + "One doc per line, first entry on the line is the label, rest is the evidence") .withShortName("i").create(); Option outputOpt = obuilder.withLongName("output").withRequired(true) .withArgument(abuilder.withName("output").withMinimum(1).withMaximum(1).create()) .withDescription("The output directory").withShortName("o").create(); Group group = gbuilder.withName("Options").withOption(helpOpt).withOption(inputDirOpt).withOption(outputOpt) .create();//from ww w . j a va2 s.co m //.withOption(gramSizeOpt).withOption(typeOpt) try { Parser parser = new Parser(); parser.setGroup(group); parser.setHelpOption(helpOpt); CommandLine cmdLine = parser.parse(args); if (cmdLine.hasOption(helpOpt)) { CommandLineUtil.printHelp(group); return; } String inputPath = (String) cmdLine.getValue(inputDirOpt); String outputPath = (String) cmdLine.getValue(outputOpt); TrainMaxent trainer = new TrainMaxent(); trainer.train(inputPath, outputPath); } catch (OptionException e) { log.error("Error while parsing options", e); } }