// For either a file to annotate or for the hardcoded text example,
// this demo file shows two ways to process the output, for teaching
// purposes. For the file, it shows both how to run NER on a String
// and how to run it on a whole file. For the hard-coded String,
// it shows how to run it on a single sentence, and how to do this
// and produce an inline XML output format.
static void Main(string[] args)
{
if (args.Length > 0)
{
var fileContent = File.ReadAllText(args[0]);
foreach (List sentence in Classifier.classify(fileContent).toArray())
{
foreach (CoreLabel word in sentence.toArray())
{
Console.Write("{0}/{1} ", word.word(), word.get(new CoreAnnotations.AnswerAnnotation().getClass()));
}
Console.WriteLine();
}
}
else
{
const string S1 = "Good afternoon Rajat Raina, how are you today?";
const string S2 = "I go to school at Stanford University, which is located in California.";
Console.WriteLine("{0}\n", Classifier.classifyToString(S1));
Console.WriteLine("{0}\n", Classifier.classifyWithInlineXML(S2));
Console.WriteLine("{0}\n", Classifier.classifyToString(S2, "xml", true));
var classification = Classifier.classify(S2).toArray();
for (var i = 0; i < classification.Length; i++)
{
Console.WriteLine("{0}\n:{1}\n", i, classification[i]);
}
}
}
public string getNER(string S)
{
CRFClassifier Classifier = CRFClassifier.getClassifierNoExceptions(@"C:\english.all.3class.distsim.crf.ser.gz");
//S = "David go to school at Stanford University, which is located in California.";
string S3 = S.Trim(new Char[] { ',', '.' });
string S2 = S3.Replace(@",", "");
// Console.WriteLine(S2);
String classify = Classifier.classifyToString(S2);
string[] words = classify.Split(' ');
string result = "";
//List<String> iList = new List<String>();ctory
//List<String> iList = new List<String>();
foreach (string s in words)
{
if (!s.EndsWith("/O"))
{
//System.Console.WriteLine(s);
result = result + s + "\n";
}
}
// Keep the console window open in debug mode.
return(result);
}
public List <string> FindTownsInTxt(List <string> sentences)
{
List <string> result = new List <string>();
foreach (var sentence in sentences)
{
string sentenceClean = sentence.Replace(Environment.NewLine, " ");
sentenceClean = sentenceClean.Replace(",", " ").Replace(";", "").Replace(":", "");
result.Add(Classifier.classifyToString(Regex.Replace(sentenceClean, @"[^0-9A-Za-z ,]", "")));
}
return(result);
}
public string[] Recognize(string txt)
{
return(ParseResult(Classifier.classifyToString(txt)));
}
static void DoTagging(CRFClassifier model, String input)
{
input = input.Trim();
Console.WriteLine(input + "=>" + model.classifyToString(input));
}
private void BgWorker_DoWork(object sender, DoWorkEventArgs e)
{
//selects the text encoding based on user selection
Encoding SelectedEncoding = null;
this.Invoke((MethodInvoker) delegate()
{
SelectedEncoding = Encoding.GetEncoding(EncodingDropdown.SelectedItem.ToString());
});
//report what we're working on
FilenameLabel.Invoke((MethodInvoker) delegate
{
FilenameLabel.Text = "Loading model... please wait...";
});
// Path to the folder with models
var segmenterData = Path.Combine(Path.GetDirectoryName(AppDomain.CurrentDomain.BaseDirectory), @"data");
var props = new Properties();
props.setProperty("sighanCorporaDict", segmenterData);
props.setProperty("serDictionary", segmenterData + @"\dict-chris6.ser.gz");
// Lines below are needed because CTBSegDocumentIteratorFactory accesses it
props.setProperty("inputEncoding", SelectedEncoding.ToString());
props.setProperty("sighanPostProcessing", "true");
var segmenter = new CRFClassifier(props);
segmenter.loadClassifierNoExceptions(segmenterData + @"\ctb.gz", props);
//get the list of files
var SearchDepth = SearchOption.TopDirectoryOnly;
if (ScanSubfolderCheckbox.Checked)
{
SearchDepth = SearchOption.AllDirectories;
}
var files = Directory.EnumerateFiles(((string[])e.Argument)[0], "*.txt", SearchDepth);
try {
string outputdir = Path.Combine(((string[])e.Argument)[1]);
Directory.CreateDirectory(outputdir);
foreach (string fileName in files)
{
//set up our variables to report
string Filename_Clean = Path.GetFileName(fileName);
//report what we're working on
FilenameLabel.Invoke((MethodInvoker) delegate
{
FilenameLabel.Text = "Analyzing: " + Filename_Clean;
});
//do stuff here
string readText = File.ReadAllText(fileName, SelectedEncoding).ToLower();
string TokenResults = segmenter.classifyToString(readText);
using (System.IO.StreamWriter fileout =
new StreamWriter(Path.Combine(outputdir, Filename_Clean), false, SelectedEncoding))
{
fileout.Write(TokenResults);
}
}
}
catch
{
MessageBox.Show("ZhToken encountered a problem while trying to tokenize/write a file.");
}
}