# -*- coding: utf-8 -*-
import codecs
import re
import textwrap
import warnings

import numpy as np

import pandas._libs.lib as lib
import pandas._libs.ops as libops
import pandas.compat as compat
from pandas.compat import zip
from pandas.util._decorators import Appender, deprecate_kwarg

from pandas.core.dtypes.common import (
    ensure_object, is_bool_dtype, is_categorical_dtype, is_integer,
    is_list_like, is_object_dtype, is_re, is_scalar, is_string_like)
from pandas.core.dtypes.generic import ABCIndexClass, ABCSeries
from pandas.core.dtypes.missing import isna

from pandas.core.algorithms import take_1d
from pandas.core.base import NoNewAttributesMixin
import pandas.core.common as com

_cpython_optimized_encoders = (
    "utf-8", "utf8", "latin-1", "latin1", "iso-8859-1", "mbcs", "ascii"
)
_cpython_optimized_decoders = _cpython_optimized_encoders + (
    "utf-16", "utf-32"
)

_shared_docs = dict()


def cat_core(list_of_columns, sep):
    """
    Auxiliary function for :meth:`str.cat`

    Parameters
    ----------
    list_of_columns : list of numpy arrays
        List of arrays to be concatenated with sep;
        these arrays may not contain NaNs!
    sep : string
        The separator string for concatenating the columns

    Returns
    -------
    nd.array
        The concatenation of list_of_columns with sep
    """
    list_with_sep = [sep] * (2 * len(list_of_columns) - 1)
    list_with_sep[::2] = list_of_columns
    return np.sum(list_with_sep, axis=0)


def _na_map(f, arr, na_result=np.nan, dtype=object):
    # should really _check_ for NA
    return _map(f, arr, na_mask=True, na_value=na_result, dtype=dtype)


def _map(f, arr, na_mask=False, na_value=np.nan, dtype=object):
    if not len(arr):
        return np.ndarray(0, dtype=dtype)

    if isinstance(arr, ABCSeries):
        arr = arr.values
    if not isinstance(arr, np.ndarray):
        arr = np.asarray(arr, dtype=object)
    if na_mask:
        mask = isna(arr)
        try:
            convert = not all(mask)
            result = lib.map_infer_mask(arr, f, mask.view(np.uint8), convert)
        except (TypeError, AttributeError) as e:
            # Reraise the exception if callable `f` got wrong number of args.
            # The user may want to be warned by this, instead of getting NaN
            if compat.PY2:
                p_err = r'takes (no|(exactly|at (least|most)) ?\d+) arguments?'
            else:
                p_err = (r'((takes)|(missing)) (?(2)from \d+ to )?\d+ '
                         r'(?(3)required )positional arguments?')

            if len(e.args) >= 1 and re.search(p_err, e.args[0]):
                raise e

            def g(x):
                try:
                    return f(x)
                except (TypeError, AttributeError):
                    return na_value

            return _map(g, arr, dtype=dtype)
        if na_value is not np.nan:
            np.putmask(result, mask, na_value)
            if result.dtype == object:
                result = lib.maybe_convert_objects(result)
        return result
    else:
        return lib.map_infer(arr, f)


def str_count(arr, pat, flags=0):
    """
    Count occurrences of pattern in each string of the Series/Index.

    This function is used to count the number of times a particular regex
    pattern is repeated in each of the string elements of the
    :class:`~pandas.Series`.

    Parameters
    ----------
    pat : str
        Valid regular expression.
    flags : int, default 0, meaning no flags
        Flags for the `re` module. For a complete list, `see here
        <https://docs.python.org/3/howto/regex.html#compilation-flags>`_.
    **kwargs
        For compatibility with other string methods. Not used.

    Returns
    -------
    Series or Index
        Same type as the calling object containing the integer counts.

    See Also
    --------
    re : Standard library module for regular expressions.
    str.count : Standard library version, without regular expression support.

    Notes
    -----
    Some characters need to be escaped when passing in `pat`.
    eg. ``'$'`` has a special meaning in regex and must be escaped when
    finding this literal character.

    Examples
    --------
    >>> s = pd.Series(['A', 'B', 'Aaba', 'Baca', np.nan, 'CABA', 'cat'])
    >>> s.str.count('a')
    0    0.0
    1    0.0
    2    2.0
    3    2.0
    4    NaN
    5    0.0
    6    1.0
    dtype: float64

    Escape ``'$'`` to find the literal dollar sign.

    >>> s = pd.Series(['$', 'B', 'Aab$', '$$ca', 'C$B$', 'cat'])
    >>> s.str.count('\\$')
    0    1
    1    0
    2    1
    3    2
    4    2
    5    0
    dtype: int64

    This is also available on Index

    >>> pd.Index(['A', 'A', 'Aaba', 'cat']).str.count('a')
    Int64Index([0, 0, 2, 1], dtype='int64')
    """
    regex = re.compile(pat, flags=flags)
    f = lambda x: len(regex.findall(x))
    return _na_map(f, arr, dtype=int)


def str_contains(arr, pat, case=True, flags=0, na=np.nan, regex=True):
    """
    Test if pattern or regex is contained within a string of a Series or Index.

    Return boolean Series or Index based on whether a given pattern or regex is
    contained within a string of a Series or Index.

    Parameters
    ----------
    pat : str
        Character sequence or regular expression.
    case : bool, default True
        If True, case sensitive.
    flags : int, default 0 (no flags)
        Flags to pass through to the re module, e.g. re.IGNORECASE.
    na : default NaN
        Fill value for missing values.
    regex : bool, default True
        If True, assumes the pat is a regular expression.

        If False, treats the pat as a literal string.

    Returns
    -------
    Series or Index of boolean values
        A Series or Index of boolean values indicating whether the
        given pattern is contained within the string of each element
        of the Series or Index.

