Add support for extracting vmlinuz/vmlinux Linux kernel images. (Closes:...

Add support for extracting vmlinuz/vmlinux Linux kernel images. (Closes: #304)

MANIFEST.in

@@ -2,4 +2,5 @@ include COPYING
 include README.rst
 include CONTRIBUTING.md
 include pyproject.toml
+graft scripts
 graft tests

diffoscope/comparators/__init__.py

@@ -118,6 +118,7 @@ class ComparatorManager:
         ("xsb.XsbFile",),
         ("berkeley_db.BerkeleyDBFile",),
         ("zst.ZstFile",),
+        ("vmlinuz.VmlinuzFile",),
     )
 
     _singleton = {}

diffoscope/comparators/vmlinuz.py

+#
+# diffoscope: in-depth comparison of files, archives, and directories
+#
+# Copyright © 2022 Chris Lamb <lamby@debian.org>
+#
+# 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 logging
+import os.path
+import pathlib
+import re
+import subprocess
+
+from diffoscope.tools import tool_required
+
+from .utils.file import File
+from .utils.archive import Archive
+
+logger = logging.getLogger(__name__)
+
+
+class VmlinuzContainer(Archive):
+    def open_archive(self):
+        return self
+
+    def close_archive(self):
+        pass
+
+    def get_member_names(self):
+        return [self.get_compressed_content_name(".vmlinuz")]
+
+    @tool_required("readelf")
+    def extract(self, member_name, dest_dir):
+        dest_path = os.path.join(dest_dir, member_name)
+        logger.debug("extracting vmlinuz to %s", dest_path)
+
+        # Locate extract-vmlinux script
+        script = pathlib.Path(__file__).parent.parent.parent.joinpath(
+            "scripts", "extract-vmlinux"
+        )
+        with open(dest_path, "wb") as f:
+            subprocess.check_call(
+                [script, self.source.path],
+                stdout=f,
+                stderr=None,
+            )
+
+        return dest_path
+
+
+class VmlinuzFile(File):
+    DESCRIPTION = "Linux kernel images"
+    CONTAINER_CLASSES = [VmlinuzContainer]
+    FILE_TYPE_RE = re.compile(r"^Linux kernel\b")

scripts/extract-vmlinux

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0-only
+# ----------------------------------------------------------------------
+# extract-vmlinux - Extract uncompressed vmlinux from a kernel image
+#
+# Inspired from extract-ikconfig
+# (c) 2009,2010 Dick Streefland <dick@streefland.net>
+#
+# (c) 2011      Corentin Chary <corentin.chary@gmail.com>
+#
+# ----------------------------------------------------------------------
+
+check_vmlinux()
+{
+	# Use readelf to check if it's a valid ELF
+	# TODO: find a better to way to check that it's really vmlinux
+	#       and not just an elf
+	readelf -h $1 > /dev/null 2>&1 || return 1
+
+	cat $1
+	exit 0
+}
+
+try_decompress()
+{
+	# The obscure use of the "tr" filter is to work around older versions of
+	# "grep" that report the byte offset of the line instead of the pattern.
+
+	# Try to find the header ($1) and decompress from here
+	for	pos in `tr "$1\n$2" "\n$2=" < "$img" | grep -abo "^$2"`
+	do
+		pos=${pos%%:*}
+		tail -c+$pos "$img" | $3 > $tmp 2> /dev/null
+		check_vmlinux $tmp
+	done
+}
+
+# Check invocation:
+me=${0##*/}
+img=$1
+if	[ $# -ne 1 -o ! -s "$img" ]
+then
+	echo "Usage: $me <kernel-image>" >&2
+	exit 2
+fi
+
+# Prepare temp files:
+tmp=$(mktemp /tmp/vmlinux-XXX)
+trap "rm -f $tmp" 0
+
+# That didn't work, so retry after decompression.
+try_decompress '\037\213\010' xy    gunzip
+try_decompress '\3757zXZ\000' abcde unxz
+try_decompress 'BZh'          xy    bunzip2
+try_decompress '\135\0\0\0'   xxx   unlzma
+try_decompress '\211\114\132' xy    'lzop -d'
+try_decompress '\002!L\030'   xxx   'lz4 -d'
+try_decompress '(\265/\375'   xxx   unzstd
+
+# Finally check for uncompressed images or objects:
+check_vmlinux $img
+
+# Bail out:
+echo "$me: Cannot find vmlinux." >&2