internal void process()
{
ObjectStream <string> untokenizedLineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
ObjectStream <string> tokenizedLineStream = new WhitespaceTokenStream(new TokenizerStream(tokenizer, untokenizedLineStream));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string tokenizedLine;
while ((tokenizedLine = tokenizedLineStream.read()) != null)
{
Console.WriteLine(tokenizedLine);
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
ChunkerModel model = (new ChunkerModelLoader()).load(new File(args[0]));
ChunkerME chunker = new ChunkerME(model, ChunkerME.DEFAULT_BEAM_SIZE);
ObjectStream <string> lineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string line;
while ((line = lineStream.read()) != null)
{
POSSample posSample;
try
{
posSample = POSSample.parse(line);
}
catch (InvalidFormatException)
{
Console.Error.WriteLine("Invalid format:");
Console.Error.WriteLine(line);
continue;
}
string[] chunks = chunker.chunk(posSample.Sentence, posSample.Tags);
Console.WriteLine((new ChunkSample(posSample.Sentence, posSample.Tags, chunks)).nicePrint());
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
/// <summary>
/// Perform sentence detection the input stream.
///
/// A newline will be treated as a paragraph boundary.
/// </summary>
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
SentenceModel model = (new SentenceModelLoader()).load(new File(args[0]));
SentenceDetectorME sdetector = new SentenceDetectorME(model);
ObjectStream <string> paraStream = new ParagraphStream(new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput)));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string para;
while ((para = paraStream.read()) != null)
{
string[] sents = sdetector.sentDetect(para);
foreach (string sentence in sents)
{
Console.WriteLine(sentence);
}
perfMon.incrementCounter(sents.Length);
Console.WriteLine();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (0 == args.Length)
{
Console.WriteLine(Help);
}
else
{
DoccatModel model = (new DoccatModelLoader()).load(new File(args[0]));
DocumentCategorizerME doccat = new DocumentCategorizerME(model);
ObjectStream <string> documentStream = new ParagraphStream(new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput)));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "doc");
perfMon.start();
try
{
string document;
while ((document = documentStream.read()) != null)
{
double[] prob = doccat.categorize(WhitespaceTokenizer.INSTANCE.tokenize(document));
string category = doccat.getBestCategory(prob);
DocumentSample sample = new DocumentSample(category, document);
Console.WriteLine(sample.ToString());
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
POSModel model = (new POSModelLoader()).load(new File(args[0]));
POSTaggerME tagger = new POSTaggerME(model);
ObjectStream <string> lineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string line;
while ((line = lineStream.read()) != null)
{
string[] whitespaceTokenizerLine = WhitespaceTokenizer.INSTANCE.tokenize(line);
string[] tags = tagger.tag(whitespaceTokenizerLine);
POSSample sample = new POSSample(whitespaceTokenizerLine, tags);
Console.WriteLine(sample.ToString());
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
Detokenizer detokenizer = new DictionaryDetokenizer((new DetokenizationDictionaryLoader()).load(new File(args[0])));
ObjectStream <string> tokenizedLineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string tokenizedLine;
while ((tokenizedLine = tokenizedLineStream.read()) != null)
{
// white space tokenize line
string[] tokens = WhitespaceTokenizer.INSTANCE.tokenize(tokenizedLine);
Console.WriteLine(detokenizer.detokenize(tokens, null));
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (args.Length == 0)
{
Console.WriteLine(Help);
}
else
{
NameFinderME[] nameFinders = new NameFinderME[args.Length];
for (int i = 0; i < nameFinders.Length; i++)
{
TokenNameFinderModel model = (new TokenNameFinderModelLoader()).load(new File(args[i]));