    See Also
    --------
    match : Analogous, but stricter, relying on re.match instead of re.search.
    Series.str.startswith : Test if the start of each string element matches a
        pattern.
    Series.str.endswith : Same as startswith, but tests the end of string.

    Examples
    --------

    Returning a Series of booleans using only a literal pattern.

    >>> s1 = pd.Series(['Mouse', 'dog', 'house and parrot', '23', np.NaN])
    >>> s1.str.contains('og', regex=False)
    0    False
    1     True
    2    False
    3    False
    4      NaN
    dtype: object

    Returning an Index of booleans using only a literal pattern.

    >>> ind = pd.Index(['Mouse', 'dog', 'house and parrot', '23.0', np.NaN])
    >>> ind.str.contains('23', regex=False)
    Index([False, False, False, True, nan], dtype='object')

    Specifying case sensitivity using `case`.

    >>> s1.str.contains('oG', case=True, regex=True)
    0    False
    1    False
    2    False
    3    False
    4      NaN
    dtype: object

    Specifying `na` to be `False` instead of `NaN` replaces NaN values
    with `False`. If Series or Index does not contain NaN values
    the resultant dtype will be `bool`, otherwise, an `object` dtype.

    >>> s1.str.contains('og', na=False, regex=True)
    0    False
    1     True
    2    False
    3    False
    4    False
    dtype: bool

    Returning 'house' or 'dog' when either expression occurs in a string.

    >>> s1.str.contains('house|dog', regex=True)
    0    False
    1     True
    2     True
    3    False
    4      NaN
    dtype: object

    Ignoring case sensitivity using `flags` with regex.

    >>> import re
    >>> s1.str.contains('PARROT', flags=re.IGNORECASE, regex=True)
    0    False
    1    False
    2     True
    3    False
    4      NaN
    dtype: object

    Returning any digit using regular expression.

    >>> s1.str.contains('\\d', regex=True)
    0    False
    1    False
    2    False
    3     True
    4      NaN
    dtype: object

    Ensure `pat` is a not a literal pattern when `regex` is set to True.
    Note in the following example one might expect only `s2[1]` and `s2[3]` to
    return `True`. However, '.0' as a regex matches any character
    followed by a 0.

    >>> s2 = pd.Series(['40', '40.0', '41', '41.0', '35'])
    >>> s2.str.contains('.0', regex=True)
    0     True
    1     True
    2    False
    3     True
    4    False
    dtype: bool
    """
    if regex:
        if not case:
            flags |= re.IGNORECASE

        regex = re.compile(pat, flags=flags)

        if regex.groups > 0:
            warnings.warn("This pattern has match groups. To actually get the"
                          " groups, use str.extract.", UserWarning,
                          stacklevel=3)

        f = lambda x: bool(regex.search(x))
    else:
        if case:
            f = lambda x: pat in x
        else:
            upper_pat = pat.upper()
            f = lambda x: upper_pat in x
            uppered = _na_map(lambda x: x.upper(), arr)
            return _na_map(f, uppered, na, dtype=bool)
    return _na_map(f, arr, na, dtype=bool)


def str_startswith(arr, pat, na=np.nan):
    """
    Test if the start of each string element matches a pattern.

    Equivalent to :meth:`str.startswith`.

    Parameters
    ----------
    pat : str
        Character sequence. Regular expressions are not accepted.
    na : object, default NaN
        Object shown if element tested is not a string.

    Returns
    -------
    Series or Index of bool
        A Series of booleans indicating whether the given pattern matches
        the start of each string element.

    See Also
    --------
    str.startswith : Python standard library string method.
    Series.str.endswith : Same as startswith, but tests the end of string.
    Series.str.contains : Tests if string element contains a pattern.

    Examples
    --------
    >>> s = pd.Series(['bat', 'Bear', 'cat', np.nan])
    >>> s
    0     bat
    1    Bear
    2     cat
    3     NaN
    dtype: object

    >>> s.str.startswith('b')
    0     True
    1    False
    2    False
    3      NaN
    dtype: object

    Specifying `na` to be `False` instead of `NaN`.

    >>> s.str.startswith('b', na=False)
    0     True
    1    False
    2    False
    3    False
    dtype: bool
    """
    f = lambda x: x.startswith(pat)
    return _na_map(f, arr, na, dtype=bool)


def str_endswith(arr, pat, na=np.nan):
    """
    Test if the end of each string element matches a pattern.

    Equivalent to :meth:`str.endswith`.

    Parameters
    ----------
    pat : str
        Character sequence. Regular expressions are not accepted.
    na : object, default NaN
        Object shown if element tested is not a string.

    Returns
    -------
    Series or Index of bool
        A Series of booleans indicating whether the given pattern matches
        the end of each string element.

    See Also
    --------
    str.endswith : Python standard library string method.
    Series.str.startswith : Same as endswith, but tests the start of string.
    Series.str.contains : Tests if string element contains a pattern.

    Examples
    --------
    >>> s = pd.Series(['bat', 'bear', 'caT', np.nan])
    >>> s
    0     bat
    1    bear
    2     caT
    3     NaN
    dtype: object

    >>> s.str.endswith('t')
    0     True
    1    False
    2    False
    3      NaN
    dtype: object

    Specifying `na` to be `False` instead of `NaN`.

    >>> s.str.endswith('t', na=False)
    0     True
    1    False
    2    False
    3    False
    dtype: bool
    """
    f = lambda x: x.endswith(pat)
    return _na_map(f, arr, na, dtype=bool)


def str_replace(arr, pat, repl, n=-1, case=None, flags=0, regex=True):
    r"""
    Replace occurrences of pattern/regex in the Series/Index with
    some other string. Equivalent to :meth:`str.replace` or
    :func:`re.sub`.

    Parameters
    ----------
    pat : str or compiled regex
        String can be a character sequence or regular expression.

        .. versionadded:: 0.20.0
            `pat` also accepts a compiled regex.

    repl : str or callable
        Replacement string or a callable. The callable is passed the regex
        match object and must return a replacement string to be used.
        See :func:`re.sub`.

