ArchiveTeam/CommonCrawl_URL_Processor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Removed multithread compression and added force overwrite for compression files

Browse Source
This commit is contained in:
datechnoman 2024-01-28 22:50:09 +00:00
parent ebc07a6974
commit 486a68a796
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
warc_wat_url_processor.py
View File

@ -60,7 +60,7 @@ def process_file(file_path):
# Use zstd command-line tool for compression # Use zstd command-line tool for compression
compressed_file_path = f'{output_file_path}.zst' compressed_file_path = f'{output_file_path}.zst'
command_compress = f'zstd -f -T0 -12 --long {output_file_path} -o {compressed_file_path}' command_compress = f'zstd -12 --long --force {output_file_path} -o {compressed_file_path}'
try: try:
# Run the compression command synchronously and wait for it to complete # Run the compression command synchronously and wait for it to complete