fix(handlers): handle dangling symlinks in MultiFile handlers.

MultiFile handlers would collect files within a directory corresponding
to a specific schema without checking if those files are actually
present.

For example, a directory could contain dangling symlinks with a name
corresponding to the glob search. This would lead to FileNotFoundError
being thrown by the multi-file handlers.

Author: qkaiser

unblob/handlers/archive/sevenzip.py

@@ -117,7 +117,9 @@ def calculate_multifile(self, file: Path) -> Optional[MultiFile]:
         size = calculate_sevenzip_size(header)
         logger.debug("Sevenzip header", header=header, size=size, _verbosity=3)
 
-        paths = sorted(file.parent.glob(f"{file.stem}.*"))
+        paths = sorted(
+            [p for p in file.parent.glob(f"{file.stem}.*") if p.resolve().exists()]
+        )
 
         files_size = sum(path.stat().st_size for path in paths)
         logger.debug(

unblob/handlers/compression/gzip.py

@@ -166,7 +166,9 @@ def is_valid_gzip(self, path: Path) -> bool:
         return True
 
     def calculate_multifile(self, file: Path) -> Optional[MultiFile]:
-        paths = sorted(file.parent.glob(f"{file.stem}.*"))
+        paths = sorted(
+            [p for p in file.parent.glob(f"{file.stem}.*") if p.resolve().exists()]
+        )
 
         # we 'discard' paths that are not the first in the ordered list,
         # otherwise we will end up with colliding reports, one for every