DataX/otsstreamreader/tools/tabulate.py

# -*- coding: utf-8 -*-

"""Pretty-print tabular data."""

from __future__ import print_function
from __future__ import unicode_literals
from collections import namedtuple, Iterable
from platform import python_version_tuple
import re


if python_version_tuple()[0] < "3":
    from itertools import izip_longest
    from functools import partial
    _none_type = type(None)
    _int_type = int
    _long_type = long
    _float_type = float
    _text_type = unicode
    _binary_type = str

    def _is_file(f):
        return isinstance(f, file)

else:
    from itertools import zip_longest as izip_longest
    from functools import reduce, partial
    _none_type = type(None)
    _int_type = int
    _long_type = int
    _float_type = float
    _text_type = str
    _binary_type = bytes

    import io
    def _is_file(f):
        return isinstance(f, io.IOBase)

try:
    import wcwidth  # optional wide-character (CJK) support
except ImportError:
    wcwidth = None


__all__ = ["tabulate", "tabulate_formats", "simple_separated_format"]
__version__ = "0.7.6-dev"


# minimum extra space in headers
MIN_PADDING = 2

# if True, enable wide-character (CJK) support
WIDE_CHARS_MODE = wcwidth is not None


Line = namedtuple("Line", ["begin", "hline", "sep", "end"])


DataRow = namedtuple("DataRow", ["begin", "sep", "end"])


# A table structure is suppposed to be:
#
#     --- lineabove ---------
#         headerrow
#     --- linebelowheader ---
#         datarow
#     --- linebewteenrows ---
#     ... (more datarows) ...
#     --- linebewteenrows ---
#         last datarow
#     --- linebelow ---------
#
# TableFormat's line* elements can be
#
#   - either None, if the element is not used,
#   - or a Line tuple,
#   - or a function: [col_widths], [col_alignments] -> string.
#
# TableFormat's *row elements can be
#
#   - either None, if the element is not used,
#   - or a DataRow tuple,
#   - or a function: [cell_values], [col_widths], [col_alignments] -> string.
#
# padding (an integer) is the amount of white space around data values.
#
# with_header_hide:
#
#   - either None, to display all table elements unconditionally,
#   - or a list of elements not to be displayed if the table has column headers.
#
TableFormat = namedtuple("TableFormat", ["lineabove", "linebelowheader",
                                         "linebetweenrows", "linebelow",
                                         "headerrow", "datarow",
                                         "padding", "with_header_hide"])


def _pipe_segment_with_colons(align, colwidth):
    """Return a segment of a horizontal line with optional colons which
    indicate column's alignment (as in `pipe` output format)."""
    w = colwidth
    if align in ["right", "decimal"]:
        return ('-' * (w - 1)) + ":"
    elif align == "center":
        return ":" + ('-' * (w - 2)) + ":"
    elif align == "left":
        return ":" + ('-' * (w - 1))
    else:
        return '-' * w


def _pipe_line_with_colons(colwidths, colaligns):
    """Return a horizontal line with optional colons to indicate column's
    alignment (as in `pipe` output format)."""
    segments = [_pipe_segment_with_colons(a, w) for a, w in zip(colaligns, colwidths)]
    return "|" + "|".join(segments) + "|"


def _mediawiki_row_with_attrs(separator, cell_values, colwidths, colaligns):
    alignment = { "left":    '',
                  "right":   'align="right"| ',
                  "center":  'align="center"| ',
                  "decimal": 'align="right"| ' }
    # hard-coded padding _around_ align attribute and value together
    # rather than padding parameter which affects only the value
    values_with_attrs = [' ' + alignment.get(a, '') + c + ' '
                         for c, a in zip(cell_values, colaligns)]
    colsep = separator*2
    return (separator + colsep.join(values_with_attrs)).rstrip()


def _textile_row_with_attrs(cell_values, colwidths, colaligns):
    cell_values[0] += ' '
    alignment = { "left": "<.", "right": ">.", "center": "=.", "decimal": ">." }
    values = (alignment.get(a, '') + v for a, v in zip(colaligns, cell_values))
    return '|' + '|'.join(values) + '|'


def _html_begin_table_without_header(colwidths_ignore, colaligns_ignore):
    # this table header will be suppressed if there is a header row
    return "\n".join(["<table>", "<tbody>"])


def _html_row_with_attrs(celltag, cell_values, colwidths, colaligns):
    alignment = { "left":    '',
                  "right":   ' style="text-align: right;"',
                  "center":  ' style="text-align: center;"',
                  "decimal": ' style="text-align: right;"' }
    values_with_attrs = ["<{0}{1}>{2}</{0}>".format(celltag, alignment.get(a, ''), c)
                         for c, a in zip(cell_values, colaligns)]
    rowhtml = "<tr>" + "".join(values_with_attrs).rstrip() + "</tr>"
    if celltag == "th":  # it's a header row, create a new table header
        rowhtml = "\n".join(["<table>",
                             "<thead>",
                             rowhtml,
                             "</thead>",
                             "<tbody>"])
    return rowhtml

def _moin_row_with_attrs(celltag, cell_values, colwidths, colaligns, header=''):
    alignment = { "left":    '',
                  "right":   '<style="text-align: right;">',
                  "center":  '<style="text-align: center;">',
                  "decimal": '<style="text-align: right;">' }
    values_with_attrs = ["{0}{1} {2} ".format(celltag,
                                              alignment.get(a, ''),
                                              header+c+header)
                         for c, a in zip(cell_values, colaligns)]
    return "".join(values_with_attrs)+"||"

def _latex_line_begin_tabular(colwidths, colaligns, booktabs=False):
    alignment = { "left": "l", "right": "r", "center": "c", "decimal": "r" }
    tabular_columns_fmt = "".join([alignment.get(a, "l") for a in colaligns])
    return "\n".join(["\\begin{tabular}{" + tabular_columns_fmt + "}",
                      "\\toprule" if booktabs else "\hline"])

