# Copyright (C) 2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-# "lei add-external --mirror" support
+# "lei add-external --mirror" support (also "public-inbox-clone");
package PublicInbox::LeiMirror;
use strict;
use v5.10.1;
use parent qw(PublicInbox::IPC);
use IO::Uncompress::Gunzip qw(gunzip $GunzipError);
-use PublicInbox::Spawn qw(popen_rd spawn);
-use PublicInbox::PktOp;
+use PublicInbox::Spawn qw(popen_rd spawn run_die);
+use File::Temp ();
+use Fcntl qw(SEEK_SET);
sub do_finish_mirror { # dwaitpid callback
my ($arg, $pid) = @_;
my ($mrr, $lei) = @$arg;
- if ($? == 0 && unlink("$mrr->{dst}/mirror.done")) {
- $lei->add_external_finish($mrr->{dst});
+ my $f = "$mrr->{dst}/mirror.done";
+ if ($?) {
+ $lei->child_error($?);
+ } elsif (!unlink($f)) {
+ $lei->err("unlink($f): $!") unless $!{ENOENT};
+ } else {
+ if ($lei->{cmd} ne 'public-inbox-clone') {
+ $lei->add_external_finish($mrr->{dst});
+ }
+ $lei->qerr("# mirrored $mrr->{src} => $mrr->{dst}");
}
$lei->dclose;
}
-sub mirror_done { # EOF callback for main daemon
+sub _lei_wq_eof { # EOF callback for main daemon
my ($lei) = @_;
- my $mrr = delete $lei->{mrr} or return;
+ my $mrr = delete $lei->{wq1} or return $lei->fail;
$mrr->wq_wait_old(\&do_finish_mirror, $lei);
}
my $uri = URI->new($self->{src});
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
- my $cmd = $curl->for_uri($lei, $uri);
+ my $cmd = $curl->for_uri($lei, $uri, '--compressed');
my $opt = { 0 => $lei->{0}, 2 => $lei->{2} };
- my $fh = popen_rd($cmd, $lei->{env}, $opt);
+ my $fh = popen_rd($cmd, undef, $opt);
my $html = do { local $/; <$fh> } // die "read(curl $uri): $!";
close($fh) or return $lei->child_error($?, "@$cmd failed");
@cmd;
}
+sub _get_txt { # non-fatal
+ my ($self, $endpoint, $file) = @_;
+ my $uri = URI->new($self->{src});
+ my $lei = $self->{lei};
+ my $path = $uri->path;
+ chop($path) eq '/' or die "BUG: $uri not canonicalized";
+ $uri->path("$path/$endpoint");
+ my $cmd = $self->{curl}->for_uri($lei, $uri, '--compressed');
+ my $ce = "$self->{dst}/$file";
+ my $ft = File::Temp->new(TEMPLATE => "$file-XXXX",
+ UNLINK => 1, DIR => $self->{dst});
+ my $opt = { 0 => $lei->{0}, 1 => $ft, 2 => $lei->{2} };
+ my $cerr = run_reap($lei, $cmd, $opt);
+ return "$uri missing" if ($cerr >> 8) == 22;
+ return "# @$cmd failed (non-fatal)" if $cerr;
+ my $f = $ft->filename;
+ rename($f, $ce) or return "rename($f, $ce): $! (non-fatal)";
+ $ft->unlink_on_destroy(0);
+ undef; # success
+}
+
# tries the relatively new /$INBOX/_/text/config/raw endpoint
sub _try_config {
my ($self) = @_;
File::Path::mkpath($dst);
-d $dst or die "mkpath($dst): $!\n";
}
- my $uri = URI->new($self->{src});
- my $lei = $self->{lei};
- my $path = $uri->path;
- chop($path) eq '/' or die "BUG: $uri not canonicalized";
- $uri->path($path . '/_/text/config/raw');
- my $cmd = $self->{curl}->for_uri($lei, $uri);
- push @$cmd, '--compressed'; # curl decompresses for us
- my $ce = "$dst/inbox.config.example";
- my $f = "$ce-$$.tmp";
- open(my $fh, '+>', $f) or return $lei->err("open $f: $! (non-fatal)");
- my $opt = { 0 => $lei->{0}, 1 => $fh, 2 => $lei->{2} };
- my $cerr = run_reap($lei, $cmd, $opt) // return;
- if (($cerr >> 8) == 22) { # 404 missing
- unlink($f) if -s $fh == 0;
- return;
- }
- return $lei->err("# @$cmd failed (non-fatal)") if $cerr;
- rename($f, $ce) or return $lei->err("link($f, $ce): $! (non-fatal)");
- my $cfg = PublicInbox::Config::git_config_dump($f);
+ my $err = _get_txt($self, qw(_/text/config/raw inbox.config.example));
+ return $self->{lei}->err($err) if $err;
+ my $f = "$self->{dst}/inbox.config.example";
+ my $cfg = PublicInbox::Config->git_config_dump($f, $self->{lei}->{2});
my $ibx = $self->{ibx} = {};
for my $sec (grep(/\Apublicinbox\./, @{$cfg->{-section_order}})) {
for (qw(address newsgroup nntpmirror)) {
}
}
+sub set_description ($) {
+ my ($self) = @_;
+ my $f = "$self->{dst}/description";
+ open my $fh, '+>>', $f or die "open($f): $!";
+ seek($fh, 0, SEEK_SET) or die "seek($f): $!";
+ chomp(my $d = do { local $/; <$fh> } // die "read($f): $!");
+ if ($d eq '($INBOX_DIR/description missing)' ||
+ $d =~ /^Unnamed repository/ || $d !~ /\S/) {
+ seek($fh, 0, SEEK_SET) or die "seek($f): $!";
+ truncate($fh, 0) or die "truncate($f): $!";
+ print $fh "mirror of $self->{src}\n" or die "print($f): $!";
+ close $fh or die "close($f): $!";
+ }
+}
+
sub index_cloned_inbox {
my ($self, $iv) = @_;
- my $ibx = delete($self->{ibx}) // {
- address => [ 'lei@example.com' ],
- version => $iv,
- };
- $ibx->{inboxdir} = $self->{dst};
- PublicInbox::Inbox->new($ibx);
- PublicInbox::InboxWritable->new($ibx);
- my $opt = {};
my $lei = $self->{lei};
- for my $sw ($lei->index_opt) {
- my ($k) = ($sw =~ /\A([\w-]+)/);
- $opt->{$k} = $lei->{opt}->{$k};
+ my $err = _get_txt($self, qw(description description));
+ $lei->err($err) if $err; # non fatal
+ eval { set_description($self) };
+ warn $@ if $@;
+
+ # n.b. public-inbox-clone works w/o (SQLite || Xapian)
+ # lei is useless without Xapian + SQLite
+ if ($lei->{cmd} ne 'public-inbox-clone') {
+ my $ibx = delete($self->{ibx}) // {
+ address => [ 'lei@example.com' ],
+ version => $iv,
+ };
+ $ibx->{inboxdir} = $self->{dst};
+ PublicInbox::Inbox->new($ibx);
+ PublicInbox::InboxWritable->new($ibx);
+ my $opt = {};
+ for my $sw ($lei->index_opt) {
+ my ($k) = ($sw =~ /\A([\w-]+)/);
+ $opt->{$k} = $lei->{opt}->{$k};
+ }
+ # force synchronous dwaitpid for v2:
+ local $PublicInbox::DS::in_loop = 0;
+ my $cfg = PublicInbox::Config->new(undef, $lei->{2});
+ my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
+ local %ENV = (%ENV, %$env) if $env;
+ PublicInbox::Admin::progress_prepare($opt, $lei->{2});
+ PublicInbox::Admin::index_inbox($ibx, undef, $opt);
}
- # force synchronous dwaitpid for v2:
- local $PublicInbox::DS::in_loop = 0;
- my $cfg = PublicInbox::Config->new;
- my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
- local %ENV = (%ENV, %$env) if $env;
- PublicInbox::Admin::progress_prepare($opt, $lei->{2});
- PublicInbox::Admin::index_inbox($ibx, undef, $opt);
open my $x, '>', "$self->{dst}/mirror.done"; # for do_finish_mirror
}
sub run_reap {
my ($lei, $cmd, $opt) = @_;
- $lei->qerr("# @$cmd");
- $opt->{pgid} = 0;
- my $pid = spawn($cmd, $lei->{env}, $opt);
+ $lei->qerr("# @$cmd" . ($opt->{-C} ? " (in $opt->{-C})" : ''));
+ $opt->{pgid} = 0 if $lei->{sock};
+ my $pid = spawn($cmd, undef, $opt);
my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid);
- my $err = waitpid($pid, 0) == $pid ? undef : "waitpid @$cmd: $!";
+ waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!";
@$reap = (); # cancel reap
- $err ? $lei->err($err) : $?
