X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=fe81b967fd4ae990c97d1db6769a7515e5e5f53e;hb=3596019278ef489f27e0659c752977f60f847903;hp=8689b825a0beb397e30389abdd27a80f3a68aafe;hpb=0c2eaee968cb59ae60c10ce89b2c236fd9369830;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 8689b825..fe81b967 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -1,15 +1,17 @@ # Copyright (C) 2021 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 $GunzipError); -use PublicInbox::Spawn qw(popen_rd spawn); +use PublicInbox::Spawn qw(popen_rd spawn run_die); +use File::Temp (); +use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY); -sub do_finish_mirror { # dwaitpid callback +sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; my ($mrr, $lei) = @$arg; my $f = "$mrr->{dst}/mirror.done"; @@ -18,18 +20,14 @@ sub do_finish_mirror { # dwaitpid callback } elsif (!unlink($f)) { $lei->err("unlink($f): $!") unless $!{ENOENT}; } else { - $lei->add_external_finish($mrr->{dst}); + if ($lei->{cmd} ne 'public-inbox-clone') { + $lei->add_external_finish($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 +42,19 @@ 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/) @@ -84,6 +86,27 @@ sub clone_cmd { @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 ($self) = @_; @@ -93,24 +116,10 @@ sub _try_config { File::Path::mkpath($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, '--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) // 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, $lei->{2}); + 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)) { @@ -119,40 +128,66 @@ sub _try_config { } } +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(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 + open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } sub run_reap { my ($lei, $cmd, $opt) = @_; $lei->qerr("# @$cmd"); - $opt->{pgid} = 0; + $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) : $? + my $ret = $?; + $? = 0; # don't let it influence normal exit + $ret; } sub clone_v1 { @@ -160,42 +195,120 @@ sub clone_v1 { my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; my $uri = URI->new($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; + my $cerr = run_reap($lei, $cmd, $opt); return $lei->child_error($cerr, "@$cmd failed") if $cerr; _try_config($self); + write_makefile($self->{dst}, 1); index_cloned_inbox($self, 1); } -sub clone_v2 { - my ($self, $v2_uris) = @_; +sub parse_epochs ($$) { + my ($opt_epochs, $v2_epochs) = @_; # $epcohs "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 ($$) { + my ($src, $edst) = @_; + PublicInbox::Import::init_bare($edst); + my $f = "$edst/config"; + open my $fh, '>>', $f or die "open($f): $!"; + print $fh <{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; - my $pfx //= $curl->torsocks($lei, $v2_uris->[0]) or return; - my @epochs; + my $pfx = $curl->torsocks($lei, (values %$v2_epochs)[0]) or return; my $dst = $self->{dst}; - my @src_edst; - for my $uri (@$v2_uris) { + my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs); + my (@src_edst, @read_only); + for my $nr (sort { $a <=> $b } keys %$v2_epochs) { + my $uri = $v2_epochs->{$nr}; my $src = $uri->as_string; my $edst = $dst; $src =~ m!/([0-9]+)(?:\.git)?\z! or die <<""; failed to extract epoch number from $src - my $nr = $1 + 0; + $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; - push @src_edst, [ $src, $edst ]; + if (!$want || $want->{$nr}) { + push @src_edst, $src, $edst; + } else { # create a placeholder so users only need to chmod +w + init_placeholder($src, $edst); + push @read_only, $edst; + } } my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; _try_config($self); my $on_destroy = $lk->lock_for_scope($$); 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) } + for my $edst (@read_only) { + my @st = stat($edst) or die "stat($edst): $!"; + chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; + } + write_makefile($self->{dst}, 2); undef $on_destroy; # unlock index_cloned_inbox($self, 2); } @@ -203,14 +316,27 @@ failed to extract epoch number from $src # PSGI mount prefixes and manifest.js.gz prefixes don't always align... sub deduce_epochs ($$) { my ($m, $path) = @_; - my ($v1_bare, @v2_epochs); + my ($v1_ent, @v2_epochs); my $path_pfx = ''; + $path =~ s!/+\z!!; do { - $v1_bare = $m->{$path}; + $v1_ent = $m->{$path}; @v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m); - } while (!defined($v1_bare) && !@v2_epochs && + } while (!defined($v1_ent) && !@v2_epochs && $path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1); - ($path_pfx, $v1_bare, @v2_epochs); + ($path_pfx, $v1_ent ? $path : undef, @v2_epochs); +} + +sub decode_manifest ($$$) { + 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 { @@ -221,46 +347,48 @@ 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; - 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 => '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, $opt); + if ($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 ($path_pfx, $v1_bare, @v2_epochs) = deduce_epochs($m, $path); + my $m = eval { decode_manifest($ft, $fn, $uri) }; + if ($@) { + warn $@; + return try_scrape($self); + } + 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: - $lei->err(<err(<path($path_pfx.$_); - $uri->clone + my ($n) = ("$uri" =~ m!/([0-9]+)\.git\z!); + $n => $uri->clone } @v2_epochs; - clone_v2($self, \@v2_epochs); - } elsif (defined $v1_bare) { + clone_v2($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"; } + 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 { @@ -310,4 +438,61 @@ sub ipc_atfork_child { $self->SUPER::ipc_atfork_child; } +sub write_makefile { + my ($dir, $ibx_ver) = @_; + my $f = "$dir/Makefile"; + if (sysopen my $fh, $f, O_CREAT|O_EXCL|O_WRONLY) { + print $fh <