nameFinders[i] = new NameFinderME(model);
}
ObjectStream <string> untokenizedLineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string line;
while ((line = untokenizedLineStream.read()) != null)
{
string[] whitespaceTokenizerLine = WhitespaceTokenizer.INSTANCE.tokenize(line);
// A new line indicates a new document,
// adaptive data must be cleared for a new document
if (whitespaceTokenizerLine.Length == 0)
{
foreach (NameFinderME nameFinder in nameFinders)
{
nameFinder.clearAdaptiveData();
}
}
IList <Span> names = new List <Span>();
foreach (TokenNameFinder nameFinder in nameFinders)
{
Collections.addAll(names, nameFinder.find(whitespaceTokenizerLine));
}
// Simple way to drop intersecting spans, otherwise the
// NameSample is invalid
Span[] reducedNames = NameFinderME.dropOverlappingSpans(names.ToArray());
NameSample nameSample = new NameSample(whitespaceTokenizerLine, reducedNames, false);
Console.WriteLine(nameSample.ToString());
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (args.Length < 1)
{
Console.WriteLine(Help);
}
else
{
ParserModel model = (new ParserModelLoader()).load(new File(args[args.Length - 1]));
int?beamSize = CmdLineUtil.getIntParameter("-bs", args);
if (beamSize == null)
{
beamSize = AbstractBottomUpParser.defaultBeamSize;
}
int? numParses = CmdLineUtil.getIntParameter("-k", args);
bool showTopK;
if (numParses == null)
{
numParses = 1;
showTopK = false;
}
else
{
showTopK = true;
}
double?advancePercentage = CmdLineUtil.getDoubleParameter("-ap", args);
if (advancePercentage == null)
{
advancePercentage = AbstractBottomUpParser.defaultAdvancePercentage;
}
opennlp.tools.parser.Parser parser = ParserFactory.create(model, beamSize.Value, advancePercentage.Value);
ObjectStream <string> lineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "sent");
perfMon.start();
try
{
string line;
while ((line = lineStream.read()) != null)
{
if (line.Length == 0)
{
Console.WriteLine();
}
else
{
Parse[] parses = parseLine(line, parser, numParses.Value);
for (int pi = 0, pn = parses.Length; pi < pn; pi++)
{
if (showTopK)
{
Console.Write(pi + " " + parses[pi].Prob + " ");
}
parses[pi].show();
perfMon.incrementCounter();
}
}
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
public override void run(string[] args)
{
if (args.Length != 1)
{
Console.WriteLine(Help);
}
else
{
TreebankLinker treebankLinker;
try
{
treebankLinker = new TreebankLinker(args[0], LinkerMode.TEST);
}
catch (IOException e)
{
throw new TerminateToolException(-1, "Failed to load all coreferencer models!", e);
}
ObjectStream <string> lineStream = new PlainTextByLineStream(new InputStreamReader(Console.OpenStandardInput));
PerformanceMonitor perfMon = new PerformanceMonitor(System.err, "parses");
perfMon.start();
try
{
int sentenceNumber = 0;
IList <Mention> document = new List <Mention>();
IList <Parse> parses = new List <Parse>();
string line;
while ((line = lineStream.read()) != null)
{
if (line.Equals(""))
{
DiscourseEntity[] entities = treebankLinker.getEntities(document.ToArray());
//showEntities(entities);
(new CorefParse(this, parses, entities)).show();
sentenceNumber = 0;
document.Clear();
parses.Clear();
}
else
{
Parse p = Parse.parseParse(line);
parses.Add(p);
Mention[] extents = treebankLinker.MentionFinder.getMentions(new DefaultParse(p, sentenceNumber));
//construct new parses for mentions which don't have constituents.
for (int ei = 0, en = extents.Length; ei < en; ei++)
{
//System.err.println("PennTreebankLiner.main: "+ei+" "+extents[ei]);
if (extents[ei].Parse == null)
{
//not sure how to get head index, but its not used at this point.
Parse snp = new Parse(p.Text, extents[ei].Span, "NML", 1.0, 0);
p.insert(snp);
extents[ei].Parse = new DefaultParse(snp, sentenceNumber);
}
}
document.AddRange(Arrays.asList(extents));
sentenceNumber++;
}
perfMon.incrementCounter();
}
}
catch (IOException e)
{
CmdLineUtil.handleStdinIoError(e);
}
perfMon.stopAndPrintFinalResult();
}
}
