[Linux-kernel-mentees] [PATCH] checkpatch: add fix and improve warning msg for Non-standard signature

[Aditya Srivastava <yashsri421@gmail.com>]

Currently checkpatch warns for BAD_SIGN_OFF on non-standard signature
styles.

A large number of these warnings occur because of typo mistakes in
signoffs.
An evaluation over v4.13..v5.8 revealed that out of 539 warnings due to
Non-standard signatures, 85 are due to typo mistakes.

Eg. running checkpatch on commit da785a87787c ("ARM: bcm2835: Fix
integer overflow in rpi_firmware_print_firmware_revision()") reports
this warning:

WARNING:Non-standard signature: Revieved-by:
Revieved-by: Petr Mladek <pmladek@suse.com>

Here the signoff 'Reviewed-by' is misspelt.

Provide a fix by calculating levenshtein distance for the signoff over
all the standard signatures and suggest a fix if the distance for any
signature is less than or equal to 2.

Signed-off-by: Aditya Srivastava <yashsri421@gmail.com>
---
applied on my last patch and next-20201120

 scripts/checkpatch.pl | 73 ++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 72 insertions(+), 1 deletion(-)

diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index b018deecec1a..2198360eebbd 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -506,6 +506,77 @@ our $signature_tags = qr{(?xi:
 	Cc:
 )};
 
+sub get_min {
+	my (@arr) = @_;
+	my $len = scalar @arr;
+	if((scalar @arr) < 1) {
+		# if underflow, return
+		return;
+	}
+	my $min = $arr[0];
+	for my $i (0 .. ($len-1)) {
+		if ($arr[$i] < $min) {
+			$min = $arr[$i];
+		}
+	}
+	return $min;
+}
+
+sub get_edit_distance {
+	my ($str1, $str2) = @_;
+	my $len1 = length($str1);
+	my $len2 = length($str2);
+	# two dimensional array storing minimum edit distance
+	my @distance;
+	for my $i (0 .. $len1) {
+		for my $j (0 .. $len2) {
+			if ($i == 0) {
+				$distance[$i][$j] = $j;
+			}
+			elsif ($j == 0) {
+				$distance[$i][$j] = $i;
+			}
+			elsif (substr($str1, $i-1, 1) eq substr($str2, $j-1, 1)) {
+				$distance[$i][$j] = $distance[$i - 1][$j - 1];
+			}
+			else {
+				my $dist1 = $distance[$i][$j - 1]; #insert distance
+				my $dist2 = $distance[$i - 1][$j]; # remove
+				my $dist3 = $distance[$i - 1][$j - 1]; #replace
+				$distance[$i][$j] = 1 + get_min($dist1, $dist2, $dist3);
+			}
+		}
+	}
+	return $distance[$len1][$len2];
+}
+
+sub get_standard_signature {
+	my ($sign_off) = @_;
+	$sign_off = lc($sign_off);
+	$sign_off =~ s/\-//g; # to match with formed hash
+	my @standard_signature_tags = (
+		'signed-off-by:', 'co-developed-by:', 'acked-by:', 'tested-by:',
+		'reviewed-by:', 'reported-by:', 'suggested-by:', 'to:', 'cc:'
+	);
+	# setting default values
+	my $standard_signature = 'signed-off-by';
+	my $min_edit_distance = 20;
+	my $edit_distance;
+	foreach (@standard_signature_tags) {
+		my $signature = $_;
+		$_ =~ s/\-//g;
+		$edit_distance = get_edit_distance($sign_off, $_);
+		if ($edit_distance < $min_edit_distance) {
+			$min_edit_distance = $edit_distance;
+			$standard_signature = $signature;
+		}
+	}
+        if($min_edit_distance<=2) {
+		return ucfirst($standard_signature);
+        }
+	return "";
+}
+
 our %standard_signature_fix = (
 	"Requested-by:" => {
 		suggestion => "Suggested-by:",
@@ -2848,7 +2919,7 @@ sub process {
 			my $ucfirst_sign_off = ucfirst(lc($sign_off));
 
 			if ($sign_off !~ /$signature_tags/) {
-				my $suggested_signature = "";
+				my $suggested_signature = get_standard_signature($sign_off);
 				my $rationale = "";
 				if (exists($standard_signature_fix{$sign_off})) {
 					$suggested_signature = $standard_signature_fix{$sign_off}{'suggestion'};
-- 
2.17.1

_______________________________________________
Linux-kernel-mentees mailing list
Linux-kernel-mentees@lists.linuxfoundation.org
https://lists.linuxfoundation.org/mailman/listinfo/linux-kernel-mentees