static void Main(string[] args)
{
String[] file = Directory.GetFiles(@"..\..\..\", "*.txt");
StreamWriter sw = new StreamWriter(@"..\..\..\output\Html.txt");
foreach (String files in file)
{
using (StreamReader sr = new StreamReader(files))
{
while (sr.Peek() != -1)
{
string line = sr.ReadLine();
int i;
java.io.InputStream modelin = new java.io.FileInputStream(string.Format(@"{0}\en-sent.bin", @"..\Debug"));
SentenceModel model = new SentenceModel(modelin);
SentenceDetector detector = new SentenceDetectorME(model);
string[] sents = detector.sentDetect(line);
foreach (var sent in sents)
{
sw.WriteLine(sent);
}
}
}
sw.Flush();
}
sw.Close();
}
private static POSTaggerME preparePOSTagger()
{
using (var modelInputStream = new java.io.FileInputStream(@"c:\projects\OTAutocompleteDSL\dep\en-pos-maxent.bin"))
{
return new POSTaggerME(new POSModel(modelInputStream)); //load the model
}
}
static Sentenizer()
{
var modelFile = HttpContext.Current.Server.MapPath("~/Files/TextAnalytics/en-sentence-model-dragon.bin");
ModelIn = new java.io.FileInputStream(modelFile);
Model = new SentenceModel(ModelIn);
}
public void Chunker()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-chunker.bin"));
var model = new opennlp.tools.chunker.ChunkerModel(modelIn);
var chunker = new opennlp.tools.chunker.ChunkerME(model);
var sent = new[]
{
"Rockwell", "International", "Corp.", "'s", "Tulsa", "unit", "said", "it", "signed",
"a", "tentative", "agreement", "extending", "its", "contract", "with", "Boeing", "Co.",
"to", "provide", "structural", "parts", "for", "Boeing", "'s", "747", "jetliners", "."
};
var pos = new[]
{
"NNP", "NNP", "NNP", "POS", "NNP", "NN", "VBD", "PRP", "VBD", "DT", "JJ", "NN", "VBG", "PRP$",
"NN", "IN", "NNP", "NNP", "TO", "VB", "JJ", "NNS", "IN", "NNP", "POS", "CD", "NNS", "."
};
var tags = chunker.chunk(sent, pos);
System.Console.WriteLine(string.Join(";", tags));
Assert.AreEqual(28, tags.Length);
var probs = chunker.probs();
System.Console.WriteLine(string.Join(";", probs));
Assert.AreEqual(28, probs.Length);
}
static Sentenizer()
{
var modelFile = ConfigurationManager.AppSettings["ModelSentenizer"] ?? string.Empty;
ModelIn = new java.io.FileInputStream(modelFile);
Model = new SentenceModel(ModelIn);
}
private static TokenizerME prepareTokenizer()
{
using (var tokenInputStream = new java.io.FileInputStream(@"c:\projects\OTAutocompleteDSL\dep\en-token.bin"))
{
var tokenModel = new opennlp.tools.tokenize.TokenizerModel(tokenInputStream); //load the token model
return new opennlp.tools.tokenize.TokenizerME(tokenModel); //create the tokenizer
}
}
private static opennlp.tools.parser.ParserModel OpenJavaModel(string fileName)
{
java.io.FileInputStream inputStream = null;
try {
inputStream = OpenNLP.OpenInputStream(fileName);
return(new opennlp.tools.parser.ParserModel(inputStream));
} finally {
inputStream?.close();
}
}
private void LoadParser()
{
if (!alreadyLoadParser)
{
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-parser-chunking.bin");
ParserModel parserModel = new ParserModel(modelInpStream);
parser = ParserFactory.create(parserModel);
alreadyLoadParser = true;
}
}
private void LoadTokenizer()
{
if (!alreadyLoadTagger)
{
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-token.bin");
TokenizerModel tokenizerModel = new TokenizerModel(modelInpStream);
tokenizer = new TokenizerME(tokenizerModel);
alreadyLoadTagger = true;
}
}
private void LoadSentenceDetector()
{
if (!alreadyLoadSentenceDetector)
{
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-sent.bin");
SentenceModel sentenceModel = new SentenceModel(modelInpStream);
sentenceDetector = new SentenceDetectorME(sentenceModel);
alreadyLoadSentenceDetector = true;
}
}
private void LoadTagger()
{
if (!alreadyLoadTokenizer)
{
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-pos-maxent.bin");
POSModel posModel = new POSModel(modelInpStream);
tagger = new POSTaggerME(posModel);
