Improve typing in sample_sheet_parser

micall/utils/sample_sheet_parser.py

@@ -2,17 +2,19 @@
 
 from csv import DictReader
 from pathlib import Path
+from typing import TextIO, Dict
 
 from micall.utils.sample_sheet_v1_parser import sample_sheet_v1_parser
 
-def sample_sheet_parser(handle):
+def sample_sheet_parser(handle: TextIO) -> Dict[str, object]:
     """
     Parse the contents of SampleSheet.csv, convert contents into a
     Python dictionary object.
     Samples are tracked by sample name and sample number (e.g., S9).
     This is to distinguish replicates of the same sample.
     """
 
+    handle.seek(0)
     return sample_sheet_v1_parser(handle)
 
 
@@ -44,7 +46,7 @@ def main():
     parser.add_argument("samplesheet")
     args = parser.parse_args()
 
-    with open(args.samplesheet, "rb") as f:
+    with open(args.samplesheet) as f:
         ss = sample_sheet_parser(f)
         print(ss)
 

micall/utils/sample_sheet_v1_parser.py

@@ -1,8 +1,8 @@
 
 import re
-from typing import List, Dict, Any
+from typing import List, Dict, Any, TextIO
 
-def sample_sheet_v1_parser(handle):
+def sample_sheet_v1_parser(handle: TextIO) -> Dict[str, object]:
     tag = None
     get_header = False
     header = []  # store Data block column labels
@@ -147,14 +147,9 @@ def sample_sheet_v1_parser(handle):
                 # the description field up and change the values in entry
                 # appropriately.
                 for desc_field in desc_fields:
-                    name, value, tmp = None, None, None
-                    if sample_sheet_version == 1:
-                        name = desc_field.split(':')[0]  # slice #actually this is wrong...
-                        value = desc_field.replace(name + ':', '')
-                        tmp = value.split(sample_delimiter)
-                    elif sample_sheet_version == 2:
-                        name, value = desc_field.split(':')
-                        tmp = value.split(sample_delimiter)
+                    name = desc_field.split(':')[0]  # slice #actually this is wrong...
+                    value = desc_field.replace(name + ':', '')
+                    tmp = value.split(sample_delimiter)
 
                     for elem in tmp:
                         samp, proj, val = None, None, None