X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=20ae3ac8f2184196ed72e7a7dd82edfadfa8547e;hb=2921a66a3d275000b471972c543f85d763bdd0e9;hp=1ca603b3003b1b06ae4a4328e0e265deb97f6d2f;hpb=a8d69227f4441be553315852b416322ee4fe0265;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index 1ca603b3..20ae3ac8 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -6,15 +6,21 @@ package PublicInbox::LeiMirror; use strict; use v5.10.1; use parent qw(PublicInbox::IPC); -use PublicInbox::Config; use IO::Uncompress::Gunzip qw(gunzip $GunzipError); use IO::Compress::Gzip qw(gzip $GzipError); -use PublicInbox::Spawn qw(popen_rd spawn); +use PublicInbox::Spawn qw(popen_rd spawn run_die); use File::Path (); use File::Temp (); +use File::Spec (); use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY); use Carp qw(croak); -our %LIVE; +use URI; +use PublicInbox::Config; +use PublicInbox::Inbox; +use PublicInbox::LeiCurl; +use PublicInbox::OnDestroy; + +our $LIVE; # pid => callback sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; @@ -22,10 +28,10 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) my $f = "$mrr->{dst}/mirror.done"; if ($?) { $lei->child_error($?); - } elsif (!unlink($f)) { + } elsif (!$mrr->{dry_run} && !unlink($f)) { warn("unlink($f): $!\n") unless $!{ENOENT}; } else { - if ($lei->{cmd} ne 'public-inbox-clone') { + if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') { # calls _finish_add_external $lei->lazy_cb('add-external', '_finish_' )->($lei, $mrr->{dst}); @@ -62,7 +68,7 @@ sub try_scrape { $n => [ URI->new($_), '' ] } @v2_urls; # uniq clone_v2($self, \%v2_epochs); - reap_live() while keys(%LIVE); + reap_live() while keys(%$LIVE); return; } @@ -92,7 +98,8 @@ sub clone_cmd { ($lei->{opt}->{jobs} // 1) > 1; push @cmd, '-v' if $lei->{opt}->{verbose}; # XXX any other options to support? - # --reference is tricky with multiple epochs... + # --reference is tricky with multiple epochs, but handled + # automatically if using manifest.js.gz @cmd; } @@ -102,7 +109,8 @@ sub ft_rename ($$$) { 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): $!"; + require File::Copy; + File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!"; $ft->unlink_on_destroy(0); } @@ -118,11 +126,12 @@ sub _get_txt_start { # non-fatal 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) >= $jobs; + reap_live() while keys(%$LIVE) >= $jobs; $lei->qerr("# @$cmd"); - $LIVE{spawn($cmd, undef, $opt)} = + return if $self->{dry_run}; + $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&_get_txt_done, $self, $endpoint, $fini ]; } @@ -169,16 +178,17 @@ sub set_description ($) { 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; + chomp(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"; + $d //= 'mirror of '.($self->{cur_src} // $self->{src}); + chomp $d; 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): $!"; + print $fh $d, "\n" or die "print($f): $!"; close $fh or die "close($f): $!"; } @@ -191,6 +201,8 @@ sub index_cloned_inbox { # n.b. public-inbox-clone works w/o (SQLite || Xapian) # lei is useless without Xapian + SQLite if ($lei->{cmd} ne 'public-inbox-clone') { + require PublicInbox::InboxWritable; + require PublicInbox::Admin; my $ibx = delete($self->{ibx}) // { address => [ 'lei@example.com' ], version => $iv, @@ -227,9 +239,10 @@ sub run_reap { sub start_clone { my ($self, $cmd, $opt, $fini) = @_; my $jobs = $self->{lei}->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + reap_live() while keys(%$LIVE) >= $jobs; $self->{lei}->qerr("# @$cmd"); - $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]; + return if $self->{dry_run}; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ] } sub clone_v1 { @@ -243,14 +256,22 @@ sub clone_v1 { my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; + my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef; + defined($ref) && -e "$self->{dst}$ref" and + push @$cmd, '--reference', "$self->{dst}$ref"; start_clone($self, $cmd, $opt, $fini); - _get_txt_start($self, '_/text/config/raw', $fini); + if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ + /\A(?:always|v1)\z/s) { + _get_txt_start($self, '_/text/config/raw', $fini); + } + my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; - defined($d) ? ($self->{'txt.description'} = $d) : + $self->{'txt.description'} = $d if defined $d; + (!defined($d) && !