[RFC PATCH v2 2/7] scripts: convert extract-module-sig.pl to Python

[Breno Rodrigues Alves]

Faithful re-implementation of extract-module-sig.pl in Python 3
(stdlib only). Same magic-number handling, same descriptor
extraction, same -0/-a/-d/-n/-k/-s output modes.

Verified byte-for-byte identical to the Perl version on a
synthetic signed module.

Signed-off-by: Breno Rodrigues Alves <breno3011alves@xxxxxxxxx>
---
 scripts/extract-module-sig.py | 103 ++++++++++++++++++++++++++++++++++
 1 file changed, 103 insertions(+)
 create mode 100755 scripts/extract-module-sig.py

diff --git a/scripts/extract-module-sig.py b/scripts/extract-module-sig.py
new file mode 100755
index 000000000..e9a43e72f
--- /dev/null
+++ b/scripts/extract-module-sig.py
@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# extract-module-sig.py <part> <module-file>
+#   -0: unsigned module  -a: all sig data  -d: descriptor
+#   -n: signer name      -k: key ID        -s: signature
+
+import struct
+import sys
+
+MAGIC = b'~Module signature appended~\n'
+
+
+def main(argv):
+    if len(argv) != 2:
+        sys.exit(f'Format: {sys.argv[0]} -[0adnks] module-file >out')
+
+    part, modfile = argv
+
+    try:
+        with open(modfile, 'rb') as f:
+            buf = f.read()
+    except OSError as e:
+        sys.exit(f'{modfile}: {e}')
+
+    print(f'Read {len(buf)} bytes from module file', file=sys.stderr)
+
+    if len(buf) < 12 + len(MAGIC):
+        sys.exit('The file is too short to have a sig magic number and descriptor')
+
+    p = len(buf) - len(MAGIC)
+    if buf[p:] != MAGIC:
+        sys.exit(f'Magic number not found at {len(buf)}')
+    print(f'Found magic number at {len(buf)}', file=sys.stderr)
+
+    p -= 12
+    info_raw = buf[p:p + 12]
+    algo = info_raw[0]
+    hash_ = info_raw[1]
+    id_type = info_raw[2]
+    name_len = info_raw[3]
+    kid_len = info_raw[4]
+    sig_len = struct.unpack('>I', info_raw[8:12])[0]
+    info = [algo, hash_, id_type, name_len, kid_len, sig_len]
+
+    type_msg = {
+        0: 'Found PGP key identifier',
+        1: 'Found X.509 cert identifier',
+        2: 'Found PKCS#7/CMS encapsulation',
+    }.get(id_type, f'Found unsupported identifier type {id_type}')
+    print(type_msg, file=sys.stderr)
+
+    if p < name_len + kid_len + sig_len:
+        sys.exit('Insufficient name+kid+sig data in file')
+
+    p -= sig_len
+    raw_sig = buf[p:p + sig_len]
+    p -= kid_len
+    raw_kid = buf[p:p + kid_len]
+    p -= name_len
+    raw_name = buf[p:p + name_len]
+    module_len = p
+
+    if sig_len > 0:
+        n = min(16, sig_len)
+        hs = ''.join(f'{b:02x}' for b in raw_sig[:n])
+        print(f'Found {sig_len} bytes of signature [{hs}]', file=sys.stderr)
+
+    if kid_len > 0:
+        n = min(16, kid_len)
+        hs = ''.join(f'{b:02x}' for b in raw_kid[:n])
+        print(f'Found {kid_len} bytes of key identifier [{hs}]',
+              file=sys.stderr)
+
+    if name_len > 0:
+        sys.stderr.buffer.write(
+            f"Found {name_len} bytes of signer's name [".encode() +
+            raw_name + b']\n')
+
+    if part == '-0':
+        sys.stdout.buffer.write(buf[:module_len])
+    elif part == '-a':
+        sys.stdout.buffer.write(buf[module_len:])
+    elif part == '-d':
+        print(' '.join(str(x) for x in info))
+    elif part == '-n':
+        if id_type == 2:
+            print("No signer's name for PKCS#7 message type sig",
+                  file=sys.stderr)
+        sys.stdout.buffer.write(raw_name)
+    elif part == '-k':
+        if id_type == 2:
+            print('No key ID for PKCS#7 message type sig', file=sys.stderr)
+        sys.stdout.buffer.write(raw_kid)
+    elif part == '-s':
+        sys.stdout.buffer.write(raw_sig)
+    else:
+        sys.exit(f'Unknown part: {part}')
+    return 0
+
+
+if __name__ == '__main__':
+    sys.exit(main(sys.argv[1:]))
\ No newline at end of file
-- 
2.43.0