wwwstream: use parent.pm and no warnings

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

diff --git a/lib/PublicInbox/Msgmap.pm b/lib/PublicInbox/Msgmap.pm
index 192e311aec2b1d459407e0853cfcecb26c2f0448..aa07e344c6a9d75a9b376af5a6fbbd5911481198 100644 (file)
--- a/lib/PublicInbox/Msgmap.pm
+++ b/lib/PublicInbox/Msgmap.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # bidirectional Message-ID <-> Article Number mapping for the NNTP
@@ -48,8 +48,15 @@ sub new_file {
 
        if ($writable) {
                create_tables($dbh);
+
+               # TRUNCATE reduces I/O compared to the default (DELETE)
+               $dbh->do('PRAGMA journal_mode = TRUNCATE');
+
                $dbh->begin_work;
                $self->created_at(time) unless $self->created_at;
+
+               my $max = $self->max // 0;
+               $self->num_highwater($max);
                $dbh->commit;
        }
        $self;
@@ -62,6 +69,7 @@ sub tmp_clone {
        $self->{dbh}->sqlite_backup_to_file($fn);
        my $tmp = ref($self)->new_file($fn, 1);
        $tmp->{dbh}->do('PRAGMA synchronous = OFF');
+       $tmp->{dbh}->do('PRAGMA journal_mode = MEMORY');
        $tmp->{tmp_name} = $fn; # SQLite won't work if unlinked, apparently
        $tmp->{pid} = $$;
        close $fh or die "failed to close $fn: $!";
@@ -107,14 +115,27 @@ sub created_at {
        $self->meta_accessor('created_at', $second);
 }
 
+sub num_highwater {
+       my ($self, $num) = @_;
+       my $high = $self->{num_highwater} ||=
+           $self->meta_accessor('num_highwater');
+       if (defined($num) && (!defined($high) || ($num > $high))) {
+               $self->{num_highwater} = $num;
+               $self->meta_accessor('num_highwater', $num);
+       }
+       $self->{num_highwater};
+}
+
 sub mid_insert {
        my ($self, $mid) = @_;
        my $dbh = $self->{dbh};
        my $sth = $dbh->prepare_cached(<<'');
-INSERT OR IGNORE INTO msgmap (mid) VALUES (?)
+INSERT INTO msgmap (mid) VALUES (?)
 
-       return if $sth->execute($mid) == 0;
-       $dbh->last_insert_id(undef, undef, 'msgmap', 'num');
+       return unless eval { $sth->execute($mid) };
+       my $num = $dbh->last_insert_id(undef, undef, 'msgmap', 'num');
+       $self->num_highwater($num) if defined($num);
+       $num;
 }
 
 sub mid_for {
@@ -137,17 +158,20 @@ sub num_for {
        $sth->fetchrow_array;
 }
 
+sub max {
+       my $sth = $_[0]->{dbh}->prepare_cached('SELECT MAX(num) FROM msgmap',
+                                               undef, 1);
+       $sth->execute;
+       $sth->fetchrow_array;
+}
+
 sub minmax {
-       my ($self) = @_;
-       my $dbh = $self->{dbh};
        # breaking MIN and MAX into separate queries speeds up from 250ms
        # to around 700us with 2.7million messages.
-       my $sth = $dbh->prepare_cached('SELECT MIN(num) FROM msgmap', undef, 1);
+       my $sth = $_[0]->{dbh}->prepare_cached('SELECT MIN(num) FROM msgmap',
+                                               undef, 1);
        $sth->execute;
-       my $min = $sth->fetchrow_array;
-       $sth = $dbh->prepare_cached('SELECT MAX(num) FROM msgmap', undef, 1);
-       $sth->execute;
-       ($min, $sth->fetchrow_array);
+       ($sth->fetchrow_array, max($_[0]));
 }
 
 sub mid_delete {
@@ -194,12 +218,13 @@ ORDER BY num ASC LIMIT 1000
 }
 
 sub msg_range {
-       my ($self, $beg, $end) = @_;
+       my ($self, $beg, $end, $cols) = @_;
+       $cols //= 'num,mid';
        my $dbh = $self->{dbh};
        my $attr = { Columns => [] };
-       my $mids = $dbh->selectall_arrayref(<<'', $attr, $$beg, $end);
-SELECT num,mid FROM msgmap WHERE num >= ? AND num <= ?
-ORDER BY num ASC
+       my $mids = $dbh->selectall_arrayref(<<"", $attr, $$beg, $end);
+SELECT $cols FROM msgmap WHERE num >= ? AND num <= ?
+ORDER BY num ASC LIMIT 1000
 
        $$beg = $mids->[-1]->[0] + 1 if @$mids;
        $mids
@@ -213,7 +238,9 @@ sub mid_set {
                $self->{dbh}->prepare(
                        'INSERT OR IGNORE INTO msgmap (num,mid) VALUES (?,?)');
        };
-       $sth->execute($num, $mid);
+       my $result = $sth->execute($num, $mid);
+       $self->num_highwater($num) if (defined($result) && $result == 1);
+       $result;
 }
 
 sub DESTROY {
@@ -243,4 +270,30 @@ sub atfork_prepare {
        %$self = (tmp_name => $f, pid => $$);
 }
 
+sub skip_artnum {
+       my ($self, $skip_artnum) = @_;
+       return meta_accessor($self, 'skip_artnum') if !defined($skip_artnum);
+
+       my $cur = num_highwater($self) // 0;
+       if ($skip_artnum < $cur) {
+               die "E: current article number $cur ",
+                       "exceeds --skip-artnum=$skip_artnum\n";
+       } else {
+               my $ok;
+               for (1..10) {
+                       my $mid = 'skip'.rand.'@'.rand.'.example.com';
+                       $ok = mid_set($self, $skip_artnum, $mid);
+                       if ($ok) {
+                               mid_delete($self, $mid);
+                               last;
+                       }
+               }
+               $ok or die '--skip-artnum failed';
+
+               # in the future, the indexer may use this value for
+               # new messages in old epochs
+               meta_accessor($self, 'skip_artnum', $skip_artnum);
+       }
+}
+
 1;