Merge pull request #468 from griffithlab/hotfix_netchop

Fix bug in split_file function of net_chop.py and netmhc_stab.py

lib/net_chop.py

@@ -7,22 +7,11 @@
 import os
 from time import sleep
 import collections
+import lib.utils
 
 cycle = ['|', '/', '-', '\\']
 methods = ['cterm', '20s']
 
-def split_file(reader, lines=400):
-    from itertools import islice, chain
-    for tmp in reader:
-        if tmp != "":
-            yield chain([tmp], islice(reader, lines-1))
-            try:
-                tmp = next(reader)
-            except StopIteration:
-                return
-        else:
-            break
-
 def main(args_input = sys.argv[1:]):
     parser = argparse.ArgumentParser("pvacseq net_chop", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument(
@@ -64,7 +53,7 @@ def main(args_input = sys.argv[1:]):
     i=1
     print("Waiting for results from NetChop... |", end='')
     sys.stdout.flush()
-    for chunk in split_file(reader, 100):
+    for chunk in lib.utils.split_file(reader, 100):
         staging_file = tempfile.NamedTemporaryFile(mode='w+')
         current_buffer = {}
         for line in chunk:

lib/netmhc_stab.py

@@ -6,22 +6,11 @@
 import re
 import os
 from time import sleep
+import lib.utils
 
 cycle = ['|', '/', '-', '\\']
 methods = ['cterm', '20s']
 
-def split_file(reader, lines=400):
-    from itertools import islice, chain
-    for tmp in reader:
-        if tmp != "":
-            yield chain([tmp], islice(reader, lines-1))
-            try:
-                tmp = next(reader)
-            except StopIteration:
-                return
-        else:
-            break
-
 def main(args_input = sys.argv[1:]):
     parser = argparse.ArgumentParser("pvacseq net_chop", formatter_class=argparse.ArgumentDefaultsHelpFormatter)
     parser.add_argument(
@@ -51,7 +40,7 @@ def main(args_input = sys.argv[1:]):
     i=1
     print("Waiting for results from NetMHCStabPan... |", end='')
     sys.stdout.flush()
-    for chunk in split_file(reader, 100):
+    for chunk in lib.utils.split_file(reader, 100):
         peptide_lengths = set()
         staging_file = tempfile.NamedTemporaryFile(mode='w+')
         current_buffer = {}

lib/utils.py

@@ -1,5 +1,13 @@
 import binascii
+from itertools import islice
 
 def is_gz_file(filepath):
     with open(filepath, 'rb') as test_f:
         return binascii.hexlify(test_f.read(2)) == b'1f8b'
+
+def split_file(reader, lines):
+    i = iter(reader)
+    piece = list(islice(i, lines))
+    while piece:
+        yield piece
+        piece = list(islice(i, lines))