X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=c51f95856a137d7f0f4dac7c855e3cf741a732cd;hb=69329215485cf2ab9d8cd1fa7faf65d8ec42dc0b;hp=7ef2a312744c97f89de32a74ee8df4867a1ee142;hpb=c515264dd69156fc89c59685f788b1093afb8731;p=public-inbox.git
diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 7ef2a312..c51f9585 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,6 +1,6 @@
#!/usr/bin/perl -w
-# Copyright (C) 2014-2015 all contributors
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2018 all contributors
+# License: AGPL-3.0+
#
# Used for training spam (via SpamAssassin) and removing messages from a
# public-inbox
@@ -10,32 +10,33 @@ use warnings;
use PublicInbox::Config;
use PublicInbox::Git;
use PublicInbox::Import;
-use Email::MIME;
-use Email::MIME::ContentType;
-$Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
+use PublicInbox::MIME;
use PublicInbox::Address;
use PublicInbox::Spamcheck::Spamc;
my $train = shift or die "usage: $usage\n";
-if ($train !~ /\A(?:ham|spam)\z/) {
+if ($train !~ /\A(?:ham|spam|rm)\z/) {
die "`$train' not recognized.\nusage: $usage\n";
}
my $spamc = PublicInbox::Spamcheck::Spamc->new;
my $pi_config = PublicInbox::Config->new;
my $err;
-my $mime = Email::MIME->new(eval {
+my $mime = PublicInbox::MIME->new(eval {
local $/;
my $data = scalar ;
- $data =~ s/\AFrom [^\r\n]*\r?\n//s;
- eval {
- if ($train eq 'ham') {
- $spamc->hamlearn(\$data);
- } else {
- $spamc->spamlearn(\$data);
- }
- die "spamc failed with: $?\n" if $?;
- };
- $err = $@;
+ $data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+
+ if ($train ne 'rm') {
+ eval {
+ if ($train eq 'ham') {
+ $spamc->hamlearn(\$data);
+ } elsif ($train eq 'spam') {
+ $spamc->spamlearn(\$data);
+ }
+ die "spamc failed with: $?\n" if $?;
+ };
+ $err = $@;
+ }
$data
});
@@ -48,6 +49,18 @@ foreach my $h (qw(Cc To)) {
}
}
+if ($train eq 'spam') {
+ $pi_config->each_inbox(sub {
+ my ($ibx) = @_;
+ my $git = $ibx->git;
+ my $name = $ibx->{name};
+ my $addr = $ibx->{-primary_address};
+ my $im = PublicInbox::Import->new($git, $name, $addr, $ibx);
+ $im->remove($mime, 'spam');
+ $im->done;
+ });
+}
+
require PublicInbox::MDA if $train eq "ham";
# n.b. message may be cross-posted to multiple public-inboxes
@@ -57,16 +70,16 @@ foreach my $recipient (keys %dests) {
my $git = PublicInbox::Git->new($git_dir);
# We do not touch GIT_COMMITTER_* env here so we can track
# who trained the message.
- my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{inbox};
+ my $name = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
my $email = $ENV{GIT_COMMITTER_EMAIL} || $recipient;
my $im = PublicInbox::Import->new($git, $name, $email);
- if ($train eq "spam") {
+ if ($train eq "spam" || $train eq "rm") {
# This needs to be idempotent, as my inotify trainer
# may train for each cross-posted message, and this
# script already learns for every list in
# ~/.public-inbox/config
- $im->remove($mime);
+ $im->remove($mime, $train);
} else { # $train eq "ham"
# no checking for spam here, we assume the message has
# been reviewed by a human at this point: