summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlvin Šipraga <alsi@bang-olufsen.dk>2023-12-19 02:25:14 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2023-12-31 10:57:42 -0800
commit9c334eb9ce886247567573074b13c5ac29d1a41a (patch)
tree2528354c28d955a023dcc2a8f25fc2cde798b2e2
parent453f5db0619e2ad64076aab16ff5a00e0f7c53a2 (diff)
get_maintainer: correctly parse UTF-8 encoded names in files
While the script correctly extracts UTF-8 encoded names from the MAINTAINERS file, the regular expressions damage my name when parsing from .yaml files. Fix this by replacing the Latin-1-compatible regular expressions with the unicode property matcher \p{L}, which matches on any letter according to the Unicode General Category of letters. The proposed solution only works if the script uses proper string encoding from the outset, so instruct Perl to unconditionally open all files with UTF-8 encoding. This should be safe, as the entire source tree is either UTF-8 or ASCII encoded anyway. See [1] for a detailed analysis. Furthermore, to prevent the \w expression from matching non-ASCII when checking for whether a name should be escaped with quotes, add the /a flag to the regular expression. The escaping logic was duplicated in two places, so it has been factored out into its own function. The original issue was also identified on the tools mailing list [2]. This should solve the observed side effects there as well. Link: https://lore.kernel.org/all/dzn6uco4c45oaa3ia4u37uo5mlt33obecv7gghj2l756fr4hdh@mt3cprft3tmq/ [1] Link: https://lore.kernel.org/tools/20230726-gush-slouching-a5cd41@meerkat/ [2] Signed-off-by: Alvin Šipraga <alsi@bang-olufsen.dk> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rwxr-xr-xscripts/get_maintainer.pl30
1 files changed, 17 insertions, 13 deletions
diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl
index 16d8ac6005b6..dac38c6e3b1c 100755
--- a/scripts/get_maintainer.pl
+++ b/scripts/get_maintainer.pl
@@ -20,6 +20,7 @@ use Getopt::Long qw(:config no_auto_abbrev);
use Cwd;
use File::Find;
use File::Spec::Functions;
+use open qw(:std :encoding(UTF-8));
my $cur_path = fastgetcwd() . '/';
my $lk_path = "./";
@@ -445,7 +446,7 @@ sub maintainers_in_file {
my $text = do { local($/) ; <$f> };
close($f);
- my @poss_addr = $text =~ m$[A-Za-zÀ-ÿ\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g;
+ my @poss_addr = $text =~ m$[\p{L}\"\' \,\.\+-]*\s*[\,]*\s*[\(\<\{]{0,1}[A-Za-z0-9_\.\+-]+\@[A-Za-z0-9\.-]+\.[A-Za-z0-9]+[\)\>\}]{0,1}$g;
push(@file_emails, clean_file_emails(@poss_addr));
}
}
@@ -1152,6 +1153,17 @@ sub top_of_kernel_tree {
return 0;
}
+sub escape_name {
+ my ($name) = @_;
+
+ if ($name =~ /[^\w \-]/ai) { ##has "must quote" chars
+ $name =~ s/(?<!\\)"/\\"/g; ##escape quotes
+ $name = "\"$name\"";
+ }
+
+ return $name;
+}
+
sub parse_email {
my ($formatted_email) = @_;
@@ -1169,13 +1181,9 @@ sub parse_email {
$name =~ s/^\s+|\s+$//g;
$name =~ s/^\"|\"$//g;
+ $name = escape_name($name);
$address =~ s/^\s+|\s+$//g;
- if ($name =~ /[^\w \-]/i) { ##has "must quote" chars
- $name =~ s/(?<!\\)"/\\"/g; ##escape quotes
- $name = "\"$name\"";
- }
-
return ($name, $address);
}
@@ -1186,13 +1194,9 @@ sub format_email {
$name =~ s/^\s+|\s+$//g;
$name =~ s/^\"|\"$//g;
+ $name = escape_name($name);
$address =~ s/^\s+|\s+$//g;
- if ($name =~ /[^\w \-]/i) { ##has "must quote" chars
- $name =~ s/(?<!\\)"/\\"/g; ##escape quotes
- $name = "\"$name\"";
- }
-
if ($usename) {
if ("$name" eq "") {
$formatted_email = "$address";
@@ -2462,13 +2466,13 @@ sub clean_file_emails {
$name = "";
}
- my @nw = split(/[^A-Za-zÀ-ÿ\'\,\.\+-]/, $name);
+ my @nw = split(/[^\p{L}\'\,\.\+-]/, $name);
if (@nw > 2) {
my $first = $nw[@nw - 3];
my $middle = $nw[@nw - 2];
my $last = $nw[@nw - 1];
- if (((length($first) == 1 && $first =~ m/[A-Za-z]/) ||
+ if (((length($first) == 1 && $first =~ m/\p{L}/) ||
(length($first) == 2 && substr($first, -1) eq ".")) ||
(length($middle) == 1 ||
(length($middle) == 2 && substr($middle, -1) eq "."))) {