Mercurial > repos > fangly > grinder
comparison tools/ngs_simulation/grinder_multiple_outputs.py @ 1:7d26d64539b2
Uploaded
| author | fangly |
|---|---|
| date | Mon, 19 Sep 2011 01:07:28 -0400 |
| parents | |
| children | 27a15723d4f0 |
comparison
equal
deleted
inserted
replaced
| 0:b35ec780aac1 | 1:7d26d64539b2 |
|---|---|
| 1 #!/usr/bin/env python | |
| 2 | |
| 3 """ | |
| 4 Move files create by Grinder to a location where it is going to be recognized by | |
| 5 Galaxy as multiple output files with the right format. See | |
| 6 http://wiki.g2.bx.psu.edu/Admin/Tools/Multiple Output Files | |
| 7 Example: python grinder_move_outputs output_dir output_id | |
| 8 Author: Florent Angly | |
| 9 """ | |
| 10 | |
| 11 import sys, os, re | |
| 12 | |
| 13 assert sys.version_info[:2] >= ( 2, 4 ) | |
| 14 | |
| 15 def stop_err( msg ): | |
| 16 sys.stderr.write( "%s\n" % msg ) | |
| 17 sys.exit() | |
| 18 | |
| 19 def __main__(): | |
| 20 # Get output dir and ID | |
| 21 args = sys.argv | |
| 22 output_dir = args[1] | |
| 23 output_id = args[2] | |
| 24 | |
| 25 # Move Grinder files to the proper output | |
| 26 # Grinder filenames look like this | |
| 27 # grinder-ranks.txt | |
| 28 # grinder-reads.fa | |
| 29 # grinder-reads.qual | |
| 30 # grinder-1-ranks.txt | |
| 31 # grinder-1-reads.fa | |
| 32 # grinder-1-reads.qual | |
| 33 # grinder-2-ranks.txt | |
| 34 # grinder-2-reads.fa | |
| 35 # grinder-2-reads.qual | |
| 36 | |
| 37 p = re.compile(output_id) | |
| 38 q = re.compile('-(\d+)-') | |
| 39 r = re.compile('-(\w+)$') | |
| 40 | |
| 41 | |
| 42 for fname in os.listdir(output_dir): | |
| 43 | |
| 44 # Skip files that do not start with the output_id | |
| 45 source = os.path.join( output_dir, fname ) | |
| 46 basename, extension = os.path.splitext(fname) | |
| 47 if not p.match(fname): | |
| 48 continue | |
| 49 | |
| 50 # Assign the dataset format | |
| 51 if extension == '.txt': | |
| 52 format = 'text' | |
| 53 elif extension == '.fa': | |
| 54 format = 'fasta' | |
| 55 elif extension == '.fna': | |
| 56 format = 'fasta' | |
| 57 elif extension == '.faa': | |
| 58 format = 'fasta' | |
| 59 elif extension == '.fasta': | |
| 60 format = 'fasta' | |
| 61 elif extension == '.fq': | |
| 62 format = 'fastq' | |
| 63 elif extension == '.fastq': | |
| 64 format = 'fastq' | |
| 65 elif extension == '.qual': | |
| 66 format = 'qual' | |
| 67 else: | |
| 68 stop_err( 'Error: File %s had the unknown extension %s' % ( fname, extension ) ) | |
| 69 | |
| 70 # Assign the dataset name | |
| 71 name = '' | |
| 72 match = q.search(basename) | |
| 73 if match != None: | |
| 74 lib_num = match.group(1) | |
| 75 name = 'lib%s' % lib_num | |
| 76 | |
| 77 match = r.search(basename) | |
| 78 if match == None: | |
| 79 stop_err( 'Error: File with basename %s did not have a recognized name' % (basename) ) | |
| 80 | |
| 81 lib_type = match.group(1) | |
| 82 if format == 'qual': | |
| 83 lib_type = 'qual' | |
| 84 | |
| 85 name = name + '-' + lib_type | |
| 86 | |
| 87 # Move the dataset to the proper place | |
| 88 optional_spec = 'asdf' | |
| 89 destination = os.path.join( output_dir, 'primary_%s_%s_visible_%s_%s' % ( output_id, name, format, optional_spec ) ) | |
| 90 | |
| 91 print "moving %s to %s" % (source, destination) | |
| 92 | |
| 93 try: | |
| 94 os.rename(source, destination) | |
| 95 except Exception, e: | |
| 96 stop_err( 'Error: ' + str( e ) ) | |
| 97 | |
| 98 if __name__ == "__main__": __main__() |
