using System;
using System.Collections.Generic;
using System.Text;
namespace BotSharp.NLP.Tokenize
{
///
/// A tokenizer is a component used for dividing text intotokens.
/// A tokenizer is language specific and takes into account the peculiarities of the language, e.g. don’t in English is tokenized as two tokens.
///
public interface ITokenizer
{
///
/// Language
///
SupportedLanguage Lang { get; set; }
///
/// Tokenize
///
/// input
/// Options such as: regex expression
///
Token[] Tokenize(string text, TokenizationOptions options);
}
}