python实现查找最长公共子序列

#!/usr/bin/python
# -*- coding: UTF-8 -*-

worlds = ['fosh','fort','vista','fish','hish','hello','ohddad','abofaboca321ADFlloaha5shcdf']
user_input = 'frt'

def find_longest_substring(world_a,world_b):
    """
    查找最长公共子序列函数

    实现公式伪代码
    if word_a[i] == word_b[j]:
        matrix[i][j] = matrix[i-1][j-1] + 1
    else:
        matrix[i][j] = max(matrix[i-1][j],matrix[i][j-1])
    """
    # 生成矩阵
    matrix = [[0 for i in range(len(world_a))]  for j in range(len(world_b))]

    for i in range(len(world_b)):
        for j in range(len(world_a)):
            if world_b[i] == world_a[j]:
                if j != 0:
                    matrix[i][j] = matrix[i-1][j-1] + 1
                else:
                    matrix[i][j] = matrix[i][j] + 1
            else:
                matrix[i][j] = max(matrix[i-1][j],matrix[i][j-1])

    return matrix[-1][-1]

longest_substring = 0
best_match = {}

for world_a in worlds:
    number = find_longest_substring(world_a,user_input)
    if number >= longest_substring:
        if number == longest_substring:
            best_match[world_a] = number
        else:
            best_match = {}
            best_match[world_a] = number

        longest_substring = number

for key in best_match:
    print "%s与%s,相似度:%.2f%%" % (user_input,key,best_match[key] / float(len(key))*100)
    # find_longest_substring(user_input,world_a)