X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=acf086654089f4d2cbf8f0d7c25eddd01271086b;hb=fe74ddc3f2d0590727c00ee41e80f3dfc7345387;hp=d955ac3b99470ba4dec1b430819f95420b05800c;hpb=1c3d7bd75e2c6f84bd511a17838fa9113c98578c;p=public-inbox.git diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm index d955ac3b..acf08665 100644 --- a/lib/PublicInbox/LeiMirror.pm +++ b/lib/PublicInbox/LeiMirror.pm @@ -3,14 +3,14 @@ # "lei add-external --mirror" support (also "public-inbox-clone"); package PublicInbox::LeiMirror; -use strict; -use v5.10.1; +use v5.12; use parent qw(PublicInbox::IPC); use IO::Uncompress::Gunzip qw(gunzip $GunzipError); use IO::Compress::Gzip qw(gzip $GzipError); 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); use URI; @@ -19,7 +19,7 @@ use PublicInbox::Inbox; use PublicInbox::LeiCurl; use PublicInbox::OnDestroy; -our %LIVE; # pid => callback +our $LIVE; # pid => callback sub _wq_done_wait { # dwaitpid callback (via wq_eof) my ($arg, $pid) = @_; @@ -42,20 +42,28 @@ sub _wq_done_wait { # dwaitpid callback (via wq_eof) # for old installations without manifest.js.gz sub try_scrape { - my ($self) = @_; + my ($self, $fallback_manifest) = @_; 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, '--compressed'); + my $cmd = $curl->for_uri($lei, $uri, qw(-f --compressed)); my $opt = { 0 => $lei->{0}, 2 => $lei->{2} }; 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"); # we grep with URL below, we don't want Subject/From headers - # making us clone random URLs + # making us clone random URLs. This assumes remote instances + # prior to public-inbox 1.7.0 + # 5b96edcb1e0d8252 (www: move mirror instructions to /text/, 2021-08-28) my @html = split(/
/, $html); my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g); + if (!@urls && $fallback_manifest) { + warn <as_string; chop($url) eq '/' or die "BUG: $uri not canonicalized"; @@ -66,8 +74,9 @@ sub try_scrape { my ($n) = (m!/([0-9]+)\z!); $n => [ URI->new($_), '' ] } @v2_urls; # uniq - clone_v2($self, \%v2_epochs); - reap_live() while keys(%LIVE); + clone_v2_prep($self, \%v2_epochs); + delete local $lei->{opt}->{epoch}; + clone_all($self); return; } @@ -97,7 +106,8 @@ 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; } @@ -122,14 +132,14 @@ sub _get_txt_start { # non-fatal 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), + my $cmd = $self->{curl}->for_uri($lei, $uri, qw(-f --compressed -R -o), $ft->filename); my $jobs = $lei->{opt}->{jobs} // 1; - reap_live() while keys(%LIVE) >= $jobs; + reap_live() while keys(%$LIVE) >= $jobs; $lei->qerr("# @$cmd"); return if $self->{dry_run}; $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ]; - $LIVE{spawn($cmd, undef, $opt)} = + $LIVE->{spawn($cmd, undef, $opt)} = [ \&_get_txt_done, $self, $endpoint, $fini ]; } @@ -176,16 +186,17 @@ sub set_description ($) { 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): $!"; } @@ -220,7 +231,7 @@ sub index_cloned_inbox { PublicInbox::Admin::progress_prepare($opt, $lei->{2}); PublicInbox::Admin::index_inbox($ibx, undef, $opt); } - return if defined $self->{cur_dst}; + return if defined $self->{cur_dst}; # one of many repos to clone open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait } @@ -236,10 +247,10 @@ 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"); return if $self->{dry_run}; - $LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ]; + $LIVE->{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ] } sub clone_v1 { @@ -253,14 +264,22 @@ sub clone_v1 { my $dst = $self->{cur_dst} // $self->{dst}; my $fini = PublicInbox::OnDestroy->new($$, \&v1_done, $self); my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}), "$uri", $dst ]; + my $ref = $self->{-ent} ? $self->{-ent}->{reference} : undef; + defined($ref) && -e "$self->{dst}$ref" and + push @$cmd, '--reference', "$self->{dst}$ref"; start_clone($self, $cmd, $opt, $fini); - _get_txt_start($self, '_/text/config/raw', $fini); + if (!$self->{-is_epoch} && $lei->{opt}->{'inbox-config'} =~ + /\A(?:always|v1)\z/s) { + _get_txt_start($self, '_/text/config/raw', $fini); + } + my $d = $self->{-ent} ? $self->{-ent}->{description} : undef; - defined($d) ? ($self->{'txt.description'} = $d) : + $self->{'txt.description'} = $d if defined $d; + (!defined($d) && !$nohang) and _get_txt_start($self, 'description', $fini); - reap_live() until ($nohang || !keys(%LIVE)); # for non-manifest clone + reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone } sub parse_epochs ($$) { @@ -307,7 +326,7 @@ EOM } sub init_placeholder ($$$) { - my ($src, $edst, $owner) = @_; + my ($src, $edst, $ent) = @_; PublicInbox::Import::init_bare($edst); my $f = "$edst/config"; open my $fh, '>>', $f or die "open($f): $!"; @@ -321,13 +340,22 @@ sub init_placeholder ($$$) { ; will not fetch updates for it unless write permission is added. ; Hint: chmod +w $edst EOM - if (defined($owner)) { + if (defined($ent->{owner})) { print $fh <{owner} EOM } - close $fh or die "close:($f): $!"; + 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 @@ -335,49 +363,59 @@ 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}; + return if $self->{dry_run} || !