X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=5e1b1c64754aed550c8a1c9a1f8ab621ace43b9e;hb=74fe3d0dc688202adc634cfc6a9e57f1aa28d85d;hp=355813bdc7af0faac86a23959dcc568d2173d1e2;hpb=02a0f3959b2e74f7217fcdca848822e7230acd6b;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 355813bd..5e1b1c64 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -1,35 +1,45 @@ -# Copyright (C) 2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ -# "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 IO::Compress::Gzip qw(gzip $GzipError); +use PublicInbox::Spawn qw(popen_rd spawn run_die); +use File::Path (); +use File::Temp (); +use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY); +use Carp qw(croak); +use URI; +use PublicInbox::Config; +use PublicInbox::Inbox; +use PublicInbox::LeiCurl; +use PublicInbox::OnDestroy; -sub do_finish_mirror { # dwaitpid callback +our %LIVE; # pid => callback + +sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; my ($mrr, $lei) = @$arg; my $f = "$mrr->{dst}/mirror.done"; if ($?) { $lei->child_error($?); } elsif (!unlink($f)) { - $lei->err("unlink($f): $!") unless $!{ENOENT}; + warn("unlink($f): $!\n") unless $!{ENOENT}; } else { - $lei->add_external_finish($mrr->{dst}); + if ($lei->{cmd} ne 'public-inbox-clone') { + # calls _finish_add_external + $lei->lazy_cb('add-external', '_finish_' + )->($lei, $mrr->{dst}); + } $lei->qerr("# mirrored $mrr->{src} => $mrr->{dst}"); } $lei->dclose; } -sub _lei_wq_eof { # EOF callback for main daemon - my ($lei) = @_; - my $mrr = delete $lei->{wq1} or return $lei->fail; - $mrr->wq_wait_old(\&do_finish_mirror, $lei); -} - # for old installations without manifest.js.gz sub try_scrape { my ($self) = @_; @@ -44,15 +54,21 @@ sub try_scrape { # we grep with URL below, we don't want Subject/From headers # making us clone random URLs - my @urls = ($html =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g); + my @html = split(/
/, $html); + my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g); my $url = $uri->as_string; chop($url) eq '/' or die "BUG: $uri not canonicalized"; # since this is for old instances w/o manifest.js.gz, try v1 first return clone_v1($self) if grep(m!\A\Q$url\E/*\z!, @urls); if (my @v2_urls = grep(m!\A\Q$url\E/[0-9]+\z!, @urls)) { - my %v2_uris = map { $_ => URI->new($_) } @v2_urls; # uniq - return clone_v2($self, [ values %v2_uris ]); + my %v2_epochs = map { + my ($n) = (m!/([0-9]+)\z!); + $n => [ URI->new($_), '' ] + } @v2_urls; # uniq + clone_v2($self, \%v2_epochs); + reap_live() while keys(%LIVE); + return; } # filter out common URLs served by WWW (e.g /$MSGID/T/) @@ -77,40 +93,72 @@ sub clone_cmd { # e.g.: git -c http.proxy=socks5h://127.0.0.1:9050 push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []}; push @cmd, qw(clone --mirror); - push @cmd, '-q' if $lei->{opt}->{quiet}; + push @cmd, '-q' if $lei->{opt}->{quiet} || + ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; # XXX any other options to support? # --reference is tricky with multiple epochs... @cmd; } -# tries the relatively new /$INBOX/_/text/config/raw endpoint -sub _try_config { - my ($self) = @_; - my $dst = $self->{dst}; - if (!-d $dst || !mkdir($dst)) { - require File::Path; - File::Path::mkpath($dst); - -d $dst or die "mkpath($dst): $!