treewide: reduce load_xapian* callsites

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

diff --git a/lib/PublicInbox/LeiStore.pm b/lib/PublicInbox/LeiStore.pm
index 2745c56047faa65efc3c2e210f6e9893043d4809..a3decf5fe74e67be609320250718c9949808454f 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
@@ -15,8 +15,8 @@ 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);
 
@@ -24,10 +24,7 @@ sub new {
        my (undef, $dir, $opt) = @_;
        my $eidx = PublicInbox::ExtSearchIdx->new($dir, $opt);
        my $self = bless { priv_eidx => $eidx }, __PACKAGE__;
-       if ($opt->{creat}) {
-               PublicInbox::SearchIdx::load_xapian_writable();
-               eidx_init($self);
-       }
+       eidx_init($self) if $opt->{creat};
        $self;
 }
 
@@ -54,7 +51,9 @@ sub git_epoch_max  {
 
 sub git_ident ($) {
        my ($git) = @_;
-       chomp(my $i = $git->qx(qw(var GIT_COMMITTER_IDENT)));
+       open my $null, '>', '/dev/null' or die "open /dev/null: $!";
+       my $opt = { 2 => $null };
+       chomp(my $i = $git->qx(qw(var GIT_COMMITTER_IDENT), undef, $opt));
        warn "$git->{git_dir} GIT_COMMITTER_IDENT failed\n" if $?;
        $i =~ /\A(.+) <([^>]+)> [0-9]+ [-\+]?[0-9]+$/ ? ($1, $2) :
                ('lei user', 'x@example.com')
@@ -107,14 +106,26 @@ 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};
@@ -199,6 +210,7 @@ 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);
@@ -206,8 +218,13 @@ 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 {