alreadyLoadTokenizer = true;
}
}
private void LoadChunker()
{
if (!alreadyLoadChunker)
{
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-chunker.bin");
ChunkerModel chunkerModel = new ChunkerModel(modelInpStream);
chunker = new ChunkerME(chunkerModel);
alreadyLoadChunker = true;
}
}
public void Tokenize()
{
var modelStream = new java.io.FileInputStream("../../Models/en-token.bin");
var model = new TokenizerModel(modelStream);
var tokenizer = new TokenizerME(model);
var txt = File.ReadAllText(@"c:\dev\d-mill\uspe\Data\uspe-sentenced.txt");
var tokens = tokenizer.tokenize(txt);
}
public NLPTool(string SSModel, string TKModel, string POSModel,
string CKModel, string PersonModel, string OrgModel, string LocModel,
string DateModel, string MoneyModel, string PercentageModel, string TimeModel,
string ParseModel, string MaltParseModel, string LemmatizeDict)
{
nlp_models = new NLPToolBox(SSModel, TKModel, POSModel, CKModel, PersonModel,
OrgModel, LocModel, DateModel, MoneyModel, PercentageModel, TimeModel,
ParseModel, MaltParseModel);
java.io.InputStream input_stream = new java.io.FileInputStream(LemmatizeDict);
lemmatizer = new SimpleLemmatizer(input_stream);
input_stream.close();
}
static Tokenizer()
{
var modelFile = HttpContext.Current.Server.MapPath("~/Files/TextAnalytics/en-token.bin");
if (!File.Exists(modelFile))
{
throw new FileNotFoundException("Unable to find tokenizer model file at " + modelFile);
}
ModelIn = new java.io.FileInputStream(modelFile);
Model = new TokenizerModel(ModelIn);
}
static void Main(string[] args)
{
java.io.InputStream model_src = new java.io.FileInputStream(@"..\..\..\..\en-sent.bin");
SentenceModel smodel = new SentenceModel(model_src);
detector = new SentenceDetectorME(smodel);
foreach (String src in Directory.GetFiles(@"..\..\..\..\Dataset"))
{
lab5(src);
}
}
public void SentenceDetection()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-sent.bin"));
var model = new opennlp.tools.sentdetect.SentenceModel(modelIn);
var sentenceDetector = new opennlp.tools.sentdetect.SentenceDetectorME(model);
var sentences = sentenceDetector.sentDetect(" First sentence. Second sentence. ");
System.Console.WriteLine(string.Join(";", sentences));
Assert.AreEqual(2, sentences.Length);
}
public void Tokenization()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-token.bin"));
var model = new opennlp.tools.tokenize.TokenizerModel(modelIn);
var tokenizer = new opennlp.tools.tokenize.TokenizerME(model);
var tokens = tokenizer.tokenize("An input sample sentence.");
System.Console.WriteLine(string.Join(";", tokens));
Assert.AreEqual(5, tokens.Length);
}
//
// DO NOT USE THIS TESTS AS SAMPLES TO BUILD YOUR STUFF !
//
// I use some things here, that are not needed in a "real" implementation
//
private static opennlp.tools.tokenize.TokenizerModel OpenJavaModel(string fileName)
{
java.io.FileInputStream inputStream = null;
try {
inputStream = OpenNLP.OpenInputStream(fileName);
return(new opennlp.tools.tokenize.TokenizerModel(inputStream));
} finally {
if (inputStream != null)
{
inputStream.close();
}
}
}
private void UnzipFile(string zipFileName)
{
try
{
string fileName;
fileName = "EQ" + dateTimePicker1.Value.Day.ToString("00") + dateTimePicker1.Value.Month.ToString("00") + dateTimePicker1.Value.Year.ToString().Replace("20", "") + ".CSV";;
sbyte[] buf = new sbyte[1024];
int len;
//filename = "EQ" + dateTimePicker1.Value.Day.ToString("00") + dateTimePicker1.Value.Month.ToString("00") + dateTimePicker1.Value.Year.ToString("00") + ".csv" ;
//filename = filename.Replace("zip", "CSV");
java.io.FileInputStream fis = new java.io.FileInputStream(zipFileName);
java.util.zip.ZipInputStream zis = new java.util.zip.ZipInputStream(fis);
java.util.zip.ZipEntry ze;
while ((ze = zis.getNextEntry()) != null)
{
if (fileName == ze.getName())
{
// File name format in zip file is:
// folder/subfolder/filename
// Let's check...