LATEX_ESCAPE_RULES = {r"&": r"\&", r"%": r"\%", r"$": r"\$", r"#": r"\#",
                      r"_": r"\_", r"^": r"\^{}", r"{": r"\{", r"}": r"\}",
                      r"~": r"\textasciitilde{}", "\\": r"\textbackslash{}",
                      r"<": r"\ensuremath{<}", r">": r"\ensuremath{>}"}


def _latex_row(cell_values, colwidths, colaligns):
    def escape_char(c):
        return LATEX_ESCAPE_RULES.get(c, c)
    escaped_values = ["".join(map(escape_char, cell)) for cell in cell_values]
    rowfmt = DataRow("", "&", "\\\\")
    return _build_simple_row(escaped_values, rowfmt)


_table_formats = {"simple":
                  TableFormat(lineabove=Line("", "-", "  ", ""),
                              linebelowheader=Line("", "-", "  ", ""),
                              linebetweenrows=None,
                              linebelow=Line("", "-", "  ", ""),
                              headerrow=DataRow("", "  ", ""),
                              datarow=DataRow("", "  ", ""),
                              padding=0,
                              with_header_hide=["lineabove", "linebelow"]),
                  "plain":
                  TableFormat(lineabove=None, linebelowheader=None,
                              linebetweenrows=None, linebelow=None,
                              headerrow=DataRow("", "  ", ""),
                              datarow=DataRow("", "  ", ""),
                              padding=0, with_header_hide=None),
                  "grid":
                  TableFormat(lineabove=Line("+", "-", "+", "+"),
                              linebelowheader=Line("+", "=", "+", "+"),
                              linebetweenrows=Line("+", "-", "+", "+"),
                              linebelow=Line("+", "-", "+", "+"),
                              headerrow=DataRow("|", "|", "|"),
                              datarow=DataRow("|", "|", "|"),
                              padding=1, with_header_hide=None),
                  "fancy_grid":
                  TableFormat(lineabove=Line("╒", "═", "╤", "╕"),
                              linebelowheader=Line("╞", "═", "╪", "╡"),
                              linebetweenrows=Line("├", "─", "┼", "┤"),
                              linebelow=Line("╘", "═", "╧", "╛"),
                              headerrow=DataRow("│", "│", "│"),
                              datarow=DataRow("│", "│", "│"),
                              padding=1, with_header_hide=None),
                  "pipe":
                  TableFormat(lineabove=_pipe_line_with_colons,
                              linebelowheader=_pipe_line_with_colons,
                              linebetweenrows=None,
                              linebelow=None,
                              headerrow=DataRow("|", "|", "|"),
                              datarow=DataRow("|", "|", "|"),
                              padding=1,
                              with_header_hide=["lineabove"]),
                  "orgtbl":
                  TableFormat(lineabove=None,
                              linebelowheader=Line("|", "-", "+", "|"),
                              linebetweenrows=None,
                              linebelow=None,
                              headerrow=DataRow("|", "|", "|"),
                              datarow=DataRow("|", "|", "|"),
                              padding=1, with_header_hide=None),
                  "jira":
                  TableFormat(lineabove=None,
                              linebelowheader=None,
                              linebetweenrows=None,
                              linebelow=None,
                              headerrow=DataRow("||", "||", "||"),
                              datarow=DataRow("|", "|", "|"),
                              padding=1, with_header_hide=None),
                  "psql":
                  TableFormat(lineabove=Line("+", "-", "+", "+"),
                              linebelowheader=Line("|", "-", "+", "|"),
                              linebetweenrows=None,
                              linebelow=Line("+", "-", "+", "+"),
                              headerrow=DataRow("|", "|", "|"),
                              datarow=DataRow("|", "|", "|"),
                              padding=1, with_header_hide=None),
                  "rst":
                  TableFormat(lineabove=Line("", "=", "  ", ""),
                              linebelowheader=Line("", "=", "  ", ""),
                              linebetweenrows=None,
                              linebelow=Line("", "=", "  ", ""),
                              headerrow=DataRow("", "  ", ""),
                              datarow=DataRow("", "  ", ""),
                              padding=0, with_header_hide=None),
                  "mediawiki":
                  TableFormat(lineabove=Line("{| class=\"wikitable\" style=\"text-align: left;\"",
                                             "", "", "\n|+ <!-- caption -->\n|-"),
                              linebelowheader=Line("|-", "", "", ""),
                              linebetweenrows=Line("|-", "", "", ""),
                              linebelow=Line("|}", "", "", ""),
                              headerrow=partial(_mediawiki_row_with_attrs, "!"),
                              datarow=partial(_mediawiki_row_with_attrs, "|"),
                              padding=0, with_header_hide=None),
                  "moinmoin":
                  TableFormat(lineabove=None,
                              linebelowheader=None,
                              linebetweenrows=None,
                              linebelow=None,
                              headerrow=partial(_moin_row_with_attrs,"||",header="'''"),
                              datarow=partial(_moin_row_with_attrs,"||"),
                              padding=1, with_header_hide=None),
                  "html":
                  TableFormat(lineabove=_html_begin_table_without_header,
                              linebelowheader="",
                              linebetweenrows=None,
                              linebelow=Line("</tbody>\n</table>", "", "", ""),
                              headerrow=partial(_html_row_with_attrs, "th"),
                              datarow=partial(_html_row_with_attrs, "td"),
                              padding=0, with_header_hide=["lineabove"]),
                  "latex":
                  TableFormat(lineabove=_latex_line_begin_tabular,
                              linebelowheader=Line("\\hline", "", "", ""),
                              linebetweenrows=None,
                              linebelow=Line("\\hline\n\\end{tabular}", "", "", ""),
                              headerrow=_latex_row,
                              datarow=_latex_row,
                              padding=1, with_header_hide=None),
                  "latex_booktabs":
                  TableFormat(lineabove=partial(_latex_line_begin_tabular, booktabs=True),
                              linebelowheader=Line("\\midrule", "", "", ""),
                              linebetweenrows=None,
                              linebelow=Line("\\bottomrule\n\\end{tabular}", "", "", ""),
                              headerrow=_latex_row,
                              datarow=_latex_row,
                              padding=1, with_header_hide=None),
                  "tsv":
                  TableFormat(lineabove=None, linebelowheader=None,
                              linebetweenrows=None, linebelow=None,
                              headerrow=DataRow("", "\t", ""),
                              datarow=DataRow("", "\t", ""),
                              padding=0, with_header_hide=None),
                  "textile":
                  TableFormat(lineabove=None, linebelowheader=None,
                              linebetweenrows=None, linebelow=None,
                              headerrow=DataRow("|_. ", "|_.", "|"),
                              datarow=_textile_row_with_attrs,
                              padding=1, with_header_hide=None)}


