update copyrights for 2021

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

diff --git a/lib/PublicInbox/MiscIdx.pm b/lib/PublicInbox/MiscIdx.pm
index acb49ce79acf041f43f76f050a07572d634e6c1b..ab5e029a4625c6b77f16c9166de1d0e9afacbf3b 100644 (file)
--- a/lib/PublicInbox/MiscIdx.pm
+++ b/lib/PublicInbox/MiscIdx.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>
 
 # like PublicInbox::SearchIdx, but for searching for non-mail messages.
@@ -21,6 +21,7 @@ use Carp qw(croak);
 use File::Path ();
 use PublicInbox::MiscSearch;
 use PublicInbox::Config;
+my $json;
 
 sub new {
        my ($class, $eidx) = @_;
@@ -30,6 +31,7 @@ sub new {
        nodatacow_dir($mi_dir);
        my $flags = $PublicInbox::SearchIdx::DB_CREATE_OR_OPEN;
        $flags |= $PublicInbox::SearchIdx::DB_NO_SYNC if $eidx->{-no_fsync};
+       $json //= PublicInbox::Config::json();
        bless {
                mi_dir => $mi_dir,
                flags => $flags,
@@ -53,6 +55,22 @@ sub commit_txn {
        delete($self->{xdb})->commit_transaction;
 }
 
+sub remove_eidx_key {
+       my ($self, $eidx_key) = @_;
+       my $xdb = $self->{xdb};
+       my $head = $xdb->postlist_begin('Q'.$eidx_key);
+       my $tail = $xdb->postlist_end('Q'.$eidx_key);
+       my @docids; # only one, unless we had bugs
+       for (; $head != $tail; $head++) {
+               push @docids, $head->get_docid;
+       }
+       for my $docid (@docids) {
+               $xdb->delete_document($docid);
+               warn "I: remove inbox docid #$docid ($eidx_key)\n";
+       }
+}
+
+# adds or updates according to $eidx_key
 sub index_ibx {
        my ($self, $ibx) = @_;
        my $eidx_key = $ibx->eidx_key;
@@ -75,17 +93,27 @@ EOF
        $xdb->delete_document($_) for @drop; # just in case
 
        my $doc = $PublicInbox::Search::X{Document}->new;
+       term_generator($self)->set_document($doc);
 
-       # allow sorting by modified
+       # allow sorting by modified and uidvalidity (created at)
        add_val($doc, $PublicInbox::MiscSearch::MODIFIED, $ibx->modified);
+       add_val($doc, $PublicInbox::MiscSearch::UIDVALIDITY, $ibx->uidvalidity);
 
-       $doc->add_boolean_term('Q'.$eidx_key);
-       $doc->add_boolean_term('T'.'inbox');
-       term_generator($self)->set_document($doc);
+       $doc->add_boolean_term('Q'.$eidx_key); # uniQue id
+       $doc->add_boolean_term('T'.'inbox'); # Type
+
+       if (defined($ibx->{newsgroup}) && $ibx->nntp_usable) {
+               $doc->add_boolean_term('T'.'newsgroup'); # additional Type
+       }
+
+       # force reread from disk, {description} could be loaded from {misc}
+       delete $ibx->{description};
+       my $desc = $ibx->description;
 
        # description = S/Subject (or title)
        # address = A/Author
-       index_text($self, $ibx->description, 1, 'S');
+       index_text($self, $desc, 1, 'S');
+       index_text($self, $ibx->{name}, 1, 'XNAME');
        my %map = (
                address => 'A',
                listid => 'XLISTID',
@@ -97,22 +125,22 @@ EOF
                        index_text($self, $v, 1, $pfx);
                }
        }
-       index_text($self, $ibx->{name}, 1, 'XNAME');
        my $data = {};
        if (defined(my $max = $ibx->max_git_epoch)) { # v2
-               my $desc = $ibx->description;
                my $pfx = "/$ibx->{name}/git/";
                for my $epoch (0..$max) {
                        my $git = $ibx->git_epoch($epoch) or return;
                        if (my $ent = $git->manifest_entry($epoch, $desc)) {
                                $data->{"$pfx$epoch.git"} = $ent;
+                               $ent->{git_dir} = $git->{git_dir};
                        }
                        $git->cleanup; # ->modified starts cat-file --batch
                }
        } elsif (my $ent = $ibx->git->manifest_entry) { # v1
+               $ent->{git_dir} = $ibx->{inboxdir};
                $data->{"/$ibx->{name}"} = $ent;
        }
-       $doc->set_data(PublicInbox::Config::json()->encode($data));
+       $doc->set_data($json->encode($data));
        if (defined $docid) {
                $xdb->replace_document($docid, $doc);
        } else {