int index = fileName.LastIndexOf('/');
if (index > 1)
{
string folder = fileName.Substring(0, index);
DirectoryInfo di = new DirectoryInfo(folder);
// Create directory if not exists
if (!di.Exists)
{
di.Create();
}
}
java.io.FileOutputStream fos = new java.io.FileOutputStream(fileName);
while ((len = zis.read(buf)) >= 0)
{
fos.write(buf, 0, len);
}
fos.close();
}
}
zis.close();
fis.close();
}
catch (Exception ex)
{
MessageBox.Show("Error" + ex.Message.ToString());
}
finally
{
// Close everything
}
}
private void Initial()
{
var basedir = (string)GlobalParameter.Get(DefaultParameter.Field.opennlp_model_dir);
var modelInputStream = new java.io.FileInputStream(Path.Combine(basedir, "en-ner-location.bin")); //load the name model into a stream
var model = new opennlp.tools.namefind.TokenNameFinderModel(modelInputStream); //load the model
locationNameFinder = new opennlp.tools.namefind.NameFinderME(model); //create the namefinder
modelInputStream = new java.io.FileInputStream(Path.Combine(basedir, "en-ner-person.bin"));
model = new opennlp.tools.namefind.TokenNameFinderModel(modelInputStream);
personNameFinder = new opennlp.tools.namefind.NameFinderME(model);
modelInputStream = new java.io.FileInputStream(Path.Combine(basedir, "en-ner-organization.bin"));
model = new opennlp.tools.namefind.TokenNameFinderModel(modelInputStream);
organizationNameFinder = new opennlp.tools.namefind.NameFinderME(model);
}
/// <summary>Obtains the audio file format of the File provided.</summary>
/// <remarks>
/// Obtains the audio file format of the File provided.
/// The File must point to valid audio file data.
/// </remarks>
/// <param name="file">
/// the File from which file format information should be
/// extracted.
/// </param>
/// <returns>an AudioFileFormat object describing the audio file format.</returns>
/// <exception>
/// UnsupportedAudioFileException
/// if the File does not point to
/// a valid audio file data recognized by the system.
/// </exception>
/// <exception>
/// IOException
/// if an I/O exception occurs.
/// </exception>
/// <exception cref="javax.sound.sampled.UnsupportedAudioFileException"></exception>
/// <exception cref="System.IO.IOException"></exception>
public override javax.sound.sampled.AudioFileFormat getAudioFileFormat(java.io.File
file)
{
java.io.InputStream inputStream = null;
try
{
inputStream = new java.io.FileInputStream(file);
return getAudioFileFormat(inputStream, (int)file.length());
}
finally
{
inputStream.close();
}
}
public static Classifier TryLoadClassifier(string modelFileName)
{
if (!System.IO.File.Exists(modelFileName))
{
byte[] d = Instance.LoadModelData(modelFileName);
if (d != null)
{
System.IO.File.WriteAllBytes(modelFileName, d);
}
}
if (System.IO.File.Exists(modelFileName))
{
java.io.FileInputStream fis = null;
try
{
Classifier cls = null;
if (modelFileName.Contains("MLEA111"))
{
cls = Feng.Windows.Utils.SerializeHelper.Deserialize <MincostLiblinearClassifier>(modelFileName);
}
else
{
//fis = new java.io.FileInputStream(modelFileName);
//var ois = new java.io.ObjectInputStream(fis);
//var cls = (Classifier)ois.readObject();
//ois.close();
//fis.close();
cls = (Classifier)weka.core.SerializationHelper.read(modelFileName);
}
//if (cls.GetType() != ClassifierType)
//{
// throw new ArgumentException("Classifier Type is wrong!");
//}
return(cls);
}
catch (Exception)
{
if (fis != null)
{
fis.close();
}
System.IO.File.Delete(modelFileName);
Instance.DeleteModelData(modelFileName);
}
}
return(null);
}
public void NameFinder()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-ner-person.bin"));