tabulate_formats = list(sorted(_table_formats.keys()))


_invisible_codes = re.compile(r"\x1b\[\d*m|\x1b\[\d*\;\d*\;\d*m")  # ANSI color codes
_invisible_codes_bytes = re.compile(b"\x1b\[\d*m|\x1b\[\d*\;\d*\;\d*m")  # ANSI color codes


def simple_separated_format(separator):
    """Construct a simple TableFormat with columns separated by a separator.

    >>> tsv = simple_separated_format("\\t") ; \
        tabulate([["foo", 1], ["spam", 23]], tablefmt=tsv) == 'foo \\t 1\\nspam\\t23'
    True

    """
    return TableFormat(None, None, None, None,
                       headerrow=DataRow('', separator, ''),
                       datarow=DataRow('', separator, ''),
                       padding=0, with_header_hide=None)


def _isconvertible(conv, string):
    try:
        n = conv(string)
        return True
    except (ValueError, TypeError):
        return False


def _isnumber(string):
    """
    >>> _isnumber("123.45")
    True
    >>> _isnumber("123")
    True
    >>> _isnumber("spam")
    False
    """
    return _isconvertible(float, string)


def _isint(string, inttype=int):
    """
    >>> _isint("123")
    True
    >>> _isint("123.45")
    False
    """
    return type(string) is inttype or\
           (isinstance(string, _binary_type) or isinstance(string, _text_type))\
            and\
            _isconvertible(inttype, string)


def _type(string, has_invisible=True):
    """The least generic type (type(None), int, float, str, unicode).

    >>> _type(None) is type(None)
    True
    >>> _type("foo") is type("")
    True
    >>> _type("1") is type(1)
    True
    >>> _type('\x1b[31m42\x1b[0m') is type(42)
    True
    >>> _type('\x1b[31m42\x1b[0m') is type(42)
    True

    """

    if has_invisible and \
       (isinstance(string, _text_type) or isinstance(string, _binary_type)):
        string = _strip_invisible(string)

    if string is None:
        return _none_type
    elif hasattr(string, "isoformat"):  # datetime.datetime, date, and time
        return _text_type
    elif _isint(string):
        return int
    elif _isint(string, _long_type):
        return int
    elif _isnumber(string):
        return float
    elif isinstance(string, _binary_type):
        return _binary_type
    else:
        return _text_type


def _afterpoint(string):
    """Symbols after a decimal point, -1 if the string lacks the decimal point.

    >>> _afterpoint("123.45")
    2
    >>> _afterpoint("1001")
    -1
    >>> _afterpoint("eggs")
    -1
    >>> _afterpoint("123e45")
    2

    """
    if _isnumber(string):
        if _isint(string):
            return -1
        else:
            pos = string.rfind(".")
            pos = string.lower().rfind("e") if pos < 0 else pos
            if pos >= 0:
                return len(string) - pos - 1
            else:
                return -1  # no point
    else:
        return -1  # not a number


def _padleft(width, s):
    """Flush right.

