-# Copyright (C) 2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# Writes PublicInbox::Eml objects atomically to a mbox variant or Maildir
package PublicInbox::LeiToMail;
use strict;
use v5.10.1;
+use parent qw(PublicInbox::IPC);
use PublicInbox::Eml;
+use PublicInbox::Lock;
+use PublicInbox::ProcessPipe;
+use PublicInbox::Spawn qw(which spawn popen_rd);
+use PublicInbox::LeiDedupe;
+use PublicInbox::OnDestroy;
+use PublicInbox::Git;
+use PublicInbox::GitAsyncCat;
+use Symbol qw(gensym);
+use IO::Handle; # ->autoflush
+use Fcntl qw(SEEK_SET SEEK_END O_CREAT O_EXCL O_WRONLY);
+use Errno qw(EEXIST ESPIPE ENOENT EPIPE);
+
+# struggles with short-lived repos, Gcf2Client makes little sense with lei;
+# but we may use in-process libgit2 in the future.
+$PublicInbox::GitAsyncCat::GCF2C = 0;
my %kw2char = ( # Maildir characters
draft => 'D',
);
sub _mbox_hdr_buf ($$$) {
- my ($eml, $type, $kw) = @_;
+ my ($eml, $type, $smsg) = @_;
$eml->header_set($_) for (qw(Lines Bytes Content-Length));
- my %hdr; # set Status, X-Status
- for my $k (@$kw) {
+
+ # Messages are always 'O' (non-\Recent in IMAP), it saves
+ # MUAs the trouble of rewriting the mbox if no other
+ # changes are made
+ my %hdr = (Status => [ 'O' ]); # set Status, X-Status
+ for my $k (@{$smsg->{kw} // []}) {
if (my $ent = $kw2status{$k}) {
push @{$hdr{$ent->[0]}}, $ent->[1];
} else { # X-Label?
# fixup old bug from import (pre-a0c07cba0e5d8b6a)
$$buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ my $ident = $smsg->{blob} // 'lei';
+ if (defined(my $pct = $smsg->{pct})) { $ident .= "=$pct" }
substr($$buf, 0, 0, # prepend From line
- "From lei\@$type Thu Jan 1 00:00:00 1970$eml->{crlf}");
+ "From $ident\@$type Thu Jan 1 00:00:00 1970$eml->{crlf}");
$buf;
}
-sub write_in_full_atomic ($$) {
- my ($fh, $buf) = @_;
- defined(my $w = syswrite($fh, $$buf)) or die "write: $!";
- $w == length($$buf) or die "short write: $w != ".length($$buf);
+sub atomic_append { # for on-disk destinations (O_APPEND, or O_EXCL)
+ my ($lei, $buf) = @_;
+ if (defined(my $w = syswrite($lei->{1} // return, $$buf))) {
+ return if $w == length($$buf);
+ $buf = "short atomic write: $w != ".length($$buf);
+ } elsif ($! == EPIPE) {
+ return $lei->note_sigpipe(1);
+ } else {
+ $buf = "atomic write: $!";
+ }
+ $lei->fail($buf);
}
sub eml2mboxrd ($;$) {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxrd', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxrd', $smsg);
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^(>*From )/>$1/gm;
$$buf .= $eml->{crlf};
}
sub eml2mboxo {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxo', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxo', $smsg);
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^From />From /gm;
$$buf .= $eml->{crlf};
$buf;
}
+sub _mboxcl_common ($$$) {
+ my ($buf, $bdy, $crlf) = @_;
+ # add Lines: so mutt won't have to add it on MUA close
+ my $lines = $$bdy =~ tr!\n!\n!;
+ $$buf .= 'Content-Length: '.length($$bdy).$crlf.
