public HashSet<Document> ProcessQuery(string query)
{
var tokenizer = new PhraseDocumentTokenizer(new PartOfSpeechTagger());
var phrases = tokenizer.Tokenize(query);
HashSet<Document> currentSet = null;
foreach (var phrase in phrases)
{
var newSet = _inverceIndex.GetDocumentSet(phrase);
HashSetHelper.AddToSet(newSet, Operator.AND, ref currentSet);
}
return currentSet ?? new HashSet<Document>();
}
private static void Main(string[] args)
{
var inputDirectory = args[0];
var documents = DocumentProvider.GetDocuments(inputDirectory);
var tokenizer = new PhraseDocumentTokenizer(new PartOfSpeechTagger());
var inverseIndex = new InverceIndex<Phrase, Document>(tokenizer);
inverseIndex.AddDocuments(documents);
var searcher = new PhraseQueryExecutor(inverseIndex);
while (true)
{
var input = Console.ReadLine();
if (!string.IsNullOrWhiteSpace(input))
{
var resultDocs = searcher.ProcessQuery(input);
Console.WriteLine(string.Join("\n", resultDocs.Select(d => d.FilePath)));
}
}
}
