Merge pull request #6837 from ThomasWaldmann/recreate-recompress-considering-level

recreate: consider level for recompression, fixes #6698, fixes #3622

src/borg/archive.py

@@ -2079,8 +2079,9 @@ class ArchiveRecreater:
         if self.recompress and not self.always_recompress and chunk_id in self.cache.chunks:
             # Check if this chunk is already compressed the way we want it
             old_chunk = self.key.decrypt(chunk_id, self.repository.get(chunk_id), decompress=False)
-            if Compressor.detect(old_chunk).name == self.key.compressor.decide(data).name:
-                # Stored chunk has the same compression we wanted
+            compressor_cls, level = Compressor.detect(old_chunk)
+            if compressor_cls.name == self.key.compressor.decide(data).name and level == self.key.compressor.level:
+                # Stored chunk has the same compression method and level as we wanted
                 overwrite = False
         chunk_entry = self.cache.add_chunk(chunk_id, data, target.stats, overwrite=overwrite, wait=False)
         self.cache.repository.async_response(wait=False)

src/borg/archiver.py

@@ -4801,9 +4801,8 @@ class Archiver:
                                    help='recompress data chunks according to `MODE` and ``--compression``. '
                                         'Possible modes are '
                                         '`if-different`: recompress if current compression is with a different '
-                                        'compression algorithm (the level is not considered); '
-                                        '`always`: recompress even if current compression is with the same '
-                                        'compression algorithm (use this to change the compression level); and '
+                                        'compression algorithm or different level; '
+                                        '`always`: recompress unconditionally; and '
                                         '`never`: do not recompress (use this option to explicitly prevent '
                                         'recompression). '
                                         'If no MODE is given, `if-different` will be used. '

src/borg/compress.pyx

@@ -66,6 +66,7 @@ cdef class CompressorBase:
 
     def __init__(self, level=255, **kwargs):
         assert 0 <= level <= 255
+        self.level = level
         if self.ID is not None:
             self.id_level = self.ID + bytes((level, ))  # level 255 means "unknown level"
             assert len(self.id_level) == 2
@@ -539,7 +540,8 @@ class ObfuscateSize(CompressorBase):
         compr_size = self.header_fmt.unpack(obfuscated_data[0:self.header_len])[0]
         compressed_data = obfuscated_data[self.header_len:self.header_len+compr_size]
         if self.compressor is None:
-            self.compressor = Compressor.detect(compressed_data)()
+            compressor_cls = Compressor.detect(compressed_data)[0]
+            self.compressor = compressor_cls()
         return self.compressor.decompress(compressed_data)  # decompress data
 
 
@@ -578,15 +580,16 @@ class Compressor:
         return self.compressor.compress(data)
 
     def decompress(self, data):
-        compressor_cls = self.detect(data)
+        compressor_cls = self.detect(data)[0]
         return compressor_cls(**self.params).decompress(data)
 
     @staticmethod
     def detect(data):
         hdr = bytes(data[:2])  # detect() does not work with memoryview
+        level = hdr[1]  # usually the level, but not for zlib_legacy
         for cls in COMPRESSOR_LIST:
             if cls.detect(hdr):
-                return cls
+                return cls, (255 if cls.name == 'zlib_legacy' else level)
         else:
             raise ValueError('No decompressor for this data found: %r.', data[:2])
 

src/borg/testsuite/compress.py

@@ -133,11 +133,11 @@ def test_auto():
     compressed_lz4 = compressor_lz4.compress(data)
     compressed_zlib = compressor_zlib.compress(data)
     ratio = len(compressed_zlib) / len(compressed_lz4)
-    assert Compressor.detect(compressed_auto_zlib) == ZLIB if ratio < 0.99 else LZ4
+    assert Compressor.detect(compressed_auto_zlib)[0] == ZLIB if ratio < 0.99 else LZ4
 
     data = b'\x00\xb8\xa3\xa2-O\xe1i\xb6\x12\x03\xc21\xf3\x8a\xf78\\\x01\xa5b\x07\x95\xbeE\xf8\xa3\x9ahm\xb1~'
     compressed = compressor_auto_zlib.compress(data)
-    assert Compressor.detect(compressed) == CNONE
+    assert Compressor.detect(compressed)[0] == CNONE
 
 
 def test_obfuscate():