summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlvin Šipraga <alsi@bang-olufsen.dk>2023-12-19 02:25:15 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2023-12-31 10:57:42 -0800
commit2639772a11c860628c5f7007842eca52a1c34d78 (patch)
treebc8c7c5a77efd3c704d48c91c64649e7974f418e
parent9c334eb9ce886247567573074b13c5ac29d1a41a (diff)
get_maintainer: remove stray punctuation when cleaning file emails
When parsing emails from .yaml files in particular, stray punctuation such as a leading '-' can end up in the name. For example, consider a common YAML section such as: maintainers: - devicetree@vger.kernel.org This would previously be processed by get_maintainer.pl as: - <devicetree@vger.kernel.org> Make the logic in clean_file_emails more robust by deleting any sub-names which consist of common single punctuation marks before proceeding to the best-effort name extraction logic. The output is then correct: devicetree@vger.kernel.org Some additional comments are added to the function to make things clearer to future readers. Link: https://lore.kernel.org/all/0173e76a36b3a9b4e7f324dd3a36fd4a9757f302.camel@perches.com/ Suggested-by: Joe Perches <joe@perches.com> Signed-off-by: Alvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rwxr-xr-xscripts/get_maintainer.pl18
1 files changed, 11 insertions, 7 deletions
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index dac38c6e3b1c..ee1aed7e090c 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -2462,11 +2462,17 @@ sub clean_file_emails {
foreach my $email (@file_emails) {
$email =~ s/[\(\<\{]{0,1}([A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+)[\)\>\}]{0,1}/\<$1\>/g;
my ($name, $address) = parse_email($email);
- if ($name eq '"[,\.]"') {
- $name = "";
- }
+ # Strip quotes for easier processing, format_email will add them back
+ $name =~ s/^"(.*)"$/$1/;
+
+ # Split into name-like parts and remove stray punctuation particles
my @nw = split(/[^\p{L}\'\,\.\+-]/, $name);
+ @nw = grep(!/^[\'\,\.\+-]$/, @nw);
+
+ # Make a best effort to extract the name, and only the name, by taking
+ # only the last two names, or in the case of obvious initials, the last
+ # three names.
if (@nw > 2) {
my $first = $nw[@nw - 3];
my $middle = $nw[@nw - 2];
@@ -2480,18 +2486,16 @@ sub clean_file_emails {
} else {
$name = "$middle $last";
}
+ } else {
+ $name = "@nw";
}
if (substr($name, -1) =~ /[,\.]/) {
$name = substr($name, 0, length($name) - 1);
- } elsif (substr($name, -2) =~ /[,\.]"/) {
- $name = substr($name, 0, length($name) - 2) . '"';
}
if (substr($name, 0, 1) =~ /[,\.]/) {
$name = substr($name, 1, length($name) - 1);
- } elsif (substr($name, 0, 2) =~ /"[,\.]/) {
- $name = '"' . substr($name, 2, length($name) - 2);
}
my $fmt_email = format_email($name, $address, $email_usename);