# 输出最长公共子序列 - 来自两个以上字符串的最长公共子字符串-Python

## 求公共子串 (5)

• 使用后缀树
• 使用动态编程。

https://code.i-harness.com

``````def get_longest_common_subseq(data):
substr = []
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and is_subseq_of_any(data[0][i:i+j], data):
substr = data[0][i:i+j]
return substr

def is_subseq_of_any(find, data):
if len(data) < 1 and len(find) < 1:
return False
for i in range(len(data)):
if not is_subseq(find, data[i]):
return False
return True

# Will also return True if possible_subseq == seq.
def is_subseq(possible_subseq, seq):
if len(possible_subseq) > len(seq):
return False
def get_length_n_slices(n):
for i in xrange(len(seq) + 1 - n):
yield seq[i:i+n]
for slyce in get_length_n_slices(len(possible_subseq)):
if slyce == possible_subseq:
return True
return False

print get_longest_common_subseq([[1, 2, 3, 4, 5], [2, 3, 4, 5, 6]])

print get_longest_common_subseq(['Oh, hello, my friend.',
'I prefer Jelly Belly beans.',
'When hell freezes over!'])
``````

``````def long_substr(data):
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and is_substr(data[0][i:i+j], data):
substr = data[0][i:i+j]
return substr

def is_substr(find, data):
if len(data) < 1 and len(find) < 1:
return False
for i in range(len(data)):
if find not in data[i]:
return False
return True

print long_substr(['Oh, hello, my friend.',
'I prefer Jelly Belly beans.',
'When hell freezes over!'])
``````

``````def long_substr(data):
substr = ''
if len(data) > 1 and len(data[0]) > 0:
for i in range(len(data[0])):
for j in range(len(data[0])-i+1):
if j > len(substr) and all(data[0][i:i+j] in x for x in data):
substr = data[0][i:i+j]
return substr
``````

``````def long_substr(data):
substrs = lambda x: {x[i:i+j] for i in range(len(x)) for j in range(len(x) - i + 1)}
s = substrs(data[0])
for val in data[1:]:
s.intersection_update(substrs(val))
return max(s, key=len)
``````

set（可能）实现为哈希映射，这使得效率有点低。 如果你（1）实现一个set数据类型作为trie和（2）只是将后缀存储在trie中然后强制每个节点成为一个端点（这相当于添加所有子串），那么理论上我会猜测这个宝宝的记忆效率很高，特别是因为尝试的交叉点非常容易。

``````def common_prefix(strings):
""" Find the longest string that is a prefix of all the strings.
"""
if not strings:
return ''
prefix = strings[0]
for s in strings:
if len(s) < len(prefix):
prefix = prefix[:len(s)]
if not prefix:
return ''
for i in range(len(prefix)):
if prefix[i] != s[i]:
prefix = prefix[:i]
break
return prefix
``````