        .. versionadded:: 0.20.0
            `repl` also accepts a callable.

    n : int, default -1 (all)
        Number of replacements to make from start.
    case : bool, default None
        - If True, case sensitive (the default if `pat` is a string)
        - Set to False for case insensitive
        - Cannot be set if `pat` is a compiled regex
    flags : int, default 0 (no flags)
        - re module flags, e.g. re.IGNORECASE
        - Cannot be set if `pat` is a compiled regex
    regex : bool, default True
        - If True, assumes the passed-in pattern is a regular expression.
        - If False, treats the pattern as a literal string
        - Cannot be set to False if `pat` is a compiled regex or `repl` is
          a callable.

        .. versionadded:: 0.23.0

    Returns
    -------
    Series or Index of object
        A copy of the object with all matching occurrences of `pat` replaced by
        `repl`.

    Raises
    ------
    ValueError
        * if `regex` is False and `repl` is a callable or `pat` is a compiled
          regex
        * if `pat` is a compiled regex and `case` or `flags` is set

    Notes
    -----
    When `pat` is a compiled regex, all flags should be included in the
    compiled regex. Use of `case`, `flags`, or `regex=False` with a compiled
    regex will raise an error.

    Examples
    --------
    When `pat` is a string and `regex` is True (the default), the given `pat`
    is compiled as a regex. When `repl` is a string, it replaces matching
    regex patterns as with :meth:`re.sub`. NaN value(s) in the Series are
    left as is:

    >>> pd.Series(['foo', 'fuz', np.nan]).str.replace('f.', 'ba', regex=True)
    0    bao
    1    baz
    2    NaN
    dtype: object

    When `pat` is a string and `regex` is False, every `pat` is replaced with
    `repl` as with :meth:`str.replace`:

    >>> pd.Series(['f.o', 'fuz', np.nan]).str.replace('f.', 'ba', regex=False)
    0    bao
    1    fuz
    2    NaN
    dtype: object

    When `repl` is a callable, it is called on every `pat` using
    :func:`re.sub`. The callable should expect one positional argument
    (a regex object) and return a string.

    To get the idea:

    >>> pd.Series(['foo', 'fuz', np.nan]).str.replace('f', repr)
    0    <_sre.SRE_Match object; span=(0, 1), match='f'>oo
    1    <_sre.SRE_Match object; span=(0, 1), match='f'>uz
    2                                                  NaN
    dtype: object

    Reverse every lowercase alphabetic word:

    >>> repl = lambda m: m.group(0)[::-1]
    >>> pd.Series(['foo 123', 'bar baz', np.nan]).str.replace(r'[a-z]+', repl)
    0    oof 123
    1    rab zab
    2        NaN
    dtype: object

    Using regex groups (extract second group and swap case):

    >>> pat = r"(?P<one>\w+) (?P<two>\w+) (?P<three>\w+)"
    >>> repl = lambda m: m.group('two').swapcase()
    >>> pd.Series(['One Two Three', 'Foo Bar Baz']).str.replace(pat, repl)
    0    tWO
    1    bAR
    dtype: object

    Using a compiled regex with flags

    >>> import re
    >>> regex_pat = re.compile(r'FUZ', flags=re.IGNORECASE)
    >>> pd.Series(['foo', 'fuz', np.nan]).str.replace(regex_pat, 'bar')
    0    foo
    1    bar
    2    NaN
    dtype: object
    """

    # Check whether repl is valid (GH 13438, GH 15055)
    if not (is_string_like(repl) or callable(repl)):
        raise TypeError("repl must be a string or callable")

    is_compiled_re = is_re(pat)
    if regex:
        if is_compiled_re:
            if (case is not None) or (flags != 0):
                raise ValueError("case and flags cannot be set"
                                 " when pat is a compiled regex")
        else:
            # not a compiled regex
            # set default case
            if case is None:
                case = True

            # add case flag, if provided
            if case is False:
                flags |= re.IGNORECASE
        if is_compiled_re or len(pat) > 1 or flags or callable(repl):
            n = n if n >= 0 else 0
            compiled = re.compile(pat, flags=flags)
            f = lambda x: compiled.sub(repl=repl, string=x, count=n)
        else:
            f = lambda x: x.replace(pat, repl, n)
    else:
        if is_compiled_re:
            raise ValueError("Cannot use a compiled regex as replacement "
                             "pattern with regex=False")
        if callable(repl):
            raise ValueError("Cannot use a callable replacement when "
                             "regex=False")
        f = lambda x: x.replace(pat, repl, n)

    return _na_map(f, arr)


def str_repeat(arr, repeats):
    """
    Duplicate each string in the Series or Index.

    Parameters
    ----------
    repeats : int or sequence of int
        Same value for all (int) or different value per (sequence).

    Returns
    -------
    Series or Index of object
        Series or Index of repeated string objects specified by
        input parameter repeats.

    Examples
    --------
    >>> s = pd.Series(['a', 'b', 'c'])
    >>> s
    0    a
    1    b
    2    c
    dtype: object

    Single int repeats string in Series

    >>> s.str.repeat(repeats=2)
    0    aa
    1    bb
    2    cc
    dtype: object

    Sequence of int repeats corresponding string in Series

    >>> s.str.repeat(repeats=[1, 2, 3])
    0      a
    1     bb
    2    ccc
    dtype: object
    """
    if is_scalar(repeats):
        def rep(x):
            try:
                return compat.binary_type.__mul__(x, repeats)
            except TypeError:
                return compat.text_type.__mul__(x, repeats)

        return _na_map(rep, arr)
    else:

        def rep(x, r):
            try:
                return compat.binary_type.__mul__(x, r)
            except TypeError:
                return compat.text_type.__mul__(x, r)

        repeats = np.asarray(repeats, dtype=object)
        result = libops.vec_binop(com.values_from_object(arr), repeats, rep)
        return result


def str_match(arr, pat, case=True, flags=0, na=np.nan):
    """
    Determine if each string matches a regular expression.

