feed: optimize query for feeds, too

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

diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index b1ea8dc7bce215b06fe3f7a4715d53f7846c3b84..43cf15baaa0c2beddb0fe3108b61fd74a7c8af0b 100644 (file)
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -9,6 +9,7 @@ use PublicInbox::Git;
 use PublicInbox::MID qw(mid2path);
 use Devel::Peek qw(SvREFCNT);
 use PublicInbox::MIME;
+use POSIX qw(strftime);
 
 my $cleanup_timer;
 eval {
@@ -82,6 +83,18 @@ sub new {
        bless $opts, $class;
 }
 
+sub git_part {
+       my ($self, $part) = @_;
+       ($self->{version} || 1) == 2 or return;
+       $self->{"$part.git"} ||= eval {
+               my $git_dir = "$self->{mainrepo}/git/$part.git";
+               my $g = PublicInbox::Git->new($git_dir);
+               $g->{-httpbackend_limiter} = $self->{-httpbackend_limiter};
+               # no cleanup needed, we never cat-file off this, only clone
+               $g;
+       };
+}
+
 sub git {
        my ($self) = @_;
        $self->{git} ||= eval {
@@ -94,9 +107,33 @@ sub git {
        };
 }
 
+sub max_git_part {
+       my ($self) = @_;
+       my $v = $self->{version};
+       return unless defined($v) && $v == 2;
+       my $part = $self->{-max_git_part};
+       my $changed = git($self)->alternates_changed;
+       if (!defined($part) || $changed) {
+               $self->git->cleanup if $changed;
+               my $gits = "$self->{mainrepo}/git";
+               if (opendir my $dh, $gits) {
+                       my $max = -1;
+                       while (defined(my $git_dir = readdir($dh))) {
+                               $git_dir =~ m!\A(\d+)\.git\z! or next;
+                               $max = $1 if $1 > $max;
+                       }
+                       $part = $self->{-max_git_part} = $max if $max >= 0;
+               } else {
+                       warn "opendir $gits failed: $!\n";
+               }
+       }
+       $part;
+}
+
 sub mm {
        my ($self) = @_;
        $self->{mm} ||= eval {
+               require PublicInbox::Msgmap;
                _cleanup_later($self);
                my $dir = $self->{mainrepo};
                if (($self->{version} || 1) >= 2) {
@@ -133,7 +170,7 @@ sub description {
        local $/ = "\n";
        chomp $desc;
        $desc =~ s/\s+/ /smg;
-       $desc = '($GIT_DIR/description missing)' if $desc eq '';
+       $desc = '($REPO_DIR/description missing)' if $desc eq '';
        $self->{description} = $desc;
 }
 
@@ -235,12 +272,10 @@ sub msg_by_path ($$;$) {
 sub msg_by_smsg ($$;$) {
        my ($self, $smsg, $ref) = @_;
 
-       return unless defined $smsg; # ghost
-
-       # backwards compat to fallback to msg_by_mid
-       # TODO: remove if we bump SCHEMA_VERSION in Search.pm:
-       defined(my $blob = $smsg->{blob}) or
-                       return msg_by_path($self, mid2path($smsg->mid), $ref);
+       # ghosts may have undef smsg (from SearchThread.node) or
+       # no {blob} field (from each_smsg_by_mid)
+       return unless defined $smsg;
+       defined(my $blob = $smsg->{blob}) or return;
 
        my $str = git($self)->cat_file($blob, $ref);
        $$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s if $str;
@@ -260,15 +295,44 @@ sub path_check {
        git($self)->check('HEAD:'.$path);
 }
 
+sub mid2num($$) {
+       my ($self, $mid) = @_;
+       my $mm = mm($self) or return;
+       $mm->num_for($mid);
+}
+
+sub smsg_by_mid ($$) {
+       my ($self, $mid) = @_;
+       my $srch = search($self) or return;
+       # favor the Message-ID we used for the NNTP article number:
+       my $num = mid2num($self, $mid);
+       defined $num ? $srch->lookup_article($num) : undef;
+}
+
 sub msg_by_mid ($$;$) {
        my ($self, $mid, $ref) = @_;
        my $srch = search($self) or
-                       return msg_by_path($self, mid2path($mid), $ref);
-       my $smsg;
-       $srch->retry_reopen(sub {
-               $smsg = $srch->lookup_skeleton($mid) and $smsg->load_expand;
-       });
+               return msg_by_path($self, mid2path($mid), $ref);
+       my $smsg = smsg_by_mid($self, $mid);
        $smsg ? msg_by_smsg($self, $smsg, $ref) : undef;
 }
 
+sub recent {
+       my ($self, $opts) = @_;
+       my $qs = '';
+       my $srch = search($self);
+       if (!$opts->{offset}) {
+               # this complicated bit cuts /$INBOX/ loading time by
+               # over 400ms on my system:
+               my ($min, $max) = mm($self)->minmax;
+               my $n = $max - $opts->{limit};
+               $n = $min if $n < $min;
+               for (; $qs eq '' && $n >= $min; --$n) {
+                       my $smsg = $srch->lookup_article($n) or next;
+                       $qs = strftime('d:%Y%m%d..', gmtime($smsg->ts));
+               }
+       }
+       $srch->query($qs, $opts);
+}
+
 1;