Add lzip comparator

I'm looking at this since it's a common form of compression for nar
archives for GNU Guix.

debian/copyright

@@ -28,6 +28,7 @@ Copyright:
  © 2019 Jelle van der Waa <jelle@archlinux.org>
  © 2020 Conrad Ratschan <ratschance@gmail.com>
  © 2020-2021 Jean-Romain Garnier <salsa@jean-romain.com>
+ © 2022 Christopher Baines <mail@cbaines.net>
 License: GPL-3+
 
 Files: diffoscope/changes.py

diffoscope/comparators/__init__.py

@@ -80,6 +80,7 @@ class ComparatorManager:
         ("iso9660.Iso9660File",),
         ("java.ClassFile",),
         ("lz4.Lz4File",),
+        ("lzip.LzipFile",),
         ("mono.MonoExeFile",),
         ("pdf.PdfFile",),
         ("png.PngFile",),

diffoscope/comparators/lzip.py

+#
+# diffoscope: in-depth comparison of files, archives, and directories
+#
+# Copyright © 2014-2015 Jérémy Bobbio <lunar@debian.org>
+# Copyright © 2015-2020 Chris Lamb <lamby@debian.org>
+# Copyright © 2022 Christopher Baines <mail@cbaines.net>
+#
+# diffoscope is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# diffoscope is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with diffoscope.  If not, see <https://www.gnu.org/licenses/>.
+
+import re
+import os.path
+import logging
+import subprocess
+
+from diffoscope.tools import tool_required
+
+from .utils.file import File
+from .utils.archive import Archive
+
+logger = logging.getLogger(__name__)
+
+
+class LzipContainer(Archive):
+    def open_archive(self):
+        return self
+
+    def close_archive(self):
+        pass
+
+    def get_member_names(self):
+        return [self.get_compressed_content_name(".lzip")]
+
+    @tool_required("lzip")
+    def extract(self, member_name, dest_dir):
+        dest_path = os.path.join(dest_dir, member_name)
+        logger.debug("lzip extracting to %s", dest_path)
+        with open(dest_path, "wb") as fp:
+            subprocess.check_call(
+                ["lzip", "--decompress", "--stdout", self.source.path],
+                stdout=fp,
+                stderr=None,
+            )
+        return dest_path
+
+
+class LzipFile(File):
+    DESCRIPTION = "lzip compressed files"
+    CONTAINER_CLASSES = [LzipContainer]
+    FILE_TYPE_RE = re.compile(r"^lzip compressed data\b")
+
+    FALLBACK_FILE_EXTENSION_SUFFIX = {".lzip"}

diffoscope/external_tools.py

@@ -125,6 +125,7 @@ EXTERNAL_TOOLS = {
         "guix": "e2fsprogs",
     },
     "lz4": {"debian": "lz4 | liblz4-tool", "FreeBSD": "lz4", "guix": "lz4"},
+    "lzip": {},
     "msgunfmt": {
         "debian": "gettext",
         "arch": "gettext",

tests/comparators/test_lzip.py

+#
+# diffoscope: in-depth comparison of files, archives, and directories
+#
+# Copyright © 2015 Jérémy Bobbio <lunar@debian.org>
+# Copyright © 2016-2017, 2020 Chris Lamb <lamby@debian.org>
+# Copyright © 2022 Christopher Baines <mail@cbaines.net>
+#
+# diffoscope is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# diffoscope is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with diffoscope.  If not, see <https://www.gnu.org/licenses/>.
+
+import shutil
+import pytest
+
+from diffoscope.comparators.lzip import LzipFile
+from diffoscope.comparators.binary import FilesystemFile
+from diffoscope.comparators.utils.specialize import specialize
+
+from ..utils.data import load_fixture, get_data
+from ..utils.tools import skip_unless_tools_exist
+from ..utils.nonexisting import assert_non_existing
+
+lzip1 = load_fixture("test1.lzip")
+lzip2 = load_fixture("test2.lzip")
+
+
+def test_identification(lzip1):
+    assert isinstance(lzip1, LzipFile)
+
+
+def test_no_differences(lzip1):
+    difference = lzip1.compare(lzip1)
+    assert difference is None
+
+
+@pytest.fixture
+def differences(lzip1, lzip2):
+    return lzip1.compare(lzip2).details
+
+
+@skip_unless_tools_exist("lzip")
+def test_content_source(differences):
+    assert differences[0].source1 == "test1"
+    assert differences[0].source2 == "test2"
+
+
+@skip_unless_tools_exist("lzip")
+def test_content_source_without_extension(tmpdir, lzip1, lzip2):
+    path1 = str(tmpdir.join("test1"))
+    path2 = str(tmpdir.join("test2"))
+    shutil.copy(lzip1.path, path1)
+    shutil.copy(lzip2.path, path2)
+    lzip1 = specialize(FilesystemFile(path1))
+    lzip2 = specialize(FilesystemFile(path2))
+    difference = lzip1.compare(lzip2).details
+    assert difference[0].source1 == "test1-content"
+    assert difference[0].source2 == "test2-content"
+
+
+@skip_unless_tools_exist("lzip")
+def test_content_diff(differences):
+    expected_diff = get_data("text_ascii_expected_diff")
+    assert differences[0].unified_diff == expected_diff
+
+
+@skip_unless_tools_exist("lzip")
+def test_compare_non_existing(monkeypatch, lzip1):
+    assert_non_existing(monkeypatch, lzip1)