# pylint: disable-msg=E1101,W0613,W0603
from itertools import islice
import os

import numpy as np

import pandas._libs.json as json
from pandas._libs.tslibs import iNaT
from pandas.compat import StringIO, long, to_str, u
from pandas.errors import AbstractMethodError

from pandas.core.dtypes.common import is_period_dtype

from pandas import DataFrame, MultiIndex, Series, compat, isna, to_datetime
from pandas.core.reshape.concat import concat

from pandas.io.common import (
    BaseIterator, _get_handle, _infer_compression, _stringify_path,
    get_filepath_or_buffer)
from pandas.io.formats.printing import pprint_thing
from pandas.io.parsers import _validate_integer

from .normalize import _convert_to_line_delimits
from .table_schema import build_table_schema, parse_table_schema

loads = json.loads
dumps = json.dumps

TABLE_SCHEMA_VERSION = '0.20.0'


# interface to/from
def to_json(path_or_buf, obj, orient=None, date_format='epoch',
            double_precision=10, force_ascii=True, date_unit='ms',
            default_handler=None, lines=False, compression='infer',
            index=True):

    if not index and orient not in ['split', 'table']:
        raise ValueError("'index=False' is only valid when 'orient' is "
                         "'split' or 'table'")

    path_or_buf = _stringify_path(path_or_buf)
    if lines and orient != 'records':
        raise ValueError(
            "'lines' keyword only valid when 'orient' is records")

    if orient == 'table' and isinstance(obj, Series):
        obj = obj.to_frame(name=obj.name or 'values')
    if orient == 'table' and isinstance(obj, DataFrame):
        writer = JSONTableWriter
    elif isinstance(obj, Series):
        writer = SeriesWriter
    elif isinstance(obj, DataFrame):
        writer = FrameWriter
    else:
        raise NotImplementedError("'obj' should be a Series or a DataFrame")

    s = writer(
        obj, orient=orient, date_format=date_format,
        double_precision=double_precision, ensure_ascii=force_ascii,
        date_unit=date_unit, default_handler=default_handler,
        index=index).write()

    if lines:
        s = _convert_to_line_delimits(s)

    if isinstance(path_or_buf, compat.string_types):
        fh, handles = _get_handle(path_or_buf, 'w', compression=compression)
        try:
            fh.write(s)
        finally:
            fh.close()
    elif path_or_buf is None:
        return s
    else:
        path_or_buf.write(s)


class Writer(object):
    def __init__(self, obj, orient, date_format, double_precision,
                 ensure_ascii, date_unit, index, default_handler=None):
        self.obj = obj

        if orient is None:
            orient = self._default_orient

        self.orient = orient
        self.date_format = date_format
        self.double_precision = double_precision
        self.ensure_ascii = ensure_ascii
        self.date_unit = date_unit
        self.default_handler = default_handler
        self.index = index

        self.is_copy = None
        self._format_axes()

    def _format_axes(self):
        raise AbstractMethodError(self)

    def write(self):
        return self._write(self.obj, self.orient, self.double_precision,
                           self.ensure_ascii, self.date_unit,
                           self.date_format == 'iso', self.default_handler)

    def _write(self, obj, orient, double_precision, ensure_ascii,
               date_unit, iso_dates, default_handler):
        return dumps(
            obj,
            orient=orient,
            double_precision=double_precision,
            ensure_ascii=ensure_ascii,
            date_unit=date_unit,
            iso_dates=iso_dates,
            default_handler=default_handler
        )


class SeriesWriter(Writer):
    _default_orient = 'index'

    def _format_axes(self):
        if not self.obj.index.is_unique and self.orient == 'index':
            raise ValueError("Series index must be unique for orient="
                             "'{orient}'".format(orient=self.orient))

    def _write(self, obj, orient, double_precision, ensure_ascii,
               date_unit, iso_dates, default_handler):
        if not self.index and orient == 'split':
            obj = {"name": obj.name, "data": obj.values}
        return super(SeriesWriter, self)._write(obj, orient,
                                                double_precision,
                                                ensure_ascii, date_unit,
                                                iso_dates, default_handler)


