[feature] Add support for zlib files

README.md

@@ -38,7 +38,7 @@ And in contrast to [tarindexer](https://github.com/devsnd/tarindexer), which als
 *TAR compressions supported for random access:*
 
  - **BZip2** as provided by [indexed_bzip2](https://github.com/mxmlnkn/indexed_bzip2) as a backend, which is a refactored and extended version of [bzcat](https://github.com/landley/toybox/blob/c77b66455762f42bb824c1aa8cc60e7f4d44bdab/toys/other/bzcat.c) from [toybox](https://landley.net/code/toybox/). See also the [reverse engineered specification](https://github.com/dsnet/compress/blob/master/doc/bzip2-format.pdf).
- - **Gzip** as provided by [rapidgzip](https://github.com/mxmlnkn/rapidgzip) or [indexed_gzip](https://github.com/pauldmccarthy/indexed_gzip) by Paul McCarthy. See also [RFC1952](https://tools.ietf.org/html/rfc1952).
+ - **Gzip** and **Zlib** as provided by [rapidgzip](https://github.com/mxmlnkn/rapidgzip) or [indexed_gzip](https://github.com/pauldmccarthy/indexed_gzip) by Paul McCarthy. See also [RFC1952](https://tools.ietf.org/html/rfc1952) and [RFC1950](https://tools.ietf.org/html/rfc1950).
  - **Xz** as provided by [python-xz](https://github.com/Rogdham/python-xz) by Rogdham or [lzmaffi](https://github.com/r3m0t/backports.lzma) by Tomer Chachamu. See also [The .xz File Format](https://tukaani.org/xz/xz-file-format.txt).
  - **Zstd** as provided by [indexed_zstd](https://github.com/martinellimarco/indexed_zstd) by Marco Martinelli. See also [Zstandard Compression Format](https://github.com/facebook/zstd/blob/master/doc/zstd_compression_format.md).
 

core/ratarmountcore/SQLiteIndex.py

@@ -1065,7 +1065,11 @@ def synchronizeCompressionOffsets(self, fileObject: IO[bytes], compression: str)
             db.commit()
             return
 
-        if hasattr(fileObject, 'import_index') and hasattr(fileObject, 'export_index') and compression == 'gz':
+        if (
+            hasattr(fileObject, 'import_index')
+            and hasattr(fileObject, 'export_index')
+            and compression in ['gz', 'zlib']
+        ):
             tables = getSqliteTables(db)
 
             if 'gzipindex' in tables or 'gzipindexes' in tables:

core/ratarmountcore/SQLiteIndexedTar.py

@@ -1050,7 +1050,7 @@ def _createIndexRecursively(
                 tarInfo = None
 
             fname = os.path.basename(self.tarFileName)
-            for suffix in ['.gz', '.bz2', '.bzip2', '.gzip', '.xz', '.zst', '.zstd']:
+            for suffix in ['.gz', '.bz2', '.bzip2', '.gzip', '.xz', '.zst', '.zstd', '.zz', '.zlib']:
                 if fname.lower().endswith(suffix) and len(fname) > len(suffix):
                     fname = fname[: -len(suffix)]
                     break

core/ratarmountcore/compressions.py

@@ -74,6 +74,22 @@
 CompressionInfo = collections.namedtuple('CompressionInfo', ['suffixes', 'doubleSuffixes', 'modules', 'checkHeader'])
 
 
+def checkZlibHeader(file):
+    header = file.read(2)
+    cmf = header[0]
+    if cmf & 0xF != 8:
+        return False
+    if cmf >> 4 > 7:
+        return False
+    flags = header[1]
+    if ((cmf << 8) + flags) % 31 != 0:
+        return False
+    usesDictionary = ((flags >> 5) & 1) != 0
+    if usesDictionary:
+        return False
+    return True
+
+
 TAR_COMPRESSION_FORMATS: Dict[str, CompressionInfo] = {
     'bz2': CompressionInfo(
         ['bz2', 'bzip2'],
@@ -106,6 +122,12 @@
         [CompressionModuleInfo('indexed_zstd', lambda x: indexed_zstd.IndexedZstdFile(x.fileno()))],
         lambda x: x.read(4) == (0xFD2FB528).to_bytes(4, 'little'),
     ),
+    'zlib': CompressionInfo(
+        ['zz', 'zlib'],
+        [],
+        [CompressionModuleInfo('rapidgzip', lambda x: rapidgzip.RapidgzipFile(x))],
+        checkZlibHeader,
+    ),
 }
 
 

tests/runtests.sh

@@ -1866,6 +1866,7 @@ pytestedTests+=(
     19696f24a91fc4e8950026f9c801a0d0 tests/simple.bz2                             simple
     19696f24a91fc4e8950026f9c801a0d0 tests/simple.gz                              simple
     19696f24a91fc4e8950026f9c801a0d0 tests/simple.xz                              simple
+    19696f24a91fc4e8950026f9c801a0d0 tests/simple.zlib                            simple
     19696f24a91fc4e8950026f9c801a0d0 tests/simple.zst                             simple
     2709a3348eb2c52302a7606ecf5860bc tests/file-existing-as-non-link-and-link.tar foo/fighter/ufo
     d3b07384d113edec49eaa6238ad5ff00 tests/two-self-links-to-existing-file.tar    bar

tests/test_cli.py

@@ -222,6 +222,7 @@ def test_password_list(tmpdir, passwords, compression):
     ("19696f24a91fc4e8950026f9c801a0d0", "simple.bz2", "simple"),
     ("19696f24a91fc4e8950026f9c801a0d0", "simple.gz", "simple"),
     ("19696f24a91fc4e8950026f9c801a0d0", "simple.xz", "simple"),
+    ("19696f24a91fc4e8950026f9c801a0d0", "simple.zlib", "simple"),
     ("19696f24a91fc4e8950026f9c801a0d0", "simple.zst", "simple"),
     ("2709a3348eb2c52302a7606ecf5860bc", "file-existing-as-non-link-and-link.tar", "foo/fighter/ufo"),
     ("d3b07384d113edec49eaa6238ad5ff00", "two-self-links-to-existing-file.tar", "bar"),