Mercurial > repos > devteam > tabular_to_fasta

comparison tabular_to_fasta.py @ 1:0a7799698fe5 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/tabular_to_fasta commit 01140c0ac1a926856c55853a0028e5d44935d9e6"
author devteam
date Wed, 05 Feb 2020 10:51:52 -0500
parents 0b4e36026794
children
comparison
equal deleted inserted replaced
0:0b4e36026794 1:0a7799698fe5
2 """ 2 """
3 Input: fasta, minimal length, maximal length 3 Input: fasta, minimal length, maximal length
4 Output: fasta 4 Output: fasta
5 Return sequences whose lengths are within the range. 5 Return sequences whose lengths are within the range.
6 """ 6 """
7 import sys, os 7 import os
8 import sys
8 9
9 assert sys.version_info[:2] >= ( 2, 4 )
10 10
11 def stop_err( msg ): 11 def stop_err(msg):
12 sys.stderr.write( msg ) 12 sys.exit(msg)
13 sys.exit() 13
14 14
15 def __main__(): 15 def __main__():
16 infile = sys.argv[1] 16 infile = sys.argv[1]
17 title_col = sys.argv[2] 17 title_col = sys.argv[2]
18 seq_col = sys.argv[3] 18 seq_col = sys.argv[3]
19 outfile = sys.argv[4] 19 outfile = sys.argv[4]
20 20
21 if title_col == None or title_col == 'None' or seq_col == None or seq_col == 'None': 21 if title_col == None or title_col == 'None' or seq_col == None or seq_col == 'None':
22 stop_err( "Columns not specified." ) 22 stop_err("Columns not specified.")
23 try: 23 try:
24 seq_col = int( seq_col ) - 1 24 seq_col = int(seq_col) - 1
25 except: 25 except:
26 stop_err( "Invalid Sequence Column: %s." %str( seq_col ) ) 26 stop_err("Invalid Sequence Column: %s." % str(seq_col))
27 27
28 title_col_list = title_col.split( ',' ) 28 title_col_list = title_col.split(',')
29 out = open( outfile, 'w' )
30 skipped_lines = 0 29 skipped_lines = 0
31 first_invalid_line = 0 30 first_invalid_line = 0
32 invalid_line = "" 31 invalid_line = ""
33 i = 0 32 i = 0
34 33
35 for i, line in enumerate( open( infile ) ): 34 with open(outfile, 'w') as out:
36 error = False 35 for i, line in enumerate(open(infile)):
37 line = line.rstrip( '\r\n' ) 36 error = False
38 if line and not line.startswith( '#' ): 37 line = line.rstrip('\r\n')
39 fields = line.split( '\t' ) 38 if line and not line.startswith('#'):
40 fasta_title = [] 39 fields = line.split('\t')
41 for j in title_col_list: 40 fasta_title = []
42 try: 41 for j in title_col_list:
43 j = int( j ) - 1 42 try:
44 fasta_title.append( fields[j] ) 43 j = int(j) - 1
45 except: 44 fasta_title.append(fields[j])
46 skipped_lines += 1 45 except:
47 if not invalid_line: 46 skipped_lines += 1
48 first_invalid_line = i + 1 47 if not invalid_line:
49 invalid_line = line 48 first_invalid_line = i + 1
50 error = True 49 invalid_line = line
51 break 50 error = True
52 if not error: 51 break
53 try: 52 if not error:
54 fasta_seq = fields[seq_col] 53 try:
55 if fasta_title[0].startswith( ">" ): 54 fasta_seq = fields[seq_col]
56 fasta_title[0] = fasta_title[0][1:] 55 if fasta_title[0].startswith(">"):
57 print >> out, ">%s\n%s" % ( "_".join( fasta_title ), fasta_seq ) 56 fasta_title[0] = fasta_title[0][1:]
58 except: 57 print(">%s\n%s" % ("_".join(fasta_title), fasta_seq), file=out)
59 skipped_lines += 1 58 except:
60 if not invalid_line: 59 skipped_lines += 1
61 first_invalid_line = i + 1 60 if not invalid_line:
62 invalid_line = line 61 first_invalid_line = i + 1
63 out.close() 62 invalid_line = line
64 63
65 if skipped_lines > 0: 64 if skipped_lines > 0:
66 print 'Data issue: skipped %d blank or invalid lines starting at #%d: "%s"' % ( skipped_lines, first_invalid_line, invalid_line ) 65 print('Data issue: skipped %d blank or invalid lines starting at #%d: "%s"' % (skipped_lines, first_invalid_line, invalid_line))
67 66
68 if __name__ == "__main__" : __main__() 67
68 if __name__ == "__main__":
69 __main__()