class FrameWriter(Writer):
    _default_orient = 'columns'

    def _format_axes(self):
        """
        Try to format axes if they are datelike.
        """
        if not self.obj.index.is_unique and self.orient in (
                'index', 'columns'):
            raise ValueError("DataFrame index must be unique for orient="
                             "'{orient}'.".format(orient=self.orient))
        if not self.obj.columns.is_unique and self.orient in (
                'index', 'columns', 'records'):
            raise ValueError("DataFrame columns must be unique for orient="
                             "'{orient}'.".format(orient=self.orient))

    def _write(self, obj, orient, double_precision, ensure_ascii,
               date_unit, iso_dates, default_handler):
        if not self.index and orient == 'split':
            obj = obj.to_dict(orient='split')
            del obj["index"]
        return super(FrameWriter, self)._write(obj, orient,
                                               double_precision,
                                               ensure_ascii, date_unit,
                                               iso_dates, default_handler)


class JSONTableWriter(FrameWriter):
    _default_orient = 'records'

    def __init__(self, obj, orient, date_format, double_precision,
                 ensure_ascii, date_unit, index, default_handler=None):
        """
        Adds a `schema` attribute with the Table Schema, resets
        the index (can't do in caller, because the schema inference needs
        to know what the index is, forces orient to records, and forces
        date_format to 'iso'.
        """
        super(JSONTableWriter, self).__init__(
            obj, orient, date_format, double_precision, ensure_ascii,
            date_unit, index, default_handler=default_handler)

        if date_format != 'iso':
            msg = ("Trying to write with `orient='table'` and "
                   "`date_format='{fmt}'`. Table Schema requires dates "
                   "to be formatted with `date_format='iso'`"
                   .format(fmt=date_format))
            raise ValueError(msg)

        self.schema = build_table_schema(obj, index=self.index)

        # NotImplementd on a column MultiIndex
        if obj.ndim == 2 and isinstance(obj.columns, MultiIndex):
            raise NotImplementedError(
                "orient='table' is not supported for MultiIndex")

        # TODO: Do this timedelta properly in objToJSON.c See GH #15137
        if ((obj.ndim == 1) and (obj.name in set(obj.index.names)) or
                len(obj.columns & obj.index.names)):
            msg = "Overlapping names between the index and columns"
            raise ValueError(msg)

        obj = obj.copy()
        timedeltas = obj.select_dtypes(include=['timedelta']).columns
        if len(timedeltas):
            obj[timedeltas] = obj[timedeltas].applymap(
                lambda x: x.isoformat())
        # Convert PeriodIndex to datetimes before serialzing
        if is_period_dtype(obj.index):
            obj.index = obj.index.to_timestamp()

        # exclude index from obj if index=False
        if not self.index:
            self.obj = obj.reset_index(drop=True)
        else:
            self.obj = obj.reset_index(drop=False)
        self.date_format = 'iso'
        self.orient = 'records'
        self.index = index

    def _write(self, obj, orient, double_precision, ensure_ascii,
               date_unit, iso_dates, default_handler):
        data = super(JSONTableWriter, self)._write(obj, orient,
                                                   double_precision,
                                                   ensure_ascii, date_unit,
                                                   iso_dates,
                                                   default_handler)
        serialized = '{{"schema": {schema}, "data": {data}}}'.format(
                     schema=dumps(self.schema), data=data)
        return serialized


def read_json(path_or_buf=None, orient=None, typ='frame', dtype=True,
              convert_axes=True, convert_dates=True, keep_default_dates=True,
              numpy=False, precise_float=False, date_unit=None, encoding=None,
              lines=False, chunksize=None, compression='infer'):
    """
    Convert a JSON string to pandas object.