var model = new opennlp.tools.namefind.TokenNameFinderModel(modelIn);
var nameFinder = new opennlp.tools.namefind.NameFinderME(model);
var sentence = new[] { "Pierre", "Vinken", "is", "61", "years", "old", "." };
var nameSpans = nameFinder.find(sentence);
System.Console.WriteLine(string.Join(";", nameSpans.Select(x => x.toString())));
Assert.AreEqual(1, nameSpans.Length);
}
static Tokenizer()
{
var modelFile = ConfigurationManager.AppSettings["ModelTokenizer"] ?? string.Empty;
if(string.IsNullOrWhiteSpace(modelFile))
throw new Exception("ModelTokenizer setting not defined in App.Config");
modelFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, modelFile);
if(!File.Exists(modelFile))
throw new FileNotFoundException("Unable to find tokenizer model file at " + modelFile);
ModelIn = new java.io.FileInputStream(modelFile);
Model = new TokenizerModel(ModelIn);
}
public static ZipFile UpdateZipFile(ZipFile file, FilterEntryMethod filter, string[] newFiles)
{
string prev = file.getName();
string tmp = System.IO.Path.GetTempFileName();
ZipOutputStream to = new ZipOutputStream(new java.io.FileOutputStream(tmp));
try
{
CopyEntries(file, to, filter);
// add entries here
if (newFiles != null)
{
foreach (string f in newFiles)
{
ZipEntry z = new ZipEntry(f.Remove(0, System.IO.Path.GetPathRoot(f).Length));
z.setMethod(ZipEntry.DEFLATED);
to.putNextEntry(z);
try
{
java.io.FileInputStream s = new java.io.FileInputStream(f);
try
{
CopyStream(s, to);
}
finally
{
s.close();
}
}
finally
{
to.closeEntry();
}
}
}
}
finally
{
to.close();
}
file.close();
// now replace the old file with the new one
System.IO.File.Copy(tmp, prev, true);
System.IO.File.Delete(tmp);
return(new ZipFile(prev));
}
static void Main(string[] args)
{
// set up logging
clog = LoggingConfigurator.configureLogging();
clog.Info("Hello from Common Logging");
string projectDir = System.IO.Directory.GetParent(
System.IO.Directory.GetParent(
Environment.CurrentDirectory.ToString()).ToString()).ToString() + "\\";
// the docx 'template'
String input_DOCX = projectDir + @"src\samples\resources\ContentControlBind\binding-simple.docx";
// the instance data
String input_XML = projectDir + @"src\samples\resources\ContentControlBind\binding-simple-data.xml";
// resulting docx
String OUTPUT_DOCX = projectDir + @"OUT_ContentControlsMergeXML.docx";
// Configure to find docx4j.properties
// .. add as URL the dir containing docx4j.properties (not the file itself!)
Plutext.PropertiesConfigurator.setDocx4jPropertiesDir(projectDir + @"src\samples\resources\");
// Load input_template.docx
WordprocessingMLPackage wordMLPackage = org.docx4j.Docx4J.load(new java.io.File(input_DOCX));
// Open the xml stream
java.io.FileInputStream xmlStream = new java.io.FileInputStream(new java.io.File(input_XML));
// Do the binding:
// FLAG_NONE means that all the steps of the binding will be done,
// otherwise you could pass a combination of the following flags:
// FLAG_BIND_INSERT_XML: inject the passed XML into the document
// FLAG_BIND_BIND_XML: bind the document and the xml (including any OpenDope handling)
// FLAG_BIND_REMOVE_SDT: remove the content controls from the document (only the content remains)
// FLAG_BIND_REMOVE_XML: remove the custom xml parts from the document
//Docx4J.bind(wordMLPackage, xmlStream, Docx4J.FLAG_NONE);
//If a document doesn't include the Opendope definitions, eg. the XPathPart,
//then the only thing you can do is insert the xml
//the example document binding-simple.docx doesn't have an XPathPart....