+ 'Lines: '.$lines.$crlf.$crlf;
+ substr($$bdy, 0, 0, $$buf); # prepend header
+ $_[0] = $bdy;
+}
+
# mboxcl still escapes "From " lines
sub eml2mboxcl {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxcl', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxcl', $smsg);
my $crlf = $eml->{crlf};
if (my $bdy = delete $eml->{bdy}) {
$$bdy =~ s/^From />From /gm;
- $$buf .= 'Content-Length: '.length($$bdy).$crlf.$crlf;
- substr($$bdy, 0, 0, $$buf); # prepend header
- $buf = $bdy;
+ _mboxcl_common($buf, $bdy, $crlf);
}
$$buf .= $crlf;
$buf;
# mboxcl2 has no "From " escaping
sub eml2mboxcl2 {
- my ($eml, $kw) = @_;
- my $buf = _mbox_hdr_buf($eml, 'mboxcl2', $kw);
+ my ($eml, $smsg) = @_;
+ my $buf = _mbox_hdr_buf($eml, 'mboxcl2', $smsg);
my $crlf = $eml->{crlf};
if (my $bdy = delete $eml->{bdy}) {
- $$buf .= 'Content-Length: '.length($$bdy).$crlf.$crlf;
- substr($$bdy, 0, 0, $$buf); # prepend header
- $buf = $bdy;
+ _mboxcl_common($buf, $bdy, $crlf);
}
$$buf .= $crlf;
$buf;
}
+sub git_to_mail { # git->cat_async callback
+ my ($bref, $oid, $type, $size, $arg) = @_;
+ if ($type ne 'blob') {
+ if ($type eq 'missing') {
+ warn "missing $oid\n";
+ } else {
+ warn "unexpected type=$type for $oid\n";
+ }
+ }
+ my ($write_cb, $smsg) = @$arg;
+ if ($smsg->{blob} ne $oid) {
+ die "BUG: expected=$smsg->{blob} got=$oid";
+ }
+ $write_cb->($bref, $smsg) if $size > 0;
+}
+
+sub reap_compress { # dwaitpid callback
+ my ($lei, $pid) = @_;
+ my $cmd = delete $lei->{"pid.$pid"};
+ return if $? == 0;
+ $lei->fail("@$cmd failed", $? >> 8);
+}
+
+# all of these support -c for stdout and -d for decompression,
+# mutt is commonly distributed with hooks for gz, bz2 and xz, at least
+# { foo => '' } means "--foo" is passed to the command-line,
+# otherwise { foo => '--bar' } passes "--bar"
+our %zsfx2cmd = (
+ gz => [ qw(GZIP pigz gzip), { rsyncable => '', threads => '-p' } ],
+ bz2 => [ 'bzip2', {} ],
+ xz => [ 'xz', { threads => '-T' } ],
+ # XXX does anybody care for these? I prefer zstd on entire FSes,
+ # so it's probably not necessary on a per-file basis
+ # zst => [ 'zstd', { -default => [ qw(-q) ], # it's noisy by default
+ # rsyncable => '', threads => '-T' } ],
+ # zz => [ 'pigz', { -default => [ '--zlib' ],
+ # rsyncable => '', threads => '-p' }],
+ # lzo => [ 'lzop', {} ],
+ # lzma => [ 'lzma', {} ],
+);
+
+sub zsfx2cmd ($$$) {
+ my ($zsfx, $decompress, $lei) = @_;
+ my $x = $zsfx2cmd{$zsfx} // die "no support for suffix=.$zsfx";
+ my @info = @$x;
+ my $cmd_opt = pop @info;
+ my @cmd = (undef, $decompress ? qw(-dc) : qw(-c));
+ for my $exe (@info) {
+ # I think respecting client's ENV{GZIP} is OK, not sure
+ # about ENV overrides for other, less-common compressors
+ if ($exe eq uc($exe)) {
+ $exe = $lei->{env}->{$exe} or next;
+ }
+ $cmd[0] = which($exe) and last;
+ }
+ $cmd[0] // die join(' or ', @info)." missing for .$zsfx";
+ # push @cmd, @{$cmd_opt->{-default}} if $cmd_opt->{-default};
+ for my $bool (qw(rsyncable)) {
+ my $switch = $cmd_opt->{rsyncable} // next;
+ push @cmd, '--'.($switch || $bool);
+ }
+ for my $key (qw(threads)) { # support compression level?