    Parameters
    ----------
    pat : str
        Character sequence or regular expression.
    case : bool, default True
        If True, case sensitive.
    flags : int, default 0 (no flags)
        re module flags, e.g. re.IGNORECASE.
    na : default NaN
        Fill value for missing values.

    Returns
    -------
    Series/array of boolean values

    See Also
    --------
    contains : Analogous, but less strict, relying on re.search instead of
        re.match.
    extract : Extract matched groups.
    """
    if not case:
        flags |= re.IGNORECASE

    regex = re.compile(pat, flags=flags)

    dtype = bool
    f = lambda x: bool(regex.match(x))

    return _na_map(f, arr, na, dtype=dtype)


def _get_single_group_name(rx):
    try:
        return list(rx.groupindex.keys()).pop()
    except IndexError:
        return None


def _groups_or_na_fun(regex):
    """Used in both extract_noexpand and extract_frame"""
    if regex.groups == 0:
        raise ValueError("pattern contains no capture groups")
    empty_row = [np.nan] * regex.groups

    def f(x):
        if not isinstance(x, compat.string_types):
            return empty_row
        m = regex.search(x)
        if m:
            return [np.nan if item is None else item for item in m.groups()]
        else:
            return empty_row
    return f


def _str_extract_noexpand(arr, pat, flags=0):
    """
    Find groups in each string in the Series using passed regular
    expression. This function is called from
    str_extract(expand=False), and can return Series, DataFrame, or
    Index.

    """
    from pandas import DataFrame, Index

    regex = re.compile(pat, flags=flags)
    groups_or_na = _groups_or_na_fun(regex)

    if regex.groups == 1:
        result = np.array([groups_or_na(val)[0] for val in arr], dtype=object)
        name = _get_single_group_name(regex)
    else:
        if isinstance(arr, Index):
            raise ValueError("only one regex group is supported with Index")
        name = None
        names = dict(zip(regex.groupindex.values(), regex.groupindex.keys()))
        columns = [names.get(1 + i, i) for i in range(regex.groups)]
        if arr.empty:
            result = DataFrame(columns=columns, dtype=object)
        else:
            result = DataFrame(
                [groups_or_na(val) for val in arr],
                columns=columns,
                index=arr.index,
                dtype=object)
    return result, name


def _str_extract_frame(arr, pat, flags=0):
    """
    For each subject string in the Series, extract groups from the
    first match of regular expression pat. This function is called from
    str_extract(expand=True), and always returns a DataFrame.

    """
    from pandas import DataFrame

    regex = re.compile(pat, flags=flags)
    groups_or_na = _groups_or_na_fun(regex)
    names = dict(zip(regex.groupindex.values(), regex.groupindex.keys()))
    columns = [names.get(1 + i, i) for i in range(regex.groups)]

    if len(arr) == 0:
        return DataFrame(columns=columns, dtype=object)
    try:
        result_index = arr.index
    except AttributeError:
        result_index = None
    return DataFrame(
        [groups_or_na(val) for val in arr],
        columns=columns,
        index=result_index,
        dtype=object)


def str_extract(arr, pat, flags=0, expand=True):
    r"""
    Extract capture groups in the regex `pat` as columns in a DataFrame.

    For each subject string in the Series, extract groups from the
    first match of regular expression `pat`.

    Parameters
    ----------
    pat : str
        Regular expression pattern with capturing groups.
    flags : int, default 0 (no flags)
        Flags from the ``re`` module, e.g. ``re.IGNORECASE``, that
        modify regular expression matching for things like case,
        spaces, etc. For more details, see :mod:`re`.
    expand : bool, default True
        If True, return DataFrame with one column per capture group.
        If False, return a Series/Index if there is one capture group
        or DataFrame if there are multiple capture groups.

        .. versionadded:: 0.18.0

    Returns
    -------
    DataFrame or Series or Index
        A DataFrame with one row for each subject string, and one
        column for each group. Any capture group names in regular
        expression pat will be used for column names; otherwise
        capture group numbers will be used. The dtype of each result
        column is always object, even when no match is found. If
        ``expand=False`` and pat has only one capture group, then
        return a Series (if subject is a Series) or Index (if subject
        is an Index).

    See Also
    --------
    extractall : Returns all matches (not just the first match).

    Examples
    --------
    A pattern with two groups will return a DataFrame with two columns.
    Non-matches will be NaN.

    >>> s = pd.Series(['a1', 'b2', 'c3'])
    >>> s.str.extract(r'([ab])(\d)')
         0    1
    0    a    1
    1    b    2
    2  NaN  NaN

    A pattern may contain optional groups.

    >>> s.str.extract(r'([ab])?(\d)')
         0  1
    0    a  1
    1    b  2
    2  NaN  3

    Named groups will become column names in the result.

    >>> s.str.extract(r'(?P<letter>[ab])(?P<digit>\d)')
      letter digit
    0      a     1
    1      b     2
    2    NaN   NaN

    A pattern with one group will return a DataFrame with one column
    if expand=True.

    >>> s.str.extract(r'[ab](\d)', expand=True)
         0
    0    1
    1    2
    2  NaN

    A pattern with one group will return a Series if expand=False.

    >>> s.str.extract(r'[ab](\d)', expand=False)
    0      1
    1      2
    2    NaN
    dtype: object
    """
    if not isinstance(expand, bool):
        raise ValueError("expand must be True or False")
    if expand:
        return _str_extract_frame(arr._orig, pat, flags=flags)
    else:
        result, name = _str_extract_noexpand(arr._parent, pat, flags=flags)
        return arr._wrap_result(result, name=name, expand=expand)


def str_extractall(arr, pat, flags=0):
    r"""
    For each subject string in the Series, extract groups from all
    matches of regular expression pat. When each subject string in the
    Series has exactly one match, extractall(pat).xs(0, level='match')
    is the same as extract(pat).

