badwords: rework exceptions, fix many of them

Also:
- support per-directory and per-upper-directory whitelist entries.
- convert badlist input grep tweak into the above format.
  (except for 'And' which had just a few hits.)
- fix many code exceptions, but do not enforce.
  (there also remain about 350 'will' uses in lib)
- fix badwords in example code, drop exceptions.
- badwords-all: convert to Perl.
  To make it usable from CMake.
- FAQ: reword to not use 'will'. Drop exception.

Closes #20886
This commit is contained in:
Viktor Szakats 2026-03-11 10:17:10 +01:00
parent 11c14b5ca5
commit 435eabeac8
No known key found for this signature in database
89 changed files with 367 additions and 344 deletions

View file

@ -17,6 +17,8 @@
use strict;
use warnings;
use File::Basename;
my @whitelist = (
# ignore what looks like URLs
'(^|\W)((https|http|ftp):\/\/[a-z0-9\-._~%:\/?\#\[\]\@!\$&\'\(\)*+,;=]+)',
@ -99,16 +101,32 @@ sub highlight {
my ($p, $w, $in, $f, $l, $lookup) = @_;
my $c = length($p)+1;
my $ch = "$f:$l:$w";
my $ch;
my $dir = dirname($f);
$ch = $dir . "/" . "::" . $w;
if($wl{$ch}) {
# whitelisted filename + line + word
# whitelisted dirname + word
return;
}
my $updir = dirname($dir);
if($dir ne $updir) {
$ch = $updir . "/" . "::" . $w;
if($wl{$ch}) {
# whitelisted upper dirname + word
return;
}
}
$ch = $f . "::" . $w;
if($wl{$ch}) {
# whitelisted filename + word
return;
}
$ch = "$f:$l:$w";
if($wl{$ch}) {
# whitelisted filename + line + word
return;
}
print STDERR "$f:$l:$c: error: found bad word \"$w\"\n";
printf STDERR " %4d | %s\n", $l, $in;