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

Bug fix for files not comparing correctly

Browse Source
This commit is contained in:
datechnoman 2024-02-20 11:09:11 +00:00
parent 0fd62a7391
commit 9144f85820
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
commoncrawl_wat_path_comparer.py
View File

@ -35,8 +35,8 @@ def main():
# Read paths from the wat.paths file # Read paths from the wat.paths file
paths = read_paths_from_file(wat_paths_file_path) paths = read_paths_from_file(wat_paths_file_path)
# Filter out paths that partially match directory lines # Filter out paths that exactly match directory lines
filtered_paths = [path for path in paths if not any(directory_line in path for directory_line in directory_files)] filtered_paths = [path for path in paths if os.path.basename(path) not in directory_files]
# Write the list of modified files to a text file # Write the list of modified files to a text file
output_file_path = 'missing_wat_files.txt' output_file_path = 'missing_wat_files.txt'