[PATCH] Check charset in scripts/checkpatch.pl

[David Woodhouse <dwmw2@infradead.org>]

Reject all legacy 8-bit character sets and allow only ASCII or UTF-8 to
be added to files or used in patch descriptions.

Signed-off-by: David Woodhouse <dwmw2@infradead.org>

Signed-off-by: asd
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 277c326..7a7f283 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -395,6 +395,22 @@ sub process {
 			$clean = 0;
 		}
 
+# UTF-8 regex found at http://www.w3.org/International/questions/qa-forms-utf-8.en.php
+		if ( ($realfile =~ /^$/ || $line =~ /^\+/) &&
+		     !($line =~ m/^(
+				[\x09\x0A\x0D\x20-\x7E]              # ASCII
+				| [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
+				|  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
+				| [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2}  # straight 3-byte
+				|  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
+				|  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
+				| [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
+				|  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
+				)*$/x ) ) {
+			print "Invalid UTF-8\n";
+			print "$herecurr";
+			$clean = 0;
+		}
 #ignore lines being removed
 		if ($line=~/^-/) {next;}
 


-- 
dwmw2