"""
Set operations for arrays based on sorting.

:Contains:
  unique,
  isin,
  ediff1d,
  intersect1d,
  setxor1d,
  in1d,
  union1d,
  setdiff1d

:Notes:

For floating point arrays, inaccurate results may appear due to usual round-off
and floating point comparison issues.

Speed could be gained in some operations by an implementation of
sort(), that can provide directly the permutation vectors, avoiding
thus calls to argsort().

To do: Optionally return indices analogously to unique for all functions.

:Author: Robert Cimrman

"""
from __future__ import division, absolute_import, print_function

import functools

import numpy as np
from numpy.core import overrides


array_function_dispatch = functools.partial(
    overrides.array_function_dispatch, module='numpy')


__all__ = [
    'ediff1d', 'intersect1d', 'setxor1d', 'union1d', 'setdiff1d', 'unique',
    'in1d', 'isin'
    ]


def _ediff1d_dispatcher(ary, to_end=None, to_begin=None):
    return (ary, to_end, to_begin)


@array_function_dispatch(_ediff1d_dispatcher)
def ediff1d(ary, to_end=None, to_begin=None):
    """
    The differences between consecutive elements of an array.

    Parameters
    ----------
    ary : array_like
        If necessary, will be flattened before the differences are taken.
    to_end : array_like, optional
        Number(s) to append at the end of the returned differences.
    to_begin : array_like, optional
        Number(s) to prepend at the beginning of the returned differences.

    Returns
    -------
    ediff1d : ndarray
        The differences. Loosely, this is ``ary.flat[1:] - ary.flat[:-1]``.

    See Also
    --------
    diff, gradient

    Notes
    -----
    When applied to masked arrays, this function drops the mask information
    if the `to_begin` and/or `to_end` parameters are used.

    Examples
    --------
    >>> x = np.array([1, 2, 4, 7, 0])
    >>> np.ediff1d(x)
    array([ 1,  2,  3, -7])

    >>> np.ediff1d(x, to_begin=-99, to_end=np.array([88, 99]))
    array([-99,   1,   2,   3,  -7,  88,  99])

    The returned array is always 1D.

    >>> y = [[1, 2, 4], [1, 6, 24]]
    >>> np.ediff1d(y)
    array([ 1,  2, -3,  5, 18])

    """
    # force a 1d array
    ary = np.asanyarray(ary).ravel()

    # enforce propagation of the dtype of input
    # ary to returned result
    dtype_req = ary.dtype

    # fast track default case
    if to_begin is None and to_end is None:
        return ary[1:] - ary[:-1]

    if to_begin is None:
        l_begin = 0
    else:
        _to_begin = np.asanyarray(to_begin, dtype=dtype_req)
        if not np.all(_to_begin == to_begin):
            raise ValueError("cannot convert 'to_begin' to array with dtype "
                            "'%r' as required for input ary" % dtype_req)
        to_begin = _to_begin.ravel()
        l_begin = len(to_begin)

    if to_end is None:
        l_end = 0
    else:
        _to_end = np.asanyarray(to_end, dtype=dtype_req)
        # check that casting has not overflowed
        if not np.all(_to_end == to_end):
            raise ValueError("cannot convert 'to_end' to array with dtype "
                             "'%r' as required for input ary" % dtype_req)
        to_end = _to_end.ravel()
        l_end = len(to_end)

    # do the calculation in place and copy to_begin and to_end
    l_diff = max(len(ary) - 1, 0)
    result = np.empty(l_diff + l_begin + l_end, dtype=ary.dtype)
    result = ary.__array_wrap__(result)
    if l_begin > 0:
        result[:l_begin] = to_begin
    if l_end > 0:
        result[l_begin + l_diff:] = to_end
    np.subtract(ary[1:], ary[:-1], result[l_begin:l_begin + l_diff])
    return result


def _unpack_tuple(x):
    """ Unpacks one-element tuples for use as return values """
    if len(x) == 1:
        return x[0]
    else:
        return x


def _unique_dispatcher(ar, return_index=None, return_inverse=None,
                       return_counts=None, axis=None):
    return (ar,)


@array_function_dispatch(_unique_dispatcher)
def unique(ar, return_index=False, return_inverse=False,
           return_counts=False, axis=None):
    """
    Find the unique elements of an array.

    Returns the sorted unique elements of an array. There are three optional
    outputs in addition to the unique elements:

    * the indices of the input array that give the unique values
    * the indices of the unique array that reconstruct the input array
    * the number of times each unique value comes up in the input array

    Parameters
    ----------
    ar : array_like
        Input array. Unless `axis` is specified, this will be flattened if it
        is not already 1-D.
    return_index : bool, optional
        If True, also return the indices of `ar` (along the specified axis,
        if provided, or in the flattened array) that result in the unique array.
    return_inverse : bool, optional
        If True, also return the indices of the unique array (for the specified
        axis, if provided) that can be used to reconstruct `ar`.
    return_counts : bool, optional
        If True, also return the number of times each unique item appears
        in `ar`.

        .. versionadded:: 1.9.0

    axis : int or None, optional
        The axis to operate on. If None, `ar` will be flattened. If an integer,
        the subarrays indexed by the given axis will be flattened and treated
        as the elements of a 1-D array with the dimension of the given axis,
        see the notes for more details.  Object arrays or structured arrays
        that contain objects are not supported if the `axis` kwarg is used. The
        default is None.