\n"; - } - my $uri = URI->new($self->{src}); +sub ft_rename ($$$) { + my ($ft, $dst, $open_mode) = @_; + my $fn = $ft->filename; + my @st = stat($dst); + my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask); + chmod($mode, $ft) or croak "E: chmod $fn: $!"; + rename($fn, $dst) or croak "E: rename($fn => $ft): $!"; + $ft->unlink_on_destroy(0); +} + +sub _get_txt_start { # non-fatal + my ($self, $endpoint, $fini) = @_; + my $uri = URI->new($self->{cur_src} // $self->{src}); my $lei = $self->{lei}; my $path = $uri->path; chop($path) eq '/' or die "BUG: $uri not canonicalized"; - $uri->path($path . '/_/text/config/raw'); - my $cmd = $self->{curl}->for_uri($lei, $uri, '--compressed'); - my $ce = "$dst/inbox.config.example"; - my $f = "$ce-$$.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, $opt); - if (($cerr >> 8) == 22) { # 404 missing - unlink($f) if -s $fh == 0; - return; + $uri->path("$path/$endpoint"); + my $f = (split(m!/!, $endpoint))[-1]; + my $ft = File::Temp->new(TEMPLATE => "$f-XXXX", TMPDIR => 1); + my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} }; + my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o), + $ft->filename); + $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; + my $jobs = $lei->{opt}->{jobs} // 1; + reap_live() while keys(%LIVE) >= $jobs; + $lei->qerr("# @$cmd"); + $LIVE{spawn($cmd, undef, $opt)} = + [ \&_get_txt_done, $self, $endpoint, $fini ]; +} + +sub _get_txt_done { # returns true on error (non-fatal), undef on success + my ($self, $endpoint) = @_; + my ($fh, $cmd, $uri) = @{delete $self->{"-get_txt.$endpoint"}}; + my $cerr = $?; + $? = 0; # don't influence normal lei exit + return warn("$uri missing\n") if ($cerr >> 8) == 22; + return warn("# @$cmd failed (non-fatal)\n") if $cerr; + seek($fh, SEEK_SET, 0) or die "seek: $!"; + $self->{"mtime.$endpoint"} = (stat($fh))[9]; + local $/; + $self->{"txt.$endpoint"} = <$fh>; + undef; # success +} + +sub _write_inbox_config { + my ($self) = @_; + my $buf = delete($self->{'txt._/text/config/raw'}) // return; + my $dst = $self->{cur_dst} // $self->{dst}; + my $f = "$dst/inbox.config.example"; + open my $fh, '>', $f or die "open($f): $!"; + print $fh $buf or die "print: $!"; + chmod(0444 & ~umask, $fh) or die "chmod($f): $!"; + my $mtime = delete $self->{'mtime._/text/config/raw'}; + $fh->flush or die "flush($f): $!"; + if (defined $mtime) { + utime($mtime, $mtime, $fh) or die "utime($f): $!"; } - return $lei->err("# @$cmd failed (non-fatal)") if $cerr; - rename($f, $ce) or return $lei->err("rename($f, $ce): $! (non-fatal)"); - my $cfg = PublicInbox::Config->git_config_dump($f, $lei->{2}); + 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)) { @@ -119,100 +167,338 @@ sub _try_config { } } +sub set_description ($) { + my ($self) = @_; + my $dst = $self->{cur_dst} // $self->{dst}; + my $f = "$dst/description"; + open my $fh, '+>>', $f or die "open($f): $!"; + seek($fh, 0, SEEK_SET) or die "seek($f): $!"; + my $d = do { local $/; <$fh> } // die "read($f): $!"; + my $orig = $d; + while (defined($d) && ($d =~ m!^\(\$INBOX_DIR/description missing\)! || + $d =~ /^Unnamed repository/ || $d !~ /\S/)) { + $d = delete($self->{'txt.description'}); + } + $d //= 'mirror of '.($self->{cur_src} // $self->{src})."