Docx4J.bind(wordMLPackage, xmlStream, Docx4J.FLAG_BIND_INSERT_XML & Docx4J.FLAG_BIND_BIND_XML);
//Save the document
Docx4J.save(wordMLPackage, new java.io.File(OUTPUT_DOCX), Docx4J.FLAG_NONE);
clog.Info("Saved: " + OUTPUT_DOCX);
}
public static object readObjectFromFile(string fileName)
{
try
{
java.io.File f = new java.io.File(fileName);
f.setReadable(true);
java.io.FileInputStream streamIn = new java.io.FileInputStream(f);
java.io.ObjectInputStream ii = new java.io.ObjectInputStream(streamIn);
object obj = ii.readObject();
streamIn.close();
return(obj);
}
catch (System.Exception)
{
return(null);
}
}
public void Parser()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-parser-chunking.bin"));
var model = new opennlp.tools.parser.ParserModel(modelIn);
var parser = opennlp.tools.parser.ParserFactory.create(model);
var sentence = "The quick brown fox jumps over the lazy dog .";
var topParses = opennlp.tools.cmdline.parser.ParserTool.parseLine(sentence, parser, 1);
System.Console.WriteLine(string.Join(";", topParses.Select(x => x.toString())));
Assert.AreEqual(1, topParses.Length);
var tree = topParses[0];
Assert.IsNull(tree.getLabel());
}
static Tokenizer()
{
var modelFile = ConfigurationManager.AppSettings["ModelTokenizer"] ?? string.Empty;
if (string.IsNullOrWhiteSpace(modelFile))
{
throw new Exception("ModelTokenizer setting not defined in App.Config");
}
modelFile = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, modelFile);
if (!File.Exists(modelFile))
{
throw new FileNotFoundException("Unable to find tokenizer model file at " + modelFile);
}
ModelIn = new java.io.FileInputStream(modelFile);
Model = new TokenizerModel(ModelIn);
}
public void SplitSentences()
{
var txt = File.ReadAllText(@"c:\dev\d-mill\uspe\Data\uspe-1.txt");
txt = Regex.Replace(txt, "\\s+", " ");
txt = Regex.Replace(txt, "\\r\\n", "");
txt = Regex.Replace(txt, "MR.\\s+", "MR.");
var modelStream = new java.io.FileInputStream("../../Models/en-sent.bin");
var model = new SentenceModel(modelStream);
var detector = new SentenceDetectorME(model);
var sentences = detector.sentDetect(txt);
File.WriteAllLines(@"c:\dev\d-mill\uspe\Data\uspe-sentenced.txt", sentences);
}
public static void Main(string[] args)
{
DirectoryInfo folder = new DirectoryInfo(@"..\..\..\..\..\Dataset");
foreach (var fname in folder.GetFiles())
{
String line = File.ReadAllText(fname.FullName);
java.io.InputStream modelIn = new java.io.FileInputStream(@"..\..\..\..\..\en-sent.bin");
SentenceModel smodel = new SentenceModel(modelIn);
SentenceDetector detector = new SentenceDetectorME(smodel);
string[] sents = detector.sentDetect(line);
using (StreamWriter sw = new StreamWriter(fname.FullName.Replace(fname.FullName.Substring(fname.FullName.Length - 3), "rtf")))
{
foreach (var sent in sents)
{
sw.WriteLine(sent);
}
}
}
}
/// <summary>
/// Return the OpenNLP analyzer given its model type (M), the type of the analyzer (T), the filename
/// of the model (i.e. en-maxent.bin) and a path to where the Models are lcoated (ModelsPath).