+ $?
}
sub clone_v1 {
my $pfx = $curl->torsocks($lei, $uri) or return;
my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}),
$uri->as_string, $self->{dst} ];
- my $cerr = run_reap($lei, $cmd, $opt) // return;
+ my $cerr = run_reap($lei, $cmd, $opt);
return $lei->child_error($cerr, "@$cmd failed") if $cerr;
_try_config($self);
index_cloned_inbox($self, 1);
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
my $pfx //= $curl->torsocks($lei, $v2_uris->[0]) or return;
- my @epochs;
my $dst = $self->{dst};
my @src_edst;
for my $uri (@$v2_uris) {
my $nr = $1 + 0;
$edst .= "/git/$nr.git";
- push @src_edst, [ $src, $edst ];
+ push @src_edst, $src, $edst;
}
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
_try_config($self);
my $on_destroy = $lk->lock_for_scope($$);
my @cmd = clone_cmd($lei, my $opt = {});
- while (my $pair = shift(@src_edst)) {
- my $cmd = [ @$pfx, @cmd, @$pair ];
- my $cerr = run_reap($lei, $cmd, $opt) // return;
+ while (my ($src, $edst) = splice(@src_edst, 0, 2)) {
+ my $cmd = [ @$pfx, @cmd, $src, $edst ];
+ my $cerr = run_reap($lei, $cmd, $opt);
return $lei->child_error($cerr, "@$cmd failed") if $cerr;
}
+ require PublicInbox::MultiGit;
+ my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
+ $mg->fill_alternates;
+ for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
undef $on_destroy; # unlock
index_cloned_inbox($self, 2);
}
+# PSGI mount prefixes and manifest.js.gz prefixes don't always align...
+sub deduce_epochs ($$) {
+ my ($m, $path) = @_;
+ my ($v1_ent, @v2_epochs);
+ my $path_pfx = '';
+ $path =~ s!/+\z!!;
+ do {
+ $v1_ent = $m->{$path};
+ @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m);
+ } while (!defined($v1_ent) && !@v2_epochs &&
+ $path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1);
+ ($path_pfx, $v1_ent ? $path : undef, @v2_epochs);
+}
+
+sub decode_manifest ($$$) {
+ my ($fh, $fn, $uri) = @_;
+ my $js;
+ my $gz = do { local $/; <$fh> } // die "slurp($fn): $!";
+ gunzip(\$gz => \$js, MultiStream => 1) or
+ die "gunzip($uri): $GunzipError\n";
+ my $m = eval { PublicInbox::Config->json->decode($js) };
+ die "$uri: error decoding `$js': $@\n" if $@;
+ ref($m) eq 'HASH' or die "$uri unknown type: ".ref($m);
+ $m;
+}
+
sub try_manifest {
my ($self) = @_;
my $uri = URI->new($self->{src});
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
- my $cmd = $curl->for_uri($lei, $uri);
- $lei->qerr("# @$cmd");
- my $opt = { 0 => $lei->{0}, 2 => $lei->{2} };
- my ($fh, $pid) = popen_rd($cmd, $lei->{env}, $opt);
- my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid);
- my $gz = do { local $/; <$fh> } // die "read(curl $uri): $!";
- close $fh;
- my $err = waitpid($pid, 0) == $pid ? undef : "waitpid @$cmd: $!";
- @$reap = ();
- return $lei->err($err) if $err;
- if ($?) {
- return try_scrape($self) if ($? >> 8) == 22; # 404 missing
- return $lei->child_error($?, "@$cmd failed");
+ my $pdir = $lei->rel2abs($self->{dst});
+ $pdir =~ s!/[^/]+/?\z!!;
+ my $ft = File::Temp->new(TEMPLATE => 'manifest-XXXX',
+ UNLINK => 1, DIR => $pdir);
+ my $fn = $ft->filename;
+ my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn);
+ my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
+ my $cerr = run_reap($lei, $cmd, $opt);
+ if ($cerr) {
+ return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