    >>> _padleft(6, '\u044f\u0439\u0446\u0430') == '  \u044f\u0439\u0446\u0430'
    True

    """
    fmt = "{0:>%ds}" % width
    return fmt.format(s)


def _padright(width, s):
    """Flush left.

    >>> _padright(6, '\u044f\u0439\u0446\u0430') == '\u044f\u0439\u0446\u0430  '
    True

    """
    fmt = "{0:<%ds}" % width
    return fmt.format(s)


def _padboth(width, s):
    """Center string.

    >>> _padboth(6, '\u044f\u0439\u0446\u0430') == ' \u044f\u0439\u0446\u0430 '
    True

    """
    fmt = "{0:^%ds}" % width
    return fmt.format(s)


def _strip_invisible(s):
    "Remove invisible ANSI color codes."
    if isinstance(s, _text_type):
        return re.sub(_invisible_codes, "", s)
    else:  # a bytestring
        return re.sub(_invisible_codes_bytes, "", s)


def _visible_width(s):
    """Visible width of a printed string. ANSI color codes are removed.

    >>> _visible_width('\x1b[31mhello\x1b[0m'), _visible_width("world")
    (5, 5)

    """
    # optional wide-character support
    if wcwidth is not None and WIDE_CHARS_MODE:
        len_fn = wcwidth.wcswidth
    else:
        len_fn = len
    if isinstance(s, _text_type) or isinstance(s, _binary_type):
        return len_fn(_strip_invisible(s))
    else:
        return len_fn(_text_type(s))


def _align_column(strings, alignment, minwidth=0, has_invisible=True):
    """[string] -> [padded_string]

    >>> list(map(str,_align_column(["12.345", "-1234.5", "1.23", "1234.5", "1e+234", "1.0e234"], "decimal")))
    ['   12.345  ', '-1234.5    ', '    1.23   ', ' 1234.5    ', '    1e+234 ', '    1.0e234']

    >>> list(map(str,_align_column(['123.4', '56.7890'], None)))
    ['123.4', '56.7890']

    """
    if alignment == "right":
        strings = [s.strip() for s in strings]
        padfn = _padleft
    elif alignment == "center":
        strings = [s.strip() for s in strings]
        padfn = _padboth
    elif alignment == "decimal":
        if has_invisible:
            decimals = [_afterpoint(_strip_invisible(s)) for s in strings]
        else:
            decimals = [_afterpoint(s) for s in strings]
        maxdecimals = max(decimals)
        strings = [s + (maxdecimals - decs) * " "
                   for s, decs in zip(strings, decimals)]
        padfn = _padleft
    elif not alignment:
        return strings
    else:
        strings = [s.strip() for s in strings]
        padfn = _padright

    enable_widechars = wcwidth is not None and WIDE_CHARS_MODE
    if has_invisible:
        width_fn = _visible_width
    elif enable_widechars: # optional wide-character support if available
        width_fn = wcwidth.wcswidth
    else:
        width_fn = len

    s_lens = list(map(len, strings))
    s_widths = list(map(width_fn, strings))
    maxwidth = max(max(s_widths), minwidth)
    if not enable_widechars and not has_invisible:
        padded_strings = [padfn(maxwidth, s) for s in strings]
    else:
        # enable wide-character width corrections
        visible_widths = [maxwidth - (w - l) for w, l in zip(s_widths, s_lens)]
        # wcswidth and _visible_width don't count invisible characters;
        # padfn doesn't need to apply another correction
        padded_strings = [padfn(w, s) for s, w in zip(strings, visible_widths)]
    return padded_strings


def _more_generic(type1, type2):
    types = { _none_type: 0, int: 1, float: 2, _binary_type: 3, _text_type: 4 }
    invtypes = { 4: _text_type, 3: _binary_type, 2: float, 1: int, 0: _none_type }
    moregeneric = max(types.get(type1, 4), types.get(type2, 4))
    return invtypes[moregeneric]


def _column_type(strings, has_invisible=True):
    """The least generic type all column values are convertible to.

    >>> _column_type(["1", "2"]) is _int_type
    True
    >>> _column_type(["1", "2.3"]) is _float_type
    True
    >>> _column_type(["1", "2.3", "four"]) is _text_type
    True
    >>> _column_type(["four", '\u043f\u044f\u0442\u044c']) is _text_type
    True
    >>> _column_type([None, "brux"]) is _text_type
    True
    >>> _column_type([1, 2, None]) is _int_type
    True
    >>> import datetime as dt
    >>> _column_type([dt.datetime(1991,2,19), dt.time(17,35)]) is _text_type
    True

    """
    types = [_type(s, has_invisible) for s in strings ]
    return reduce(_more_generic, types, int)


def _format(val, valtype, floatfmt, missingval="", has_invisible=True):
    """Format a value accoding to its type.

