Last active
July 31, 2024 19:31
-
-
Save dmsnell/febbe9a3d9bd265af5bc4564dcbe1f86 to your computer and use it in GitHub Desktop.
Prepend the BOM to indicate a file is UTF-8
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
import codecs | |
import sys | |
def prepend_bom(filename): | |
with open( filename, 'r+b' ) as csv: | |
existing = csv.read() | |
if b'\xef\xbb\xbf' == existing[0:3]: | |
print("Byte-order mark already present: leaving file as-is.") | |
return | |
print("Adding byte-order mark to beginning of file to indicate that it's a UTF-8 file.") | |
csv.seek(0) | |
csv.write(codecs.BOM_UTF8) | |
csv.write(existing) | |
if __name__ == '__main__': | |
if len(sys.argv) < 2: | |
print(f"Supply a filename: python3 {sys.argv[0]} survey-results.csv") | |
sys.exit(1) | |
filename = sys.argv[1] | |
prepend_bom(filename) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment