class DataSet(object):
    """
    This is a virtual base class or interface for datasets.
    A dataset is basically an iterator over examples. It does not necessarily
    have a fixed length (this is useful for 'streams' which feed on-line learning).
    Datasets with fixed and known length are FiniteDataSet, a subclass of DataSet.
    Examples and datasets have named fields. 
    One can obtain a sub-dataset by taking dataset.field or dataset(field1,field2,field3,...).
    Fields are not mutually exclusive, i.e. two fields can overlap in their actual content.
    The content of a field can be of any type, but often will be a numpy tensor.
    """

    def __init__(self):
        pass

    def __iter__():
        return self

    def next():
        """Return the next example in the dataset."""
        raise NotImplementedError

    def __getattr__(fieldname):
        """Return a sub-dataset containing only the given fieldname as field."""
        return self(fieldname)

    def __call__(*fieldnames):
        """Return a sub-dataset containing only the given fieldnames as fields."""
        raise NotImplementedError

    fieldNames(self):
        """Return the list of field names that are supported by getattr and getFields."""
        raise NotImplementedError

class FiniteDataSet(DataSet):
    """
    Virtual interface, a subclass of DataSet for datasets which have a finite, known length.
    Examples are indexed by an integer between 0 and self.length()-1,
    and a subdataset can be obtained by slicing.
    """

    def __init__(self):
        pass

    def __len__(self):
        """len(dataset) returns the number of examples in the dataset."""
        raise NotImplementedError
    
    def __getitem__(self,i):
        """dataset[i] returns the (i+1)-th example of the dataset."""
        raise NotImplementedError

    def __getslice__(self,*slice_args):
        """dataset[i:j] returns the subdataset with examples i,i+1,...,j-1."""
        raise NotImplementedError