\n"; + return if $d eq $orig; + seek($fh, 0, SEEK_SET) or die "seek($f): $!"; + truncate($fh, 0) or die "truncate($f): $!"; + print $fh $d or die "print($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}; + 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') { + require PublicInbox::InboxWritable; + require PublicInbox::Admin; + my $ibx = delete($self->{ibx}) // { + address => [ 'lei@example.com' ], + version => $iv, + }; + $ibx->{inboxdir} = $self->{cur_dst} // $self->{dst}; + PublicInbox::Inbox->new($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(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); - open my $x, '>', "$self->{dst}/mirror.done"; # for do_finish_mirror + return if defined $self->{cur_dst}; + open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } sub run_reap { my ($lei, $cmd, $opt) = @_; $lei->qerr("# @$cmd"); - $opt->{pgid} = 0; - my $pid = spawn($cmd, undef, $opt); - my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid); - waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!"; - @$reap = (); # cancel reap - $? + waitpid(spawn($cmd, undef, $opt), 0) // die "waitpid: $!"; + my $ret = $?; + $? = 0; # don't let it influence normal exit + $ret; +} + +sub start_clone { + my ($self, $cmd, $opt, $fini) = @_; + my $jobs = $self->{lei}->{opt}->{jobs} // 1; + reap_live() while keys(%LIVE) >= $jobs; + $self->{lei}->qerr("# @$cmd"); + $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]; } sub clone_v1 { - my ($self) = @_; + my ($self, $nohang) = @_; my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $uri = URI->new($self->{src}); + my $uri = URI->new($self->{cur_src} // $self->{src}); + defined($lei->{opt}->{epoch}) and + die "$uri is a v1 inbox, --epoch is not supported\n"; 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 $lei->child_error($cerr, "@$cmd failed") if $cerr; - _try_config($self); + my $dst = $self->{cur_dst} // $self->{dst}; + my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); + my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; + start_clone($self, $cmd, $opt, $fini); + + _get_txt_start($self, '_/text/config/raw', $fini); + my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; + defined($d) ? ($self->{'txt.description'} = $d) : + _get_txt_start($self, 'description', $fini); + + reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone +} + +sub parse_epochs ($$) { + my ($opt_epochs, $v2_epochs) = @_; # $epochs "LOW..HIGH" + $opt_epochs // return; # undef => all epochs + my ($lo, $dotdot, $hi, @extra) = split(/(\.\.)/, $opt_epochs); + undef($lo) if ($lo // '') eq ''; + my $re = qr/\A~?[0-9]+\z/; + if (@extra || (($lo // '0') !~ $re) || + (($hi // '0') !~ $re) || + !(grep(defined, $lo, $hi))) { + die < $b } keys %$v2_epochs; + for (grep(defined, $lo, $hi)) { + if (/\A[0-9]+\z/) { + $_ > $n[-1] and die +"`$_' exceeds maximum available epoch ($n[-1])\n"; + $_ < $n[0] and die +"`$_' is lower than minimum available epoch ($n[0])\n"; + } elsif (/\A~([0-9]+)/) { + my $off = -$1 - 1; + $n[$off] // die "`$_' is out of range\n"; + $_ = $n[$off]; + } else { die "`$_' not understood\n" } + } + defined($lo) && defined($hi) && $lo > $hi and die +"low value (`$lo') exceeds high (`$hi')\n"; + $lo //= $n[0] if $dotdot; + $hi //= $n[-1] if $dotdot; + $hi //= $lo; + my $want = {}; + for ($lo..$hi) { + if (defined $v2_epochs->{$_}) { + $want->{$_} = 1; + } else { + warn +"# epoch $_ is not available (non-fatal, $lo..$hi)\n"; + } + } + $want +} + +sub init_placeholder ($$$) { + my ($src, $edst, $owner) = @_; + PublicInbox::Import::init_bare($edst); + my $f = "$edst/config"; + open my $fh, '>>', $f or die "open($f): $!"; + print $fh <{lei}->child_error($cerr, "@$cmd failed"); + } +} + +sub v1_done { # called via OnDestroy + my ($self) = @_; + _write_inbox_config($self); + my $dst = $self->{cur_dst} // $self->{dst}; + if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) { + run_die([qw(git config -f), "$dst/config", 'gitweb.owner', $o]); + } + write_makefile($dst, 1); index_cloned_inbox($self, 1); } -sub clone_v2 { - my ($self, $v2_uris) = @_; +sub v2_done { # called via OnDestroy + my ($self) = @_; + _write_inbox_config($self); + require PublicInbox::MultiGit; + my $dst = $self->{cur_dst} // $self->{dst}; + my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); + $mg->fill_alternates; + for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } + my $edst_owner = delete($self->{-owner}) // []; + while (@$edst_owner) { + my ($edst, $o) = splice(@$edst_owner); + run_die [qw(git config -f), "$edst/config", 'gitweb.owner', $o]; + } + for my $edst (@{delete($self->{-read_only}) // []}) { + my @st = stat($edst) or die "stat($edst): $!"; + chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + } + write_makefile($dst, 2); + delete $self->{-locked} // die "BUG: $dst not locked"; # unlock + index_cloned_inbox($self, 2); +} + +sub reap_live { + my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; + if (my $x = delete $LIVE{$pid}) { + my $cb = shift @$x; + $cb->(@$x); + } else { + warn "reaped unknown PID=$pid ($?)\n"; + } +} + +sub clone_v2 ($$;$) { + my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref 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 $first_uri = (map { $_->[0] } values %$v2_epochs)[0]; + my $pfx = $curl->torsocks($lei, $first_uri) or return; + my $dst = $self->{cur_dst} // $self->{dst}; + my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); + my $task = $m ? bless { %$self }, __PACKAGE__ : $self; + my (@src_edst, @skip); + for my $nr (sort { $a <=> $b } keys %$v2_epochs) { + my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; my $edst = $dst; $src =~ m!/([0-9]+)(?:\.git)?\z! or die <<""; failed to extract epoch number from $src - my $nr = $1 + 0; + $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; - push @src_edst, [ $src, $edst ]; + $m->{$key} // die "BUG: `$key' not in manifest.js.gz"; + if (!$want || $want->{$nr}) { + push @src_edst, $src, $edst; + my $o = $m->{$key}->{owner}; + push(@{$task->{-owner}}, $edst, $o) if defined($o); + } else { # create a placeholder so users only need to chmod +w + init_placeholder($src, $edst, $m->{$key}->{owner}); + push @{$task->{-read_only}}, $edst; + push @skip, $key; + } } + # filter out the epochs we skipped + $self->{-culled_manifest} = 1 if delete(@$m{@skip}); + + -d $dst || File::Path::mkpath($dst); + require PublicInbox::Lock; my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; - _try_config($self); - my $on_destroy = $lk->lock_for_scope($$); + my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); + + _get_txt_start($task, '_/text/config/raw', $fini); + _get_txt_start($self, 'description', $fini); + + $task->{-locked} = $lk->lock_for_scope($$); my @cmd = clone_cmd($lei, my $opt = {}); - while (my $pair = shift(@src_edst)) { - my $cmd = [ @$pfx, @cmd, @$pair ]; - my $cerr = run_reap($lei, $cmd, $opt); - return $lei->child_error($cerr, "@$cmd failed") if $cerr; + while (@src_edst && !$lei->{child_error}) { + my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ]; + start_clone($self, $cmd, $opt, $fini); } - undef $on_destroy; # unlock - index_cloned_inbox($self, 2); } -# PSGI mount prefixes and manifest.js.gz prefixes don't always align... -sub deduce_epochs ($$) { - my ($m, $path) = @_; - my ($v1_bare, @v2_epochs); +sub decode_manifest ($$$) { + my ($fh, $fn, $uri) = @_; + my $js; + my $gz = do { local $/; <$fh> } // die "slurp($fn): $!"; + gunzip(\$gz => \$js, MultiStream => 1) or + die "gunzip($uri): $GunzipError\n"; + my $m = eval { PublicInbox::Config->json->decode($js) }; + die "$uri: error decoding `$js': $@\n" if $@; + ref($m) eq 'HASH' or die "$uri unknown type: ".ref($m); + $m; +} + +sub multi_inbox ($$$) { + my ($self, $path, $m) = @_; + my $incl = $self->{lei}->{opt}->{include}; + my $excl = $self->{lei}->{opt}->{exclude}; + + # assuming everything not v2 is v1, for now + my @v1 = sort grep(!m!.