    Unicode is supported:

    >>> hrow = ['\u0431\u0443\u043a\u0432\u0430', '\u0446\u0438\u0444\u0440\u0430'] ; \
        tbl = [['\u0430\u0437', 2], ['\u0431\u0443\u043a\u0438', 4]] ; \
        good_result = '\\u0431\\u0443\\u043a\\u0432\\u0430      \\u0446\\u0438\\u0444\\u0440\\u0430\\n-------  -------\\n\\u0430\\u0437             2\\n\\u0431\\u0443\\u043a\\u0438           4' ; \
        tabulate(tbl, headers=hrow) == good_result
    True

    """
    if val is None:
        return missingval

    if valtype in [int, _text_type]:
        return "{0}".format(val)
    elif valtype is _binary_type:
        try:
            return _text_type(val, "ascii")
        except TypeError:
            return _text_type(val)
    elif valtype is float:
        is_a_colored_number = has_invisible and isinstance(val, (_text_type, _binary_type))
        if is_a_colored_number:
            raw_val = _strip_invisible(val)
            formatted_val = format(float(raw_val), floatfmt)
            return val.replace(raw_val, formatted_val)
        else:
            return format(float(val), floatfmt)
    else:
        return "{0}".format(val)


def _align_header(header, alignment, width, visible_width):
    "Pad string header to width chars given known visible_width of the header."
    width += len(header) - visible_width
    if alignment == "left":
        return _padright(width, header)
    elif alignment == "center":
        return _padboth(width, header)
    elif not alignment:
        return "{0}".format(header)
    else:
        return _padleft(width, header)


def _prepend_row_index(rows, index):
    """Add a left-most index column."""
    if index is None or index is False:
        return rows
    if len(index) != len(rows):
        print('index=', index)
        print('rows=', rows)
        raise ValueError('index must be as long as the number of data rows')
    rows = [[v]+list(row) for v,row in zip(index, rows)]
    return rows


def _bool(val):
    "A wrapper around standard bool() which doesn't throw on NumPy arrays"
    try:
        return bool(val)
    except ValueError:  # val is likely to be a numpy array with many elements
        return False


def _normalize_tabular_data(tabular_data, headers, showindex="default"):
    """Transform a supported data type to a list of lists, and a list of headers.

    Supported tabular data types:

    * list-of-lists or another iterable of iterables

    * list of named tuples (usually used with headers="keys")

    * list of dicts (usually used with headers="keys")

    * list of OrderedDicts (usually used with headers="keys")

    * 2D NumPy arrays

    * NumPy record arrays (usually used with headers="keys")

    * dict of iterables (usually used with headers="keys")

    * pandas.DataFrame (usually used with headers="keys")

    The first row can be used as headers if headers="firstrow",
    column indices can be used as headers if headers="keys".

    If showindex="default", show row indices of the pandas.DataFrame.
    If showindex="always", show row indices for all types of data.
    If showindex="never", don't show row indices for all types of data.
    If showindex is an iterable, show its values as row indices.

    """

    try:
        bool(headers)
        is_headers2bool_broken = False
    except ValueError: # numpy.ndarray, pandas.core.index.Index, ...
        is_headers2bool_broken = True
        headers = list(headers)

    index = None
    if hasattr(tabular_data, "keys") and hasattr(tabular_data, "values"):
        # dict-like and pandas.DataFrame?
        if hasattr(tabular_data.values, "__call__"):
            # likely a conventional dict
            keys = tabular_data.keys()
            rows = list(izip_longest(*tabular_data.values()))  # columns have to be transposed
        elif hasattr(tabular_data, "index"):
            # values is a property, has .index => it's likely a pandas.DataFrame (pandas 0.11.0)
            keys = tabular_data.keys()
            vals = tabular_data.values  # values matrix doesn't need to be transposed
            # for DataFrames add an index per default
            index = list(tabular_data.index)
            rows = [list(row) for row in vals]
        else:
            raise ValueError("tabular data doesn't appear to be a dict or a DataFrame")

        if headers == "keys":
            headers = list(map(_text_type,keys))  # headers should be strings

    else:  # it's a usual an iterable of iterables, or a NumPy array
        rows = list(tabular_data)

        if (headers == "keys" and
            hasattr(tabular_data, "dtype") and
            getattr(tabular_data.dtype, "names")):
            # numpy record array
            headers = tabular_data.dtype.names
        elif (headers == "keys"
              and len(rows) > 0
              and isinstance(rows[0], tuple)
              and hasattr(rows[0], "_fields")):
            # namedtuple
            headers = list(map(_text_type, rows[0]._fields))
        elif (len(rows) > 0
              and isinstance(rows[0], dict)):
            # dict or OrderedDict
            uniq_keys = set() # implements hashed lookup
            keys = [] # storage for set
            if headers == "firstrow":
                firstdict = rows[0] if len(rows) > 0 else {}
                keys.extend(firstdict.keys())
                uniq_keys.update(keys)
                rows = rows[1:]
            for row in rows:
                for k in row.keys():
                    #Save unique items in input order
                    if k not in uniq_keys:
                        keys.append(k)
                        uniq_keys.add(k)
            if headers == 'keys':
                headers = keys
            elif isinstance(headers, dict):
                # a dict of headers for a list of dicts
                headers = [headers.get(k, k) for k in keys]
                headers = list(map(_text_type, headers))
            elif headers == "firstrow":
                if len(rows) > 0:
                    headers = [firstdict.get(k, k) for k in keys]
                    headers = list(map(_text_type, headers))
                else:
                    headers = []
            elif headers:
                raise ValueError('headers for a list of dicts is not a dict or a keyword')
            rows = [[row.get(k) for k in keys] for row in rows]

        elif headers == "keys" and len(rows) > 0:
            # keys are column indices
            headers = list(map(_text_type, range(len(rows[0]))))

