X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMailSync.pm;h=d9b9e117a742b8801f7d9bfb6ff4c3924139c010;hb=0c385e6500f26babc47a0768b730ea38e290a5f5;hp=ec05404ad004fc9740e7aec781fd9ddc96efd539;hpb=10b523eb017162240b1ac3647f8dcbbf2be348a7;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMailSync.pm b/lib/PublicInbox/LeiMailSync.pm index ec05404a..d9b9e117 100644 --- a/lib/PublicInbox/LeiMailSync.pm +++ b/lib/PublicInbox/LeiMailSync.pm @@ -5,6 +5,7 @@ package PublicInbox::LeiMailSync; use strict; use v5.10.1; +use parent qw(PublicInbox::Lock); use DBI; use PublicInbox::ContentHash qw(git_sha); use Carp (); @@ -13,6 +14,11 @@ sub dbh_new { my ($self, $rw) = @_; my $f = $self->{filename}; my $creat = $rw && !-s $f; + if ($creat) { + require PublicInbox::Spawn; + open my $fh, '+>>', $f or Carp::croak "open($f): $!"; + PublicInbox::Spawn::nodatacow_fd(fileno($fh)); + } my $dbh = DBI->connect("dbi:SQLite:dbname=$f",'','', { AutoCommit => 1, RaiseError => 1, @@ -21,7 +27,7 @@ sub dbh_new { sqlite_use_immediate_transaction => 1, }); # no sqlite_unicode, here, all strings are binary - create_tables($dbh) if $rw; + create_tables($self, $dbh) if $rw; $dbh->do('PRAGMA journal_mode = WAL') if $creat; $dbh->do('PRAGMA case_sensitive_like = ON'); $dbh; @@ -29,15 +35,24 @@ sub dbh_new { sub new { my ($cls, $f) = @_; - bless { filename => $f, fmap => {} }, $cls; + bless { + filename => $f, + fmap => {}, + lock_path => "$f.flock", + }, $cls; } -sub lms_commit { delete($_[0]->{dbh})->commit } +sub lms_write_prepare { ($_[0]->{dbh} //= dbh_new($_[0], 1)); $_[0] } -sub lms_begin { ($_[0]->{dbh} //= dbh_new($_[0], 1))->begin_work }; +sub lms_pause { + my ($self) = @_; + $self->{fmap} = {}; + delete $self->{dbh}; +} sub create_tables { - my ($dbh) = @_; + my ($self, $dbh) = @_; + my $lk = $self->lock_for_scope; $dbh->do(<<''); CREATE TABLE IF NOT EXISTS folders ( @@ -79,8 +94,8 @@ sub fid_for { my ($fid) = $dbh->selectrow_array($sel, undef, $folder); return $fid if defined $fid; + # caller had trailing slash (LeiToMail) if ($folder =~ s!\A((?:maildir|mh):.*?)/+\z!$1!i) { - warn "folder: $folder/ had trailing slash in arg\n"; ($fid) = $dbh->selectrow_array($sel, undef, $folder); if (defined $fid) { $dbh->do(<lock_for_scope; + for my $f (@folders) { $self->{fmap}->{$f} //= fid_for($self, $f, 1) } +} + sub set_src { - my ($self, $oidhex, $folder, $id) = @_; + my ($self, $oidbin, $folder, $id) = @_; + my $lk = $self->lock_for_scope; my $fid = $self->{fmap}->{$folder} //= fid_for($self, $folder, 1); my $sth; if (ref($id)) { # scalar name @@ -131,11 +153,12 @@ INSERT OR IGNORE INTO blob2name (oidbin, fid, name) VALUES (?, ?, ?) INSERT OR IGNORE INTO blob2num (oidbin, fid, uid) VALUES (?, ?, ?) } - $sth->execute(pack('H*', $oidhex), $fid, $id); + $sth->execute($oidbin, $fid, $id); } sub clear_src { my ($self, $folder, $id) = @_; + my $lk = $self->lock_for_scope; my $fid = $self->{fmap}->{$folder} //= fid_for($self, $folder, 1); my $sth; if (ref($id)) { # scalar name @@ -154,33 +177,63 @@ DELETE FROM blob2num WHERE fid = ? AND uid = ? # Maildir-only sub mv_src { my ($self, $folder, $oidbin, $id, $newbn) = @_; + my $lk = $self->lock_for_scope; my $fid = $self->{fmap}->{$folder} //= fid_for($self, $folder, 1); my $sth = $self->{dbh}->prepare_cached(<<''); UPDATE blob2name SET name = ? WHERE fid = ? AND oidbin = ? AND name = ? - $sth->execute($newbn, $fid, $oidbin, $$id); + my $nr = $sth->execute($newbn, $fid, $oidbin, $$id); + if ($nr == 0) { # may race with a clear_src, ensure new value exists + $sth = $self->{dbh}->prepare_cached(<<''); +INSERT OR IGNORE INTO blob2name (oidbin, fid, name) VALUES (?, ?, ?) + + $sth->execute($oidbin, $fid, $newbn); + } } # read-only, iterates every oidbin + UID or name for a given folder sub each_src { my ($self, $folder, $cb, @args) = @_; my $dbh = $self->{dbh} //= dbh_new($self); - my ($fid, $sth); + my $fid; if (ref($folder) eq 'HASH') { $fid = $folder->{fid} // die "BUG: no `fid'"; } else { $fid = $self->{fmap}->{$folder} //= fid_for($self, $folder) // return; } - $sth = $dbh->prepare('SELECT oidbin,uid FROM blob2num WHERE fid = ?'); - $sth->execute($fid); - while (my ($oidbin, $id) = $sth->fetchrow_array) { - $cb->($oidbin, $id, @args); + + # minimize implicit txn time to avoid blocking writers by + # batching SELECTs. This looks wonky but is necessary since + # $cb-> may access the DB on its own. + my $ary = $dbh->selectall_arrayref(<<'', undef, $fid); +SELECT _rowid_,oidbin,uid FROM blob2num WHERE fid = ? +ORDER BY _rowid_ ASC LIMIT 1000 + + my $min = @$ary ? $ary->[-1]->[0] : undef; + while (defined $min) { + for my $row (@$ary) { $cb->($row->[1], $row->[2], @args) } + + $ary = $dbh->selectall_arrayref(<<'', undef, $fid, $min); +SELECT _rowid_,oidbin,uid FROM blob2num WHERE fid = ? AND _rowid_ > ? +ORDER BY _rowid_ ASC LIMIT 1000 + + $min = @$ary ? $ary->[-1]->[0] : undef; } - $sth = $dbh->prepare('SELECT oidbin,name FROM blob2name WHERE fid = ?'); - $sth->execute($fid); - while (my ($oidbin, $id) = $sth->fetchrow_array) { - $cb->($oidbin, \$id, @args); + + $ary = $dbh->selectall_arrayref(<<'', undef, $fid); +SELECT _rowid_,oidbin,name FROM blob2name WHERE fid = ? +ORDER BY _rowid_ ASC LIMIT 1000 + + $min = @$ary ? $ary->[-1]->[0] : undef; + while (defined $min) { + for my $row (@$ary) { $cb->($row->[1], \($row->[2]), @args) } + + $ary = $dbh->selectall_arrayref(<<'', undef, $fid, $min); +SELECT _rowid_,oidbin,name FROM blob2name WHERE fid = ? AND _rowid_ > ? +ORDER BY _rowid_ ASC LIMIT 1000 + + $min = @$ary ? $ary->[-1]->[0] : undef; } } @@ -194,28 +247,30 @@ sub location_stats { SELECT COUNT(name) FROM blob2name WHERE fid = ? $ret->{'name.count'} = $row if $row; + my $ntype = ($folder =~ m!\A(?:nntps?|s?news)://!i) ? 'article' : + (($folder =~ m!\Aimaps?://!i) ? 'uid' : "TODO<$folder>"); for my $op (qw(count min max)) { ($row) = $dbh->selectrow_array(<<"", undef, $fid); SELECT $op(uid) FROM blob2num WHERE fid = ? $row or last; - $ret->{"uid.$op"} = $row; + $ret->{"$ntype.$op"} = $row; } $ret; } # returns a { location => [ list-of-ids-or-names ] } mapping sub locations_for { - my ($self, $oidhex) = @_; + my ($self, $oidbin) = @_; my ($fid, $sth, $id, %fid2id); my $dbh = $self->{dbh} //= dbh_new($self); $sth = $dbh->prepare('SELECT fid,uid FROM blob2num WHERE oidbin = ?'); - $sth->execute(pack('H*', $oidhex)); + $sth->execute($oidbin); while (my ($fid, $uid) = $sth->fetchrow_array) { push @{$fid2id{$fid}}, $uid; } $sth = $dbh->prepare('SELECT fid,name FROM blob2name WHERE oidbin = ?'); - $sth->execute(pack('H*', $oidhex)); + $sth->execute($oidbin); while (my ($fid, $name) = $sth->fetchrow_array) { push @{$fid2id{$fid}}, $name; } @@ -225,6 +280,7 @@ sub locations_for { $sth->execute($fid); my ($loc) = $sth->fetchrow_array; unless (defined $loc) { + my $oidhex = unpack('H*', $oidbin); warn "E: fid=$fid for $oidhex unknown:\n", map { 'E: '.