Fix symlink extraction to preserve symlink identity instead of resolving to target #404
      
        
          +120
        
        
          −3
        
        
          
        
      
    
  
  Add this suggestion to a batch that can be applied as a single commit.
  This suggestion is invalid because no changes were made to the code.
  Suggestions cannot be applied while the pull request is closed.
  Suggestions cannot be applied while viewing a subset of changes.
  Only one suggestion per line can be applied in a batch.
  Add this suggestion to a batch that can be applied as a single commit.
  Applying suggestions on deleted lines is not supported.
  You must change the existing code in this line in order to create a valid suggestion.
  Outdated suggestions cannot be applied.
  This suggestion has been applied or marked resolved.
  Suggestions cannot be applied from pending reviews.
  Suggestions cannot be applied on multi-line comments.
  Suggestions cannot be applied while the pull request is queued to merge.
  Suggestion cannot be applied right now. Please check back later.
  
    
  
    
When extracting archives containing symlinks,
FileUtils.resolveFile()callsgetCanonicalFile(), which follows symlinks to their targets. On re-extraction, a symlink namedsymlink→target_fileresolves totarget_file(canonical path), causing the code to attempt creating a symlink namedtarget_fileinstead ofsymlink.Changes
resolveFileWithoutFollowingSymlinks(): Path resolution without canonicalization for symlink entriesextractFile(): Conditionally use non-canonicalizing resolution whensymlinkDestinationis presenttoPath().toAbsolutePath().normalize()instead of following to targetSecurity checks for path traversal remain intact via normalized absolute path validation.
Original prompt
✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.