lei_search: try harder to associate "lei index"-ed messages

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

diff --git a/lib/PublicInbox/LeiSearch.pm b/lib/PublicInbox/LeiSearch.pm
index d0963e928c6500402f8560f6e89515ce957d3f95..1fb38da1d7aaac22d7f9475cb342a4cdb4e0b3e4 100644 (file)
--- a/lib/PublicInbox/LeiSearch.pm
+++ b/lib/PublicInbox/LeiSearch.pm
@@ -5,30 +5,20 @@
 package PublicInbox::LeiSearch;
 use strict;
 use v5.10.1;
-use parent qw(PublicInbox::ExtSearch);
+use parent qw(PublicInbox::ExtSearch); # PublicInbox::Search->reopen
 use PublicInbox::Search qw(xap_terms);
-use PublicInbox::ContentHash qw(content_digest content_hash);
+use PublicInbox::ContentHash qw(content_digest content_hash git_sha);
 use PublicInbox::MID qw(mids mids_for_index);
-
-# get combined docid from over.num:
-# (not generic Xapian, only works with our sharding scheme)
-sub num2docid ($$) {
-       my ($self, $num) = @_;
-       my $nshard = $self->{nshard};
-       ($num - 1) * $nshard + $num % $nshard + 1;
-}
+use Carp qw(croak);
 
 sub _msg_kw { # retry_reopen callback
-       my ($self, $num) = @_; # num_or_mitem
-       my $xdb = $self->xdb; # set {nshard};
-       my $docid = ref($num) ? $num->get_docid : num2docid($self, $num);
-       my $kw = xap_terms('K', $xdb, $docid);
-       warn "E: #$docid ($num): $@\n" if $@;
-       wantarray ? sort(keys(%$kw)) : $kw;
+       my ($self, $num) = @_;
+       my $xdb = $self->xdb; # set {nshard} for num2docid;
+       xap_terms('K', $xdb, $self->num2docid($num));
 }
 
-sub msg_keywords {
-       my ($self, $num) = @_; # num_or_mitem
+sub msg_keywords { # array or hashref
+       my ($self, $num) = @_;
        $self->retry_reopen(\&_msg_kw, $num);
 }
 
@@ -37,7 +27,7 @@ sub _oid_kw { # retry_reopen callback
        my $xdb = $self->xdb; # set {nshard};
        my %kw;
        for my $num (@$nums) { # there should only be one...
-               my $doc = $xdb->get_document(num2docid($self, $num));
+               my $doc = $xdb->get_document($self->num2docid($num));
                my $x = xap_terms('K', $doc);
                %kw = (%kw, %$x);
        }
@@ -45,9 +35,9 @@ sub _oid_kw { # retry_reopen callback
 }
 
 # returns undef if blob is unknown
-sub oid_keywords {
-       my ($self, $oidhex) = @_;
-       my @num = $self->over->blob_exists($oidhex) or return;
+sub oidbin_keywords {
+       my ($self, $oidbin) = @_;
+       my @num = $self->over->oidbin_exists($oidbin) or return;
        $self->retry_reopen(\&_oid_kw, \@num);
 }
 
@@ -58,7 +48,7 @@ sub _xsmsg_vmd { # retry_reopen
        $kw{flagged} = 1 if delete($smsg->{lei_q_tt_flagged});
        my @num = $self->over->blob_exists($smsg->{blob});
        for my $num (@num) { # there should only be one...
-               $doc = $xdb->get_document(num2docid($self, $num));
+               $doc = $xdb->get_document($self->num2docid($num));
                $x = xap_terms('K', $doc);
                %kw = (%kw, %$x);
                if ($want_label) { # JSON/JMAP only
@@ -74,7 +64,8 @@ sub _xsmsg_vmd { # retry_reopen
 sub xsmsg_vmd {
        my ($self, $smsg, $want_label) = @_;
        return if $smsg->{kw}; # already set by LeiXSearch->mitem_kw
-       $self->retry_reopen(\&_xsmsg_vmd, $smsg, $want_label);
+       eval { $self->retry_reopen(\&_xsmsg_vmd, $smsg, $want_label) };
+       warn "$$ $0 (nshard=$self->{nshard}) $smsg->{blob}: $@" if $@;
 }
 
 # when a message has no Message-IDs at all, this is needed for
@@ -120,26 +111,43 @@ sub xoids_for {
                                $git->cat_async($cur->{blob}, \&_cmp_1st,
                                                [$chash, $xoids, $cur, $lms]);
                                if ($min && scalar(keys %$xoids) >= $min) {
-                                       $git->cat_async_wait;
+                                       $git->async_wait_all;
                                        return $xoids;
                                }
                        }
                }
        }
-       $git->cat_async_wait;
+       $git->async_wait_all;
+
+       # it could be an 'lei index'-ed file that just got renamed
+       if (scalar(keys %$xoids) < ($min // 1) && defined($self->{topdir})) {
+               my $hex = git_sha(1, $eml)->hexdigest;
+               my @n = $overs[0]->blob_exists($hex);
+               for (@n) { $xoids->{$hex} //= $_ }
+       }
        scalar(keys %$xoids) ? $xoids : undef;
 }
 
 # returns true if $eml is indexed by lei/store and keywords don't match
 sub kw_changed {
        my ($self, $eml, $new_kw_sorted, $docids) = @_;
+       my $cur_kw;
        if ($eml) {
                my $xoids = xoids_for($self, $eml) // return;
                $docids //= [];
                @$docids = sort { $a <=> $b } values %$xoids;
+               if (!@$docids && $self->over) {
+                       my $bin = git_sha(1, $eml)->digest;
+                       @$docids = $self->over->oidbin_exists($bin);
+               }
+       }
+       for my $id (@$docids) {
+               $cur_kw = eval { msg_keywords($self, $id) } and last;
+       }
+       if (!defined($cur_kw) && $@) {
+               $docids = join(', num:', @$docids);
+               croak "E: num:$docids keyword lookup failure: $@";
        }
-       my $cur_kw = msg_keywords($self, $docids->[0]);
-
        # RFC 5550 sec 5.9 on the $Forwarded keyword states:
        # "Once set, the flag SHOULD NOT be cleared"
        if (exists($cur_kw->{forwarded}) &&