Mercurial > repos > greg > fasta_extract

changeset 12:da6ab598f025 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Sun, 10 Jan 2016 14:53:59 -0500
parents 48f6e9f1c19d
children a5d7ed2680c3
files fasta_extract.py
diffstat 1 files changed, 9 insertions(+), 2 deletions(-) [+]
line wrap: on
line diff
--- a/fasta_extract.py	Sun Jan 10 14:42:37 2016 -0500
+++ b/fasta_extract.py	Sun Jan 10 14:53:59 2016 -0500
@@ -24,7 +24,7 @@
     else:
         format = 'fasta'
         output_dir = 'output_dir'
-    return os.path.join(output_dir, '%s_on_data_%d.%s' % (attrs, hid, format))
+    return os.path.join(output_dir, '%s_on_data_%s.%s' % (attrs, hid, format))
 
 
 def stop_err(msg):
@@ -43,16 +43,18 @@
 
 fasta = Fasta(args.genome_file)
 
+dh = open('debug.log', 'wb')
 for (input_filename, hid) in args.inputs:
-    hid = int(hid)
     extend_existing = args.extend_existing == 'existing'
     consider_strand = args.strand == 'yes'
+
     reader = csv.reader(open(input_filename, 'rU'), delimiter='\t')
     fasta_output_path = get_output_path(hid,
                                         args.subtract_from_start,
                                         args.add_to_end,
                                         extend_existing,
                                         consider_strand)
+    dh.write('\n fasta_output_path: %s\n' % str(fasta_output_path))
     output = open(fasta_output_path, 'wb')
     gff_output_path = get_output_path(hid,
                                       args.subtract_from_start,
@@ -60,8 +62,11 @@
                                       extend_existing,
                                       consider_strand,
                                       orphan=True)
+    dh.write('\n gff_output_path: %s\n' % str(gff_output_path))
     orphan_writer = csv.writer(open(gff_output_path, 'wb'), delimiter='\t')
+
     for row in reader:
+        dh.write('\n row: %s\n' % str(row))
         if len(row) != 9 or row[0].startswith('#'):
             continue
         try:
@@ -81,6 +86,7 @@
                 bases = fasta[cname][start-1:end]
                 if consider_strand and strand == '-':
                     bases = reverse_complement(bases)
+                dh.write('\n bases: %s\n' % str(bases))
                 output.write('%s\n' % bases)
             else:
                 orphan_writer.writerow(row)
@@ -88,3 +94,4 @@
             stop_err(str(e))
         finally:
             output.close()
+            dh.close()