checkpatch: check utf-8 content from a commit log when it's missing from charset

Check that a commit log doesn't contain UTF-8 when a mail header
explicitly defines a different charset, like

'Content-Type: text/plain; charset="us-ascii"'

Signed-off-by: Pasi Savanainen <pasi.savanainen@nixu.com>
Cc: Joe Perches <joe@perches.com>
Cc: Andy Whitcroft <apw@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 12 insertions, 3 deletions

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index ca05ba217f5f..5ae91889bc6b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -1386,6 +1386,8 @@ sub process {
 	my $in_header_lines = 1;
 	my $in_commit_log = 0;		#Scanning lines before patch
 
+	my $non_utf8_charset = 0;
+
 	our @report = ();
 	our $cnt_lines = 0;
 	our $cnt_error = 0;
@@ -1686,10 +1688,17 @@ sub process {
 			$in_commit_log = 1;
 		}
 
-# Still not yet in a patch, check for any UTF-8
-		if ($in_commit_log && $realfile =~ /^$/ &&
+# Check if there is UTF-8 in a commit log when a mail header has explicitly
+# declined it, i.e defined some charset where it is missing.
+		if ($in_header_lines &&
+		    $rawline =~ /^Content-Type:.+charset="(.+)".*$/ &&
+		    $1 !~ /utf-8/i) {
+			$non_utf8_charset = 1;
+		}
+
+		if ($in_commit_log && $non_utf8_charset && $realfile =~ /^$/ &&
 		    $rawline =~ /$NON_ASCII_UTF8/) {
-			CHK("UTF8_BEFORE_PATCH",
+			WARN("UTF8_BEFORE_PATCH",
 			    "8-bit UTF-8 used in possible commit log\n" . $herecurr);
 		}