chrislit/abydos

# Copyright 2018-2020 by Christopher C. Little.
# This file is part of Abydos.
#
# Abydos is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# Abydos is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Abydos. If not, see <http://www.gnu.org/licenses/>.

"""abydos.distance._lcprefix.

Longest common prefix
"""

from os.path import commonprefix
from typing import List, cast

from ._distance import _Distance

__all__ = ['LCPrefix']


class LCPrefix(_Distance):
    """Longest common prefix.

    .. versionadded:: 0.4.0
    """

    def lcprefix(self, strings: List[str]) -> str:
        """Return the longest common prefix of a list of strings.

        Longest common prefix (LCPrefix).

        Parameters
        ----------
        strings : list of strings
            Strings for comparison

        Returns
        -------
        str
            The longest common prefix

        Examples
        --------
        >>> pfx = LCPrefix()
        >>> pfx.lcprefix(['cat', 'hat'])
        ''
        >>> pfx.lcprefix(['Niall', 'Neil'])
        'N'
        >>> pfx.lcprefix(['aluminum', 'Catalan'])
        ''
        >>> pfx.lcprefix(['ATCG', 'TAGC'])
        ''


        .. versionadded:: 0.4.0

        """
        return cast(str, commonprefix(strings))

    def dist_abs(self, src: str, tar: str, *args: str) -> int:
        """Return the length of the longest common prefix of the strings.

        Parameters
        ----------
        src : str
            Source string for comparison
        tar : str
            Target string for comparison
        *args : strs
            Additional strings for comparison

        Raises
        ------
        ValueError
            All arguments must be of type str

        Returns
        -------
        int
            The length of the longest common prefix

        Examples
        --------
        >>> pfx = LCPrefix()
        >>> pfx.dist_abs('cat', 'hat')
        0
        >>> pfx.dist_abs('Niall', 'Neil')
        1
        >>> pfx.dist_abs('aluminum', 'Catalan')
        0
        >>> pfx.dist_abs('ATCG', 'TAGC')
        0


        .. versionadded:: 0.4.0

        """
        strings = [src, tar]
        for arg in args:
            if isinstance(arg, str):
                strings.append(arg)
            else:
                raise TypeError('All arguments must be of type str')

        return len(self.lcprefix(strings))

    def sim(self, src: str, tar: str, *args: str) -> float:
        r"""Return the longest common prefix similarity of two or more strings.

        Longest common prefix similarity (:math:`sim_{LCPrefix}`).

        This employs the LCPrefix function to derive a similarity metric:
        :math:`sim_{LCPrefix}(s,t) = \frac{|LCPrefix(s,t)|}{max(|s|, |t|)}`

        Parameters
        ----------
        src : str
            Source string for comparison
        tar : str
            Target string for comparison
        *args : strs
            Additional strings for comparison

        Returns
        -------
        float
            LCPrefix similarity

        Examples
        --------
        >>> pfx = LCPrefix()
        >>> pfx.sim('cat', 'hat')
        0.0
        >>> pfx.sim('Niall', 'Neil')
        0.2
        >>> pfx.sim('aluminum', 'Catalan')
        0.0
        >>> pfx.sim('ATCG', 'TAGC')
        0.0


        .. versionadded:: 0.4.0

        """
        if src == tar:
            return 1.0
        elif not src or not tar:
            return 0.0
        dist = self.dist_abs(src, tar, *args)
        maxlen = max(len(src), len(tar), *[len(arg) for arg in args])
        return dist / maxlen


if __name__ == '__main__':
    import doctest

    doctest.testmod()