diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 2f81371ffb..d24c9441ee 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -262,6 +262,19 @@ our $UTF8 = qr{ | $NON_ASCII_UTF8 }x; +# some readers default to ISO-8859-1 when showing email source. detect +# when UTF-8 is incorrectly interpreted as ISO-8859-1 and reencoded back. +# False positives are possible but very unlikely. +our $UTF8_MOJIBAKE = qr{ + \xC3[\x82-\x9F] \xC2[\x80-\xBF] # c2-df 80-bf + | \xC3\xA0 \xC2[\xA0-\xBF] \xC2[\x80-\xBF] # e0 a0-bf 80-bf + | \xC3[\xA1-\xAC\xAE\xAF] (?: \xC2[\x80-\xBF]){2} # e1-ec/ee/ef 80-bf 80-bf + | \xC3\xAD \xC2[\x80-\x9F] \xC2[\x80-\xBF] # ed 80-9f 80-bf + | \xC3\xB0 \xC2[\x90-\xBF] (?: \xC2[\x80-\xBF]){2} # f0 90-bf 80-bf 80-bf + | \xC3[\xB1-\xB3] (?: \xC2[\x80-\xBF]){3} # f1-f3 80-bf 80-bf 80-bf + | \xC3\xB4 \xC2[\x80-\x8F] (?: \xC2[\x80-\xBF]){2} # f4 80-b8 80-bf 80-bf +}x; + # There are still some false positives, but this catches most # common cases. our $typeTypedefs = qr{(?x: @@ -1506,6 +1519,9 @@ sub process { ERROR("Invalid UTF-8, patch and commit message should be encoded in UTF-8\n" . $hereptr); } + if ($rawline =~ m/$UTF8_MOJIBAKE/) { + ERROR("Doubly-encoded UTF-8\n" . $herecurr); + } # Check if it's the start of a commit log # (not a header line and we haven't seen the patch filename) if ($in_header_lines && $realfile =~ /^$/ &&