over: ensure old, merged {tid} is really gone

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

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 9f4a56fbd4861b9978a3a3146317a42d597a95f1..840e2c2a11aa92047a7fd0c3c51c40ebe7299337 100644 (file)
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -9,14 +9,13 @@
 # are denoted by a negative NNTP article number.
 package PublicInbox::OverIdx;
 use strict;
-use warnings;
-use base qw(PublicInbox::Over);
+use v5.10.1;
+use parent qw(PublicInbox::Over);
 use IO::Handle;
 use DBI qw(:sql_types); # SQL_BLOB
 use PublicInbox::MID qw/id_compress mids_for_index references/;
 use PublicInbox::Smsg qw(subject_normalized);
 use Compress::Zlib qw(compress);
-use PublicInbox::Search;
 use Carp qw(croak);
 
 sub dbh_new {
@@ -171,8 +170,14 @@ 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;
 }
@@ -185,23 +190,20 @@ sub resolve_mid_to_tid {
        if (my $del = delete $self->{-ghosts_to_delete}) {
                delete_by_num($self, $_) for @$del;
        }
-       $tid // create_ghost($self, $mid);
-}
-
-sub create_ghost {
-       my ($self, $mid) = @_;
-       my $id = mid2id($self, $mid);
-       my $num = next_ghost_num($self);
-       $num < 0 or die "ghost num is non-negative: $num\n";
-       my $tid = next_tid($self);
-       my $dbh = $self->{dbh};
-       $dbh->prepare_cached(<<'')->execute($num, $tid);
+       $tid // do { # create a new ghost
+               my $id = mid2id($self, $mid);
+               my $num = next_ghost_num($self);
+               $num < 0 or die "ghost num is non-negative: $num\n";
+               $tid = next_tid($self);
+               my $dbh = $self->{dbh};
+               $dbh->prepare_cached(<<'')->execute($num, $tid);
 INSERT INTO over (num, tid) VALUES (?,?)
 
-       $dbh->prepare_cached(<<'')->execute($id, $num);
+               $dbh->prepare_cached(<<'')->execute($id, $num);
 INSERT INTO id2num (id, num) VALUES (?,?)
 
-       $tid;
+               $tid;
+       };
 }
 
 sub merge_threads {
@@ -298,7 +300,7 @@ 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++;
        }
@@ -383,12 +385,12 @@ sub create_tables {
 
        $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS over (
-       num INTEGER NOT NULL,
-       tid INTEGER NOT NULL,
-       sid INTEGER,
-       ts INTEGER,
-       ds INTEGER,
-       ddd VARBINARY, /* doc-data-deflated */
+       num INTEGER 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)
 )
 
@@ -410,13 +412,13 @@ CREATE TABLE IF NOT EXISTS counter (
        $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS subject (
        sid INTEGER PRIMARY KEY AUTOINCREMENT,
-       path VARCHAR(40) NOT NULL,
+       path VARCHAR(40) NOT NULL, /* SHA-1 of normalized subject */
        UNIQUE (path)
 )
 
        $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS id2num (
-       id INTEGER NOT NULL,
+       id INTEGER NOT NULL, /* <=> msgid.id */
        num INTEGER NOT NULL,
        UNIQUE (id, num)
 )
@@ -427,7 +429,7 @@ CREATE TABLE IF NOT EXISTS id2num (
 
        $dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS msgid (
-       id INTEGER PRIMARY KEY AUTOINCREMENT,
+       id INTEGER PRIMARY KEY AUTOINCREMENT, /* <=> id2num.id */
        mid VARCHAR(244) NOT NULL,
        UNIQUE (mid)
 )
@@ -443,7 +445,7 @@ sub commit_lazy {
 sub begin_lazy {
        my ($self) = @_;
        return if $self->{txn};
-       my $dbh = $self->connect or return;
+       my $dbh = $self->dbh or return;
        $dbh->begin_work;
        # $dbh->{Profile} = 2;
        $self->{txn} = 1;
@@ -455,10 +457,10 @@ sub rollback_lazy {
        $self->{dbh}->rollback;
 }
 
-sub disconnect {
+sub dbh_close {
        my ($self) = @_;
        die "in transaction" if $self->{txn};
-       $self->SUPER::disconnect;
+       $self->SUPER::dbh_close;
 }
 
 sub create {
@@ -469,8 +471,8 @@ sub create {
                File::Path::mkpath(File::Basename::dirname($self->{filename}));
        }
        # create the DB:
-       PublicInbox::Over::connect($self);
-       $self->disconnect;
+       PublicInbox::Over::dbh($self);
+       $self->dbh_close;
 }
 
 sub rethread_prepare {