[PATCH] checkpatch: Remove email address comment from email address comparisons

[Joe Perches]

About 2% of the last 100K commits have email addresses that include an
RFC2822 compliant comment like:

	Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>

checkpatch currently does a comparison of the complete name and address
to the submitted author to determine if the author has signed-off and
emits a warning if the exact email names and addresses do not match.

Unfortunately, the author email address can be written without the comment
like:

	Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Add logic to compare the comment stripped email addresses to avoid this
warning.

Signed-off-by: Joe Perches <joe@xxxxxxxxxxx>
Reported-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 scripts/checkpatch.pl | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index f3b8434..17637d0 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -1132,6 +1132,7 @@ sub parse_email {
 	my ($formatted_email) = @_;
 
 	my $name = "";
+	my $name_comment = "";
 	my $address = "";
 	my $comment = "";
 
@@ -1164,6 +1165,10 @@ sub parse_email {
 
 	$name = trim($name);
 	$name =~ s/^\"|\"$//g;
+	$name =~ s/(\s*\([^\)]+\))\s*//;
+	if (defined($1)) {
+		$name_comment = trim($1);
+	}
 	$address = trim($address);
 	$address =~ s/^\<|\>$//g;
 
@@ -1172,7 +1177,7 @@ sub parse_email {
 		$name = "\"$name\"";
 	}
 
-	return ($name, $address, $comment);
+	return ($name, $name_comment, $address, $comment);
 }
 
 sub format_email {
@@ -1198,6 +1203,23 @@ sub format_email {
 	return $formatted_email;
 }
 
+sub reformat_email {
+	my ($email) = @_;
+
+	my ($email_name, $name_comment, $email_address, $comment) = parse_email($email);
+	return format_email($email_name, $email_address);
+}
+
+sub same_email_addresses {
+	my ($email1, $email2) = @_;
+
+	my ($email1_name, $name1_comment, $email1_address, $comment1) = parse_email($email1);
+	my ($email2_name, $name2_comment, $email2_address, $comment2) = parse_email($email2);
+
+	return $email1_name eq $email2_name &&
+	       $email1_address eq $email2_address;
+}
+
 sub which {
 	my ($bin) = @_;
 
@@ -2618,17 +2640,16 @@ sub process {
 			$author = $1;
 			$author = encode("utf8", $author) if ($line =~ /=\?utf-8\?/i);
 			$author =~ s/"//g;
+			$author = reformat_email($author);
 		}
 
 # Check the patch for a signoff:
-		if ($line =~ /^\s*signed-off-by:/i) {
+		if ($line =~ /^\s*signed-off-by:\s*(.*)/i) {
 			$signoff++;
 			$in_commit_log = 0;
 			if ($author ne '') {
-				my $l = $line;
-				$l =~ s/"//g;
-				if ($l =~ /^\s*signed-off-by:\s*\Q$author\E/i) {
-				    $authorsignoff = 1;
+				if (same_email_addresses($1, $author)) {
+					$authorsignoff = 1;
 				}
 			}
 		}
@@ -2678,7 +2699,7 @@ sub process {
 				}
 			}
 
-			my ($email_name, $email_address, $comment) = parse_email($email);
+			my ($email_name, $name_comment, $email_address, $comment) = parse_email($email);
 			my $suggested_email = format_email(($email_name, $email_address));
 			if ($suggested_email eq "") {
 				ERROR("BAD_SIGN_OFF",
@@ -2689,9 +2710,7 @@ sub process {
 				$dequoted =~ s/" </ </;
 				# Don't force email to have quotes
 				# Allow just an angle bracketed address
-				if ("$dequoted$comment" ne $email &&
-				    "<$email_address>$comment" ne $email &&
-				    "$suggested_email$comment" ne $email) {
+				if (!same_email_addresses($email, $suggested_email)) {
 					WARN("BAD_SIGN_OFF",
 					     "email address '$email' might be better as '$suggested_email$comment'\n" . $herecurr);
 				}