Last active
May 1, 2021 07:11
-
-
Save ashnair1/1b0e97f9d54a6a10966b2ddb72fe6121 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
import os | |
import shutil | |
src_dir = "./Files" | |
dst_dir = "./Result" | |
""" | |
Accepted format | |
{dialect}_{question}__{arab_pnc}_{keyword(s)}_timestamp.txt | |
Number of keywords range from 1 to 2 | |
""" | |
def main(): | |
files = os.listdir(src_dir) | |
for dia_dir in files: | |
for i in os.listdir(os.path.join(src_dir, dia_dir)): | |
name = i.split('_') | |
dialect = name[0] | |
question = name[1] | |
arab_pnc = name[3] | |
timestamp = name[-1][:-4] | |
#import pdb; pdb.set_trace() | |
if len(name) not in [6,7]: | |
continue | |
#raise AssertionError(f"Filename {i} is invalid") | |
if len(name) == 7: | |
keywords = [dialect, name[4], name[5]] | |
else: | |
keywords = [dialect, name[4]] | |
cls_dir_name = '_'.join(keywords) | |
#print(f"Creating {cls_dir_name}") | |
dst_name = os.path.join(dst_dir, cls_dir_name) | |
if not os.path.isdir(dst_name): | |
os.makedirs(dst_name, exist_ok=True) | |
#print(f"Copying {cls_dir_name}") | |
src_path = os.path.join(src_dir, dia_dir, i) | |
dst_path = os.path.join(dst_name, i) | |
shutil.copy(src_path, dst_path) | |
if __name__ == "__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment