X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FFetch.pm;h=f93eeebeae29f85c0fd20374f42724f0a0941447;hb=refs%2Fheads%2Fmaster;hp=7881b402e3f6c2b7d870a115b50f30286a029ab4;hpb=77b3dac08f58503e374e98c29b9e0ee7c866c0e5;p=public-inbox.git diff --git a/lib/PublicInbox/Fetch.pm b/lib/PublicInbox/Fetch.pm index 7881b402..f93eeebe 100644 --- a/lib/PublicInbox/Fetch.pm +++ b/lib/PublicInbox/Fetch.pm @@ -2,42 +2,45 @@ # License: AGPL-3.0+ # 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_die spawn); use PublicInbox::Admin; use PublicInbox::LEI; use PublicInbox::LeiCurl; use PublicInbox::LeiMirror; use File::Temp (); -use PublicInbox::Config; -use IO::Compress::Gzip qw(gzip $GzipError); 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 $fh = popen_rd($cmd, undef, { -C => $dir, 2 => $lei->{2} }); + my $url = <$fh>; + close $fh or next; + $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 ($$$) { @@ -45,16 +48,15 @@ sub do_manifest ($$$) { 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); @@ -65,7 +67,7 @@ sub do_manifest ($$$) { return; } my $m1 = eval { - PublicInbox::LeiMirror::decode_manifest($ft, $fn, $muri); + PublicInbox::LeiMirror::decode_manifest($ft, $ft, $muri); } or return [ 404, $muri ]; my $mdiff = { %$m1 }; @@ -84,15 +86,22 @@ sub do_manifest ($$$) { return; } my (undef, $v1_path, @v2_epochs) = - PublicInbox::LeiMirror::deduce_epochs($mdiff, $ibx_uri->path); + deduce_epochs($mdiff, $ibx_uri->path); [ 200, $muri, $v1_path, \@v2_epochs, $ft, $mf, $m1 ]; } sub get_fingerprint2 { my ($git_dir) = @_; - require Digest::SHA; + require PublicInbox::SHA; my $rd = popen_rd([qw(git show-ref)], undef, { -C => $git_dir }); - Digest::SHA::sha256(do { local $/; <$rd> }); + PublicInbox::SHA::sha256(do { local $/; <$rd> }); +} + +sub writable_dir ($) { + my ($dir) = @_; + return unless -d $dir && -w _; + my @st = stat($dir); + $st[2] & 0222; # any writable bits set? (in case of root) } sub do_fetch { # main entry point @@ -103,7 +112,7 @@ sub do_fetch { # main entry point my ($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; @@ -112,7 +121,7 @@ sub do_fetch { # main entry point 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; } @@ -121,7 +130,11 @@ sub do_fetch { # main entry point $git_url = $url; $epoch = $nr; } else { - warn "W: $edir missing remote.origin.url\n"; + warn "W: $edir missing remote.*.url\n"; + my $pid = spawn([qw(git config -l)], undef, + { 1 => $lei->{2}, 2 => $lei->{2} }); + waitpid($pid, 0); + $lei->child_error($?) if $?; } } @epochs = grep { !$skip->{$_} } @epochs if $skip; @@ -177,7 +190,7 @@ 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!); @@ -203,13 +216,8 @@ EOM } for my $i (@new_epoch) { $mg->epoch_cfg_set($i) } if ($ft) { - my $fn = $ft->filename; - if ($mculled) { - my $json = PublicInbox::Config->json->encode($m1); - gzip(\$json => $fn) or die "gzip: $GzipError"; - } - rename($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; }