def make_circular_overlapping_sequence(sequences, min_overlap=1, max_overlap=5):
# start by mapping prefixes to full sequences
prefixes = {}
for seq in sequences:
for length in range(min_overlap, max_overlap+1):
prefixes[seq[:length]] = seq
# pick arbitrary a start sequence
start = current = sequences[0]
# build a chain of sequences with overlapping suffixes and prefixes
chain = [start]
while True:
# try longest suffixes first
for length in range(max_overlap, min_overlap-1, -1):
suffix = current[-1-length:]
if suffix in prefixes:
current = prefixes[suffix]
if current == start: # looped around, so we're done
return "".join(chain)
chain.append(current[length+1:]) # don't duplicate the prefix
break
else: # for loop ended without breaking
raise ValueError("No match found for sequence {!r}"
.format(current))
我想你可以通过编一本前缀词典来解决这个问题。一旦你有了它,从任意序列开始,找到它的后缀在前缀列表中。然后转到有那个前缀的序列,构建一个链。在
下面是一些代码:
测试输出:
^{pr2}$注意事项:
"...ABC"
,后面可能跟"ABC..."
或{["A...B", "B..C", "C..B"]
),则它可能永远运行。在return "".join(chain)[:-length]
相关问题 更多 >
编程相关推荐