    # take headers from the first row if necessary
    if headers == "firstrow" and len(rows) > 0:
        if index is not None:
            headers = [index[0]] + list(rows[0])
            index = index[1:]
        else:
            headers = rows[0]
        headers = list(map(_text_type, headers)) # headers should be strings
        rows = rows[1:]

    headers = list(map(_text_type,headers))
    rows = list(map(list,rows))

    # add or remove an index column
    showindex_is_a_str = type(showindex) in [_text_type, _binary_type]
    if showindex == "default" and index is not None:
        rows = _prepend_row_index(rows, index)
    elif isinstance(showindex, Iterable) and not showindex_is_a_str:
        rows = _prepend_row_index(rows, list(showindex))
    elif showindex == "always" or (_bool(showindex) and not showindex_is_a_str):
        if index is None:
            index = list(range(len(rows)))
        rows = _prepend_row_index(rows, index)
    elif showindex == "never" or (not _bool(showindex) and not showindex_is_a_str):
        pass

    # pad with empty headers for initial columns if necessary
    if headers and len(rows) > 0:
       nhs = len(headers)
       ncols = len(rows[0])
       if nhs < ncols:
           headers = [""]*(ncols - nhs) + headers

    return rows, headers


def tabulate(tabular_data, headers=(), tablefmt="simple",
             floatfmt="g", numalign="decimal", stralign="left",
             missingval="", showindex="default"):
    """Format a fixed width table for pretty printing.

    >>> print(tabulate([[1, 2.34], [-56, "8.999"], ["2", "10001"]]))
    ---  ---------
      1      2.34
    -56      8.999
      2  10001
    ---  ---------

    The first required argument (`tabular_data`) can be a
    list-of-lists (or another iterable of iterables), a list of named
    tuples, a dictionary of iterables, an iterable of dictionaries,
    a two-dimensional NumPy array, NumPy record array, or a Pandas'
    dataframe.


    Table headers
    -------------

    To print nice column headers, supply the second argument (`headers`):

      - `headers` can be an explicit list of column headers
      - if `headers="firstrow"`, then the first row of data is used
      - if `headers="keys"`, then dictionary keys or column indices are used

    Otherwise a headerless table is produced.

    If the number of headers is less than the number of columns, they
    are supposed to be names of the last columns. This is consistent
    with the plain-text format of R and Pandas' dataframes.

    >>> print(tabulate([["sex","age"],["Alice","F",24],["Bob","M",19]],
    ...       headers="firstrow"))
           sex      age
    -----  -----  -----
    Alice  F         24
    Bob    M         19

    By default, pandas.DataFrame data have an additional column called
    row index. To add a similar column to all other types of data,
    use `showindex="always"` or `showindex=True`. To suppress row indices
    for all types of data, pass `showindex="never" or `showindex=False`.
    To add a custom row index column, pass `showindex=some_iterable`.

    >>> print(tabulate([["F",24],["M",19]], showindex="always"))
    -  -  --
    0  F  24
    1  M  19
    -  -  --


    Column alignment
    ----------------

    `tabulate` tries to detect column types automatically, and aligns
    the values properly. By default it aligns decimal points of the
    numbers (or flushes integer numbers to the right), and flushes
    everything else to the left. Possible column alignments
    (`numalign`, `stralign`) are: "right", "center", "left", "decimal"
    (only for `numalign`), and None (to disable alignment).


    Table formats
    -------------

    `floatfmt` is a format specification used for columns which
    contain numeric data with a decimal point.

    `None` values are replaced with a `missingval` string:

    >>> print(tabulate([["spam", 1, None],
    ...                 ["eggs", 42, 3.14],
    ...                 ["other", None, 2.7]], missingval="?"))
    -----  --  ----
    spam    1  ?
    eggs   42  3.14
    other   ?  2.7
    -----  --  ----

    Various plain-text table formats (`tablefmt`) are supported:
    'plain', 'simple', 'grid', 'pipe', 'orgtbl', 'rst', 'mediawiki',
     'latex', and 'latex_booktabs'. Variable `tabulate_formats` contains the list of
    currently supported formats.

    "plain" format doesn't use any pseudographics to draw tables,
    it separates columns with a double space:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                 ["strings", "numbers"], "plain"))
    strings      numbers
    spam         41.9999
    eggs        451

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="plain"))
    spam   41.9999
    eggs  451

    "simple" format is like Pandoc simple_tables:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                 ["strings", "numbers"], "simple"))
    strings      numbers
    ---------  ---------
    spam         41.9999
    eggs        451

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="simple"))
    ----  --------
    spam   41.9999
    eggs  451
    ----  --------

    "grid" is similar to tables produced by Emacs table.el package or
    Pandoc grid_tables:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                ["strings", "numbers"], "grid"))
    +-----------+-----------+
    | strings   |   numbers |
    +===========+===========+
    | spam      |   41.9999 |
    +-----------+-----------+
    | eggs      |  451      |
    +-----------+-----------+

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="grid"))
    +------+----------+
    | spam |  41.9999 |
    +------+----------+
    | eggs | 451      |
    +------+----------+

    "fancy_grid" draws a grid using box-drawing characters:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                ["strings", "numbers"], "fancy_grid"))
    ╒═══════════╤═══════════╕
    │ strings   │   numbers │
    ╞═══════════╪═══════════╡
    │ spam      │   41.9999 │
    ├───────────┼───────────┤
    │ eggs      │  451      │
    ╘═══════════╧═══════════╛

