GitHub/pbot
3
0
Fork 0
mirror of https://github.com/pragma-/pbot.git synced 2025-01-22 01:54:17 +01:00
Code Issues Projects Releases Wiki Activity

Plugin/UrlTitles: add logging to reveal why some URLs are disregarded

Browse Source
This commit is contained in:
Pragmatic Software 2023-06-13 23:19:21 -07:00
parent f3ad345340
commit bfa08ee8d6
2 changed files with 14 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
lib/PBot/Plugin/UrlTitles.pm
View File

@ -184,7 +184,10 @@ sub get_title($self, $context) {
# disregard one-word titles; these aren't usually interesting
# (and are usually already present in the URL itself)
return 0 if $title !~ /\s/;
if ($title !~ /\s/) {
$self->{pbot}->{logger}->log("Disregarding one-word title ($title)\n");
return 0;
}
# truncate long title
if (length $title > 400) {
@ -200,10 +203,16 @@ sub get_title($self, $context) {
my $length = (length $file > length $title) ? length $file : length $title;
# disregard title if 75%+ similiar to file
return 0 if $distance / $length < 0.75;
if ($distance / $length < 0.75) {
$self->{pbot}->{logger}->log("URL ($url) is 75% similar to title ($title), disregarding\n");
return 0;
}
# disregard ignored titles
return 0 if $self->is_ignored_title($title);
if ($self->is_ignored_title($title)) {
$self->{pbot}->{logger}->log("Disregarding ignored title\n");
return 0;
}
# send result back to parent
$context->{result} = $title;

4
lib/PBot/VERSION.pm
View File

@ -25,8 +25,8 @@ use PBot::Imports;
# These are set by the /misc/update_version script
use constant {
BUILD_NAME => "PBot",
BUILD_REVISION => 4678,
BUILD_DATE => "2023-05-21",
BUILD_REVISION => 4679,
BUILD_DATE => "2023-06-13",
};
sub initialize {}