/// </summary>
public T ResolveOpenNlpTool <M, T>(string modelPath)
where T : class
where M : class
{
var modelStream = new java.io.FileInputStream(Path.Combine(ModelsPath, modelPath));
M model;
try
{
model = (M)Activator.CreateInstance(typeof(M), modelStream);
}
finally
{
if (modelStream != null)
{
modelStream.close();
}
}
return((T)Activator.CreateInstance(typeof(T), model));
}
public NLP()
{
//loading sentence detector model
java.io.FileInputStream modelInpStream = new java.io.FileInputStream("Resources\\en-sent.bin");
SentenceModel sentenceModel = new SentenceModel(modelInpStream);
sentenceDetector = new SentenceDetectorME(sentenceModel);
//loading tokenizer model
modelInpStream = new java.io.FileInputStream("Resources\\en-token.bin");
TokenizerModel tokenizerModel = new TokenizerModel(modelInpStream);
tokenizer = new TokenizerME(tokenizerModel);
modelInpStream = new java.io.FileInputStream("Resources\\en-pos-maxent.bin");
POSModel posModel = new POSModel(modelInpStream);
tagger = new POSTaggerME(posModel);
modelInpStream = new java.io.FileInputStream("Resources\\en-chunker.bin");
ChunkerModel chunkerModel = new ChunkerModel(modelInpStream);
chunker = new ChunkerME(chunkerModel);
modelInpStream = new java.io.FileInputStream("Resources\\en-parser-chunking.bin");
ParserModel parserModel = new ParserModel(modelInpStream);
parser = ParserFactory.create(parserModel);
//loading stop words list
StreamReader sr = new StreamReader("Resources\\english.stop.txt");
string line;
while ((line = sr.ReadLine()) != null)
{
stopwords.Add(Stemming(line));
stopwords.Add(line);
}
}
public void PartOfSpeechTagger()
{
using var modelIn = new java.io.FileInputStream(GetModel("en-pos-maxent.bin"));
var model = new opennlp.tools.postag.POSModel(modelIn);
var tagger = new opennlp.tools.postag.POSTaggerME(model);
var sentence = new[]
{
"Most", "large", "cities", "in", "the", "US", "had",
"morning", "and", "afternoon", "newspapers", "."
};
var tags = tagger.tag(sentence);
System.Console.WriteLine(string.Join(";", tags));
Assert.AreEqual(12, tags.Length);
var probs = tagger.probs();
System.Console.WriteLine(string.Join(";", probs));
Assert.AreEqual(12, probs.Length);
}
static void Main(string[] args)
{
StreamWriter sw = new StreamWriter(@"..\..\Data\result.txt");
StreamReader sr = new StreamReader(@"..\..\Data\data.txt");
while (sr.Peek() != -1)
{
string line = sr.ReadLine();
java.io.InputStream modelIn = new java.io.FileInputStream("en-sent.bin");
SentenceModel smodel = new SentenceModel(modelIn);
SentenceDetector detector = new SentenceDetectorME(smodel);
string[] sents = detector.sentDetect(line);
foreach (var sent in sents)
{
sw.WriteLine(sent);
sw.WriteLine();
}
sw.Flush();
}
sr.Close();
sw.Close();
}
private static NameFinderME prepareTimeFinder()
{
var modelInputStream = new java.io.FileInputStream(@"c:\projects\OTAutocompleteDSL\dep\en-ner-time.bin"); //load the name model into a stream
var model = new TokenNameFinderModel(modelInputStream); //load the model
return new NameFinderME(model); //create the namefinder
}
private static opennlp.tools.namefind.NameFinderME prepareNameFinder()
{
var modelInputStream = new java.io.FileInputStream(@"c:\projects\OTAutocompleteDSL\dep\en-ner-location.bin"); //load the name model into a stream
var model = new opennlp.tools.namefind.TokenNameFinderModel(modelInputStream); //load the model
return new opennlp.tools.namefind.NameFinderME(model); //create the namefinder
}
private opennlp.tools.sentdetect.SentenceDetectorME prepareSentenceDetector()
{
java.io.FileInputStream sentModelStream = new java.io.FileInputStream(sentenceModelPath); //load the sentence model into a stream
opennlp.tools.sentdetect.SentenceModel sentModel = new opennlp.tools.sentdetect.SentenceModel(sentModelStream);// load the model
return new opennlp.tools.sentdetect.SentenceDetectorME(sentModel); //create sentence detector
}
static Sentenizer()
{
var modelFile = ConfigurationManager.AppSettings["ModelSentenizer"] ?? string.Empty;
ModelIn = new java.io.FileInputStream(modelFile);
Model = new SentenceModel(ModelIn);
}
private opennlp.tools.namefind.NameFinderME prepareNameFinder()
{
java.io.FileInputStream modelInputStream = new java.io.FileInputStream(nameFinderModelPath); //load the name model into a stream
