public static void Main(string[] args) { string filepath = "t8.shakespeare.txt"; string indexpath = "index"; Document document; Token token; DocumentReader reader = new DocumentReader(filepath); ITokeniser tokeniser = new TokeniserFilter(new SimpleTokeniser()); SimpleIndexer indexer = new SimpleIndexer(); SimpleIndexWriter writer = new SimpleIndexWriter(indexpath); while ((document = reader.ReadDocument()) != null) { tokeniser.SetDocument(document); while ((token = tokeniser.GetToken()) != null) { indexer.indexToken(token); } } indexer.writeIndex(writer); IndexReader indexReader = new IndexReader(indexpath); VocabularyEntry entry = indexReader.GetVocabularyEntry("william"); string line = indexReader.GetPostingsListLine(entry.ByteOffset); Console.WriteLine(entry); Console.WriteLine(line); }
public static void Main(string[] args) { if (args.Length != 2) { Console.WriteLine("usage: Program.exe <inputpath> <indexpath>"); Environment.Exit(0); } string filename = args[0]; string indexpath = args[1]; Document document; Token token; ITokeniser tokeniser = new TokeniserFilter(new SimpleTokeniser()); DocumentReader documentReader = new DocumentReader(filename); IndexFile indexFile = new IndexFile(indexpath); Indexer indexer = new Indexer(); while ((document = documentReader.ReadDocument()) != null) { tokeniser.SetDocument(document); while ((token = tokeniser.GetToken()) != null) { //Console.WriteLine(token); indexer.index(token); } } indexer.SaveTo(indexFile); }