3.7_longest_common_sequence_最长公共子序列 (LCS)

--- 最长公共子序列 (LCS) ---
    一个序列的子序列是在该序列中删去若干元素后得到的序列
        例："ABCD"和"BDF"都是"ABCDEFG"的子序列

    最长公共子序列 (LCS) 问题：
        给定两个序列 X 和 Y，求 X 和 Y 长度最大的公共子序列
        例：X = "ABBCBDE", Y = "DBBCDB", LCS(X, Y) = "BBCD"

    适用场景：
        1. 字符串相似度比对

def lcs_length(x, y):

    m, n = len(x), len(y)
    dp = [[0 for _ in range(n + 1)] for _ in range(m + 1)]

    for i in range(1, m + 1):
        for j in range(1, n + 1):
            # i j 位置上的字符匹配时，来自于左上方+1
            if x[i - 1] == y[j - 1]:
                dp[i][j] = dp[i - 1][j - 1] + 1
            else:
                dp[i][j] = max(dp[i - 1][j], dp[i][j - 1])

    return dp[m][n]


def lcs(x, y):

    m, n = len(x), len(y)
    dp = [[0 for _ in range(n + 1)] for _ in range(m + 1)]
    # 记录路径：1. 左上方，2. 上方，3. 左方
    trace = [[0 for _ in range(n + 1)] for _ in range(m + 1)]

    for i in range(1, m + 1):
        for j in range(1, n + 1):
            # 来自于左上方
            if x[i - 1] == y[j - 1]:
                dp[i][j] = dp[i - 1][j - 1] + 1
                trace[i][j] = 1
            # 来自于上方
            elif dp[i - 1][j] > dp[i][j - 1]:
                dp[i][j] = dp[i - 1][j]
                trace[i][j] = 2
            # 来自于左方
            else:
                dp[i][j] = dp[i][j - 1]
                trace[i][j] = 3

    return dp[m][n], trace


def lcs_traceback(x, y):

    dp, trace = lcs(x, y)
    i, j = len(x), len(y)
    res = []

    while i and j:
        # 来自于左上方：匹配
        if trace[i][j] == 1:
            res.append(x[i - 1])
            i -= 1
            j -= 1
        # 来自于上方：不匹配
        elif trace[i][j] == 2:
            i -= 1
        # 来自于左方：不匹配
        else:
            j -= 1

    return ''.join(reversed(res))