"""
Record Arrays
=============
Record arrays expose the fields of structured arrays as properties.

Most commonly, ndarrays contain elements of a single type, e.g. floats,
integers, bools etc.  However, it is possible for elements to be combinations
of these using structured types, such as::

  >>> a = np.array([(1, 2.0), (1, 2.0)], dtype=[('x', int), ('y', float)])
  >>> a
  array([(1, 2.0), (1, 2.0)],
        dtype=[('x', '<i4'), ('y', '<f8')])

Here, each element consists of two fields: x (and int), and y (a float).
This is known as a structured array.  The different fields are analogous
to columns in a spread-sheet.  The different fields can be accessed as
one would a dictionary::

  >>> a['x']
  array([1, 1])

  >>> a['y']
  array([ 2.,  2.])

Record arrays allow us to access fields as properties::

  >>> ar = np.rec.array(a)

  >>> ar.x
  array([1, 1])

  >>> ar.y
  array([ 2.,  2.])

"""
from __future__ import division, absolute_import, print_function

import sys
import os
import warnings

from . import numeric as sb
from . import numerictypes as nt
from numpy.compat import isfileobj, bytes, long, unicode, os_fspath
from numpy.core.overrides import set_module
from .arrayprint import get_printoptions

# All of the functions allow formats to be a dtype
__all__ = ['record', 'recarray', 'format_parser']


ndarray = sb.ndarray

_byteorderconv = {'b':'>',
                  'l':'<',
                  'n':'=',
                  'B':'>',
                  'L':'<',
                  'N':'=',
                  'S':'s',
                  's':'s',
                  '>':'>',
                  '<':'<',
                  '=':'=',
                  '|':'|',
                  'I':'|',
                  'i':'|'}

# formats regular expression
# allows multidimension spec with a tuple syntax in front
# of the letter code '(2,3)f4' and ' (  2 ,  3  )  f4  '
# are equally allowed

numfmt = nt.typeDict

def find_duplicate(list):
    """Find duplication in a list, return a list of duplicated elements"""
    dup = []
    for i in range(len(list)):
        if (list[i] in list[i + 1:]):
            if (list[i] not in dup):
                dup.append(list[i])
    return dup


@set_module('numpy')
class format_parser(object):
    """
    Class to convert formats, names, titles description to a dtype.

    After constructing the format_parser object, the dtype attribute is
    the converted data-type:
    ``dtype = format_parser(formats, names, titles).dtype``

    Attributes
    ----------
    dtype : dtype
        The converted data-type.

    Parameters
    ----------
    formats : str or list of str
        The format description, either specified as a string with
        comma-separated format descriptions in the form ``'f8, i4, a5'``, or
        a list of format description strings  in the form
        ``['f8', 'i4', 'a5']``.
    names : str or list/tuple of str
        The field names, either specified as a comma-separated string in the
        form ``'col1, col2, col3'``, or as a list or tuple of strings in the
        form ``['col1', 'col2', 'col3']``.
        An empty list can be used, in that case default field names
        ('f0', 'f1', ...) are used.
    titles : sequence
        Sequence of title strings. An empty list can be used to leave titles
        out.
    aligned : bool, optional
        If True, align the fields by padding as the C-compiler would.
        Default is False.
    byteorder : str, optional
        If specified, all the fields will be changed to the
        provided byte-order.  Otherwise, the default byte-order is
        used. For all available string specifiers, see `dtype.newbyteorder`.

    See Also
    --------
    dtype, typename, sctype2char

    Examples
    --------
    >>> np.format_parser(['f8', 'i4', 'a5'], ['col1', 'col2', 'col3'],
    ...                  ['T1', 'T2', 'T3']).dtype
    dtype([(('T1', 'col1'), '<f8'), (('T2', 'col2'), '<i4'),
           (('T3', 'col3'), '|S5')])

    `names` and/or `titles` can be empty lists. If `titles` is an empty list,
    titles will simply not appear. If `names` is empty, default field names
    will be used.

    >>> np.format_parser(['f8', 'i4', 'a5'], ['col1', 'col2', 'col3'],
    ...                  []).dtype
    dtype([('col1', '<f8'), ('col2', '<i4'), ('col3', '|S5')])
    >>> np.format_parser(['f8', 'i4', 'a5'], [], []).dtype
    dtype([('f0', '<f8'), ('f1', '<i4'), ('f2', '|S5')])

    """

    def __init__(self, formats, names, titles, aligned=False, byteorder=None):
        self._parseFormats(formats, aligned)
        self._setfieldnames(names, titles)
        self._createdescr(byteorder)
        self.dtype = self._descr

    def _parseFormats(self, formats, aligned=0):
        """ Parse the field formats """

        if formats is None:
            raise ValueError("Need formats argument")
        if isinstance(formats, list):
            if len(formats) < 2:
                formats.append('')
            formats = ','.join(formats)
        dtype = sb.dtype(formats, aligned)
        fields = dtype.fields
        if fields is None:
            dtype = sb.dtype([('f1', dtype)], aligned)
            fields = dtype.fields
        keys = dtype.names
        self._f_formats = [fields[key][0] for key in keys]
        self._offsets = [fields[key][1] for key in keys]
        self._nfields = len(keys)

    def _setfieldnames(self, names, titles):
        """convert input field names into a list and assign to the _names
        attribute """

        if (names):
            if (type(names) in [list, tuple]):
                pass
            elif isinstance(names, (str, unicode)):
                names = names.split(',')
            else:
                raise NameError("illegal input names %s" % repr(names))

            self._names = [n.strip() for n in names[:self._nfields]]
        else:
            self._names = []

