fix(metadata): do not report the whole header.

Author: qkaiser

unblob/handlers/archive/sevenzip.py

@@ -18,8 +18,9 @@
 https://py7zr.readthedocs.io/en/latest/archive_format.html
 """
 import binascii
-from typing import Optional
+from typing import Dict, Optional
 
+from dissect.cstruct import Instance
 from structlog import get_logger
 
 from unblob.extractors import Command
@@ -57,6 +58,9 @@ class SevenZipHandler(StructHandler):
     HEADER_STRUCT = "sevenzip_header_t"
     EXTRACTOR = Command("7z", "x", "-p", "-y", "{inpath}", "-o{outdir}")
 
+    def get_metadata(self, header: Instance) -> Dict:
+        return {"version_maj": header.version_maj, "version_min": header.version_min}
+
     def calculate_chunk(self, file: File, start_offset: int) -> Optional[ValidChunk]:
         header = self.parse_header(file)
 
@@ -67,9 +71,10 @@ def calculate_chunk(self, file: File, start_offset: int) -> Optional[ValidChunk]
             logger.debug("Invalid header CRC", _verbosity=2)
             return None
 
+        metadata = self.get_metadata(header)
         # We read the signature header here to get the offset to the header database
         first_db_header = start_offset + len(header) + header.next_header_offset
         end_offset = first_db_header + header.next_header_size
         return ValidChunk(
-            start_offset=start_offset, end_offset=end_offset, metadata=header
+            start_offset=start_offset, end_offset=end_offset, metadata=metadata
         )