    "pipe" is like tables in PHP Markdown Extra extension or Pandoc
    pipe_tables:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                ["strings", "numbers"], "pipe"))
    | strings   |   numbers |
    |:----------|----------:|
    | spam      |   41.9999 |
    | eggs      |  451      |

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="pipe"))
    |:-----|---------:|
    | spam |  41.9999 |
    | eggs | 451      |

    "orgtbl" is like tables in Emacs org-mode and orgtbl-mode. They
    are slightly different from "pipe" format by not using colons to
    define column alignment, and using a "+" sign to indicate line
    intersections:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                ["strings", "numbers"], "orgtbl"))
    | strings   |   numbers |
    |-----------+-----------|
    | spam      |   41.9999 |
    | eggs      |  451      |


    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="orgtbl"))
    | spam |  41.9999 |
    | eggs | 451      |

    "rst" is like a simple table format from reStructuredText; please
    note that reStructuredText accepts also "grid" tables:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]],
    ...                ["strings", "numbers"], "rst"))
    =========  =========
    strings      numbers
    =========  =========
    spam         41.9999
    eggs        451
    =========  =========

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="rst"))
    ====  ========
    spam   41.9999
    eggs  451
    ====  ========

    "mediawiki" produces a table markup used in Wikipedia and on other
    MediaWiki-based sites:

    >>> print(tabulate([["strings", "numbers"], ["spam", 41.9999], ["eggs", "451.0"]],
    ...                headers="firstrow", tablefmt="mediawiki"))
    {| class="wikitable" style="text-align: left;"
    |+ <!-- caption -->
    |-
    ! strings   !! align="right"|   numbers
    |-
    | spam      || align="right"|   41.9999
    |-
    | eggs      || align="right"|  451
    |}

    "html" produces HTML markup:

    >>> print(tabulate([["strings", "numbers"], ["spam", 41.9999], ["eggs", "451.0"]],
    ...                headers="firstrow", tablefmt="html"))
    <table>
    <thead>
    <tr><th>strings  </th><th style="text-align: right;">  numbers</th></tr>
    </thead>
    <tbody>
    <tr><td>spam     </td><td style="text-align: right;">  41.9999</td></tr>
    <tr><td>eggs     </td><td style="text-align: right;"> 451     </td></tr>
    </tbody>
    </table>

    "latex" produces a tabular environment of LaTeX document markup:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="latex"))
    \\begin{tabular}{lr}
    \\hline
     spam &  41.9999 \\\\
     eggs & 451      \\\\
    \\hline
    \\end{tabular}

    "latex_booktabs" produces a tabular environment of LaTeX document markup
    using the booktabs.sty package:

    >>> print(tabulate([["spam", 41.9999], ["eggs", "451.0"]], tablefmt="latex_booktabs"))
    \\begin{tabular}{lr}
    \\toprule
     spam &  41.9999 \\\\
     eggs & 451      \\\\
    \\bottomrule
    \end{tabular}
    """
    if tabular_data is None:
        tabular_data = []
    list_of_lists, headers = _normalize_tabular_data(
            tabular_data, headers, showindex=showindex)

    # optimization: look for ANSI control codes once,
    # enable smart width functions only if a control code is found
    plain_text = '\n'.join(['\t'.join(map(_text_type, headers))] + \
                            ['\t'.join(map(_text_type, row)) for row in list_of_lists])

    has_invisible = re.search(_invisible_codes, plain_text)
    enable_widechars = wcwidth is not None and WIDE_CHARS_MODE
    if has_invisible:
        width_fn = _visible_width
    elif enable_widechars: # optional wide-character support if available
        width_fn = wcwidth.wcswidth
    else:
        width_fn = len

    # format rows and columns, convert numeric values to strings
    cols = list(zip(*list_of_lists))
    coltypes = list(map(_column_type, cols))
    cols = [[_format(v, ct, floatfmt, missingval, has_invisible) for v in c]
             for c,ct in zip(cols, coltypes)]

    # align columns
    aligns = [numalign if ct in [int,float] else stralign for ct in coltypes]
    minwidths = [width_fn(h) + MIN_PADDING for h in headers] if headers else [0]*len(cols)
    cols = [_align_column(c, a, minw, has_invisible)
            for c, a, minw in zip(cols, aligns, minwidths)]

    if headers:
        # align headers and add headers
        t_cols = cols or [['']] * len(headers)
        t_aligns = aligns or [stralign] * len(headers)
        minwidths = [max(minw, width_fn(c[0])) for minw, c in zip(minwidths, t_cols)]
        headers = [_align_header(h, a, minw, width_fn(h))
                   for h, a, minw in zip(headers, t_aligns, minwidths)]
        rows = list(zip(*cols))
    else:
        minwidths = [width_fn(c[0]) for c in cols]
        rows = list(zip(*cols))

    if not isinstance(tablefmt, TableFormat):
        tablefmt = _table_formats.get(tablefmt, _table_formats["simple"])

    return _format_table(tablefmt, headers, rows, minwidths, aligns)


def _build_simple_row(padded_cells, rowfmt):
    "Format row according to DataRow format without padding."
    begin, sep, end = rowfmt
    return (begin + sep.join(padded_cells) + end).rstrip()