        # if the names are not specified, they will be assigned as
        #  "f0, f1, f2,..."
        # if not enough names are specified, they will be assigned as "f[n],
        # f[n+1],..." etc. where n is the number of specified names..."
        self._names += ['f%d' % i for i in range(len(self._names),
                                                 self._nfields)]
        # check for redundant names
        _dup = find_duplicate(self._names)
        if _dup:
            raise ValueError("Duplicate field names: %s" % _dup)

        if (titles):
            self._titles = [n.strip() for n in titles[:self._nfields]]
        else:
            self._titles = []
            titles = []

        if (self._nfields > len(titles)):
            self._titles += [None] * (self._nfields - len(titles))

    def _createdescr(self, byteorder):
        descr = sb.dtype({'names':self._names,
                          'formats':self._f_formats,
                          'offsets':self._offsets,
                          'titles':self._titles})
        if (byteorder is not None):
            byteorder = _byteorderconv[byteorder[0]]
            descr = descr.newbyteorder(byteorder)

        self._descr = descr

class record(nt.void):
    """A data-type scalar that allows field access as attribute lookup.
    """

    # manually set name and module so that this class's type shows up
    # as numpy.record when printed
    __name__ = 'record'
    __module__ = 'numpy'

    def __repr__(self):
        if get_printoptions()['legacy'] == '1.13':
            return self.__str__()
        return super(record, self).__repr__()

    def __str__(self):
        if get_printoptions()['legacy'] == '1.13':
            return str(self.item())
        return super(record, self).__str__()

    def __getattribute__(self, attr):
        if attr in ['setfield', 'getfield', 'dtype']:
            return nt.void.__getattribute__(self, attr)
        try:
            return nt.void.__getattribute__(self, attr)
        except AttributeError:
            pass
        fielddict = nt.void.__getattribute__(self, 'dtype').fields
        res = fielddict.get(attr, None)
        if res:
            obj = self.getfield(*res[:2])
            # if it has fields return a record,
            # otherwise return the object
            try:
                dt = obj.dtype
            except AttributeError:
                #happens if field is Object type
                return obj
            if dt.fields:
                return obj.view((self.__class__, obj.dtype.fields))
            return obj
        else:
            raise AttributeError("'record' object has no "
                    "attribute '%s'" % attr)

    def __setattr__(self, attr, val):
        if attr in ['setfield', 'getfield', 'dtype']:
            raise AttributeError("Cannot set '%s' attribute" % attr)
        fielddict = nt.void.__getattribute__(self, 'dtype').fields
        res = fielddict.get(attr, None)
        if res:
            return self.setfield(val, *res[:2])
        else:
            if getattr(self, attr, None):
                return nt.void.__setattr__(self, attr, val)
            else:
                raise AttributeError("'record' object has no "
                        "attribute '%s'" % attr)

    def __getitem__(self, indx):
        obj = nt.void.__getitem__(self, indx)

        # copy behavior of record.__getattribute__,
        if isinstance(obj, nt.void) and obj.dtype.fields:
            return obj.view((self.__class__, obj.dtype.fields))
        else:
            # return a single element
            return obj

    def pprint(self):
        """Pretty-print all fields."""
        # pretty-print all fields
        names = self.dtype.names
        maxlen = max(len(name) for name in names)
        fmt = '%% %ds: %%s' % maxlen
        rows = [fmt % (name, getattr(self, name)) for name in names]
        return "\n".join(rows)

# The recarray is almost identical to a standard array (which supports
#   named fields already)  The biggest difference is that it can use
#   attribute-lookup to find the fields and it is constructed using
#   a record.

# If byteorder is given it forces a particular byteorder on all
#  the fields (and any subfields)

class recarray(ndarray):
    """Construct an ndarray that allows field access using attributes.

    Arrays may have a data-types containing fields, analogous
    to columns in a spread sheet.  An example is ``[(x, int), (y, float)]``,
    where each entry in the array is a pair of ``(int, float)``.  Normally,
    these attributes are accessed using dictionary lookups such as ``arr['x']``
    and ``arr['y']``.  Record arrays allow the fields to be accessed as members
    of the array, using ``arr.x`` and ``arr.y``.

    Parameters
    ----------
    shape : tuple
        Shape of output array.
    dtype : data-type, optional
        The desired data-type.  By default, the data-type is determined
        from `formats`, `names`, `titles`, `aligned` and `byteorder`.
    formats : list of data-types, optional
        A list containing the data-types for the different columns, e.g.
        ``['i4', 'f8', 'i4']``.  `formats` does *not* support the new
        convention of using types directly, i.e. ``(int, float, int)``.
        Note that `formats` must be a list, not a tuple.
        Given that `formats` is somewhat limited, we recommend specifying
        `dtype` instead.
    names : tuple of str, optional
        The name of each column, e.g. ``('x', 'y', 'z')``.
    buf : buffer, optional
        By default, a new array is created of the given shape and data-type.
        If `buf` is specified and is an object exposing the buffer interface,
        the array will use the memory from the existing buffer.  In this case,
        the `offset` and `strides` keywords are available.

    Other Parameters
    ----------------
    titles : tuple of str, optional
        Aliases for column names.  For example, if `names` were
        ``('x', 'y', 'z')`` and `titles` is
        ``('x_coordinate', 'y_coordinate', 'z_coordinate')``, then
        ``arr['x']`` is equivalent to both ``arr.x`` and ``arr.x_coordinate``.
    byteorder : {'<', '>', '='}, optional
        Byte-order for all fields.