upstream/fasta_to_tabular/fasta_to_tabular.py
1#!/usr/bin/env python
2# This code exists in 2 places: ~/datatypes/converters and ~/tools/fasta_tools
3"""
4Input: fasta (input file), tabular (output file), int (truncation of id), int (columns from description)
5Output: tabular
6format convert: fasta to tabular
7"""
8
9import sys
10
11
12def stop_err(msg):
13 sys.exit(msg)
14
15
16def __main__():
17 if len(sys.argv) != 5:
18 stop_err("Wrong number of argument. Expect four (fasta, tabular, truncation, columns)")
19 infile = sys.argv[1]
20 outfile = sys.argv[2]
21 keep_first = int(sys.argv[3])
22 descr_split = int(sys.argv[4])
23 if keep_first == 0:
24 keep_first = None
25 elif descr_split == 1:
26 # Added one for the ">" character
27 # (which is removed if using descr_split > 1)
28 keep_first += 1
29 if descr_split < 1:
30 stop_err("Bad description split value (should be 1 or more)")
31 with open(outfile, 'w') as out, open(infile) as in_fh:
32 for i, line in enumerate(in_fh):
33 line = line.rstrip('\r\n')
34 if not line or line.startswith('#'):
35 continue
36 if line.startswith('>'):
37 # Don't want any existing tabs to trigger extra columns:
38 line = line.replace('\t', ' ')
39 if i > 0:
40 out.write('\n')
41 if descr_split == 1:
42 out.write(line[1:keep_first])
43 else:
44 words = line[1:].split(None, descr_split - 1)
45 # apply any truncation to first word (the id)
46 words[0] = words[0][0:keep_first]
47 # pad with empty columns if required
48 words += [""] * (descr_split - len(words))
49 out.write("\t".join(words))
50 out.write('\t')
51 else:
52 out.write(line)
53 if i > 0:
54 out.write('\n')
55
56
57if __name__ == "__main__":
58 __main__()