opennlp.tools.namefind.TokenNameFinderModel model = new opennlp.tools.namefind.TokenNameFinderModel(modelInputStream); //load the model
return new opennlp.tools.namefind.NameFinderME(model); //create the namefinder
}
private SSLSocketFactory getSSLSocketFactory()
{
SSLSocketFactory factory = null;
try
{
//reading the keyStore path and password from the environment properties
string keyStorePath = java.lang.System.getProperty("javax.net.ssl.keyStore");
java.io.FileInputStream keyStoreStream = null;
if (keyStorePath != null)
{
java.io.File file = new java.io.File(keyStorePath);
if(file.exists())
keyStoreStream = new java.io.FileInputStream(file);
else
keyStoreStream = searchDefaultCacerts();
}
else
keyStoreStream = searchDefaultCacerts();
string keyStorePassWord = java.lang.System.getProperty("javax.net.ssl.keyStorePassword");
if (keyStorePassWord == null)
keyStorePassWord = "******";
char[] passphrase = keyStorePassWord.ToCharArray();
//initiating SSLContext
SSLContext ctx = SSLContext.getInstance("TLS");
KeyManagerFactory kmf = KeyManagerFactory.getInstance(KeyManagerFactory.getDefaultAlgorithm());
TrustManagerFactory tmf = TrustManagerFactory.getInstance(TrustManagerFactory.getDefaultAlgorithm());
KeyStore ks = KeyStore.getInstance("JKS");
if (keyStoreStream != null)
ks.load(keyStoreStream,passphrase);
else
ks.load(null,null);
kmf.init(ks, passphrase);
tmf.init(ks);
ctx.init(kmf.getKeyManagers(), tmf.getTrustManagers(), null);
factory = ctx.getSocketFactory();
}
catch (Exception e)
{
factory = null;
#if DEBUG
Console.WriteLine("Can't get SSL Socket Factory, the exception is {0}, {1}", e.GetType(), e.Message);
#endif
}
return factory;
}
/// <summary>Obtains an audio input stream from the File provided.</summary>
/// <remarks>
/// Obtains an audio input stream from the File provided.
/// The File must point to valid audio file data.
/// </remarks>
/// <param name="file">the File for which the AudioInputStream should be constructed.
/// </param>
/// <returns>
/// an AudioInputStream object based on the audio file data pointed to
/// by the File.
/// </returns>
/// <exception>
/// UnsupportedAudioFileException
/// if the File does not point to
/// a valid audio file data recognized by the system.
/// </exception>
/// <exception>
/// IOException
/// if an I/O exception occurs.
/// </exception>
/// <exception cref="javax.sound.sampled.UnsupportedAudioFileException"></exception>
/// <exception cref="System.IO.IOException"></exception>
public override javax.sound.sampled.AudioInputStream getAudioInputStream(java.io.File
file)
{
java.io.InputStream inputStream = new java.io.FileInputStream(file);
try
{
return getAudioInputStream(inputStream, (int)file.length());
}
catch (javax.sound.sampled.UnsupportedAudioFileException e)
{
inputStream.close();
throw;
}
catch (System.IO.IOException e)
{
inputStream.close();
throw;
}
}
static void Main(string[] args)
{
string projectDir = System.IO.Directory.GetParent(
System.IO.Directory.GetParent(
Environment.CurrentDirectory.ToString()).ToString()).ToString() + "\\";
// the docx 'template'
String input_DOCX = projectDir + @"src\samples\resources\ContentControlBind\binding-simple.docx";
// the instance data
String input_XML = projectDir + @"src\samples\resources\ContentControlBind\binding-simple-data.xml";
// resulting docx
String OUTPUT_DOCX = projectDir + @"OUT_ContentControlsMergeXML.docx";
// Programmatically configure Common Logging
// (alternatively, you could do it declaratively in app.config)
NameValueCollection commonLoggingproperties = new NameValueCollection();
commonLoggingproperties["showDateTime"] = "false";
commonLoggingproperties["level"] = "INFO";
LogManager.Adapter = new Common.Logging.Simple.ConsoleOutLoggerFactoryAdapter(commonLoggingproperties);
ILog log = LogManager.GetCurrentClassLogger();
log.Info("Hello from Common Logging");
// Necessary, if slf4j-api and slf4j-NetCommonLogging are separate DLLs
ikvm.runtime.Startup.addBootClassPathAssembly(
System.Reflection.Assembly.GetAssembly(
typeof(org.slf4j.impl.StaticLoggerBinder)));
// Configure to find docx4j.properties
// .. add as URL the dir containing docx4j.properties (not the file itself!)