    .. versionadded:: 0.18.0

    Parameters
    ----------
    pat : str
        Regular expression pattern with capturing groups.
    flags : int, default 0 (no flags)
        A ``re`` module flag, for example ``re.IGNORECASE``. These allow
        to modify regular expression matching for things like case, spaces,
        etc. Multiple flags can be combined with the bitwise OR operator,
        for example ``re.IGNORECASE | re.MULTILINE``.

    Returns
    -------
    DataFrame
        A ``DataFrame`` with one row for each match, and one column for each
        group. Its rows have a ``MultiIndex`` with first levels that come from
        the subject ``Series``. The last level is named 'match' and indexes the
        matches in each item of the ``Series``. Any capture group names in
        regular expression pat will be used for column names; otherwise capture
        group numbers will be used.

    See Also
    --------
    extract : Returns first match only (not all matches).

    Examples
    --------
    A pattern with one group will return a DataFrame with one column.
    Indices with no matches will not appear in the result.

    >>> s = pd.Series(["a1a2", "b1", "c1"], index=["A", "B", "C"])
    >>> s.str.extractall(r"[ab](\d)")
             0
      match
    A 0      1
      1      2
    B 0      1

    Capture group names are used for column names of the result.

    >>> s.str.extractall(r"[ab](?P<digit>\d)")
            digit
      match
    A 0         1
      1         2
    B 0         1

    A pattern with two groups will return a DataFrame with two columns.

    >>> s.str.extractall(r"(?P<letter>[ab])(?P<digit>\d)")
            letter digit
      match
    A 0          a     1
      1          a     2
    B 0          b     1

    Optional groups that do not match are NaN in the result.

    >>> s.str.extractall(r"(?P<letter>[ab])?(?P<digit>\d)")
            letter digit
      match
    A 0          a     1
      1          a     2
    B 0          b     1
    C 0        NaN     1
    """

    regex = re.compile(pat, flags=flags)
    # the regex must contain capture groups.
    if regex.groups == 0:
        raise ValueError("pattern contains no capture groups")

    if isinstance(arr, ABCIndexClass):
        arr = arr.to_series().reset_index(drop=True)

    names = dict(zip(regex.groupindex.values(), regex.groupindex.keys()))
    columns = [names.get(1 + i, i) for i in range(regex.groups)]
    match_list = []
    index_list = []
    is_mi = arr.index.nlevels > 1

    for subject_key, subject in arr.iteritems():
        if isinstance(subject, compat.string_types):

            if not is_mi:
                subject_key = (subject_key, )

            for match_i, match_tuple in enumerate(regex.findall(subject)):
                if isinstance(match_tuple, compat.string_types):
                    match_tuple = (match_tuple,)
                na_tuple = [np.NaN if group == "" else group
                            for group in match_tuple]
                match_list.append(na_tuple)
                result_key = tuple(subject_key + (match_i, ))
                index_list.append(result_key)

    from pandas import MultiIndex
    index = MultiIndex.from_tuples(
        index_list, names=arr.index.names + ["match"])

    result = arr._constructor_expanddim(match_list, index=index,
                                        columns=columns)
    return result


def str_get_dummies(arr, sep='|'):
    """
    Split each string in the Series by sep and return a DataFrame
    of dummy/indicator variables.

    Parameters
    ----------
    sep : str, default "|"
        String to split on.

    Returns
    -------
    DataFrame
        Dummy variables corresponding to values of the Series.

    See Also
    --------
    get_dummies : Convert categorical variable into dummy/indicator
        variables.

    Examples
    --------
    >>> pd.Series(['a|b', 'a', 'a|c']).str.get_dummies()
       a  b  c
    0  1  1  0
    1  1  0  0
    2  1  0  1

    >>> pd.Series(['a|b', np.nan, 'a|c']).str.get_dummies()
       a  b  c
    0  1  1  0
    1  0  0  0
    2  1  0  1
    """
    arr = arr.fillna('')
    try:
        arr = sep + arr + sep
    except TypeError:
        arr = sep + arr.astype(str) + sep

    tags = set()
    for ts in arr.str.split(sep):
        tags.update(ts)
    tags = sorted(tags - {""})

    dummies = np.empty((len(arr), len(tags)), dtype=np.int64)

    for i, t in enumerate(tags):
        pat = sep + t + sep
        dummies[:, i] = lib.map_infer(arr.values, lambda x: pat in x)
    return dummies, tags


def str_join(arr, sep):
    """
    Join lists contained as elements in the Series/Index with passed delimiter.

    If the elements of a Series are lists themselves, join the content of these
    lists using the delimiter passed to the function.
    This function is an equivalent to :meth:`str.join`.

    Parameters
    ----------
    sep : str
        Delimiter to use between list entries.

    Returns
    -------
    Series/Index: object
        The list entries concatenated by intervening occurrences of the
        delimiter.

    Raises
    -------
    AttributeError
        If the supplied Series contains neither strings nor lists.

    See Also
    --------
    str.join : Standard library version of this method.
    Series.str.split : Split strings around given separator/delimiter.

    Notes
    -----
    If any of the list items is not a string object, the result of the join
    will be `NaN`.

    Examples
    --------
    Example with a list that contains non-string elements.

    >>> s = pd.Series([['lion', 'elephant', 'zebra'],
    ...                [1.1, 2.2, 3.3],
    ...                ['cat', np.nan, 'dog'],
    ...                ['cow', 4.5, 'goat'],
    ...                ['duck', ['swan', 'fish'], 'guppy']])
    >>> s
    0        [lion, elephant, zebra]
    1                [1.1, 2.2, 3.3]
    2                [cat, nan, dog]
    3               [cow, 4.5, goat]
    4    [duck, [swan, fish], guppy]
    dtype: object

    Join all lists using a '-'. The lists containing object(s) of types other
    than str will produce a NaN.