(ref() ? $$_ : "#$_")."\n"; } @$ids; @@ -315,6 +371,65 @@ sub match_imap_url { "E: `$url' is ambiguous:\n\t".join("\n\t", @match)."\n"; } +sub match_nntp_url ($$$) { + my ($self, $url, $all) = @_; # $all = [ $lms->folders ]; + $all //= [ $self->folders ]; + require PublicInbox::URInntps; + my $want = PublicInbox::URInntps->new($url)->canonical; + my ($s, $h, $p) = ($want->scheme, $want->host, $want->port); + my $ng = $want->group; # force scalar (no article ranges) + my @uri = map { PublicInbox::URInntps->new($_)->canonical } + grep(m!\A\Q$s\E://.*?\Q$h\E\b.*?/\Q$ng\E\b!, @$all); + my @match; + for my $x (@uri) { + next if $x->group ne $ng || $x->host ne $h || $x->port != $p; + # maybe user was forgotten on CLI: + if (defined($x->userinfo) && !defined($want->userinfo)) { + push @match, $x; + } elsif (($x->userinfo//"\0") eq ($want->userinfo//"\0")) { + push @match, $x; + } + } + return @match if wantarray; + scalar(@match) <= 1 ? $match[0] : + "E: `$url' is ambiguous:\n\t".join("\n\t", @match)."\n"; +} + +# returns undef on failure, number on success +sub group2folders { + my ($self, $lei, $all, $folders) = @_; + return $lei->fail(< $_ } split(/,/, $all); + my @ok = grep(defined, delete(@x{qw(local remote), ''})); + push(@ok, '') if $all eq ''; + my @no = keys %x; + if (@no) { + @no = (join(',', @no)); + return $lei->fail(<folders; + for my $ok (@ok) { + if ($ok eq 'local') { + @inc = grep(!m!\A[a-z0-9\+]+://!i, @all); + } elsif ($ok eq 'remote') { + @inc = grep(m!\A[a-z0-9\+]+://!i, @all); + } elsif ($ok ne '') { + return $lei->fail("--all=$all not understood"); + } else { + @inc = @all; + } + push(@$folders, (grep { !$seen{$_}++ } @inc)); + } + scalar(@$folders) || $lei->fail(<{qerr}}, <err($res) if defined $res; + push @no, $orig; + } + } elsif (m!\A(?:nntps?|s?news)://!i) { + my $orig = $_; + my $res = match_nntp_url($self, $orig, \@all); + if (ref $res) { + $_ = $$res; + push(@{$err->{qerr}}, <err($res) if defined $res; @@ -358,15 +485,41 @@ EOF $err; } -sub forget_folder { - my ($self, $folder) = @_; - my ($fid, $sth); - $fid = delete($self->{fmap}->{$folder}) // - fid_for($self, $folder) // return; - my $dbh = $self->{dbh}; - $dbh->do('DELETE FROM blob2name WHERE fid = ?', undef, $fid); - $dbh->do('DELETE FROM blob2num WHERE fid = ?', undef, $fid); - $dbh->do('DELETE FROM folders WHERE fid = ?', undef, $fid); +sub forget_folders { + my ($self, @folders) = @_; + my $lk = $self->lock_for_scope; + for my $folder (@folders) { + my $fid = delete($self->{fmap}->{$folder}) // + fid_for($self, $folder) // next; + for my $t (qw(blob2name blob2num folders)) { + $self->{dbh}->do("DELETE FROM $t WHERE fid = ?", + undef, $fid); + } + } +} + +# only used for changing canonicalization errors +sub rename_folder { + my ($self, $old, $new) = @_; + my $lk = $self->lock_for_scope; + my $ofid = delete($self->{fmap}->{$old}) // + fid_for($self, $old) // return; + eval { + $self->{dbh}->do(<{fmap}->{$new} // fid_for($self, $new); + for my $t (qw(blob2name blob2num)) { + $self->{dbh}->do(<{dbh}->do(<" is causing uncommitted transaction -# warnings, not sure what... -sub DESTROY { - my ($self) = @_; - my $dbh = delete($self->{dbh}) or return; - return if $dbh->{ReadOnly}; - use Carp; - undef $dbh; - warn "BUG $$ $0 $self {dbh} OPEN ppid=".getppid.' '.Carp::longmess(); -} - 1;