python-string-similarity/strsimpy/optimal_string_alignment.py

# Copyright (c) 2018 luozhouyang
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.


from .string_distance import StringDistance


class OptimalStringAlignment(StringDistance):

    def distance(self, s0, s1):
        if s0 is None:
            raise TypeError("Argument s0 is NoneType.")
        if s1 is None:
            raise TypeError("Argument s1 is NoneType.")
        if s0 == s1:
            return 0.0

        n, m = len(s0), len(s1)
        if n == 0:
            return 1.0 * n
        if m == 0:
            return 1.0 * m

        d = [[0] * (m + 2) for _ in range(n + 2)]
        for i in range(n + 1):
            d[i][0] = i
        for j in range(m + 1):
            d[0][j] = j

        for i in range(1, n + 1):
            for j in range(1, m + 1):
                cost = 1
                if s0[i - 1] == s1[j - 1]:
                    cost = 0
                d[i][j] = min(d[i - 1][j - 1] + cost, d[i][j - 1] + 1, d[i - 1][j] + 1)

                if i > 1 and j > 1 and s0[i - 1] == s1[j - 2] and s0[i - 2] == s1[j - 1]:
                    d[i][j] = min(d[i][j], d[i - 2][j - 2] + cost)

        return d[n][m]