Merge remote-tracking branch 'origin/master' into lorelei

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 07cca4e5bb30d9c2053d9bb8ab62788571f2289b..bc2e3ef40b0b3980fe8b7de4d8bdd572f276232c 100644 (file)
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -79,6 +79,11 @@ SELECT $id_col FROM $tbl WHERE $val_col = ? LIMIT 1
        }
 }
 
+sub ibx_id {
+       my ($self, $eidx_key) = @_;
+       id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+}
+
 sub sid {
        my ($self, $path) = @_;
        return unless defined $path && $path ne '';
@@ -170,8 +175,14 @@ sub _resolve_mid_to_tid {
                $$tid = $cur_tid;
        } else { # rethreading, queue up dead ghosts
                $$tid = next_tid($self);
-               my $num = $smsg->{num};
-               push(@{$self->{-ghosts_to_delete}}, $num) if $num < 0;
+               my $n = $smsg->{num};
+               if ($n > 0) {
+                       $self->{dbh}->prepare_cached(<<'')->execute($$tid, $n);
+UPDATE over SET tid = ? WHERE num = ?
+
+               } elsif ($n < 0) {
+                       push(@{$self->{-ghosts_to_delete}}, $n);
+               }
        }
        1;
 }
@@ -298,7 +309,7 @@ sub _add_over {
                }
        } elsif ($n < 0) { # ghost
                $$old_tid //= $cur_valid ? $cur_tid : next_tid($self);
-               link_refs($self, $refs, $$old_tid);
+               $$old_tid = link_refs($self, $refs, $$old_tid);
                delete_by_num($self, $n);
                $$v++;
        }
@@ -383,13 +394,12 @@ sub create_tables {
 
        $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS over (
-       num INTEGER NOT NULL, /* NNTP article number == IMAP UID */
+       num INTEGER PRIMARY KEY NOT NULL, /* NNTP article number == IMAP UID */
        tid INTEGER NOT NULL, /* THREADID (IMAP REFERENCES threading, JMAP) */
        sid INTEGER, /* Subject ID (IMAP ORDEREDSUBJECT "threading") */
        ts INTEGER, /* IMAP INTERNALDATE (Received: header, git commit time) */
        ds INTEGER, /* RFC-2822 sent Date: header, git author time */
-       ddd VARBINARY, /* doc-data-deflated (->to_doc_data, ->load_from_data) */
-       UNIQUE (num)
+       ddd VARBINARY /* doc-data-deflated (->to_doc_data, ->load_from_data) */
 )
 
        $dbh->do('CREATE INDEX IF NOT EXISTS idx_tid ON over (tid)');
@@ -463,10 +473,14 @@ sub dbh_close {
 
 sub create {
        my ($self) = @_;
-       unless (-r $self->{filename}) {
+       my $fn = $self->{filename} // do {
+               Carp::confess('BUG: no {filename}') unless $self->{dbh};
+               return;
+       };
+       unless (-r $fn) {
                require File::Path;
                require File::Basename;
-               File::Path::mkpath(File::Basename::dirname($self->{filename}));
+               File::Path::mkpath(File::Basename::dirname($fn));
        }
        # create the DB:
        PublicInbox::Over::dbh($self);
@@ -553,6 +567,15 @@ CREATE TABLE IF NOT EXISTS eidx_meta (
        val VARCHAR(255) NOT NULL
 )
 
+               # A queue of current docids which need reindexing.
+               # eidxq persists across aborted -extindex invocations
+               # Currently used for "-extindex --reindex" for Xapian
+               # data, but may be used in more places down the line.
+               $dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS eidxq (
+       docid INTEGER PRIMARY KEY NOT NULL
+)
+
                $dbh;
        };
 }
@@ -583,7 +606,7 @@ sub eidx_max {
 sub add_xref3 {
        my ($self, $docid, $xnum, $oidhex, $eidx_key) = @_;
        begin_lazy($self);
-       my $ibx_id = id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+       my $ibx_id = ibx_id($self, $eidx_key);
        my $oidbin = pack('H*', $oidhex);
        my $sth = $self->{dbh}->prepare_cached(<<'');
 INSERT OR IGNORE INTO xref3 (docid, ibx_id, xnum, oidbin) VALUES (?, ?, ?, ?)
@@ -602,8 +625,7 @@ sub remove_xref3 {
        my $oidbin = pack('H*', $oidhex);
        my ($sth, $ibx_id);
        if (defined $eidx_key) {
-               $ibx_id = id_for($self, 'inboxes', 'ibx_id',
-                                       eidx_key => $eidx_key);
+               $ibx_id = ibx_id($self, $eidx_key);
                $sth = $self->{dbh}->prepare_cached(<<'');
 DELETE FROM xref3 WHERE docid = ? AND ibx_id = ? AND oidbin = ?
 
@@ -652,4 +674,28 @@ UPDATE over SET ddd = ? WHERE num = ?
        $sth->execute;
 }
 
+sub eidxq_add {
+       my ($self, $docid) = @_;
+       $self->dbh->prepare_cached(<<'')->execute($docid);
+INSERT OR IGNORE INTO eidxq (docid) VALUES (?)
+
+}
+
+sub eidxq_del {
+       my ($self, $docid) = @_;
+       $self->dbh->prepare_cached(<<'')->execute($docid);
+DELETE FROM eidxq WHERE docid = ?
+
+}
+
+sub blob_exists {
+       my ($self, $oidhex) = @_;
+       my $sth = $self->dbh->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE oidbin = ?
+
+       $sth->bind_param(1, pack('H*', $oidhex), SQL_BLOB);
+       $sth->execute;
+       $sth->fetchrow_array;
+}
+
 1;