+ return $lei->child_error($cerr, "@$cmd failed");
}
- my $js;
- gunzip(\$gz => \$js, MultiStream => 1) or
- die "gunzip($uri): $GunzipError";
- my $m = eval { PublicInbox::Config->json->decode($js) };
- die "$uri: error decoding `$js': $@" if $@;
- ref($m) eq 'HASH' or die "$uri unknown type: ".ref($m);
-
- my $v1_bare = $m->{$path};
- my @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m);
+ my $m = decode_manifest($ft, $fn, $uri);
+ my ($path_pfx, $v1_path, @v2_epochs) = deduce_epochs($m, $path);
if (@v2_epochs) {
# It may be possible to have v1 + v2 in parallel someday:
- $lei->err(<<EOM) if defined $v1_bare;
-# `$v1_bare' appears to be a v1 inbox while v2 epochs exist:
+ $lei->err(<<EOM) if defined $v1_path;
+# `$v1_path' appears to be a v1 inbox while v2 epochs exist:
# @v2_epochs
-# ignoring $v1_bare (use --inbox-version=1 to force v1 instead)
+# ignoring $v1_path (use --inbox-version=1 to force v1 instead)
EOM
- @v2_epochs = map { $uri->path($_); $uri->clone } @v2_epochs;
+ @v2_epochs = map {
+ $uri->path($path_pfx.$_);
+ $uri->clone
+ } @v2_epochs;
clone_v2($self, \@v2_epochs);
- } elsif ($v1_bare) {
+ } elsif (defined $v1_path) {
clone_v1($self);
- } elsif (my @maybe = grep(m!\Q$path\E!, keys %$m)) {
- die "E: confused by <$uri>, possible matches:\n@maybe";
} else {
- die "E: confused by <$uri>";
+ die "E: confused by <$uri>, possible matches:\n\t",
+ join(', ', sort keys %$m), "\n";
}
+ my $fin = "$self->{dst}/manifest.js.gz";
+ rename($fn, $fin) or die "E: rename($fn, $fin): $!";
+ $ft->unlink_on_destroy(0);
}
sub start_clone_url {
die "TODO: non-HTTP/HTTPS clone of $self->{src} not supported, yet";
}
-sub do_mirror { # via wq_do
+sub do_mirror { # via wq_io_do
my ($self) = @_;
my $lei = $self->{lei};
eval {
return start_clone_url($self) if $self->{src} =~ m!://!;
die "TODO: cloning local directories not supported, yet";
};
- return $lei->fail($@) if $@;
- $lei->qerr("# mirrored $self->{src} => $self->{dst}");
+ $lei->fail($@) if $@;
}
sub start {
my ($cls, $lei, $src, $dst) = @_;
- my $self = bless { lei => $lei, src => $src, dst => $dst }, $cls;
- $lei->{mrr} = $self;
+ my $self = bless { src => $src, dst => $dst }, $cls;
if ($src =~ m!https?://!) {
require URI;
require PublicInbox::LeiCurl;
require PublicInbox::Inbox;
require PublicInbox::Admin;
require PublicInbox::InboxWritable;
- my $ops = {
- '!' => [ $lei->can('fail_handler'), $lei ],
- 'x_it' => [ $lei->can('x_it'), $lei ],
- 'child_error' => [ $lei->can('child_error'), $lei ],
- '' => [ \&mirror_done, $lei ],
- };
- ($lei->{pkt_op_c}, $lei->{pkt_op_p}) = PublicInbox::PktOp->pair($ops);
- $self->wq_workers_start('lei_mirror', 1, $lei->oldset, {lei => $lei});
- my $op = delete $lei->{pkt_op_c};
- delete $lei->{pkt_op_p};
- $self->wq_do('do_mirror', []);
+ my ($op_c, $ops) = $lei->workers_start($self, 1);
+ $lei->{wq1} = $self;
+ $self->wq_io_do('do_mirror', []);
$self->wq_close(1);
- $lei->event_step_init; # wait for shutdowns
- if ($lei->{oneshot}) {
- while ($op->{sock}) { $op->event_step }
- }
+ $lei->wait_wq_events($op_c, $ops);
}
sub ipc_atfork_child {
my ($self) = @_;
- $self->{lei}->lei_atfork_child;
+ $self->{lei}->_lei_atfork_child;
$SIG{TERM} = sub { exit(128 + 15) }; # trigger OnDestroy $reap
$self->SUPER::ipc_atfork_child;
}