Created
March 6, 2015 21:53
-
-
Save adamrp/cc337b63e7ac33160f4b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
from sys import argv | |
with open(argv[1], 'U') as input_f, open(argv[2], 'w') as output_f: | |
for line in input_f: | |
# Write comment/header line(s) to output file unmodified | |
if line.startswith('#'): | |
output_f.write(line) | |
continue | |
sample_id, other = line.split('\t', 1) | |
# Check if this ID is just a number or a number with a decimal point | |
try: | |
test = float(sample_id) | |
except ValueError: | |
# If not, then it's a BLANK or something, so write it unmodified | |
output_f.write(line) | |
continue | |
# If it has a dot, then it should be 15 digits long (9 for barcode, | |
# dot, and 5-digit unique number from old database) | |
if '.' in sample_id: | |
sample_id = sample_id.zfill(15) | |
else: | |
# If it's just a number, then it should be a 9-digit number | |
sample_id = sample_id.zfill(9) | |
output_f.write(sample_id + '\t' + other) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment