diff nested_collection.py @ 4:154147805a33 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/percolator commit 9db2c1bb610ff3a6940f0a037c0fccf337692c36
author galaxyp
date Fri, 28 Apr 2017 12:25:36 -0400
parents abed51712ed0
children 07107a686ce9
line wrap: on
line diff
--- a/nested_collection.py	Sat Apr 08 08:23:12 2017 -0400
+++ b/nested_collection.py	Fri Apr 28 12:25:36 2017 -0400
@@ -20,18 +20,19 @@
                                    realnames, p_id)) for p_id in pool_ids])
     else:
         filegroups = {1: range(len(realnames))}
-    batch = []
+    batch, in_pool_indices = [], []
     for pool_id, grouped_indices in filegroups.items():
         if pool_id == 1:
             pool_id = 'pool0'
-        for index in grouped_indices:
-            batch.append(index)
+        for in_pool_index, total_index in enumerate(grouped_indices):
+            batch.append(total_index)
+            in_pool_indices.append(in_pool_index)
             if batchsize and len(batch) == int(batchsize):
-                yield pool_id, batch
-                batch = []
+                yield pool_id, batch, in_pool_indices
+                batch, in_pool_indices = [], []
         if len(batch) > 0:
-            yield pool_id, batch
-            batch = []
+            yield pool_id, batch, in_pool_indices
+            batch, in_pool_indices = [], []
 
 
 def main():
@@ -41,12 +42,20 @@
     parser.add_argument('--galaxy-files', dest='galaxyfiles', nargs='+')
     parser.add_argument('--pool-ids', dest='poolids', nargs='+', default=False)
     args = parser.parse_args()
-    for batchcount, (pool_id, batch) in enumerate(get_batches_of_galaxyfiles(
-            args.realnames, args.batchsize, args.poolids)):
-        for fncount, batchfile in enumerate([args.galaxyfiles[index] for index in batch]):
-            dsetname = '{}_batch{}___inputfn{}.data'.format(pool_id, batchcount, fncount)
+    batches = [x for x in get_batches_of_galaxyfiles(args.realnames, args.batchsize, args.poolids)]
+    batchdigits = len(str(len(batches)))
+    if args.poolids:
+        pooldigits = {pid: [] for pid in args.poolids}
+        for batchdata in batches:
+            pooldigits[batchdata[0]].append(len(batchdata[1]))
+        pooldigits = {pid: len(str(sum(batchlengths))) for pid, batchlengths in pooldigits.items()}
+    else:
+        pooldigits = {'pool0': len(str(len(args.galaxyfiles)))}
+    for batchcount, (pool_id, batch, in_pool_indices) in enumerate(batches):
+        for fnindex, in_pool_index in zip(batch, in_pool_indices):
+            dsetname = '{pid}_batch{bi:0{bd}d}___inputfn{fi:0{pd}d}_{real}.data'.format(pid=pool_id, bi=batchcount, bd=batchdigits, fi=in_pool_index, pd=pooldigits[pool_id], real=args.realnames[fnindex])
             print('producing', dsetname)
-            os.symlink(batchfile, dsetname)
+            os.symlink(args.galaxyfiles[fnindex], dsetname)
 
 if __name__ == '__main__':
     main()