+/git/[0-9]+\.git\z!, keys %$m); + my @v2_epochs = sort grep(m!.+/git/[0-9]+\.git\z!, keys %$m); + my $v2 = {}; + + for (@v2_epochs) { + m!\A(/.+)/git/[0-9]+\.git\z! or die "BUG: $_"; + push @{$v2->{$1}}, $_; + } + my $n = scalar(keys %$v2) + scalar(@v1); + my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : (); + if (defined $incl) { + my $re = '(?:'.join('|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/ + } @$incl).')'; + my @gone = delete @$v2{grep(!/$re/, keys %$v2)}; + delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; + delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1; + @v1 = grep(/$re/, @v1); + } + if (defined $excl) { + my $re = '(?:'.join('|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/ + } @$excl).')'; + my @gone = delete @$v2{grep(/$re/, keys %$v2)}; + delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; + delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1; + @v1 = grep(!/$re/, @v1); + } + my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }} + $ret->{v1} = \@v1 if @v1; + $ret->{v2} = $v2 if keys %$v2; + $ret //= @orig ? "Nothing to clone, available repositories:\n\t". + join("\n\t", sort @orig) + : "Nothing available to clone\n"; my $path_pfx = ''; - do { - $v1_bare = $m->{$path}; - @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m); - } while (!defined($v1_bare) && !@v2_epochs && - $path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1); - ($path_pfx, $v1_bare, @v2_epochs); + + # PSGI mount prefixes and manifest.js.gz prefixes don't always align... + if (@v2_epochs) { + until (grep(m!\A\Q$$path\E/git/[0-9]+\.git\z!, + @v2_epochs) == @v2_epochs) { + $$path =~ s!\A(/[^/]+)/!/! or last; + $path_pfx .= $1; + } + } elsif (@v1) { + while (!defined($m->{$$path}) && $$path =~ s!\A(/[^/]+)/!/!) { + $path_pfx .= $1; + } + } + ($path_pfx, $n, $ret); } +# FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; my $uri = URI->new($self->{src}); @@ -221,45 +507,91 @@ sub try_manifest { 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, undef, $opt); - my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid); - my $gz = do { local $/; <$fh> } // die "read(curl $uri): $!"; - close $fh; - waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!"; - @$reap = (); - 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!!; + -d $pdir || File::Path::mkpath($pdir); + my $ft = File::Temp->new(TEMPLATE => 'm-XXXX', + UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp'); + my $fn = $ft->filename; + my ($bn) = ($fn =~ m!/([^/]+)\z!); + my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $bn); + my $opt = { -C => $pdir }; + $opt->{$_} = $lei->{$_} for (0..2); + my $cerr = run_reap($lei, $cmd, $opt); + local %LIVE; + if ($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 $m = eval { decode_manifest($ft, $fn, $uri) }; + if ($@) { + warn $@; + return try_scrape($self); + } + my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m); + return $lei->child_error(1, $multi) if !ref($multi); + if (my $v2 = delete $multi->{v2}) { + for my $name (sort keys %$v2) { + my $epochs = delete $v2->{$name}; + my %v2_epochs = map { + $uri->path($n > 1 ? $path_pfx.