+ my $switch = $cmd_opt->{$key} // next;
+ my $val = $lei->{opt}->{$key} // next;
+ push @cmd, $switch, $val;
+ }
+ \@cmd;
+}
+
+sub _post_augment_mbox { # open a compressor process
+ my ($self, $lei, $zpipe) = @_;
+ my $zsfx = $self->{zsfx} or return;
+ my $cmd = zsfx2cmd($zsfx, undef, $lei);
+ my ($r, $w) = splice(@$zpipe, 0, 2);
+ my $rdr = { 0 => $r, 1 => $lei->{1}, 2 => $lei->{2} };
+ my $pid = spawn($cmd, $lei->{env}, $rdr);
+ my $pp = gensym;
+ my $dup = bless { "pid.$pid" => $cmd }, ref($lei);
+ $dup->{$_} = $lei->{$_} for qw(2 sock);
+ tie *$pp, 'PublicInbox::ProcessPipe', $pid, $w, \&reap_compress, $dup;
+ $lei->{1} = $pp;
+ die 'BUG: unexpected {ovv}->{lock_path}' if $lei->{ovv}->{lock_path};
+ $lei->{ovv}->ovv_out_lk_init;
+}
+
+sub decompress_src ($$$) {
+ my ($in, $zsfx, $lei) = @_;
+ my $cmd = zsfx2cmd($zsfx, 1, $lei);
+ popen_rd($cmd, $lei->{env}, { 0 => $in, 2 => $lei->{2} });
+}
+
+sub dup_src ($) {
+ my ($in) = @_;
+ open my $dup, '+>>&', $in or die "dup: $!";
+ $dup;
+}
+
+# --augment existing output destination, with deduplication
+sub _augment { # MboxReader eml_cb
+ my ($eml, $lei) = @_;
+ # ignore return value, just populate the skv
+ $lei->{dedupe}->is_dup($eml);
+}
+
+sub _mbox_write_cb ($$) {
+ my ($self, $lei) = @_;
+ my $ovv = $lei->{ovv};
+ my $m = 'eml2'.$ovv->{fmt};
+ my $eml2mbox = $self->can($m) or die "$self->$m missing";
+ $lei->{1} // die "no stdout ($m, $ovv->{dst})"; # redirected earlier
+ $lei->{1}->autoflush(1);
+ my $atomic_append = !defined($ovv->{lock_path});
+ my $dedupe = $lei->{dedupe};
+ $dedupe->prepare_dedupe;
+ sub { # for git_to_mail
+ my ($buf, $smsg, $eml) = @_;
+ $eml //= PublicInbox::Eml->new($buf);
+ return if $dedupe->is_dup($eml, $smsg->{blob});
+ $buf = $eml2mbox->($eml, $smsg);
+ return atomic_append($lei, $buf) if $atomic_append;
+ my $lk = $ovv->lock_for_scope;
+ $lei->out($$buf);
+ }
+}
+
+sub _maildir_each_file ($$;@) {
+ my ($dir, $cb, @arg) = @_;
+ for my $d (qw(new/ cur/)) {
+ my $pfx = $dir.$d;
+ opendir my $dh, $pfx or next;
+ while (defined(my $fn = readdir($dh))) {
+ $cb->($pfx.$fn, @arg) if $fn =~ /:2,[A-Za-z]*\z/;
+ }
+ }
+}
+
+sub _augment_file { # _maildir_each_file cb
+ my ($f, $lei) = @_;
+ my $eml = PublicInbox::InboxWritable::eml_from_path($f) or return;
+ _augment($eml, $lei);
+}
+
+# _maildir_each_file callback, \&CORE::unlink doesn't work with it
+sub _unlink { unlink($_[0]) }
+
+sub _rand () {
+ state $seq = 0;
+ sprintf('%x,%x,%x,%x', rand(0xffffffff), time, $$, ++$seq);
+}
+
+sub _buf2maildir {
+ my ($dst, $buf, $smsg) = @_;
+ my $kw = $smsg->{kw} // [];
+ my $sfx = join('', sort(map { $kw2char{$_} // () } @$kw));
+ my $rand = ''; # chosen by die roll :P
+ my ($tmp, $fh, $final, $ok);
+ my $common = $smsg->{blob} // _rand;
+ if (defined(my $pct = $smsg->{pct})) { $common .= "=$pct" }
+ do {
+ $tmp = $dst.'tmp/'.$rand.$common;
+ } while (!($ok = sysopen($fh, $tmp, O_CREAT|O_EXCL|O_WRONLY)) &&
+ $! == EEXIST && ($rand = _rand.','));
+ if ($ok && print $fh $$buf and close($fh)) {
+ # ignore new/ and write only to cur/, otherwise MUAs
+ # with R/W access to the Maildir will end up doing
+ # a mass rename which can take a while with thousands
+ # of messages.
