我有一个 python 2.7 脚本，它通过解决折叠仅按序列号更改的几行的更一般问题来解决您的问题
import re
def do_compress(old_ints, ints):
"""
whether the ints of the current entry is the continuation of the previous
entry
returns a list of the indexes to compress, or [] or False when the current
line is not part of an indexed sequence
"""
return len(old_ints) == len(ints) and \
[i for o, n, i in zip(old_ints, ints, xrange(len(ints))) if n - o == 1]
def basic_format(file_start, file_stop):
return "[seq]{} .. {}".format(file_start, file_stop)
def compress(files, do_compress=do_compress, seq_format=basic_format):
p = None
old_ints = ()
old_indexes = ()
seq_and_files_list = []
# list of file names or dictionaries that represent sequences:
# {start, stop, start_f, stop_f}
for f in files:
ints = ()
indexes = ()
m = p is not None and p.match(f) # False, None, or a valid match
if m:
ints = [int(x) for x in m.groups()]
indexes = do_compress(old_ints, ints)
# state variations
if not indexes: # end of sequence or no current sequence
p = re.compile( \
'(\d+)'.join(re.escape(x) for x in re.split('\d+',f)) + '$')
m = p.match(f)
old_ints = [int(x) for x in m.groups()]
old_indexes = ()
seq_and_files_list.append(f)
elif indexes == old_indexes: # the sequence continues
seq_and_files_list[-1]['stop'] = old_ints = ints
seq_and_files_list[-1]['stop_f'] = f
old_indexes = indexes
elif old_indexes == (): # sequence started on previous filename
start_f = seq_and_files_list.pop()
s = {'start': old_ints, 'stop': ints, \
'start_f': start_f, 'stop_f': f}
seq_and_files_list.append(s)
old_ints = ints
old_indexes = indexes
else: # end of sequence, but still matches previous pattern
old_ints = ints
old_indexes = ()
seq_and_files_list.append(f)
return [ isinstance(f, dict) and seq_format(f['start_f'], f['stop_f']) or f
for f in seq_and_files_list ]
if __name__ == "__main__":
import sys
if len(sys.argv) == 1:
import os
lst = sorted(os.listdir('.'))
elif sys.argv[1] in ("-h", "--help"):
print """USAGE: {} [FILE ...]
compress the listing of the current directory, or the content of the files by
collapsing identical lines, except for a sequence number
"""
sys.exit(0)
else:
import string
lst = [string.rstrip(l, '\r\n') for f in sys.argv[1:] for l in open(f)])
for x in compress(lst):
print x
也就是说，在您的数据上：
bernard $ ./ls_sequence_compression.py given_data
[seq]filename_v003_0001.geo .. filename_v003_0007.geo
[seq]filename_v003_0032.geo .. filename_v003_0036.geo
[seq]testxxtest.0057.exr .. testxxtest.0063.exr
它基于与非数字文本匹配的两个连续行中存在的整数之间的差异。这允许在用作序列基础的字段更改时处理非统一输入...
这是一个输入示例：
01 - test8.txt
01 - test9.txt
01 - test10.txt
02 - test11.txt
02 - test12.txt
03 - test13.txt
04 - test13.txt
05 - test13.txt
06
07
08
09
10
给出：
[seq]01 - test8.txt .. 01 - test10.txt
[seq]02 - test11.txt .. 02 - test12.txt
[seq]03 - test13.txt .. 05 - test13.txt
[seq]06 .. 10
欢迎评论！
哈...我差点忘了：没有参数，这个脚本输出当前目录的折叠内容。