DecompressedHash should fail on trailing input

Otherwise all files smaller than 10 bytes are successfully hashed to the
hash of the empty input when using the GzipDecompressor.

Reported-By: Olly Betts

1 files changed, 4 insertions, 0 deletions

diff --git a/dedup/hashing.py b/dedup/hashing.py
index 002eda8..5f015b2 100644
--- a/dedup/hashing.py
+++ b/dedup/hashing.py
@@ -49,9 +49,13 @@ class DecompressedHash(object):
 
     def hexdigest(self):
         if not hasattr(self.decompressor, "flush"):
+            if self.decompressor.unused_data:
+                raise ValueError("decompressor did not consume all data")
             return self.hashobj.hexdigest()
         tmpdecomp = self.decompressor.copy()
         data = tmpdecomp.flush()
+        if tmpdecomp.unused_data:
+            raise ValueError("decompressor did not consume all data")
         tmphash = self.hashobj.copy()
         tmphash.update(data)
         return tmphash.hexdigest()