add detection of truncated final record, as per #138

webrecorder · Mar 21, 2024 · 162ca0a · 162ca0a
1 parent 8c305f5
commit 162ca0a
Showing 1 changed file with 7 additions and 1 deletion.
diff --git a/warcio/archiveiterator.py b/warcio/archiveiterator.py
@@ -113,7 +113,13 @@ def _iterate_records(self):
 
                 yield self.record
 
-            except EOFError:
+            except EOFError as e:
+                if self.reader.decompressor:
+                    if not self.reader.decompressor.eof:
+                        msg = "warning: final record appears to be truncated"
+                        sys.stderr.write(msg + "\n")
+                        raise ArchiveLoadFailed(msg)
+
                 empty_record = True
 
             self.read_to_end()