$LIVE; _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]); } + 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}; + 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($$); _write_inbox_config($self); require PublicInbox::MultiGit; - my $dst = $self->{cur_dst} // $self->{dst}; my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git'); $mg->fill_alternates; for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) } - my $edst_owner = delete($self->{-owner}) // []; - while (@$edst_owner) { - my ($edst, $o) = splice(@$edst_owner); - run_die [qw(git config -f), "$edst/config", 'gitweb.owner', $o]; - } for my $edst (@{delete($self->{-read_only}) // []}) { my @st = stat($edst) or die "stat($edst): $!"; chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!"; } write_makefile($dst, 2); - delete $self->{-locked} // die "BUG: $dst not locked"; # unlock + undef $lck; # unlock index_cloned_inbox($self, 2); } sub reap_live { my $pid = waitpid(-1, 0) // die "waitpid(-1): $!"; - if (my $x = delete $LIVE{$pid}) { + if (my $x = delete $LIVE->{$pid}) { my $cb = shift @$x; $cb->(@$x); } else { @@ -385,7 +423,7 @@ sub reap_live { } } -sub clone_v2 ($$;$) { +sub clone_v2_prep ($$;$) { my ($self, $v2_epochs, $m) = @_; # $m => manifest.js.gz hashref my $lei = $self->{lei}; my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return; @@ -394,7 +432,8 @@ sub clone_v2 ($$;$) { 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, @entv); for my $nr (sort { $a <=> $b } keys %$v2_epochs) { my ($uri, $key) = @{$v2_epochs->{$nr}}; my $src = $uri->as_string; @@ -404,34 +443,47 @@ failed to extract epoch number from $src $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr"; $edst .= "/git/$nr.git"; - $m->{$key} // die "BUG: `$key' not in manifest.js.gz"; + my $ent; + if ($m) { + $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; - my $o = $m->{$key}->{owner}; - push(@{$task->{-owner}}, $edst, $o) if defined($o); + push @entv, $edst, $ent; + $self->{any_want}->{$key} = 1; } else { # create a placeholder so users only need to chmod +w - init_placeholder($src, $edst, $m->{$key}->{owner}); + init_placeholder($src, $edst, $ent); push @{$task->{-read_only}}, $edst; push @skip, $key; } } # filter out the epochs we skipped - $self->{-culled_manifest} = 1 if delete(@$m{@skip}); + $self->{-culled_manifest} = 1 if $m && delete(@$m{@skip}); (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst); - require PublicInbox::Lock; - my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock'; my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task); - _get_txt_start($task, '_/text/config/raw', $fini); - _get_txt_start($self, 'description', $fini); - - $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run}; - my @cmd = clone_cmd($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', $fini); + while (@entv) { + my ($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} = $fini; + push @{$self->{todo}->{($ent->{reference} // '')}}, $etask; } } @@ -464,18 +516,18 @@ sub multi_inbox ($$$) { my $n = scalar(keys %$v2) + scalar(@v1); my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : (); if (defined $incl) { - my $re = '(?:'.join('|', map { - $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/ - } @$incl).')'; + my $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$incl).'\\z)'; my @gone = delete @$v2{grep(!/$re/, keys %$v2)}; delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1; @v1 = grep(/$re/, @v1); } if (defined $excl) { - my $re = '(?:'.join('|', map { - $self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/ - } @$excl).')'; + my $re = '(?:'.join('\\z|', map { + $self->{lei}->glob2re($_) // qr/\A\Q$_\E/ + } @$excl).'\\z)'; my @gone = delete @$v2{grep(/$re/, keys %$v2)}; delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1; delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1; @@ -504,6 +556,45 @@ sub multi_inbox ($$$) { ($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, $nxt); + # resolve multi-level references + while ($m && defined($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 + } + } + reap_live() while keys(%$LIVE); +} + # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz sub try_manifest { my ($self) = @_; @@ -516,10 +607,9 @@ sub try_manifest { my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX', UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp'); my $fn = $ft->filename; - my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn); + my $cmd = $curl->for_uri($lei, $uri, qw(-f -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, "@$cmd failed"); @@ -531,7 +621,9 @@ sub try_manifest { } my ($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 { @@ -552,7 +644,7 @@ sub try_manifest { index($self->{cur_dst}, "\n") >= 0 and die <{cur_dst}' must not contain newline EOM - clone_v2($self, \%v2_epochs, $m); + clone_v2_prep($self, \%v2_epochs, $m); return if $self->{lei}->{child_error}; } } @@ -561,8 +653,6 @@ EOM chop($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 `$name' in manifest"); @@ -576,13 +666,17 @@ EOM E: `$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; # for clone_all + $self->{any_want}->{$name} = 1; } } - reap_live() while keys(%LIVE); + delete local $lei->{opt}->{epoch} if defined($v2); + clone_all($self, $m); return if $self->{lei}->{child_error} || $self->{dry_run}; - if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude + # set by clone_v2_prep/-I/--exclude + if (delete $self->{-culled_manifest}) { # 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 @@ -601,20 +695,24 @@ 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 $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"; - } - return start_clone_url($self) if $self->{src} =~ m!://!; - die "TODO: cloning local directories not supported, yet"; + 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' + + local $LIVE; + my $iv = $lei->{opt}->{'inbox-version'} // + return start_clone_url($self); + return clone_v1($self) if $iv == 1; + die "bad --inbox-version=$iv\n" if $iv != 2; + die <{src} !~ m!://!; +cloning local v2 inboxes not supported +EOM + try_scrape($self, 1); }; $lei->fail($@) if $@; }