    >>> s.str.join('-')
    0    lion-elephant-zebra
    1                    NaN
    2                    NaN
    3                    NaN
    4                    NaN
    dtype: object
    """
    return _na_map(sep.join, arr)


def str_findall(arr, pat, flags=0):
    """
    Find all occurrences of pattern or regular expression in the Series/Index.

    Equivalent to applying :func:`re.findall` to all the elements in the
    Series/Index.

    Parameters
    ----------
    pat : str
        Pattern or regular expression.
    flags : int, default 0
        Flags from ``re`` module, e.g. `re.IGNORECASE` (default is 0, which
        means no flags).

    Returns
    -------
    Series/Index of lists of strings
        All non-overlapping matches of pattern or regular expression in each
        string of this Series/Index.

    See Also
    --------
    count : Count occurrences of pattern or regular expression in each string
        of the Series/Index.
    extractall : For each string in the Series, extract groups from all matches
        of regular expression and return a DataFrame with one row for each
        match and one column for each group.
    re.findall : The equivalent ``re`` function to all non-overlapping matches
        of pattern or regular expression in string, as a list of strings.

    Examples
    --------

    >>> s = pd.Series(['Lion', 'Monkey', 'Rabbit'])

    The search for the pattern 'Monkey' returns one match:

    >>> s.str.findall('Monkey')
    0          []
    1    [Monkey]
    2          []
    dtype: object

    On the other hand, the search for the pattern 'MONKEY' doesn't return any
    match:

    >>> s.str.findall('MONKEY')
    0    []
    1    []
    2    []
    dtype: object

    Flags can be added to the pattern or regular expression. For instance,
    to find the pattern 'MONKEY' ignoring the case:

    >>> import re
    >>> s.str.findall('MONKEY', flags=re.IGNORECASE)
    0          []
    1    [Monkey]
    2          []
    dtype: object

    When the pattern matches more than one string in the Series, all matches
    are returned:

    >>> s.str.findall('on')
    0    [on]
    1    [on]
    2      []
    dtype: object

    Regular expressions are supported too. For instance, the search for all the
    strings ending with the word 'on' is shown next:

    >>> s.str.findall('on$')
    0    [on]
    1      []
    2      []
    dtype: object

    If the pattern is found more than once in the same string, then a list of
    multiple strings is returned:

    >>> s.str.findall('b')
    0        []
    1        []
    2    [b, b]
    dtype: object
    """
    regex = re.compile(pat, flags=flags)
    return _na_map(regex.findall, arr)


def str_find(arr, sub, start=0, end=None, side='left'):
    """
    Return indexes in each strings in the Series/Index where the
    substring is fully contained between [start:end]. Return -1 on failure.

    Parameters
    ----------
    sub : str
        Substring being searched.
    start : int
        Left edge index.
    end : int
        Right edge index.
    side : {'left', 'right'}, default 'left'
        Specifies a starting side, equivalent to ``find`` or ``rfind``.

    Returns
    -------
    Series or Index
        Indexes where substring is found.
    """

    if not isinstance(sub, compat.string_types):
        msg = 'expected a string object, not {0}'
        raise TypeError(msg.format(type(sub).__name__))

    if side == 'left':
        method = 'find'
    elif side == 'right':
        method = 'rfind'
    else:  # pragma: no cover
        raise ValueError('Invalid side')

    if end is None:
        f = lambda x: getattr(x, method)(sub, start)
    else:
        f = lambda x: getattr(x, method)(sub, start, end)

    return _na_map(f, arr, dtype=int)


def str_index(arr, sub, start=0, end=None, side='left'):
    if not isinstance(sub, compat.string_types):
        msg = 'expected a string object, not {0}'
        raise TypeError(msg.format(type(sub).__name__))

    if side == 'left':
        method = 'index'
    elif side == 'right':
        method = 'rindex'
    else:  # pragma: no cover
        raise ValueError('Invalid side')

    if end is None:
        f = lambda x: getattr(x, method)(sub, start)
    else:
        f = lambda x: getattr(x, method)(sub, start, end)

    return _na_map(f, arr, dtype=int)


def str_pad(arr, width, side='left', fillchar=' '):
    """
    Pad strings in the Series/Index up to width.

    Parameters
    ----------
    width : int
        Minimum width of resulting string; additional characters will be filled
        with character defined in `fillchar`.
    side : {'left', 'right', 'both'}, default 'left'
        Side from which to fill resulting string.
    fillchar : str, default ' '
        Additional character for filling, default is whitespace.

    Returns
    -------
    Series or Index of object
        Returns Series or Index with minimum number of char in object.

    See Also
    --------
    Series.str.rjust : Fills the left side of strings with an arbitrary
        character. Equivalent to ``Series.str.pad(side='left')``.
    Series.str.ljust : Fills the right side of strings with an arbitrary
        character. Equivalent to ``Series.str.pad(side='right')``.
    Series.str.center : Fills boths sides of strings with an arbitrary
        character. Equivalent to ``Series.str.pad(side='both')``.
    Series.str.zfill :  Pad strings in the Series/Index by prepending '0'
        character. Equivalent to ``Series.str.pad(side='left', fillchar='0')``.

