X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMsgmap.pm;h=9523752e9af07f8b973ac45d5a5aeda408801513;hb=95bdac7f09c69036efed537a4d03d5bdd2ae4eb6;hp=3fb3805fe82abea0c23684890d1f33004e6815d5;hpb=58a5bb3e18901237b1ca34ef8f03f696be27d305;p=public-inbox.git

diff --git a/lib/PublicInbox/Msgmap.pm b/lib/PublicInbox/Msgmap.pm
index 3fb3805f..9523752e 100644
--- a/lib/PublicInbox/Msgmap.pm
+++ b/lib/PublicInbox/Msgmap.pm
@@ -1,5 +1,5 @@
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# 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
 # and web interfaces.  This is required for implementing stable article
@@ -12,6 +12,7 @@ use strict;
 use warnings;
 use DBI;
 use DBD::SQLite;
+use File::Temp qw(tempfile);
 
 sub new {
 	my ($class, $git_dir, $writable) = @_;
@@ -23,9 +24,11 @@ sub new {
 	new_file($class, "$d/msgmap.sqlite3", $writable);
 }
 
-sub new_file {
-	my ($class, $f, $writable) = @_;
-
+sub dbh_new {
+	my ($f, $writable) = @_;
+	if ($writable && !-f $f) { # SQLite defaults mode to 0644, we want 0666
+		open my $fh, '+>>', $f or die "failed to open $f: $!";
+	}
 	my $dbh = DBI->connect("dbi:SQLite:dbname=$f",'','', {
 		AutoCommit => 1,
 		RaiseError => 1,
@@ -33,38 +36,59 @@ sub new_file {
 		ReadOnly => !$writable,
 		sqlite_use_immediate_transaction => 1,
 	});
-	$dbh->do('PRAGMA case_sensitive_like = ON');
+	$dbh;
+}
+
+sub new_file {
+	my ($class, $f, $writable) = @_;
+	return if !$writable && !-r $f;
+
+	my $dbh = dbh_new($f, $writable);
 	my $self = bless { dbh => $dbh }, $class;
 
 	if ($writable) {
 		create_tables($dbh);
 		$dbh->begin_work;
 		$self->created_at(time) unless $self->created_at;
+
+		my (undef, $max) = $self->minmax();
+		$max ||= 0;
+		$self->num_highwater($max);
 		$dbh->commit;
 	}
 	$self;
 }
 
+# used to keep track of used numeric mappings for v2 reindex
+sub tmp_clone {
+	my ($self) = @_;
+	my ($fh, $fn) = tempfile('msgmap-XXXXXXXX', EXLOCK => 0, TMPDIR => 1);
+	$self->{dbh}->sqlite_backup_to_file($fn);
+	my $tmp = ref($self)->new_file($fn, 1);
+	$tmp->{dbh}->do('PRAGMA synchronous = OFF');
+	$tmp->{tmp_name} = $fn; # SQLite won't work if unlinked, apparently
+	$tmp->{pid} = $$;
+	close $fh or die "failed to close $fn: $!";
+	$tmp;
+}
+
 # n.b. invoked directly by scripts/xhdr-num2mid
 sub meta_accessor {
 	my ($self, $key, $value) = @_;
-	use constant {
-		meta_select => 'SELECT val FROM meta WHERE key = ? LIMIT 1',
-		meta_update => 'UPDATE meta SET val = ? WHERE key = ? LIMIT 1',
-		meta_insert => 'INSERT INTO meta (key,val) VALUES (?,?)',
-	};
 
+	my $sql = 'SELECT val FROM meta WHERE key = ? LIMIT 1';
 	my $dbh = $self->{dbh};
 	my $prev;
-	defined $value or
-		return $dbh->selectrow_array(meta_select, undef, $key);
+	defined $value or return $dbh->selectrow_array($sql, undef, $key);
 
-	$prev = $dbh->selectrow_array(meta_select, undef, $key);
+	$prev = $dbh->selectrow_array($sql, undef, $key);
 
 	if (defined $prev) {
-		$dbh->do(meta_update, undef, $value, $key);
+		$sql = 'UPDATE meta SET val = ? WHERE key = ?';
+		$dbh->do($sql, undef, $value, $key);
 	} else {
-		$dbh->do(meta_insert, undef, $key, $value);
+		$sql = 'INSERT INTO meta (key,val) VALUES (?,?)';
+		$dbh->do($sql, undef, $key, $value);
 	}
 	$prev;
 }
@@ -74,26 +98,47 @@ sub last_commit {
 	$self->meta_accessor('last_commit', $commit);
 }
 
