X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=e356b5c57e553ce9d8f4b22619660e10d9fe7821;hb=d922fc44d1afb5e4400f2606c475e42aee087c24;hp=6bfa4b6f320ec582e000c4b8189a195ab6cb618b;hpb=7d2f9f7caf63256bab7b3342c52a1d97c889ada4;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 6bfa4b6f..e356b5c5 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # "lei add-external --mirror" support (also "public-inbox-clone"); @@ -6,10 +6,14 @@ package PublicInbox::LeiMirror; use strict; use v5.10.1; use parent qw(PublicInbox::IPC); +use PublicInbox::Config; +use PublicInbox::AutoReap; use IO::Uncompress::Gunzip qw(gunzip $GunzipError); -use PublicInbox::Spawn qw(popen_rd spawn run_die); +use IO::Compress::Gzip qw(gzip $GzipError); +use PublicInbox::Spawn qw(popen_rd spawn); use File::Temp (); use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY); +use Carp qw(croak); sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; @@ -18,10 +22,12 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) if ($?) { $lei->child_error($?); } elsif (!unlink($f)) { - $lei->err("unlink($f): $!") unless $!{ENOENT}; + warn("unlink($f): $!\n") unless $!{ENOENT}; } else { if ($lei->{cmd} ne 'public-inbox-clone') { - $lei->add_external_finish($mrr->{dst}); + # calls _finish_add_external + $lei->lazy_cb('add-external', '_finish_' + )->($lei, $mrr->{dst}); } $lei->qerr("# mirrored $mrr->{src} => $mrr->{dst}"); } @@ -42,15 +48,19 @@ sub try_scrape { # we grep with URL below, we don't want Subject/From headers # making us clone random URLs - my @urls = ($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 + return clone_v2($self, \%v2_epochs); } # filter out common URLs served by WWW (e.g /$MSGID/T/) @@ -82,39 +92,48 @@ sub clone_cmd { @cmd; } +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 { # non-fatal - my ($self, $endpoint, $file) = @_; - my $uri = URI->new($self->{src}); + my ($self, $endpoint, $file, $mode) = @_; + 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/$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 $dst = $self->{cur_dst} // $self->{dst}; + my $ft = File::Temp->new(TEMPLATE => "$file-XXXX", DIR => $dst); + 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); 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); + ft_rename($ft, "$dst/$file", $mode); undef; # success } # tries the relatively new /$INBOX/_/text/config/raw endpoint sub _try_config { my ($self) = @_; - my $dst = $self->{dst}; + my $dst = $self->{cur_dst} // $self->{dst}; if (!-d $dst || !mkdir($dst)) { require File::Path; File::Path::mkpath($dst); -d $dst or die "mkpath($dst): $!\n"; } - 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 $err = _get_txt($self, + qw(_/text/config/raw inbox.config.example), 0444); + return warn($err, "\n") if $err; + my $f = "$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}})) { @@ -126,7 +145,8 @@ sub _try_config { sub set_description ($) { my ($self) = @_; - my $f = "$self->{dst}/description"; + 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): $!"; chomp(my $d = do { local $/; <$fh> } // die "read($f): $!"); @@ -134,7 +154,8 @@ sub set_description ($) { $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): $!"; + my $src = $self->{cur_src} // $self->{src}; + print $fh "mirror of $src\n" or die "print($f): $!"; close $fh or die "close($f): $!"; } } @@ -142,8 +163,8 @@ sub set_description ($) { sub index_cloned_inbox { my ($self, $iv) = @_; my $lei = $self->{lei}; - my $err = _get_txt($self, qw(description description)); - $lei->err($err) if $err; # non fatal + my $err = _get_txt($self, qw(description description), 0666); + warn($err, "\n") if $err; # non fatal eval { set_description($self) }; warn $@ if $@; @@ -154,7 +175,7 @@ sub index_cloned_inbox { address => [ 'lei@example.com' ], version => $iv, }; - $ibx->{inboxdir} = $self->{dst}; + $ibx->{inboxdir} = $self->{cur_dst} // $self->{dst}; PublicInbox::Inbox->new($ibx); PublicInbox::InboxWritable->new($ibx); my $opt = {}; @@ -170,52 +191,126 @@ sub index_cloned_inbox { PublicInbox::Admin::progress_prepare($opt, $lei->{2}); PublicInbox::Admin::index_inbox($ibx, undef, $opt); } + 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 if $lei->{sock}; - 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 - $? + my $ar = PublicInbox::AutoReap->new(spawn($cmd, undef, $opt)); + $ar->join; + my $ret = $?; + $? = 0; # don't let it influence normal exit + $ret; } sub clone_v1 { my ($self) = @_; 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 $dst = $self->{cur_dst} // $self->{dst}; my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), - $uri->as_string, $self->{dst} ]; + $uri->as_string, $dst ]; my $cerr = run_reap($lei, $cmd, $opt); return $lei->child_error($cerr, "@$cmd failed") if $cerr; _try_config($self); - write_makefile($self->{dst}, 1); + write_makefile($dst, 1); index_cloned_inbox($self, 1); } -sub clone_v2 { - my ($self, $v2_uris) = @_; +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 ($$) { + my ($src, $edst) = @_; + PublicInbox::Import::init_bare($edst); + my $f = "$edst/config"; + open my $fh, '>>', $f or die "open($f): $!"; + print $fh < manifest.js.gz hashref my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $pfx //= $curl->torsocks($lei, $v2_uris->[0]) or return; - my $dst = $self->{dst}; - my @src_edst; - for my $uri (@$v2_uris) { + my $first_uri = (map { $_->[0] } values %$v2_epochs)[0]; + my $pfx = $curl->torsocks($lei, $first_uri) or return; + my $dst = $self->{cur_dst} // $self->{dst}; + my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); + my (@src_edst, @read_only, @skip); + for my $nr (sort { $a <=> $b } keys %$v2_epochs) { + my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; my $edst = $dst; $src =~ m!/([0-9]+)(?:\.git)?\z! or die <<""; failed to extract epoch number from $src - my $nr = $1 + 0; + $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; - push @src_edst, $src, $edst; + if (!$want || $want->{$nr}) { + push @src_edst, $src, $edst; + } else { # create a placeholder so users only need to chmod +w + init_placeholder($src, $edst); + push @read_only, $edst; + push @skip, $key; + } } + # filter out the epochs we skipped + $self->{-culled_manifest} = 1 if delete(@$m{@skip}); my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; _try_config($self); my $on_destroy = $lk->lock_for_scope($$); @@ -229,25 +324,15 @@ failed to extract epoch number from $src my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); $mg->fill_alternates; for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } - write_makefile($self->{dst}, 2); + for my $edst (@read_only) { + my @st = stat($edst) or die "stat($edst): $!"; + chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + } + write_makefile($dst, 2); 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; @@ -260,6 +345,40 @@ sub decode_manifest ($$$) { $m; } +sub multi_inbox ($$$) { + my ($self, $path, $m) = @_; + + # assuming everything not v2 is v1, for now + my @v1 = sort grep(!m!.+/git/[0-9]+\.git\z!, keys %$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 $ret; # { v1 => [ ... ], v2 => { $inbox_name => [ epochs ] }} + $ret->{v1} = \@v1 if @v1; + $ret->{v2} = $v2 if keys %$v2; + my $path_pfx = ''; + + # 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}); @@ -282,29 +401,65 @@ sub try_manifest { return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing return $lei->child_error($cerr, "@$cmd failed"); } - 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(<{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 - @v2_epochs = map { - $uri->path($path_pfx.$_); - $uri->clone - } @v2_epochs; - clone_v2($self, \@v2_epochs); - } elsif (defined $v1_path) { - clone_v1($self); - } else { - die "E: confused by <$uri>, possible matches:\n\t", - join(', ', sort keys %$m), "\n"; + clone_v2($self, \%v2_epochs, $m); + } } - my $fin = "$self->{dst}/manifest.js.gz"; - rename($fn, $fin) or die "E: rename($fn, $fin): $!"; - $ft->unlink_on_destroy(0); + 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) { + local $self->{cur_src} = "$uri"; + local $self->{cur_dst} = $self->{dst}; + if ($n > 1) { + $self->{cur_dst} .= $name; + $self->{cur_src} .= $name; + } + index($self->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline +EOM + $self->{cur_src} .= '/'; + clone_v1($self, 1); + } + } + if (delete $self->{-culled_manifest}) { # set by clone_v2 + # 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 { @@ -316,6 +471,7 @@ 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) { @@ -340,17 +496,17 @@ sub start { 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; }