$nohang) and _get_txt_start($self, 'description', $fini); - reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone + reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone } sub parse_epochs ($$) { @@ -296,8 +317,8 @@ EOM $want } -sub init_placeholder ($$) { - my ($src, $edst) = @_; +sub init_placeholder ($$$) { + my ($src, $edst, $ent) = @_; PublicInbox::Import::init_bare($edst); my $f = "$edst/config"; open my $fh, '>>', $f or die "open($f): $!"; @@ -311,7 +332,22 @@ sub init_placeholder ($$) { ; will not fetch updates for it unless write permission is added. ; Hint: chmod +w $edst EOM - close $fh or die "close:($f): $!"; + if (defined($ent->{owner})) { + print $fh <{owner} +EOM + } + close $fh or die "close($f): $!"; + my %map = (head => 'HEAD', description => undef); + while (my ($key, $fn) = each %map) { + my $val = $ent->{$key} // next; + $fn //= $key; + $fn = "$edst/$fn"; + open $fh, '>', $fn or die "open($fn): $!"; + print $fh $val, "\n" or die "print($fn): $!"; + close $fh or die "close($fn): $!"; + } } sub reap_clone { # async, called via SIGCHLD @@ -319,38 +355,72 @@ sub reap_clone { # async, called via SIGCHLD my $cerr = $?; $? = 0; # don't let it influence normal exit if ($cerr) { - kill('TERM', keys %LIVE); + kill('TERM', keys %$LIVE); $self->{lei}->child_error($cerr, "@$cmd failed"); } } sub v1_done { # called via OnDestroy my ($self) = @_; + return if $self->{dry_run} || !$LIVE; _write_inbox_config($self); - write_makefile($self->{cur_dst} // $self->{dst}, 1); + my $dst = $self->{cur_dst} // $self->{dst}; + if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) { + run_die([qw(git config -f), "$dst/config", 'gitweb.owner', $o]); + } + my $o = "$dst/objects"; + if (open(my $fh, '<', "$o/info/alternates")) { + chomp(my @l = <$fh>); + for (@l) { $_ = File::Spec->abs2rel($_, $o)."\n" } + my $f = File::Temp->new(TEMPLATE => '.XXXX', DIR => "$o/info"); + print $f @l; + $f->flush or die "flush($f): $!"; + rename($f->filename, "$o/info/alternates") or + die "rename($f, $o/info/alternates): $!"; + $f->unlink_on_destroy(0); + } + return if $self->{-is_epoch}; + write_makefile($dst, 1); index_cloned_inbox($self, 1); } sub v2_done { # called via OnDestroy my ($self) = @_; + return if $self->{dry_run} || !$LIVE; + my $dst = $self->{cur_dst} // $self->{dst}; + require PublicInbox::Lock; + my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; + my $lck = $lk->lock_for_scope($$); _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 $entries = delete($self->{-entv}) // []; + while (@$entries) { + my ($edst, $ent) = splice(@$entries); + if (defined(my $o = $ent->{owner})) { + run_die [qw(git config -f), "$edst/config", + 'gitweb.owner', $o]; + } + my $d = $ent->{description} // next; + my $fn = "$edst/description"; + open my $fh, '>', $fn or die "open($fn): $!"; + print $fh $d, "\n" or die "print($fn): $!"; + close $fh or die "close($fn): $!"; + } 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 + undef $lck; # unlock index_cloned_inbox($self, 2); } sub reap_live { my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; - if (my $x = delete $LIVE{$pid}) { + if (my $x = delete $LIVE->{$pid}) { my $cb = shift @$x; $cb->(@$x); } else { @@ -367,7 +437,8 @@ sub clone_v2 ($$;$) { 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); + delete $task->{todo}; # $self->{todo} still exists + my (@src_edst, @skip, $desc); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; @@ -377,10 +448,17 @@ failed to extract epoch number from $src $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; + my $ent = $m->{$key} // die "BUG: `$key' not in manifest.js.gz"; + if (defined(my $d = $ent->{description})) { + $d =~ s/ \[epoch [0-9]+\]\z//s; + $desc = $d; + } if (!$want || $want->{$nr}) { push @src_edst, $src, $edst; + push @{$task->{-entv}}, $edst, $ent; + $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w - init_placeholder($src, $edst); + init_placeholder($src, $edst, $ent); push @{$task->{-read_only}}, $edst; push @skip, $key; } @@ -388,18 +466,36 @@ failed to extract epoch number from $src # filter out the epochs we skipped $self->{-culled_manifest} = 1 if delete(@$m{@skip}); - -d $dst || File::Path::mkpath($dst); - my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; - my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); + (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); - _get_txt_start($task, '_/text/config/raw', $fini); - _get_txt_start($self, 'description', $fini); + my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); - $task->{-locked} = $lk->lock_for_scope($$); - my @cmd = clone_cmd($lei, my $opt = {}); - while (@src_edst && !