+# v2 uses this to keep track of how up-to-date Xapian is
+# old versions may be automatically GC'ed away in the future,
+# but it's a trivial amount of storage.
+sub last_commit_xap {
+	my ($self, $version, $i, $commit) = @_;
+	$self->meta_accessor("last_xap$version-$i", $commit);
+}
+
 sub created_at {
 	my ($self, $second) = @_;
 	$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};
-	use constant MID_INSERT => 'INSERT INTO msgmap (mid) VALUES (?)';
-	my $sth = $self->{mid_insert} ||= $dbh->prepare(MID_INSERT);
-	$sth->bind_param(1, $mid);
-	$sth->execute;
-	$dbh->last_insert_id(undef, undef, 'msgmap', 'num');
+	my $sth = $dbh->prepare_cached(<<'');
+INSERT INTO msgmap (mid) VALUES (?)
+
+	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 {
 	my ($self, $num) = @_;
 	my $dbh = $self->{dbh};
-	use constant MID_FOR => 'SELECT mid FROM msgmap WHERE num = ? LIMIT 1';
-	my $sth = $self->{mid_for} ||= $dbh->prepare(MID_FOR);
+	my $sth = $self->{mid_for} ||=
+		$dbh->prepare('SELECT mid FROM msgmap WHERE num = ? LIMIT 1');
 	$sth->bind_param(1, $num);
 	$sth->execute;
 	$sth->fetchrow_array;
@@ -102,8 +147,8 @@ sub mid_for {
 sub num_for {
 	my ($self, $mid) = @_;
 	my $dbh = $self->{dbh};
-	use constant NUM_FOR => 'SELECT num FROM msgmap WHERE mid = ? LIMIT 1';
-	my $sth = $self->{num_for} ||= $dbh->prepare(NUM_FOR);
+	my $sth = $self->{num_for} ||=
+		$dbh->prepare('SELECT num FROM msgmap WHERE mid = ? LIMIT 1');
 	$sth->bind_param(1, $mid);
 	$sth->execute;
 	$sth->fetchrow_array;
@@ -112,38 +157,32 @@ sub num_for {
 sub minmax {
 	my ($self) = @_;
 	my $dbh = $self->{dbh};
-	use constant NUM_MINMAX => 'SELECT MIN(num),MAX(num) FROM msgmap';
-	my $sth = $self->{num_minmax} ||= $dbh->prepare(NUM_MINMAX);
+	# 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);
 	$sth->execute;
-        $sth->fetchrow_array;
-}
-
-sub mid_prefixes {
-	my ($self, $pfx, $limit) = @_;
-
-	die "No prefix given" unless (defined $pfx && $pfx ne '');
-	$pfx =~ s/([%_])/\\$1/g;
-	$pfx .= '%';
-
-	$limit ||= 100;
-	$limit += 0; # force to integer
-	$limit ||= 100;
-
-	$self->{dbh}->selectcol_arrayref('SELECT mid FROM msgmap ' .
-					 'WHERE mid LIKE ? ESCAPE ? ' .
-					 "ORDER BY num DESC LIMIT $limit",
-					 undef, $pfx, '\\');
+	my $min = $sth->fetchrow_array;
+	$sth = $dbh->prepare_cached('SELECT MAX(num) FROM msgmap', undef, 1);
+	$sth->execute;
+	($min, $sth->fetchrow_array);
 }
 
 sub mid_delete {
 	my ($self, $mid) = @_;
 	my $dbh = $self->{dbh};
-	use constant MID_DELETE => 'DELETE FROM msgmap WHERE mid = ?';
-	my $sth = $dbh->prepare(MID_DELETE);
+	my $sth = $dbh->prepare('DELETE FROM msgmap WHERE mid = ?');
 	$sth->bind_param(1, $mid);
 	$sth->execute;
 }
 
+sub num_delete {
+	my ($self, $num) = @_;
+	my $dbh = $self->{dbh};
+	my $sth = $dbh->prepare('DELETE FROM msgmap WHERE num = ?');
+	$sth->bind_param(1, $num);
+	$sth->execute;
+}
+
 sub create_tables {
 	my ($dbh) = @_;
 	my $e;
@@ -161,28 +200,67 @@ sub create_tables {
 }
 
 # used by NNTP.pm
-sub id_batch {
-	my ($self, $num, $cb) = @_;
+sub ids_after {
+	my ($self, $num) = @_;
+	my $ids = $self->{dbh}->selectcol_arrayref(<<'', undef, $$num);
+SELECT num FROM msgmap WHERE num > ?
+ORDER BY num ASC LIMIT 1000
+
+	$$num = $ids->[-1] if @$ids;
+	$ids;
+}
+
+sub msg_range {
+	my ($self, $beg, $end, $cols) = @_;
+	$cols //= 'num,mid';
 	my $dbh = $self->{dbh};
-	my $sth = $dbh->prepare('SELECT num FROM msgmap WHERE num > ? '.
-				'ORDER BY num ASC LIMIT 1000');
-	$sth->execute($num);
-	my $ary = $sth->fetchall_arrayref;
-	@$ary = map { $_->[0] } @$ary;
-	my $nr = scalar @$ary;
-	$cb->($ary) if $nr;
-	$nr;
+	my $attr = { Columns => [] };
+	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
 }
 
 # only used for mapping external serial numbers (e.g. articles from gmane)
-# see scripts/xhdr-num2mid for usage
+# see scripts/xhdr-num2mid or PublicInbox::Filter::RubyLang for usage
 sub mid_set {
 	my ($self, $num, $mid) = @_;
 	my $sth = $self->{mid_set} ||= do {
-		my $sql = 'INSERT INTO msgmap (num, mid) VALUES (?,?)';
-		$self->{dbh}->prepare($sql);
+		$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);
+	$result;
+}
+
+sub DESTROY {
+	my ($self) = @_;
+	delete $self->{dbh};
+	my $f = delete $self->{tmp_name};
+	if (defined $f && $self->{pid} == $$) {
+		unlink $f or warn "failed to unlink $f: $!\n";
+	}
+}
+
+sub atfork_parent {
+	my ($self) = @_;
+	my $f = $self->{tmp_name} or die "not a temporary clone\n";
+	delete $self->{dbh} and die "tmp_clone dbh not prepared for parent";
+	my $dbh = $self->{dbh} = dbh_new($f, 1);
+	$dbh->do('PRAGMA synchronous = OFF');
+}
+
+sub atfork_prepare {
+	my ($self) = @_;
+	my $f = $self->{tmp_name} or die "not a temporary clone\n";
+	$self->{pid} == $$ or
+		die "BUG: atfork_prepare not called from $self->{pid}\n";
+	$self->{dbh} or die "temporary clone not open\n";
+	# must clobber prepared statements
+	%$self = (tmp_name => $f, pid => $$);
 }
 
 1;