Skip to content

Commit c0fdcaa

Browse files
[Feature] Prevent tokens from being generated multiple times (#19)
1 parent d46cef3 commit c0fdcaa

File tree

1 file changed

+3
-1
lines changed

1 file changed

+3
-1
lines changed

bin/tokenize_all.py

+3-1
Original file line numberDiff line numberDiff line change
@@ -83,7 +83,9 @@ def main():
8383
if not os.path.isdir(my_tokenized_dir):
8484
os.makedirs(my_tokenized_dir)
8585
my_tokenized_file=os.path.join(my_tokenized_dir,"tokens.json")
86-
tokenize(args,my_concatenated_file,my_tokenized_file)
86+
# Check to see if we have already tokenized...
87+
if(not os.path.isfile(my_tokenized_file)):
88+
tokenize(args,my_concatenated_file,my_tokenized_file)
8789

8890
print ("done")
8991

0 commit comments

Comments
 (0)