Mercurial > repos > davidvanzessen > sff_extract_demultiplex

comparison trim.py @ 4:8e3d95d7f342 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 07 Jul 2014 05:49:20 -0400
parents 79be0752711d
children 35b55f1c0c59
comparison
equal deleted inserted replaced
3:79be0752711d 4:8e3d95d7f342
1 import argparse 1 import argparse
2 2
3 #docs.python.org/dev/library/argparse.html 3 #docs.python.org/dev/library/argparse.html
4 parser = argparse.ArgumentParser() 4 parser = argparse.ArgumentParser()
5 parser.add_argument("--input", help="Input folder with files") 5 parser.add_argument("--input", help="Input fasta")
6 parser.add_argument("--output", help="Output file") 6 parser.add_argument("--output", help="Output fasta")
7 parser.add_argument("--start", help="How many nucleotides to trim from the start", type=int) 7 parser.add_argument("--start", help="How many nucleotides to trim from the start", type=int)
8 parser.add_argument("--end", help="How many nucleotides to trim from the end", type=int) 8 parser.add_argument("--end", help="How many nucleotides to trim from the end", type=int)
9 9
10 args = parser.parse_args() 10 args = parser.parse_args()
11 start = int(args.start) 11 start = int(args.start)
12 end = int(args.end) 12 end = int(args.end)
13 13
14 if end <= 0: 14 if end <= 0 and start <= 0:
15 import shutil 15 import shutil
16 shutil.copy(args.input, args.output) 16 shutil.copy(args.input, args.output)
17 import sys 17 import sys
18 sys.exit() 18 sys.exit()
19
20
19 21
20 currentSeq = "" 22 currentSeq = ""
21 currentId = "" 23 currentId = ""
22 24
23 with open(args.input, 'r') as i: 25 if end is 0:
24 with open(args.output, 'w') as o: 26 with open(args.input, 'r') as i:
25 for line in i.readlines(): 27 with open(args.output, 'w') as o:
26 if line[0] is ">": 28 for line in i.readlines():
27 if currentSeq is not "" or currentId is not "": 29 if line[0] is ">":
28 o.write(currentId) 30 currentSeq = currentSeq[start:]
29 o.write(currentSeq[start:-end] + "\n") 31 if currentSeq is not "" and currentId is not "":
30 currentId = line 32 o.write(currentId)
31 currentSeq = "" 33 o.write(currentSeq + "\n")
32 else: 34 currentId = line
33 currentSeq += line.rstrip() 35 currentSeq = ""
34 o.write(currentId) 36 else:
35 o.write(currentSeq.rstrip()[start:-end] + "\n") 37 currentSeq += line.rstrip()
38 o.write(currentId)
39 o.write(currentSeq[start:] + "\n")
40 else:
41 with open(args.input, 'r') as i:
42 with open(args.output, 'w') as o:
43 for line in i.readlines():
44 if line[0] is ">":
45 currentSeq = currentSeq[start:-end]
46 if currentSeq is not "" and currentId is not "":
47 o.write(currentId)
48 o.write(currentSeq + "\n")
49 currentId = line
50 currentSeq = ""
51 else:
52 currentSeq += line.rstrip()
53 o.write(currentId)
54 o.write(currentSeq[start:-end] + "\n")