Dvs / split_file.py
Muttered3's picture
Create split_file.py
eb6a7c1 verified
import os
def split_massive_file(input_file="words.txt", lines_per_file=200000):
# Check if the giant file exists
if not os.path.exists(input_file):
print(f"❌ Error: Could not find '{input_file}' in this folder.")
return
print(f"⏳ Reading massive file '{input_file}'...")
# Read all lines
with open(input_file, 'r', encoding='utf-8') as f:
# Strip whitespace/newlines to clean it up while reading
lines = [line.strip() for line in f if line.strip()]
total_lines = len(lines)
print(f"βœ… Loaded {total_lines:,} total words.")
# Split and save into chunks
for i in range(0, total_lines, lines_per_file):
chunk = lines[i:i + lines_per_file]
part_num = (i // lines_per_file) + 1
output_file = f"part{part_num}.txt"
with open(output_file, 'w', encoding='utf-8') as out:
out.write('\n'.join(chunk))
print(f"πŸ“¦ Created {output_file} ({len(chunk):,} words)")
print("\nπŸŽ‰ All done! You can now upload these parts to the bot one by one.")
if __name__ == "__main__":
# You can change "words.txt" if your giant file is named something else
# 200000 is the safe limit for a 256MB Redis database
split_massive_file("words.txt", 200000)