$path.$_ + : $path_pfx.$_); + my ($e) = ("$uri" =~ m!/([0-9]+)\.git\z!); + $e // die "no [0-9]+\.git in `$uri'"; + $e => [ $uri->clone, $_ ]; + } @$epochs; + ("$uri" =~ m!\A(.+/)git/[0-9]+\.git\z!) or + die "BUG: `$uri' !~ m!/git/[0-9]+.git!"; + local $self->{cur_src} = $1; + local $self->{cur_dst} = $self->{dst}; + if ($n > 1 && $uri->path =~ m!\A\Q$path_pfx$path\E/(.+)/ + git/[0-9]+\.git\z!x) { + $self->{cur_dst} .= "/$1"; + } + index($self->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline +EOM + clone_v2($self, \%v2_epochs, $m); + return if $self->{lei}->{child_error}; + } + } + if (my $v1 = delete $multi->{v1}) { + my $p = $path_pfx.$path; + chop($p) if substr($p, -1, 1) eq '/'; + $uri->path($p); + for my $name (@$v1) { + return if $self->{lei}->{child_error}; - my ($path_pfx, $v1_bare, @v2_epochs) = deduce_epochs($m, $path); - if (@v2_epochs) { - # It may be possible to have v1 + v2 in parallel someday: - $lei->err(<{-ent} = $m->{$name} // + die("BUG: no `$name' in manifest"); + $task->{cur_src} = "$uri"; + $task->{cur_dst} = $task->{dst}; + if ($n > 1) { + $task->{cur_dst} .= $name; + $task->{cur_src} .= $name; + } + index($task->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline EOM - @v2_epochs = map { - $uri->path($path_pfx.$_); - $uri->clone - } @v2_epochs; - clone_v2($self, \@v2_epochs); - } elsif (defined $v1_bare) { - clone_v1($self); - } else { - die "E: confused by <$uri>, possible matches:\n\t", - join(', ', sort keys %$m), "\n"; + $task->{cur_src} .= '/'; + clone_v1($task, 1); + } + } + reap_live() while keys(%LIVE); + return if $self->{lei}->{child_error}; + + if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude + # write the smaller manifest if epochs were skipped so + # users won't have to delete manifest if they +w an + # epoch they no longer want to skip + my $json = PublicInbox::Config->json->encode($m); + my $mtime = (stat($fn))[9]; + gzip(\$json => $fn) or die "gzip: $GzipError"; + utime($mtime, $mtime, $fn) or die "utime(..., $fn): $!"; } + ft_rename($ft, "$self->{dst}/manifest.js.gz", 0666); + open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } sub start_clone_url { @@ -271,9 +603,11 @@ sub start_clone_url { sub do_mirror { # via wq_io_do my ($self) = @_; my $lei = $self->{lei}; + umask($lei->{client_umask}) if defined $lei->{client_umask}; eval { my $iv = $lei->{opt}->{'inbox-version'}; if (defined $iv) { + local %LIVE; return clone_v1($self) if $iv == 1; return try_scrape($self) if $iv == 2; die "bad --inbox-version=$iv\n"; @@ -287,26 +621,75 @@ sub do_mirror { # via wq_io_do sub start { my ($cls, $lei, $src, $dst) = @_; my $self = bless { src => $src, dst => $dst }, $cls; - if ($src =~ m!https?://!) { - require URI; - require PublicInbox::LeiCurl; - } - require PublicInbox::Lock; - require PublicInbox::Inbox; - require PublicInbox::Admin; - require PublicInbox::InboxWritable; + $lei->request_umask; my ($op_c, $ops) = $lei->workers_start($self, 1); $lei->{wq1} = $self; $self->wq_io_do('do_mirror', []); - $self->wq_close(1); + $self->wq_close; $lei->wait_wq_events($op_c, $ops); } sub ipc_atfork_child { my ($self) = @_; $self->{lei}->_lei_atfork_child; - $SIG{TERM} = sub { exit(128 + 15) }; # trigger OnDestroy $reap $self->SUPER::ipc_atfork_child; } +sub write_makefile { + my ($dir, $ibx_ver) = @_; + my $f = "$dir/Makefile"; + if (sysopen my $fh, $f, O_CREAT|O_EXCL|O_WRONLY) { + print $fh <