        .. versionadded:: 1.13.0

    Returns
    -------
    unique : ndarray
        The sorted unique values.
    unique_indices : ndarray, optional
        The indices of the first occurrences of the unique values in the
        original array. Only provided if `return_index` is True.
    unique_inverse : ndarray, optional
        The indices to reconstruct the original array from the
        unique array. Only provided if `return_inverse` is True.
    unique_counts : ndarray, optional
        The number of times each of the unique values comes up in the
        original array. Only provided if `return_counts` is True.

        .. versionadded:: 1.9.0

    See Also
    --------
    numpy.lib.arraysetops : Module with a number of other functions for
                            performing set operations on arrays.

    Notes
    -----
    When an axis is specified the subarrays indexed by the axis are sorted.
    This is done by making the specified axis the first dimension of the array
    and then flattening the subarrays in C order. The flattened subarrays are
    then viewed as a structured type with each element given a label, with the
    effect that we end up with a 1-D array of structured types that can be
    treated in the same way as any other 1-D array. The result is that the
    flattened subarrays are sorted in lexicographic order starting with the
    first element.

    Examples
    --------
    >>> np.unique([1, 1, 2, 2, 3, 3])
    array([1, 2, 3])
    >>> a = np.array([[1, 1], [2, 3]])
    >>> np.unique(a)
    array([1, 2, 3])

    Return the unique rows of a 2D array

    >>> a = np.array([[1, 0, 0], [1, 0, 0], [2, 3, 4]])
    >>> np.unique(a, axis=0)
    array([[1, 0, 0], [2, 3, 4]])

    Return the indices of the original array that give the unique values:

    >>> a = np.array(['a', 'b', 'b', 'c', 'a'])
    >>> u, indices = np.unique(a, return_index=True)
    >>> u
    array(['a', 'b', 'c'],
           dtype='|S1')
    >>> indices
    array([0, 1, 3])
    >>> a[indices]
    array(['a', 'b', 'c'],
           dtype='|S1')

    Reconstruct the input array from the unique values:

    >>> a = np.array([1, 2, 6, 4, 2, 3, 2])
    >>> u, indices = np.unique(a, return_inverse=True)
    >>> u
    array([1, 2, 3, 4, 6])
    >>> indices
    array([0, 1, 4, 3, 1, 2, 1])
    >>> u[indices]
    array([1, 2, 6, 4, 2, 3, 2])

    """
    ar = np.asanyarray(ar)
    if axis is None:
        ret = _unique1d(ar, return_index, return_inverse, return_counts)
        return _unpack_tuple(ret)

    # axis was specified and not None
    try:
        ar = np.swapaxes(ar, axis, 0)
    except np.AxisError:
        # this removes the "axis1" or "axis2" prefix from the error message
        raise np.AxisError(axis, ar.ndim)

    # Must reshape to a contiguous 2D array for this to work...
    orig_shape, orig_dtype = ar.shape, ar.dtype
    ar = ar.reshape(orig_shape[0], -1)
    ar = np.ascontiguousarray(ar)
    dtype = [('f{i}'.format(i=i), ar.dtype) for i in range(ar.shape[1])]

    try:
        consolidated = ar.view(dtype)
    except TypeError:
        # There's no good way to do this for object arrays, etc...
        msg = 'The axis argument to unique is not supported for dtype {dt}'
        raise TypeError(msg.format(dt=ar.dtype))

    def reshape_uniq(uniq):
        uniq = uniq.view(orig_dtype)
        uniq = uniq.reshape(-1, *orig_shape[1:])
        uniq = np.swapaxes(uniq, 0, axis)
        return uniq

    output = _unique1d(consolidated, return_index,
                       return_inverse, return_counts)
    output = (reshape_uniq(output[0]),) + output[1:]
    return _unpack_tuple(output)


def _unique1d(ar, return_index=False, return_inverse=False,
              return_counts=False):
    """
    Find the unique elements of an array, ignoring shape.
    """
    ar = np.asanyarray(ar).flatten()

    optional_indices = return_index or return_inverse

    if optional_indices:
        perm = ar.argsort(kind='mergesort' if return_index else 'quicksort')
        aux = ar[perm]
    else:
        ar.sort()
        aux = ar
    mask = np.empty(aux.shape, dtype=np.bool_)
    mask[:1] = True
    mask[1:] = aux[1:] != aux[:-1]

    ret = (aux[mask],)
    if return_index:
        ret += (perm[mask],)
    if return_inverse:
        imask = np.cumsum(mask) - 1
        inv_idx = np.empty(mask.shape, dtype=np.intp)
        inv_idx[perm] = imask
        ret += (inv_idx,)
    if return_counts:
        idx = np.concatenate(np.nonzero(mask) + ([mask.size],))
        ret += (np.diff(idx),)
    return ret


def _intersect1d_dispatcher(
        ar1, ar2, assume_unique=None, return_indices=None):
    return (ar1, ar2)


@array_function_dispatch(_intersect1d_dispatcher)
def intersect1d(ar1, ar2, assume_unique=False, return_indices=False):
    """
    Find the intersection of two arrays.

    Return the sorted, unique values that are in both of the input arrays.

    Parameters
    ----------