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>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Message-id: 20180430124651.10340-3-stefanha@redhat.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>
(cherry picked from commit fa64205df9dfd7b7662cc64a7e82115c00e428e5)
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index c667d08..25bf43b 100755 (executable)
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -1186,6 +1186,8 @@ 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;
@@ -1414,8 +1416,15 @@ 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/) {
                        WARN("8-bit UTF-8 used in possible commit log\n" . $herecurr);
                }