[编程题] 最长公共子序列

最长公共子序列(Longest-Common Subsequence)

问题描述: 给出两个字符串，找到最长公共子序列(LCS)，返回LCS的长度。
最长公共子序列的定义：最长公共子序列问题是在一组序列中找到最长公共子序列(不同于公共子串，LCS不需要是连续的子串)
输入: 给出字符串”ABCD”和字符串“EDCA”
输出: 1

"""
            dp[i - 1][j - 1] + 1                if s1[i] == s2[j]
dp[i][j] =  max(dp[i -1][j], dp[i][j - 1])      others

"""


def LCS(s1, s2):
    def show(mat):
        for i in mat: print(i)
    if not s1 or not s1: return 0

    m, n = len(s1), len(s2)
    # tmp is a obejct
    tmp = [0, ] * n
    dp = []
    # deep copy
    for i in range(m):
        dp.append(tmp.copy())
    # 1. 处理S1与S2[0]的情况
    index = [0, ]
    for i in range(m):
        if s1[i] == s2[0]:
            index[0] = i
            break

    for j in range(index[0], m):
        dp[j][0] = 1

    # 2. 处理S1[0]与S[1]的情况
    for x in range(n):
        if s1[0] == s2[x]:
            index[0] = x
            break
    for y in range(index[0], n):
        dp[0][y] = 1

    # dp state
    # show(dp)

    # 3. 处理其余情况
    for i in range(1, m):
        for j in range(1, n):
            if s1[i] == s2[j]:
                dp[i][j] = dp[i - 1][j - 1] + 1
            else:
                dp[i][j] = max(dp[i - 1][j], dp[i][j - 1])
    show(dp)
    return dp[m -1][n -1]


if __name__ == '__main__':
    # sample1
    s1 = 'blog.csdn.net'
    s2 = 'csdn.blogt'
    result = LCS(s1, s2)
    print(result)  # for sample1, the answer should be 6

    # sample2
    s1 = "A1BC2"
    s2 = "ABB4C"
    result = LCS(s1, s2)
    print(result)       # for sample2, the answer should be 3