def _build_row(padded_cells, colwidths, colaligns, rowfmt):
    "Return a string which represents a row of data cells."
    if not rowfmt:
        return None
    if hasattr(rowfmt, "__call__"):
        return rowfmt(padded_cells, colwidths, colaligns)
    else:
        return _build_simple_row(padded_cells, rowfmt)


def _build_line(colwidths, colaligns, linefmt):
    "Return a string which represents a horizontal line."
    if not linefmt:
        return None
    if hasattr(linefmt, "__call__"):
        return linefmt(colwidths, colaligns)
    else:
        begin, fill, sep,  end = linefmt
        cells = [fill*w for w in colwidths]
        return _build_simple_row(cells, (begin, sep, end))


def _pad_row(cells, padding):
    if cells:
        pad = " "*padding
        padded_cells = [pad + cell + pad for cell in cells]
        return padded_cells
    else:
        return cells


def _format_table(fmt, headers, rows, colwidths, colaligns):
    """Produce a plain-text representation of the table."""
    lines = []
    hidden = fmt.with_header_hide if (headers and fmt.with_header_hide) else []
    pad = fmt.padding
    headerrow = fmt.headerrow

    padded_widths = [(w + 2*pad) for w in colwidths]
    padded_headers = _pad_row(headers, pad)
    padded_rows = [_pad_row(row, pad) for row in rows]

    if fmt.lineabove and "lineabove" not in hidden:
        lines.append(_build_line(padded_widths, colaligns, fmt.lineabove))

    if padded_headers:
        lines.append(_build_row(padded_headers, padded_widths, colaligns, headerrow))
        if fmt.linebelowheader and "linebelowheader" not in hidden:
            lines.append(_build_line(padded_widths, colaligns, fmt.linebelowheader))

    if padded_rows and fmt.linebetweenrows and "linebetweenrows" not in hidden:
        # initial rows with a line below
        for row in padded_rows[:-1]:
            lines.append(_build_row(row, padded_widths, colaligns, fmt.datarow))
            lines.append(_build_line(padded_widths, colaligns, fmt.linebetweenrows))
        # the last row without a line below
        lines.append(_build_row(padded_rows[-1], padded_widths, colaligns, fmt.datarow))
    else:
        for row in padded_rows:
            lines.append(_build_row(row, padded_widths, colaligns, fmt.datarow))

    if fmt.linebelow and "linebelow" not in hidden:
        lines.append(_build_line(padded_widths, colaligns, fmt.linebelow))

    return "\n".join(lines)


def _main():
    """\
    Usage: tabulate [options] [FILE ...]

    Pretty-print tabular data.
    See also https://bitbucket.org/astanin/python-tabulate

    FILE                      a filename of the file with tabular data;
                              if "-" or missing, read data from stdin.

    Options:

    -h, --help                show this message
    -1, --header              use the first row of data as a table header
    -o FILE, --output FILE    print table to FILE (default: stdout)
    -s REGEXP, --sep REGEXP   use a custom column separator (default: whitespace)
    -F FPFMT, --float FPFMT   floating point number format (default: g)
    -f FMT, --format FMT      set output table format; supported formats:
                              plain, simple, grid, fancy_grid, pipe, orgtbl,
                              rst, mediawiki, html, latex, latex_booktabs, tsv
                              (default: simple)
    """
    import getopt
    import sys
    import textwrap
    usage = textwrap.dedent(_main.__doc__)
    try:
        opts, args = getopt.getopt(sys.argv[1:],
                     "h1o:s:F:f:",
                     ["help", "header", "output", "sep=", "float=", "format="])
    except getopt.GetoptError as e:
        print(e)
        print(usage)
        sys.exit(2)
    headers = []
    floatfmt = "g"
    tablefmt = "simple"
    sep = r"\s+"
    outfile = "-"
    for opt, value in opts:
        if opt in ["-1", "--header"]:
            headers = "firstrow"
        elif opt in ["-o", "--output"]:
            outfile = value
        elif opt in ["-F", "--float"]:
            floatfmt = value
        elif opt in ["-f", "--format"]:
            if value not in tabulate_formats:
                print("%s is not a supported table format" % value)
                print(usage)
                sys.exit(3)
            tablefmt = value
        elif opt in ["-s", "--sep"]:
            sep = value
        elif opt in ["-h", "--help"]:
            print(usage)
            sys.exit(0)
    files = [sys.stdin] if not args else args
    with (sys.stdout if outfile == "-" else open(outfile, "w")) as out:
        for f in files:
            if f == "-":
                f = sys.stdin
            if _is_file(f):
                _pprint_file(f, headers=headers, tablefmt=tablefmt,
                             sep=sep, floatfmt=floatfmt, file=out)
            else:
                with open(f) as fobj:
                    _pprint_file(fobj, headers=headers, tablefmt=tablefmt,
                                 sep=sep, floatfmt=floatfmt, file=out)


def _pprint_file(fobject, headers, tablefmt, sep, floatfmt, file):
    rows = fobject.readlines()
    table = [re.split(sep, r.rstrip()) for r in rows if r.strip()]
    print(tabulate(table, headers, tablefmt, floatfmt=floatfmt), file=file)


if __name__ == "__main__":
    _main()