+ $dst .= 'cur/';
+ $rand = '';
+ do {
+ $final = $dst.$rand.$common.':2,'.$sfx;
+ } while (!link($tmp, $final) && $! == EEXIST &&
+ ($rand = _rand.','));
+ unlink($tmp) or warn "W: failed to unlink $tmp: $!\n";
+ } else {
+ my $err = "Error writing $smsg->{blob} to $dst: $!\n";
+ $_[0] = undef; # clobber dst
+ unlink($tmp);
+ die $err;
+ }
+}
+
+sub _maildir_write_cb ($$) {
+ my ($self, $lei) = @_;
+ my $dedupe = $lei->{dedupe};
+ $dedupe->prepare_dedupe if $dedupe;
+ my $dst = $lei->{ovv}->{dst};
+ sub { # for git_to_mail
+ my ($buf, $smsg, $eml) = @_;
+ $dst // return $lei->fail; # dst may be undef-ed in last run
+ $buf //= \($eml->as_string);
+ return _buf2maildir($dst, $buf, $smsg) if !$dedupe;
+ $eml //= PublicInbox::Eml->new($$buf); # copy buf
+ return if $dedupe->is_dup($eml, $smsg->{blob});
+ undef $eml;
+ _buf2maildir($dst, $buf, $smsg);
+ }
+}
+
+sub write_cb { # returns a callback for git_to_mail
+ my ($self, $lei) = @_;
+ # _mbox_write_cb or _maildir_write_cb
+ my $m = "_$self->{base_type}_write_cb";
+ $self->$m($lei);
+}
+
+sub new {
+ my ($cls, $lei) = @_;
+ my $fmt = $lei->{ovv}->{fmt};
+ my $dst = $lei->{ovv}->{dst};
+ my $self = bless {}, $cls;
+ if ($fmt eq 'maildir') {
+ $self->{base_type} = 'maildir';
+ -e $dst && !-d _ and die
+ "$dst exists and is not a directory\n";
+ $lei->{ovv}->{dst} = $dst .= '/' if substr($dst, -1) ne '/';
+ } elsif (substr($fmt, 0, 4) eq 'mbox') {
+ (-d $dst || (-e _ && !-w _)) and die
+ "$dst exists and is not a writable file\n";
+ $self->can("eml2$fmt") or die "bad mbox --format=$fmt\n";
+ $self->{base_type} = 'mbox';
+ } else {
+ die "bad mail --format=$fmt\n";
+ }
+ $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei);
+ $self;
+}
+
+sub _pre_augment_maildir {} # noop
+
+sub _do_augment_maildir {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ if ($lei->{opt}->{augment}) {
+ my $dedupe = $lei->{dedupe};
+ if ($dedupe && $dedupe->prepare_dedupe) {
+ require PublicInbox::InboxWritable; # eml_from_path
+ _maildir_each_file($dst, \&_augment_file, $lei);
+ $dedupe->pause_dedupe;
+ }
+ } else { # clobber existing Maildir
+ _maildir_each_file($dst, \&_unlink);
+ }
+}
+
+sub _post_augment_maildir {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ for my $x (qw(tmp new cur)) {
+ my $d = $dst.$x;
+ next if -d $d;
+ require File::Path;
+ File::Path::mkpath($d);
+ -d $d or die "$d is not a directory";
+ }
+}
+
+sub _pre_augment_mbox {
+ my ($self, $lei) = @_;
+ my $dst = $lei->{ovv}->{dst};
+ if ($dst ne '/dev/stdout') {