$lei->{child_error}) { - my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ]; - start_clone($self, $cmd, $opt, $fini); + $lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and + _get_txt_start($task, '_/text/config/raw', $fini); + + defined($desc) ? ($task->{'txt.description'} = $desc) : + _get_txt_start($task, 'description', $fini); + if (my $todo = $self->{todo}) { # manifest clone, deal with references + my $entv = delete $task->{-entv}; + while (@$entv) { + my ($edst, $ent) = splice(@$entv, 0, 2); + my $etask = bless { %$task }, __PACKAGE__; + $etask->{-ent} = $ent; # may have {reference} + $etask->{cur_src} = shift @src_edst // + die 'BUG: no cur_src'; + $etask->{cur_dst} = shift @src_edst // + die 'BUG: no cur_dst'; + $etask->{cur_dst} eq $edst or + die "BUG: `$etask->{cur_dst}' != `$edst'"; + $etask->{-is_epoch} = $fini; + push @{$todo->{($ent->{reference} // '')}}, $etask; + } + } else { + my @cmd = clone_cmd($lei, my $opt = {}); + while (@src_edst && !$lei->{child_error}) { + my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ]; + start_clone($self, $cmd, $opt, $fini); + } } } @@ -432,18 +528,18 @@ sub multi_inbox ($$$) { 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 $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$incl).'\\z)'; 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 $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$excl).'\\z)'; 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; @@ -472,6 +568,44 @@ sub multi_inbox ($$$) { ($path_pfx, $n, $ret); } +sub clone_all ($$) { + my ($self, $m) = @_; + my $todo = delete $self->{todo}; + my $nodep = delete $todo->{''}; + + # do not download unwanted deps + my $any_want = delete $self->{any_want}; + my @unwanted = grep { !$any_want->{$_} } keys %$todo; + my @nodep = delete(@$todo{@unwanted}); + push(@$nodep, @$_) for @nodep; + + # handle no-dependency repos, first + for (@$nodep) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + # resolve references, deepest, first: + while (scalar keys %$todo) { + for my $x (keys %$todo) { + my $nr; + # resolve multi-level references + while (defined(my $nxt = $m->{$x}->{reference})) { + exists($todo->{$nxt}) or last; + die < 1000; +E: dependency loop detected (`$x' => `$nxt') +EOM + $x = $nxt; + } + my $y = delete $todo->{$x} // next; # already done + for (@$y) { + clone_v1($_, 1); + return if $self->{lei}->{child_error}; + } + last; # restart %$todo iteration + } + } +} + # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; @@ -481,18 +615,13 @@ sub try_manifest { my $path = $uri->path; chop($path) eq '/' or die "BUG: $uri not canonicalized"; $uri->path($path . '/manifest.js.gz'); - 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 $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', + UNLINK => 1, TMPDIR => 1, 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; + my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn); + my %opt = map { $_ => $lei->{$_} } (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, "@$cmd failed"); @@ -504,7 +633,9 @@ sub try_manifest { } my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m); return $lei->child_error(1, $multi) if !ref($multi); - if (my $v2 = delete $multi->{v2}) { + my $v2 = delete $multi->{v2}; + local $self->{todo} = {}; + if ($v2) { for my $name (sort keys %$v2) { my $epochs = delete $v2->{$name}; my %v2_epochs = map { @@ -534,8 +665,6 @@ EOM chop($p) if substr($p, -1, 1) eq '/'; $uri->path($p); for my $name (@$v1) { - return if $self->{lei}->{child_error}; - my $task = bless { %$self }, __PACKAGE__; $task->{-ent} = $m->{$name} // die("BUG: no `$name' in manifest"); @@ -549,11 +678,15 @@ EOM E: `$task->{cur_dst}' must not contain newline EOM $task->{cur_src} .= '/'; - clone_v1($task, 1); + my $dep = $task->{-ent}->{reference} // ''; + push @{$self->{todo}->{$dep}}, $task; + $self->{any_want}->{$name} = 1; } } - reap_live() while keys(%LIVE); - return if $self->{lei}->{child_error}; + delete local $lei->{opt}->{epoch} if defined($v2); + clone_all($self, $m); + reap_live() while keys(%$LIVE); + return if $self->{lei}->{child_error} || $self->{dry_run}; if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude # write the smaller manifest if epochs were skipped so @@ -574,14 +707,18 @@ sub start_clone_url { die "TODO: non-HTTP/HTTPS clone of $self->{src} not supported, yet"; } -sub do_mirror { # via wq_io_do +sub do_mirror { # via wq_io_do or public-inbox-clone my ($self) = @_; my $lei = $self->{lei}; umask($lei->{client_umask}) if defined $lei->{client_umask}; eval { + my $ic = $lei->{opt}->{'inbox-config'} //= 'always'; + $ic =~ /\A(?:v1|v2|always|never)\z/s or die <<""; +--inbox-config must be one of `always', `v2', `v1', or `never' + my $iv = $lei->{opt}->{'inbox-version'}; if (defined $iv) { - local %LIVE; + local $LIVE; return clone_v1($self) if $iv == 1; return try_scrape($self) if $iv == 2; die "bad --inbox-version=$iv\n"; @@ -595,14 +732,6 @@ 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;