|
0
|
1 # ----------------------------------------------------------------------#
|
|
|
2 # Copyright (c) 2011, Richard Lupat & Jason Li.
|
|
|
3 #
|
|
|
4 # > Source License <
|
|
|
5 # This file is part of CONTRA.
|
|
|
6 #
|
|
|
7 # CONTRA is free software: you can redistribute it and/or modify
|
|
|
8 # it under the terms of the GNU General Public License as published by
|
|
|
9 # the Free Software Foundation, either version 3 of the License, or
|
|
|
10 # (at your option) any later version.
|
|
|
11 #
|
|
|
12 # CONTRA is distributed in the hope that it will be useful,
|
|
|
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
|
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
|
15 # GNU General Public License for more details.
|
|
|
16 #
|
|
|
17 # You should have received a copy of the GNU General Public License
|
|
|
18 # along with CONTRA. If not, see <http://www.gnu.org/licenses/>.
|
|
|
19 #
|
|
|
20 #
|
|
|
21 #-----------------------------------------------------------------------#
|
|
|
22 # Last Updated : 05 October 2011 16:43PM
|
|
|
23
|
|
|
24
|
|
|
25 import subprocess, shlex
|
|
|
26
|
|
|
27 def get_genome(srcFile, genomeOut):
|
|
|
28 genome = open(genomeOut, "w")
|
|
|
29
|
|
|
30 args = shlex.split("samtools view -H %s" %(srcFile))
|
|
|
31 raw_header = subprocess.Popen(args, stdout = subprocess.PIPE).communicate()[0]
|
|
|
32 headers = raw_header.split("\n")
|
|
|
33
|
|
|
34 for header in headers:
|
|
|
35 header = header.split("\t")
|
|
|
36 if header[0][1:] != "SQ":
|
|
|
37 continue
|
|
|
38
|
|
|
39 genome.write(header[1].strip("SN:") + "\t" + header[2].strip("LN:") + "\n")
|
|
|
40
|
|
|
41 genome.close()
|
|
|
42
|
|
|
43
|