    Examples
    --------
    >>> s = pd.Series(["caribou", "tiger"])
    >>> s
    0    caribou
    1      tiger
    dtype: object

    >>> s.str.pad(width=10)
    0       caribou
    1         tiger
    dtype: object

    >>> s.str.pad(width=10, side='right', fillchar='-')
    0    caribou---
    1    tiger-----
    dtype: object

    >>> s.str.pad(width=10, side='both', fillchar='-')
    0    -caribou--
    1    --tiger---
    dtype: object
    """
    if not isinstance(fillchar, compat.string_types):
        msg = 'fillchar must be a character, not {0}'
        raise TypeError(msg.format(type(fillchar).__name__))

    if len(fillchar) != 1:
        raise TypeError('fillchar must be a character, not str')

    if not is_integer(width):
        msg = 'width must be of integer type, not {0}'
        raise TypeError(msg.format(type(width).__name__))

    if side == 'left':
        f = lambda x: x.rjust(width, fillchar)
    elif side == 'right':
        f = lambda x: x.ljust(width, fillchar)
    elif side == 'both':
        f = lambda x: x.center(width, fillchar)
    else:  # pragma: no cover
        raise ValueError('Invalid side')

    return _na_map(f, arr)


def str_split(arr, pat=None, n=None):

    if pat is None:
        if n is None or n == 0:
            n = -1
        f = lambda x: x.split(pat, n)
    else:
        if len(pat) == 1:
            if n is None or n == 0:
                n = -1
            f = lambda x: x.split(pat, n)
        else:
            if n is None or n == -1:
                n = 0
            regex = re.compile(pat)
            f = lambda x: regex.split(x, maxsplit=n)
    res = _na_map(f, arr)
    return res


def str_rsplit(arr, pat=None, n=None):

    if n is None or n == 0:
        n = -1
    f = lambda x: x.rsplit(pat, n)
    res = _na_map(f, arr)
    return res


def str_slice(arr, start=None, stop=None, step=None):
    """
    Slice substrings from each element in the Series or Index.

    Parameters
    ----------
    start : int, optional
        Start position for slice operation.
    stop : int, optional
        Stop position for slice operation.
    step : int, optional
        Step size for slice operation.

    Returns
    -------
    Series or Index of object
        Series or Index from sliced substring from original string object.

    See Also
    --------
    Series.str.slice_replace : Replace a slice with a string.
    Series.str.get : Return element at position.
        Equivalent to `Series.str.slice(start=i, stop=i+1)` with `i`
        being the position.

    Examples
    --------
    >>> s = pd.Series(["koala", "fox", "chameleon"])
    >>> s
    0        koala
    1          fox
    2    chameleon
    dtype: object

    >>> s.str.slice(start=1)
    0        oala
    1          ox
    2    hameleon
    dtype: object

    >>> s.str.slice(stop=2)
    0    ko
    1    fo
    2    ch
    dtype: object

    >>> s.str.slice(step=2)
    0      kaa
    1       fx
    2    caeen
    dtype: object

    >>> s.str.slice(start=0, stop=5, step=3)
    0    kl
    1     f
    2    cm
    dtype: object

    Equivalent behaviour to:

    >>> s.str[0:5:3]
    0    kl
    1     f
    2    cm
    dtype: object
    """
    obj = slice(start, stop, step)
    f = lambda x: x[obj]
    return _na_map(f, arr)


def str_slice_replace(arr, start=None, stop=None, repl=None):
    """
    Replace a positional slice of a string with another value.

    Parameters
    ----------
    start : int, optional
        Left index position to use for the slice. If not specified (None),
        the slice is unbounded on the left, i.e. slice from the start
        of the string.
    stop : int, optional
        Right index position to use for the slice. If not specified (None),
        the slice is unbounded on the right, i.e. slice until the
        end of the string.
    repl : str, optional
        String for replacement. If not specified (None), the sliced region
        is replaced with an empty string.

    Returns
    -------
    Series or Index
        Same type as the original object.

    See Also
    --------
    Series.str.slice : Just slicing without replacement.

    Examples
    --------
    >>> s = pd.Series(['a', 'ab', 'abc', 'abdc', 'abcde'])
    >>> s
    0        a
    1       ab
    2      abc
    3     abdc
    4    abcde
    dtype: object

    Specify just `start`, meaning replace `start` until the end of the
    string with `repl`.

    >>> s.str.slice_replace(1, repl='X')
    0    aX
    1    aX
    2    aX
    3    aX
    4    aX
    dtype: object

    Specify just `stop`, meaning the start of the string to `stop` is replaced
    with `repl`, and the rest of the string is included.

    >>> s.str.slice_replace(stop=2, repl='X')
    0       X
    1       X
    2      Xc
    3     Xdc
    4    Xcde
    dtype: object

    Specify `start` and `stop`, meaning the slice from `start` to `stop` is
    replaced with `repl`. Everything before or after `start` and `stop` is
    included as is.

    >>> s.str.slice_replace(start=1, stop=3, repl='X')
    0      aX
    1      aX
    2      aX
    3     aXc
    4    aXde
    dtype: object
    """
    if repl is None:
        repl = ''

    def f(x):
        if x[start:stop] == '':
            local_stop = start
        else:
            local_stop = stop
        y = ''
        if start is not None:
            y += x[:start]
        y += repl
        if stop is not None:
            y += x[local_stop:]
        return y

    return _na_map(f, arr)


def str_strip(arr, to_strip=None, side='both'):
    """
    Strip whitespace (including newlines) from each string in the
    Series/Index.

    Parameters
    ----------
    to_strip : str or unicode
    side : {'left', 'right', 'both'}, default 'both'

    Returns
    -------
    Series or Index
    """
    if side == 'both':
        f = lambda x: x.strip(to_strip)
    elif side == 'left':
        f = lambda x: x.lstrip(to_strip)
    elif side == 'right':
        f = lambda x: x.rstrip(to_strip)
    else:  # pragma: no cover
        raise ValueError('Invalid side')
    return _na_map(f, arr)


def str_wrap(arr, width, **kwargs):
    r"""
    Wrap long strings in the Series/Index to be formatted in
    paragraphs with length less than a given width.

    This method has the same keyword parameters and defaults as
    :class:`textwrap.TextWrapper`.

