シーケンス番号によってのみ変更される複数の行を折りたたむというより一般的な問題を解決することにより、問題を解決するpython 2.7スクリプトを取得しました
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
つまり、あなたのデータでは：
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
これは、数字以外のテキストに一致する 2 つの連続する行に存在する整数の違いに基づいています。これにより、シーケンスの基礎として使用されるフィールドの変更時に、不均一な入力を処理できます...
入力の例を次に示します。
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
これは次を与えます:
[seq]01 - test8.txt .. 01 - test10.txt
[seq]02 - test11.txt .. 02 - test12.txt
[seq]03 - test13.txt .. 05 - test13.txt
[seq]06 .. 10
どんなコメントでも大歓迎です！
はあ...忘れていました。引数がなければ、このスクリプトは現在のディレクトリの折りたたまれた内容を出力します。