X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-learn;h=8b8e1b7732938bc8369813866fed9dad59ae6de6;hp=d2d665d580b5f4803d2afd66fd45b333b4c1a99b;hb=refs%2Fheads%2Fmaster;hpb=bc6b44cd7feee7e83ef1dcf26092808f92f757d9

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index d2d665d5..8b8e1b77 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -1,28 +1,45 @@
 #!/usr/bin/perl -w
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Used for training spam (via SpamAssassin) and removing messages from a
 # public-inbox
-my $usage = "$0 (spam|ham) < /path/to/message";
+my $help = <<EOF;
+usage: public-inbox-learn [OPTIONS] [spam|ham|rm] </path/to/RFC2822_message
+
+required action argument:
+
+   spam  unindex the message and train as spam
+     rm  remove the message without training as spam
+    ham  index the message (based on To:/Cc: headers) and train as ham
+
+options:
+
+  --all  scan all inboxes on `rm'
+
+See public-inbox-learn(1) man page for full documentation.
+EOF
 use strict;
-use warnings;
 use PublicInbox::Config;
 use PublicInbox::InboxWritable;
-use PublicInbox::MIME;
+use PublicInbox::Eml;
 use PublicInbox::Address;
 use PublicInbox::Spamcheck::Spamc;
-my $train = shift or die "usage: $usage\n";
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+my %opt = (all => 0);
+GetOptions(\%opt, qw(all help|h)) or die $help;
+
+my $train = shift or die $help;
 if ($train !~ /\A(?:ham|spam|rm)\z/) {
-	die "`$train' not recognized.\nusage: $usage\n";
+	die "`$train' not recognized.\n$help";
 }
+die "--all only works with `rm'\n" if $opt{all} && $train ne 'rm';
 
 my $spamc = PublicInbox::Spamcheck::Spamc->new;
-my $pi_config = PublicInbox::Config->new;
+my $pi_cfg = PublicInbox::Config->new;
 my $err;
-my $mime = PublicInbox::MIME->new(eval {
-	local $/;
-	my $data = scalar <STDIN>;
+my $mime = PublicInbox::Eml->new(do{
+	defined(my $data = do { local $/; <STDIN> }) or die "read STDIN: $!\n";
 	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
 
 	if ($train ne 'rm') {
@@ -36,56 +53,69 @@ my $mime = PublicInbox::MIME->new(eval {
 		};
 		$err = $@;
 	}
-	$data
+	\$data
 });
 
-# spam is removed from all known inboxes
-if ($train eq 'spam') {
-	$pi_config->each_inbox(sub {
+sub remove_or_add ($$$$) {
+	my ($ibx, $train, $mime, $addr) = @_;
+
+	# We do not touch GIT_COMMITTER_* env here so we can track
+	# who trained the message.
+	$ibx->{name} = $ENV{GIT_COMMITTER_NAME} // $ibx->{name};
+	$ibx->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} // $addr;
+	$ibx = PublicInbox::InboxWritable->new($ibx);
+	my $im = $ibx->importer(0);
+
+	if ($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, $train);
+	} elsif ($train eq "ham") {
+		# no checking for spam here, we assume the message has
+		# been reviewed by a human at this point:
+		PublicInbox::MDA->set_list_headers($mime, $ibx);
+
+		# Ham messages are trained when they're marked into
+		# a SEEN state, so this is idempotent:
+		$im->add($mime);
+	}
+	$im->done;
+}
+
+# spam is removed from all known inboxes since it is often Bcc:-ed
+if ($train eq 'spam' || ($train eq 'rm' && $opt{all})) {
+	$pi_cfg->each_inbox(sub {
 		my ($ibx) = @_;
 		$ibx = PublicInbox::InboxWritable->new($ibx);
 		my $im = $ibx->importer(0);
-		$im->remove($mime, 'spam');
+		$im->remove($mime, $train);
 		$im->done;
 	});
 } else {
-	require PublicInbox::MDA if $train eq "ham";
+	require PublicInbox::MDA;
 
 	# get all recipients
 	my %dests; # address => <PublicInbox::Inbox|0(false)>
 	for ($mime->header('Cc'), $mime->header('To')) {
 		foreach my $addr (PublicInbox::Address::emails($_)) {
 			$addr = lc($addr);
-			$dests{$addr} //= $pi_config->lookup($addr) // 0;
+			$dests{$addr} //= $pi_cfg->lookup($addr) // 0;
 		}
 	}
 
 	# n.b. message may be cross-posted to multiple public-inboxes
-	while (my ($addr, $dst) = each %dests) {
-		next unless ref($dst);
-		# We do not touch GIT_COMMITTER_* env here so we can track
-		# who trained the message.
-		$dst->{name} = $ENV{GIT_COMMITTER_NAME} || $dst->{name};
-		$dst->{-primary_address} = $ENV{GIT_COMMITTER_EMAIL} || $addr;
-		$dst = PublicInbox::InboxWritable->new($dst);
-		my $im = $dst->importer(0);
-
-		if ($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, $train);
-		} elsif ($train eq "ham") {
-			# no checking for spam here, we assume the message has
-			# been reviewed by a human at this point:
-			PublicInbox::MDA->set_list_headers($mime, $dst);
-
-			# Ham messages are trained when they're marked into
-			# a SEEN state, so this is idempotent:
-			$im->add($mime);
-		}
-		$im->done;
+	my %seen;
+	while (my ($addr, $ibx) = each %dests) {
+		next unless ref($ibx); # $ibx may be 0
+		next if $seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $addr);
+	}
+	my $dests = PublicInbox::MDA->inboxes_for_list_id($pi_cfg, $mime);
+	for my $ibx (@$dests) {
+		next if $seen{"$ibx"}++;
+		remove_or_add($ibx, $train, $mime, $ibx->{-primary_address});
 	}
 }