From 77547d5313ea916d2fb64ca5a8812734e9b50f92 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Zbigniew=20J=C4=99drzejewski-Szmek?= <zbyszek@in.waw.pl>
Date: Fri, 17 Jul 2020 11:09:31 +0200
Subject: [PATCH] hwdb: check that uppercase digits are used in modalias
 patterns

This is all confusing as hell, becuase in some places lowercase hexadecimal
digits are used, and in other places uppercase. This adds a check for the
most common case that we and others got wrong.

I tried to extend the general grammar in hwdb_grammar() to include this check,
but it quickly became very complicated and didn't seem to work properly. Doing
initial parsing with more general rules is easier and also seems to give better
error messages:

/home/zbyszek/src/systemd-work/build/../hwdb.d/60-autosuspend.hwdb: 3 match groups, 5 matches, 3 properties
Pattern 'v058fp9540*' is invalid: Expected W:(0123...), found 'f'  (at char 4), (line:1, col:5)
---
 hwdb.d/parse_hwdb.py | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/hwdb.d/parse_hwdb.py b/hwdb.d/parse_hwdb.py
index c9851ca64c9..025133416f6 100755
--- a/hwdb.d/parse_hwdb.py
+++ b/hwdb.d/parse_hwdb.py
@@ -79,6 +79,9 @@ GENERAL_MATCHES = {'acpi',
                    'OUI',
                    }
 
+def upperhex_word(length):
+    return Word(nums + 'ABCDEF', exact=length)
+
 @lru_cache()
 def hwdb_grammar():
     ParserElement.setDefaultWhitespaceChars('')
@@ -180,8 +183,27 @@ def parse(fname):
         return []
     return [convert_properties(g) for g in parsed.GROUPS]
 
-def check_match_uniqueness(groups):
+def check_matches(groups):
     matches = sum((group[0] for group in groups), [])
+
+    # This is a partial check. The other cases could be also done, but those
+    # two are most commonly wrong.
+    grammars = { 'usb' : 'v' + upperhex_word(4) + Optional('p' + upperhex_word(4)),
+                 'pci' : 'v' + upperhex_word(8) + Optional('d' + upperhex_word(8)),
+    }
+
+    for match in matches:
+        prefix, rest = match.split(':', maxsplit=1)
+        gr = grammars.get(prefix)
+        if gr:
+            try:
+                gr.parseString(rest)
+            except ParseBaseException as e:
+                error('Pattern {!r} is invalid: {}', rest, e)
+                continue
+            if rest[-1] not in '*:':
+                error('pattern {} does not end with "*" or ":"', match)
+
     matches.sort()
     prev = None
     for match in matches:
@@ -256,7 +278,7 @@ if __name__ == '__main__':
     for fname in args:
         groups = parse(fname)
         print_summary(fname, groups)
-        check_match_uniqueness(groups)
+        check_matches(groups)
         check_properties(groups)
 
     sys.exit(ERROR)