public LemmatizerPrebuiltFull(LanguagePrebuilt lang) : base(lang)
{
Stream stream = GetResourceStream(ResourceFileName);
this.Deserialize(stream);
stream.Close();
}
static void Main(string[] args)
{
LanguagePrebuilt language = args != null && args.Length > 0 ? getLanguage(args[0]) : getLanguage();
ILemmatizer lemmatizer = new LemmatizerPrebuiltCompact(language);
if (args.Length == 0 || args.Length == 1)
{
Console.WriteLine("Batch-processing all files contained in the subfolder 'lemma-source' into 'lemma-output'");
string[] fileList = FileTraverser.getFileList();
foreach (string file in fileList)
{
processFile(file, lemmatizer);
}
}
else if (args.Length == 2)
{
Logger.logError("Missing argument");
}
else if (args.Length == 3)
{
processFile(args[1], lemmatizer, args[2]);
}
else
{
Logger.logError("Argument count mismatch, expected max 3 received {0}", args.Length.ToString());
}
}
public LemmatizerPrebuiltCompact(LanguagePrebuilt lang)
: base(lang)
{
Stream stream = GetResourceStream(ResourceFileName);
this.Deserialize(stream);
stream.Close();
}
public LemmatizerPrebuiltFull(LanguagePrebuilt lang)
: base(lang)
{
Stream stream = GetResourceStream(GetResourceFileName(FILEMASK));
Deserialize(stream);
stream.Close();
}
public LemmatizerPrebuiltData(LanguagePrebuilt lang, LemmatizerSettings lsett)
: base(lang,lsett)
{
Stream stream = GetResourceStream(ResourceFileName);
StreamReader srIn = new StreamReader(stream, LanguageEncoding);
AddMultextFile(srIn, "WLM");
srIn.Close();
BuildModel();
}
public LemmatizerPrebuiltData(LanguagePrebuilt lang, LemmatizerSettings lsett)
: base(lang, lsett)
{
Stream stream = GetResourceStream(ResourceFileName);
StreamReader srIn = new StreamReader(stream, LanguageEncoding);
AddMultextFile(srIn, "WLM");
srIn.Close();
BuildModel();
}
/// <summary>
/// Initializes a new instance of the TagCloudSetting class.
/// </summary>
public TagCloudSetting(LanguagePrebuilt lang)
{
switch (lang)
{
case LanguagePrebuilt.German:
defaultStopWords = LoadStopWords(Resources.de_stop);
break;
default:
defaultStopWords = LoadStopWords(Resources.en_US_stop);
break;
}
this.WordFinder = defaultWordFinder;
this.Lemmatizer = new LemmatizerPrebuiltCompact(lang);
this.StopWords = defaultStopWords;
this.MaxCloudSize = 100;
this.NumCategories = 10;
}
public static LexiconPrebuilt GetLexicon(LanguagePrebuilt lang)
{
return (LexiconPrebuilt)Enum.Parse(typeof(LexiconPrebuilt), asLangMapping[((int)lang) * 2 + 1], true);
}
public LemmatizerPrebuiltData(LanguagePrebuilt lang) : this(lang, new LemmatizerSettings())
{
}
public static string GetResourceFileName(string sFileMask, LanguagePrebuilt lang)
{
string langFileName = AsLangMapping[(int)lang * 2 + 1] + '-' + AsLangMapping[(int)lang * 2];
return(String.Format(sFileMask, langFileName));
}
public LemmatizerPrebuilt(LanguagePrebuilt lang, LemmatizerSettings lsett) : base(lsett)
{
this.lang = lang;
}
// Constructor(s) & Destructor(s) ----------------------
public LemmatizerPrebuilt(LanguagePrebuilt lang)
{
this.lang = lang;
}
// Public Properties ---------------------------------
public static LexiconPrebuilt GetLexicon(LanguagePrebuilt lang)
{
return((LexiconPrebuilt)Enum.Parse(typeof(LexiconPrebuilt), AsLangMapping[((int)lang) * 2 + 1], true));
}
public LemmatizerPrebuilt(LanguagePrebuilt lang)
: base()
{
this.lang = lang;
}
public LemmatizerPrebuilt(LanguagePrebuilt lang, LemmatizerSettings lsett)
: base(lsett)
{
this.lang = lang;
}
public static string GetResourceFileName(string sFileMask, LanguagePrebuilt lang) {
string langFileName = asLangMapping[(int)lang * 2 + 1] + '-' +asLangMapping[(int)lang * 2];
return String.Format(sFileMask, langFileName);
}
protected static string GetResourceFileName(string sFileMask, LanguagePrebuilt lang)
{
return String.Format(sFileMask, asLangMapping[(int)lang]);
}
public LemmatizerPrebuiltData(LanguagePrebuilt lang)
: this(lang, new LemmatizerSettings())
{
}
protected static string GetResourceFileName(string sFileMask, LanguagePrebuilt lang)
{
return(String.Format(sFileMask, asLangMapping[(int)lang]));
}
