Merge branch 'learn'

* learn:
  doc: add public-inbox-learn(1) manpage
  mda: support multiple List-ID matches
  mda: prepare for multiple destinations
  inboxwritable: add assert_usable_dir sub
  mda: skip MIME parsing if spam
  mda: hoist out mda_filter_adjust
  filter/base: remove MAX_MID_SIZE constant
  mda: hoist out List-ID handling and reuse in -learn
  learn: hoist out remove_or_add subroutine
  learn: GIT_COMMITTER_<NAME|EMAIL> may be "" or "0"
  learn: update usage statement
  learn: only map recipient list on "ham" or "rm"
  learn: support multiple To/Cc headers

4 files changed, 31 insertions, 5 deletions

diff --git a/lib/PublicInbox/Filter/Base.pm b/lib/PublicInbox/Filter/Base.pm
index 052cd332..7a0c720f 100644
--- a/lib/PublicInbox/Filter/Base.pm
+++ b/lib/PublicInbox/Filter/Base.pm
@@ -6,7 +6,6 @@ package PublicInbox::Filter::Base;
 use strict;
 use warnings;
 use PublicInbox::MsgIter;
-use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
 
 sub No ($) { "*** We only accept plain-text mail, No $_[0] ***" }
 
diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index ab7b0ed5..9eab394d 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -30,12 +30,19 @@ sub new {
         $self;
 }
 
+sub assert_usable_dir {
+        my ($self) = @_;
+        my $dir = $self->{inboxdir};
+        return $dir if defined($dir) && $dir ne '';
+        die "no inboxdir defined for $self->{name}\n";
+}
+
 sub init_inbox {
         my ($self, $shards, $skip_epoch, $skip_artnum) = @_;
         # TODO: honor skip_artnum
         my $v = $self->{version} || 1;
         if ($v == 1) {
-                my $dir = $self->{inboxdir} or die "no inboxdir in inbox\n";
+                my $dir = assert_usable_dir($self);
                 PublicInbox::Import::init_bare($dir);
         } else {
                 my $v2w = importer($self);
diff --git a/lib/PublicInbox/MDA.pm b/lib/PublicInbox/MDA.pm
index 9cafda13..b0dfac45 100644
--- a/lib/PublicInbox/MDA.pm
+++ b/lib/PublicInbox/MDA.pm
@@ -83,4 +83,25 @@ sub set_list_headers {
         }
 }
 
+sub inboxes_for_list_id ($$) {
+        my ($klass, $config, $simple) = @_;
+
+        # newer Email::Simple allows header_raw, as does Email::MIME:
+        my @list_ids = $simple->can('header_raw') ?
+                        $simple->header_raw('List-Id') :
+                        $simple->header('List-Id');
+        my @dests;
+        for my $list_id (@list_ids) {
+                $list_id =~ /<[ \t]*(.+)?[ \t]*>/ or next;
+                if (my $ibx = $config->lookup_list_id($1)) {
+                        push @dests, $ibx;
+                }
+        }
+        if (scalar(@list_ids) > 1) {
+                warn "W: multiple List-IDs in message:\n";
+                warn "W: List-ID: $_\n" for @list_ids
+        }
+        \@dests;
+}
+
 1;
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index ad2e8e62..1825da2c 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -77,7 +77,8 @@ sub new {
         # $creat may be any true value, or 0/undef.  A hashref is true,
         # and $creat->{nproc} may be set to an integer
         my ($class, $v2ibx, $creat) = @_;
-        my $dir = $v2ibx->{inboxdir} or die "no inboxdir in inbox\n";
+        $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
+        my $dir = $v2ibx->assert_usable_dir;
         unless (-d $dir) {
                 if ($creat) {
                         require File::Path;
@@ -86,8 +87,6 @@ sub new {
                         die "$dir does not exist\n";
                 }
         }
-
-        $v2ibx = PublicInbox::InboxWritable->new($v2ibx);
         $v2ibx->umask_prepare;
 
         my $xpfx = "$dir/xap" . PublicInbox::Search::SCHEMA_VERSION;