From 3fc59df0d633a17e0c5e43d633d12e8772c06ec3 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Tue, 10 Jan 2017 21:40:37 +0000
Subject: introduce PublicInbox::MIME wrapper class

This should fix problems with multipart messages where
text/plain parts lack a header.

cf. git clone --mirror https://github.com/rjbs/Email-MIME.git
    refs/pull/28/head

In the future, we may still introduce as streaming
interface to reduce memory usage on large emails.
---
 script/public-inbox-learn | 4 ++--
 script/public-inbox-mda   | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'script')

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index 396ab489..a696d348 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -10,7 +10,7 @@ use warnings;
 use PublicInbox::Config;
 use PublicInbox::Git;
 use PublicInbox::Import;
-use Email::MIME;
+use PublicInbox::MIME;
 use Email::MIME::ContentType;
 $Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
 use PublicInbox::Address;
@@ -23,7 +23,7 @@ if ($train !~ /\A(?:ham|spam)\z/) {
 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 <STDIN>;
 	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
diff --git a/script/public-inbox-mda b/script/public-inbox-mda
index 8b5258f5..60f817dc 100755
--- a/script/public-inbox-mda
+++ b/script/public-inbox-mda
@@ -52,7 +52,7 @@ $simple = undef;
 $emm = PublicInbox::Emergency->new($emergency);
 $emm->prepare(\$str);
 $ems = $ems->abort;
-my $mime = Email::MIME->new(\$str);
+my $mime = PublicInbox::MIME->new(\$str);
 $str = '';
 do_exit(0) unless $spam_ok;
 
-- 
cgit v1.2.3-24-ge0c7


From 24d417a8943d6ddac8f903731918c97d0f034c5b Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Thu, 19 Jan 2017 00:31:30 +0000
Subject: learn: implement "rm" only functionality

Do not consider this interface stable, but I just needed a
way to remove mis-imported multipart messages so
public-inbox-watch could pick them up again from my Maildir.
---
 script/public-inbox-learn | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

(limited to 'script')

diff --git a/script/public-inbox-learn b/script/public-inbox-learn
index a696d348..38c83243 100755
--- a/script/public-inbox-learn
+++ b/script/public-inbox-learn
@@ -16,7 +16,7 @@ $Email::MIME::ContentType::STRICT_PARAMS = 0; # user input is imperfect
 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";
 }
 
@@ -27,15 +27,18 @@ my $mime = PublicInbox::MIME->new(eval {
 	local $/;
 	my $data = scalar <STDIN>;
 	$data =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
-	eval {
-		if ($train eq 'ham') {
-			$spamc->hamlearn(\$data);
-		} else {
-			$spamc->spamlearn(\$data);
-		}
-		die "spamc failed with: $?\n" if $?;
-	};
-	$err = $@;
+
+	if ($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
 });
 
@@ -61,7 +64,7 @@ foreach my $recipient (keys %dests) {
 	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
-- 
cgit v1.2.3-24-ge0c7