static void SerializerTest() { string language = "test"; Corpora cops = new Corpora(); cops.Init(language); XmlSerializer ser = new XmlSerializer(typeof(Corpora)); string filename = "data.xml"; TextWriter writer = new StreamWriter(filename); ser.Serialize(writer, cops); writer.Close(); }
public static Corpora ExtractCorporaFromFile(string filename) { string language = Path.GetFileName(filename).Replace(".txt", ""); Corpora cops = new Corpora(); cops.Init(language); StreamReader file = new StreamReader(filename); string line; while ((line = file.ReadLine()) != null) { string str_in_process = TrimNoneAlphabetChars(line); if (2 <= str_in_process.Length) { List <Tuple <char, char> > bigrams = BuildBigramsFromString(str_in_process); IrrigateCorporaWithBigrams(cops, bigrams); } } file.Close(); return(cops); }