Plutext.PropertiesConfigurator.setDocx4jPropertiesDir(projectDir + @"src\samples\resources\");
// Load input_template.docx
WordprocessingMLPackage wordMLPackage = org.docx4j.Docx4J.load(new java.io.File(input_DOCX));
// Open the xml stream
java.io.FileInputStream xmlStream = new java.io.FileInputStream(new java.io.File(input_XML));
// Do the binding:
// FLAG_NONE means that all the steps of the binding will be done,
// otherwise you could pass a combination of the following flags:
// FLAG_BIND_INSERT_XML: inject the passed XML into the document
// FLAG_BIND_BIND_XML: bind the document and the xml (including any OpenDope handling)
// FLAG_BIND_REMOVE_SDT: remove the content controls from the document (only the content remains)
// FLAG_BIND_REMOVE_XML: remove the custom xml parts from the document
//Docx4J.bind(wordMLPackage, xmlStream, Docx4J.FLAG_NONE);
//If a document doesn't include the Opendope definitions, eg. the XPathPart,
//then the only thing you can do is insert the xml
//the example document binding-simple.docx doesn't have an XPathPart....
Docx4J.bind(wordMLPackage, xmlStream, Docx4J.FLAG_BIND_INSERT_XML & Docx4J.FLAG_BIND_BIND_XML);
//Save the document
Docx4J.save(wordMLPackage, new java.io.File(OUTPUT_DOCX), Docx4J.FLAG_NONE);
log.Info("Saved: " + OUTPUT_DOCX);
}
private opennlp.tools.tokenize.TokenizerME prepareTokenizer()
{
java.io.FileInputStream tokenInputStream = new java.io.FileInputStream(tokenModelPath); //load the token model into a stream
opennlp.tools.tokenize.TokenizerModel tokenModel = new opennlp.tools.tokenize.TokenizerModel(tokenInputStream); //load the token model
return new opennlp.tools.tokenize.TokenizerME(tokenModel); //create the tokenizer
}
/*
/**********************************************************
/* Parser factories (new ones, as per [Issue-25])
/**********************************************************
*/
/// <summary>
/// Method for constructing JSON parser instance to parse
/// contents of specified file.
/// </summary>
/// <remarks>
/// Method for constructing JSON parser instance to parse
/// contents of specified file. Encoding is auto-detected
/// from contents according to JSON specification recommended
/// mechanism.
/// <p>
/// Underlying input stream (needed for reading contents)
/// will be <b>owned</b> (and managed, i.e. closed as need be) by
/// the parser, since caller has no access to it.
/// </remarks>
/// <param name="f">File that contains JSON content to parse</param>
/// <since>2.1</since>
/// <exception cref="System.IO.IOException"/>
/// <exception cref="com.fasterxml.jackson.core.JsonParseException"/>
public virtual com.fasterxml.jackson.core.JsonParser createParser(Sharpen.FilePath
f)
{
// true, since we create InputStream from File
com.fasterxml.jackson.core.io.IOContext ctxt = _createContext(f, true);
Sharpen.InputStream @in = new java.io.FileInputStream(f);
return _createParser(_decorate(@in, ctxt), ctxt);
}
private bool AddToZip(java.io.FileOutputStream fos, java.util.zip.ZipOutputStream zos, string sourceFile, string destName)
{
try
{
Thread.Sleep(6000);
java.io.FileInputStream fis = new java.io.FileInputStream(sourceFile);
java.util.zip.ZipEntry ze = new java.util.zip.ZipEntry(destName);
zos.putNextEntry(ze);
byte[] buffer = new byte[1024];
int len;
while ((len = fis.read(buffer)) >= 0)
{
zos.write(buffer, 0, len);
}
zos.closeEntry();
fis.close();
}
catch (Exception)
{
File.AppendAllText("log_save.txt", DateTime.Now.ToShortDateString() + " " + DateTime.Now.ToShortTimeString() + ": " + sourceFile + Environment.NewLine);
AddToZip( fos, zos, sourceFile, destName);
}
return true;
}
