update copyrights for 2021

[public-inbox.git] / lib / PublicInbox / LeiStore.pm

diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm
index a17c7bab423d26c90055a54fe6b0fa0731707bdc..a23efed55198e96c4ac5446c7681af235b58781c 100644 (file)
--- a/lib/PublicInbox/LeiStore.pm
+++ b/lib/PublicInbox/LeiStore.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Local storage (cache/memo) for lei(1), suitable for personal/private
@@ -9,14 +9,14 @@
 package PublicInbox::LeiStore;
 use strict;
 use v5.10.1;
-use parent qw(PublicInbox::Lock);
+use parent qw(PublicInbox::Lock PublicInbox::IPC);
 use PublicInbox::SearchIdx qw(crlf_adjust);
 use PublicInbox::ExtSearchIdx;
 use PublicInbox::Import;
 use PublicInbox::InboxWritable;
 use PublicInbox::V2Writable;
-use PublicInbox::ContentHash qw(content_hash);
-use PublicInbox::MID qw(mids);
+use PublicInbox::ContentHash qw(content_hash content_digest);
+use PublicInbox::MID qw(mids mids_in);
 use PublicInbox::LeiSearch;
 use List::Util qw(max);
 
@@ -60,24 +60,6 @@ sub git_ident ($) {
                ('lei user', 'x@example.com')
 }
 
-# We will support users combining storage across multiple machines
-# somehow.  Use per-machine refnames to make it easy-to-identify
-# where a message came from
-sub host_head () {
-       state $h = do {
-               my $x = PublicInbox::ExtSearchIdx::host_ident;
-               # Similar rules found in git.git/remote.c::valid_remote_nick
-               # and git.git/refs.c::check_refname_component
-               $x =~ s!(?:\.lock|/)+\z!!gs; # must not end with ".lock" or "/"
-               $x =~ tr/././s; # no dot-dot, collapse them
-               $x =~ s/@\{/\@-/gs;
-               $x =~ s/\A\./-/s;
-               # no "*", ":", "?", "[", "\", "^", "~", SP, TAB; "]" is OK
-               $x =~ tr^a-zA-Z0-9!"#$%&'()+,\-.;<=>@]_`{|}^-^c;
-               $x
-       };
-}
-
 sub importer {
        my ($self) = @_;
        my $max;
@@ -96,7 +78,7 @@ sub importer {
        while (1) {
                my $latest = "$pfx/$max.git";
                my $old = -e $latest;
-               PublicInbox::Import::init_bare($latest, host_head);
+               PublicInbox::Import::init_bare($latest);
                my $git = PublicInbox::Git->new($latest);
                $git->qx(qw(config core.sharedRepository 0600)) if !$old;
                my $packed_bytes = $git->packed_bytes;
@@ -110,7 +92,6 @@ sub importer {
                $im->{bytes_added} = int($packed_bytes / $self->packing_factor);
                $im->{lock_path} = undef;
                $im->{path_type} = 'v2';
-               $im->{'ref'} = host_head;
                return $im;
        }
 }
@@ -126,14 +107,26 @@ sub eidx_init {
        $eidx;
 }
 
+# when a message has no Message-IDs at all, this is needed for
+# unsent Draft messages, at least
+sub _fake_mid_for ($$) {
+       my ($eml, $dig) = @_;
+       my $mids = mids_in($eml, qw(X-Alt-Message-ID Resent-Message-ID));
+       $eml->{-lei_fake_mid} =
+               $mids->[0] // PublicInbox::Import::digest2mid($dig, $eml);
+}
+
 sub _docids_for ($$) {
        my ($self, $eml) = @_;
        my %docids;
-       my $chash = content_hash($eml);
+       my $dig = content_digest($eml);
+       my $chash = $dig->clone->digest;
        my $eidx = eidx_init($self);
        my $oidx = $eidx->{oidx};
        my $im = $self->{im};
-       for my $mid (@{mids($eml)}) {
+       my $mids = mids($eml);
+       $mids->[0] //= _fake_mid_for($eml, $dig);
+       for my $mid (@$mids) {
                my ($id, $prev);
                while (my $cur = $oidx->next_by_mid($mid, \$id, \$prev)) {
                        my $oid = $cur->{blob};
@@ -218,6 +211,7 @@ sub add_eml {
                        $idx->shard_add_eidx_info($docid, '.', $eml); # List-Id
                        $idx->shard_add_keywords($docid, @kw) if @kw;
                }
+               \@docids;
        } else {
                $smsg->{num} = $oidx->adj_counter('eidx_docid', '+');
                $oidx->add_overview($eml, $smsg);
@@ -225,8 +219,13 @@ sub add_eml {
                my $idx = $eidx->idx_shard($smsg->{num});
                $idx->index_raw($msgref, $eml, $smsg);
                $idx->shard_add_keywords($smsg->{num}, @kw) if @kw;
+               $smsg;
        }
-       $smsg->{blob}
+}
+
+sub set_eml {
+       my ($self, $eml, @kw) = @_;
+       add_eml($self, $eml, @kw) // set_eml_keywords($self, $eml, @kw);
 }
 
 sub done {