    Parameters
    ----------
    width : int
        Maximum line width.
    expand_tabs : bool, optional
        If True, tab characters will be expanded to spaces (default: True).
    replace_whitespace : bool, optional
        If True, each whitespace character (as defined by string.whitespace)
        remaining after tab expansion will be replaced by a single space
        (default: True).
    drop_whitespace : bool, optional
        If True, whitespace that, after wrapping, happens to end up at the
        beginning or end of a line is dropped (default: True).
    break_long_words : bool, optional
        If True, then words longer than width will be broken in order to ensure
        that no lines are longer than width. If it is false, long words will
        not be broken, and some lines may be longer than width (default: True).
    break_on_hyphens : bool, optional
        If True, wrapping will occur preferably on whitespace and right after
        hyphens in compound words, as it is customary in English. If false,
        only whitespaces will be considered as potentially good places for line
        breaks, but you need to set break_long_words to false if you want truly
        insecable words (default: True).

    Returns
    -------
    Series or Index

    Notes
    -----
    Internally, this method uses a :class:`textwrap.TextWrapper` instance with
    default settings. To achieve behavior matching R's stringr library str_wrap
    function, use the arguments:

    - expand_tabs = False
    - replace_whitespace = True
    - drop_whitespace = True
    - break_long_words = False
    - break_on_hyphens = False

    Examples
    --------

    >>> s = pd.Series(['line to be wrapped', 'another line to be wrapped'])
    >>> s.str.wrap(12)
    0             line to be\nwrapped
    1    another line\nto be\nwrapped
    dtype: object
    """
    kwargs['width'] = width

    tw = textwrap.TextWrapper(**kwargs)

    return _na_map(lambda s: '\n'.join(tw.wrap(s)), arr)


def str_translate(arr, table, deletechars=None):
    """
    Map all characters in the string through the given mapping table.
    Equivalent to standard :meth:`str.translate`. Note that the optional
    argument deletechars is only valid if you are using python 2. For python 3,
    character deletion should be specified via the table argument.

    Parameters
    ----------
    table : dict (python 3), str or None (python 2)
        In python 3, table is a mapping of Unicode ordinals to Unicode
        ordinals, strings, or None. Unmapped characters are left untouched.
        Characters mapped to None are deleted. :meth:`str.maketrans` is a
        helper function for making translation tables.
        In python 2, table is either a string of length 256 or None. If the
        table argument is None, no translation is applied and the operation
        simply removes the characters in deletechars. :func:`string.maketrans`
        is a helper function for making translation tables.
    deletechars : str, optional (python 2)
        A string of characters to delete. This argument is only valid
        in python 2.

    Returns
    -------
    Series or Index
    """
    if deletechars is None:
        f = lambda x: x.translate(table)
    else:
        if compat.PY3:
            raise ValueError("deletechars is not a valid argument for "
                             "str.translate in python 3. You should simply "
                             "specify character deletions in the table "
                             "argument")
        f = lambda x: x.translate(table, deletechars)
    return _na_map(f, arr)


def str_get(arr, i):
    """
    Extract element from each component at specified position.

    Extract element from lists, tuples, or strings in each element in the
    Series/Index.

    Parameters
    ----------
    i : int
        Position of element to extract.

    Returns
    -------
    Series or Index

    Examples
    --------
    >>> s = pd.Series(["String",
    ...               (1, 2, 3),
    ...               ["a", "b", "c"],
    ...               123,
    ...               -456,
    ...               {1: "Hello", "2": "World"}])
    >>> s
    0                        String
    1                     (1, 2, 3)
    2                     [a, b, c]
    3                           123
    4                          -456
    5    {1: 'Hello', '2': 'World'}
    dtype: object

    >>> s.str.get(1)
    0        t
    1        2
    2        b
    3      NaN
    4      NaN
    5    Hello
    dtype: object

    >>> s.str.get(-1)
    0      g
    1      3
    2      c
    3    NaN
    4    NaN
    5    None
    dtype: object
    """
    def f(x):
        if isinstance(x, dict):
            return x.get(i)
        elif len(x) > i >= -len(x):
            return x[i]
        return np.nan
    return _na_map(f, arr)


def str_decode(arr, encoding, errors="strict"):
    """
    Decode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.decode` in python2 and :meth:`bytes.decode` in
    python3.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    Series or Index
    """
    if encoding in _cpython_optimized_decoders:
        # CPython optimized implementation
        f = lambda x: x.decode(encoding, errors)
    else:
        decoder = codecs.getdecoder(encoding)
        f = lambda x: decoder(x, errors)[0]
    return _na_map(f, arr)


def str_encode(arr, encoding, errors="strict"):
    """
    Encode character string in the Series/Index using indicated encoding.
    Equivalent to :meth:`str.encode`.

    Parameters
    ----------
    encoding : str
    errors : str, optional

    Returns
    -------
    encoded : Series/Index of objects
    """
    if encoding in _cpython_optimized_encoders:
        # CPython optimized implementation
        f = lambda x: x.encode(encoding, errors)
    else:
        encoder = codecs.getencoder(encoding)
        f = lambda x: encoder(x, errors)[0]
    return _na_map(f, arr)


def _noarg_wrapper(f, docstring=None, **kargs):
    def wrapper(self):
        result = _na_map(f, self._parent, **kargs)
        return self._wrap_result(result)

    wrapper.__name__ = f.__name__
    if docstring is not None:
        wrapper.__doc__ = docstring
    else:
        raise ValueError('Provide docstring')

    return wrapper


def _pat_wrapper(f, flags=False, na=False, **kwargs):
    def wrapper1(self, pat):
        result = f(self._parent, pat)
        return self._wrap_result(result)

    def wrapper2(self, pat, flags=0, **kwargs):
        result = f(self._parent, pat, flags=flags, **kwargs)
        return self._wrap_result(result)

    def wrapper3(self, pat, na=np.nan):
        result = f(self._parent, pat, na=na)
        return self._wrap_result(result)

    wrapper = wrapper3 if na else wrapper2 if flags else wrapper1

    wrapper.__name__ = f.__name__
    if f.__doc__:
        wrapper.__doc__ = f.__doc__

    return wrapper


def copy(source):
    "Copy a docstring from another source function (if…