+ my $mode = -p $dst ? '>' : '+>>';
+ if (-f _ && !$lei->{opt}->{augment} and !unlink($dst)) {
+ $! == ENOENT or die "unlink($dst): $!";
+ }
+ open my $out, $mode, $dst or die "open($dst): $!";
+ $lei->{old_1} = $lei->{1};
+ $lei->{1} = $out;
+ }
+ # Perl does SEEK_END even with O_APPEND :<
+ $self->{seekable} = seek($lei->{1}, 0, SEEK_SET);
+ if (!$self->{seekable} && $! != ESPIPE && $dst ne '/dev/stdout') {
+ die "seek($dst): $!\n";
+ }
+ state $zsfx_allow = join('|', keys %zsfx2cmd);
+ ($self->{zsfx}) = ($dst =~ /\.($zsfx_allow)\z/) or return;
+ pipe(my ($r, $w)) or die "pipe: $!";
+ [ $r, $w ];
+}
+
+sub _do_augment_mbox {
+ my ($self, $lei) = @_;
+ return if !$lei->{opt}->{augment};
+ my $dedupe = $lei->{dedupe};
+ my $dst = $lei->{ovv}->{dst};
+ die "cannot augment $dst, not seekable\n" if !$self->{seekable};
+ my $out = $lei->{1};
+ if (-s $out && $dedupe && $dedupe->prepare_dedupe) {
+ my $zsfx = $self->{zsfx};
+ my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) :
+ dup_src($out);
+ my $fmt = $lei->{ovv}->{fmt};
+ require PublicInbox::MboxReader;
+ PublicInbox::MboxReader->$fmt($rd, \&_augment, $lei);
+ }
+ # maybe some systems don't honor O_APPEND, Perl does this:
+ seek($out, 0, SEEK_END) or die "seek $dst: $!";
+ $dedupe->pause_dedupe if $dedupe;
+}
+
+sub pre_augment { # fast (1 disk seek), runs in main daemon
+ my ($self, $lei) = @_;
+ # _pre_augment_maildir, _pre_augment_mbox
+ my $m = "_pre_augment_$self->{base_type}";
+ $self->$m($lei);
+}
+
+sub do_augment { # slow, runs in wq worker
+ my ($self, $lei) = @_;
+ # _do_augment_maildir, _do_augment_mbox
+ my $m = "_do_augment_$self->{base_type}";
+ $self->$m($lei);
+}
+
+sub post_augment { # fast (spawn compressor or mkdir), runs in main daemon
+ my ($self, $lei, @args) = @_;
+ # _post_augment_maildir, _post_augment_mbox
+ my $m = "_post_augment_$self->{base_type}";
+ $self->$m($lei, @args);
+}
+
+sub write_mail { # via ->wq_do
+ my ($self, $git_dir, $smsg, $lei) = @_;
+ my $not_done = delete $self->{$lei->{each_smsg_not_done}};
+ my $wcb = $self->{wcb} //= do { # first message
+ $lei->atfork_child_wq($self);
+ $self->write_cb($lei);
+ };
+ my $git = $self->{"$$\0$git_dir"} //= PublicInbox::Git->new($git_dir);
+ git_async_cat($git, $smsg->{blob}, \&git_to_mail,
+ [$wcb, $smsg, $not_done]);
+}
+
+sub wq_atexit_child {
+ my ($self) = @_;
+ delete $self->{wcb};
+ for my $git (delete @$self{grep(/\A$$\0/, keys %$self)}) {
+ $git->async_wait_all;
+ }
+ $SIG{__WARN__} = 'DEFAULT';
+}
+
1;