diff options
Diffstat (limited to 'lib/PublicInbox/Fetch.pm')
| -rw-r--r-- | lib/PublicInbox/Fetch.pm | 104 |
1 files changed, 63 insertions, 41 deletions
diff --git a/lib/PublicInbox/Fetch.pm b/lib/PublicInbox/Fetch.pm index 0bd6502c..b0f1437c 100644 --- a/lib/PublicInbox/Fetch.pm +++ b/lib/PublicInbox/Fetch.pm @@ -2,40 +2,45 @@ # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> # Wrapper to "git fetch" remote public-inboxes package PublicInbox::Fetch; -use strict; -use v5.10.1; +use v5.12; use parent qw(PublicInbox::IPC); use URI (); -use PublicInbox::Spawn qw(popen_rd run_die); +use PublicInbox::Spawn qw(popen_rd run_qx run_wait); use PublicInbox::Admin; use PublicInbox::LEI; use PublicInbox::LeiCurl; use PublicInbox::LeiMirror; +use PublicInbox::SHA qw(sha_all); use File::Temp (); sub new { bless {}, __PACKAGE__ } -sub fetch_args ($$) { - my ($lei, $opt) = @_; - my @cmd; # (git --git-dir=...) to be added by caller - $opt->{$_} = $lei->{$_} for (0..2); - # we support "-c $key=$val" for arbitrary git config options - # e.g.: git -c http.proxy=socks5h://127.0.0.1:9050 - push(@cmd, '-c', $_) for @{$lei->{opt}->{c} // []}; - push @cmd, 'fetch'; - push @cmd, '-q' if $lei->{opt}->{quiet}; - push @cmd, '-v' if $lei->{opt}->{verbose}; - @cmd; +sub remote_url ($$) { + my ($lei, $dir) = @_; + my $rn = $lei->{opt}->{'try-remote'} // [ 'origin', '_grokmirror' ]; + for my $r (@$rn) { + my $cmd = [ qw(git config), "remote.$r.url" ]; + my $url = run_qx($cmd, undef, { -C => $dir, 2 => $lei->{2} }); + next if $?; + $url =~ s!/*\n!!s; + return $url; + } + undef } -sub remote_url ($$) { - my ($lei, $dir) = @_; # TODO: support non-"origin"? - my $cmd = [ qw(git config remote.origin.url) ]; - my $fh = popen_rd($cmd, undef, { -C => $dir, 2 => $lei->{2} }); - my $url = <$fh>; - close $fh or return; - $url =~ s!/*\n!!s; - $url; +# PSGI mount prefixes and manifest.js.gz prefixes don't always align... +# TODO: remove, handle multi-inbox fetch +sub deduce_epochs ($$) { + 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 do_manifest ($$$) { @@ -43,26 +48,27 @@ sub do_manifest ($$$) { my $muri = URI->new("$ibx_uri/manifest.js.gz"); my $ft = File::Temp->new(TEMPLATE => 'm-XXXX', UNLINK => 1, DIR => $dir, SUFFIX => '.tmp'); - my $fn = $ft->filename; my $mf = "$dir/manifest.js.gz"; my $m0; # current manifest.js.gz contents if (open my $fh, '<', $mf) { $m0 = eval { PublicInbox::LeiMirror::decode_manifest($fh, $mf, $mf) }; - $lei->err($@) if $@; + warn($@) if $@; } - my ($bn) = ($fn =~ m!/([^/]+)\z!); + my ($bn) = ($ft->filename =~ m!/([^/]+)\z!); my $curl_cmd = $lei->{curl}->for_uri($lei, $muri, qw(-R -o), $bn); my $opt = { -C => $dir }; $opt->{$_} = $lei->{$_} for (0..2); my $cerr = PublicInbox::LeiMirror::run_reap($lei, $curl_cmd, $opt); if ($cerr) { - return [ 404 ] if ($cerr >> 8) == 22; # 404 Missing + return [ 404, $muri ] if ($cerr >> 8) == 22; # 404 Missing $lei->child_error($cerr, "@$curl_cmd failed"); return; } - my $m1 = PublicInbox::LeiMirror::decode_manifest($ft, $fn, $muri); + my $m1 = eval { + PublicInbox::LeiMirror::decode_manifest($ft, $ft, $muri); + } or return [ 404, $muri ]; my $mdiff = { %$m1 }; # filter out unchanged entries. We check modified, too, since @@ -80,15 +86,21 @@ sub do_manifest ($$$) { return; } my (undef, $v1_path, @v2_epochs) = - PublicInbox::LeiMirror::deduce_epochs($mdiff, $ibx_uri->path); - [ 200, $v1_path, \@v2_epochs, $muri, $ft, $mf ]; + deduce_epochs($mdiff, $ibx_uri->path); + [ 200, $muri, $v1_path, \@v2_epochs, $ft, $mf, $m1 ]; } sub get_fingerprint2 { my ($git_dir) = @_; - require Digest::SHA; my $rd = popen_rd([qw(git show-ref)], undef, { -C => $git_dir }); - Digest::SHA::sha256(do { local $/; <$rd> }); + sha_all(256, $rd)->digest; # ignore show-ref errors +} + +sub writable_dir ($) { + my ($dir) = @_; + return unless -d $dir && -w _; + my @st = stat($dir); + $st[2] & 0222; # any writable bits set? (in case of root) } sub do_fetch { # main entry point @@ -99,25 +111,29 @@ sub do_fetch { # main entry point my ($ibx_uri, @git_dir, @epochs, $mg, @new_epoch, $skip); if ($ibx_ver == 1) { my $url = remote_url($lei, $dir) // - die "E: $dir missing remote.origin.url\n"; + die "E: $dir missing remote.*.url\n"; $ibx_uri = URI->new($url); } else { # v2: require PublicInbox::MultiGit; $mg = PublicInbox::MultiGit->new($dir, 'all.git', 'git'); - my @epochs = $mg->git_epochs; + @epochs = $mg->git_epochs; my ($git_url, $epoch); for my $nr (@epochs) { # try newest epoch, first my $edir = "$dir/git/$nr.git"; - unless (-d $edir && -w _) { # must be writable dir + if (!writable_dir($edir)) { $skip->{$nr} = 1; next; } + next if defined $git_url; if (defined(my $url = remote_url($lei, $edir))) { $git_url = $url; $epoch = $nr; - last; } else { - warn "W: $edir missing remote.origin.url\n"; + warn "W: $edir missing remote.*.url\n"; + my $o = { -C => $edir }; + $o->{1} = $o->{2} = $lei->{2}; + run_wait([qw(git config -l)], undef, $o) and + $lei->child_error($?); } } @epochs = grep { !$skip->{$_} } @epochs if $skip; @@ -133,7 +149,7 @@ EOM PublicInbox::LeiMirror::write_makefile($dir, $ibx_ver); $lei->qerr("# inbox URL: $ibx_uri/"); my $res = do_manifest($lei, $dir, $ibx_uri) or return; - my ($code, $v1_path, $v2_epochs, $muri, $ft, $mf) = @$res; + my ($code, $muri, $v1_path, $v2_epochs, $ft, $mf, $m1) = @$res; if ($code == 404) { # any pre-manifest.js.gz instances running? Just fetch all # existing ones and unconditionally try cloning the next @@ -145,6 +161,7 @@ EOM } else { $code == 200 or die "BUG unexpected code $code\n"; } + my $mculled; if ($ibx_ver == 2) { defined($v1_path) and warn <<EOM; E: got v1 `$v1_path' when expecting v2 epoch(s) in <$muri>, WTF? @@ -153,6 +170,12 @@ EOM my ($nr) = (m!/([0-9]+)\.git\z!g); $skip->{$nr} ? () : $nr; } @$v2_epochs; + if ($m1 && scalar keys %$skip) { + my $re = join('|', keys %$skip); + my @del = grep(m!/git/$re\.git\z!, keys %$m1); + delete @$m1{@del}; + $mculled = 1; + } } else { $git_dir[0] = $dir; } @@ -166,7 +189,7 @@ EOM if (-d $d) { $fp2->[0] = get_fingerprint2($d) if $fp2; $cmd = [ @$torsocks, 'git', "--git-dir=$d", - fetch_args($lei, $opt) ]; + PublicInbox::LeiMirror::fetch_args($lei, $opt)]; } else { my $e_uri = $ibx_uri->clone; my ($epath) = ($d =~ m!(/git/[0-9]+\.git)\z!); @@ -192,9 +215,8 @@ EOM } for my $i (@new_epoch) { $mg->epoch_cfg_set($i) } if ($ft) { - my $fn = $ft->filename; - rename($fn, $mf) or die "E: rename($fn, $mf): $!\n"; - $ft->unlink_on_destroy(0); + PublicInbox::LeiMirror::dump_manifest($m1 => $ft) if $mculled; + PublicInbox::LeiMirror::ft_rename($ft, $mf, 0666); } $lei->child_error($xit << 8) if $fp2 && $xit; } |