    Parameters
    ----------
    path_or_buf : a valid JSON string or file-like, default: None
        The string could be a URL. Valid URL schemes include http, ftp, s3,
        gcs, and file. For file URLs, a host is expected. For instance, a local
        file could be ``file://localhost/path/to/table.json``

    orient : string,
        Indication of expected JSON string format.
        Compatible JSON strings can be produced by ``to_json()`` with a
        corresponding orient value.
        The set of possible orients is:

        - ``'split'`` : dict like
          ``{index -> [index], columns -> [columns], data -> [values]}``
        - ``'records'`` : list like
          ``[{column -> value}, ... , {column -> value}]``
        - ``'index'`` : dict like ``{index -> {column -> value}}``
        - ``'columns'`` : dict like ``{column -> {index -> value}}``
        - ``'values'`` : just the values array

        The allowed and default values depend on the value
        of the `typ` parameter.

        * when ``typ == 'series'``,

          - allowed orients are ``{'split','records','index'}``
          - default is ``'index'``
          - The Series index must be unique for orient ``'index'``.

        * when ``typ == 'frame'``,

          - allowed orients are ``{'split','records','index',
            'columns','values', 'table'}``
          - default is ``'columns'``
          - The DataFrame index must be unique for orients ``'index'`` and
            ``'columns'``.
          - The DataFrame columns must be unique for orients ``'index'``,
            ``'columns'``, and ``'records'``.

        .. versionadded:: 0.23.0
           'table' as an allowed value for the ``orient`` argument

    typ : type of object to recover (series or frame), default 'frame'
    dtype : boolean or dict, default True
        If True, infer dtypes, if a dict of column to dtype, then use those,
        if False, then don't infer dtypes at all, applies only to the data.
    convert_axes : boolean, default True
        Try to convert the axes to the proper dtypes.
    convert_dates : boolean, default True
        List of columns to parse for dates; If True, then try to parse
        datelike columns default is True; a column label is datelike if

        * it ends with ``'_at'``,

        * it ends with ``'_time'``,

        * it begins with ``'timestamp'``,

        * it is ``'modified'``, or

        * it is ``'date'``

    keep_default_dates : boolean, default True
        If parsing dates, then parse the default datelike columns
    numpy : boolean, default False
        Direct decoding to numpy arrays. Supports numeric data only, but
        non-numeric column and index labels are supported. Note also that the
        JSON ordering MUST be the same for each term if numpy=True.
    precise_float : boolean, default False
        Set to enable usage of higher precision (strtod) function when
        decoding string to double values. Default (False) is to use fast but
        less precise builtin functionality
    date_unit : string, default None
        The timestamp unit to detect if converting dates. The default behaviour
        is to try and detect the correct precision, but if this is not desired
        then pass one of 's', 'ms', 'us' or 'ns' to force parsing only seconds,
        milliseconds, microseconds or nanoseconds respectively.
    encoding : str, default is 'utf-8'
        The encoding to use to decode py3 bytes.

        .. versionadded:: 0.19.0

    lines : boolean, default False
        Read the file as a json object per line.

        .. versionadded:: 0.19.0

    chunksize : integer, default None
        Return JsonReader object for iteration.
        See the `line-delimted json docs
        <http://pandas.pydata.org/pandas-docs/stable/io.html#io-jsonl>`_
        for more information on ``chunksize``.
        This can only be passed if `lines=True`.
        If this is None, the file will be read into memory all at once.

        .. versionadded:: 0.21.0

    compression : {'infer', 'gzip', 'bz2', 'zip', 'xz', None}, default 'infer'
        For on-the-fly decompression of on-disk data. If 'infer', then use
        gzip, bz2, zip or xz if path_or_buf is a string ending in
        '.gz', '.bz2', '.zip', or 'xz', respectively, and no decompression
        otherwise. If using 'zip', the ZIP file must contain only one data
        file to be read in. Set to None for no decompression.

        .. versionadded:: 0.21.0

    Returns
    -------
    result : Series or DataFrame, depending on the value of `typ`.