X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FFetch.pm;h=7881b402e3f6c2b7d870a115b50f30286a029ab4;hb=77b3dac08f58503e374e98c29b9e0ee7c866c0e5;hp=184b4f26319f1f01ddf846a97ae0a3612bffeb3c;hpb=5d9dcc31959d520d3e7bed3f68871245bc915ca3;p=public-inbox.git

diff --git a/lib/PublicInbox/Fetch.pm b/lib/PublicInbox/Fetch.pm
index 184b4f26..7881b402 100644
--- a/lib/PublicInbox/Fetch.pm
+++ b/lib/PublicInbox/Fetch.pm
@@ -12,12 +12,14 @@ 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_cmd ($$) {
+sub fetch_args ($$) {
 	my ($lei, $opt) = @_;
-	my @cmd = qw(git);
+	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
@@ -41,10 +43,9 @@ sub remote_url ($$) {
 sub do_manifest ($$$) {
 	my ($lei, $dir, $ibx_uri) = @_;
 	my $muri = URI->new("$ibx_uri/manifest.js.gz");
-	my $ft = File::Temp->new(TEMPLATE => 'manifest-XXXX',
-				UNLINK => 1, DIR => $dir);
+	my $ft = File::Temp->new(TEMPLATE => 'm-XXXX',
+				UNLINK => 1, DIR => $dir, SUFFIX => '.tmp');
 	my $fn = $ft->filename;
-	my @opt = (qw(-R -o), $fn);
 	my $mf = "$dir/manifest.js.gz";
 	my $m0; # current manifest.js.gz contents
 	if (open my $fh, '<', $mf) {
@@ -53,16 +54,19 @@ sub do_manifest ($$$) {
 		};
 		$lei->err($@) if $@;
 	}
-	my $curl_cmd = $lei->{curl}->for_uri($lei, $muri, @opt);
-	my $opt = {};
+	my ($bn) = ($fn =~ 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, $fn, $muri);
+	} or return [ 404, $muri ];
 	my $mdiff = { %$m1 };
 
 	# filter out unchanged entries.  We check modified, too, since
@@ -81,7 +85,7 @@ sub do_manifest ($$$) {
 	}
 	my (undef, $v1_path, @v2_epochs) =
 		PublicInbox::LeiMirror::deduce_epochs($mdiff, $ibx_uri->path);
-	[ 200, $v1_path, \@v2_epochs, $muri, $ft, $mf ];
+	[ 200, $muri, $v1_path, \@v2_epochs, $ft, $mf, $m1 ];
 }
 
 sub get_fingerprint2 {
@@ -96,7 +100,7 @@ sub do_fetch { # main entry point
 	my $ibx_ver;
 	$lei->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
 	my $dir = PublicInbox::Admin::resolve_inboxdir($cd, \$ibx_ver);
-	my ($ibx_uri, @git_dir, @epochs, $mg, @new_epoch);
+	my ($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";
@@ -104,18 +108,24 @@ sub do_fetch { # main entry point
 	} 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
+				$skip->{$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: $edir missing remote.origin.url\n";
 			}
 		}
+		@epochs = grep { !$skip->{$_} } @epochs if $skip;
+		$skip //= {}; # makes code below easier
 		$git_url or die "Unable to determine git URL\n";
 		my $inbox_url = $git_url;
 		$inbox_url =~ s!/git/$epoch(?:\.git)?/?\z!! or
@@ -127,21 +137,33 @@ 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
 		$v2_epochs = [ map { "$dir/git/$_.git" } @epochs ];
-		push @$v2_epochs, "$dir/git/".($epochs[-1] + 1) if @epochs;
+		if (@epochs) {
+			my $n = $epochs[-1] + 1;
+			push @$v2_epochs, "$dir/git/$n.git" if !$skip->{$n};
+		}
 	} 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 <$muri>, WTF?
 EOM
-		@git_dir = map { "$dir/git/$_.git" } sort { $a <=> $b }
-			map { my ($nr) = (m!/([0-9]+)\.git\z!g) } @$v2_epochs;
+		@git_dir = map { "$dir/git/$_.git" } sort { $a <=> $b } map {
+				my ($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;
 	}
@@ -153,9 +175,9 @@ EOM
 		my $cmd;
 		my $opt = {}; # for spawn
 		if (-d $d) {
-			$opt->{-C} = $d;
 			$fp2->[0] = get_fingerprint2($d) if $fp2;
-			$cmd = [ @$torsocks, fetch_cmd($lei, $opt) ];
+			$cmd = [ @$torsocks, 'git', "--git-dir=$d",
+				fetch_args($lei, $opt) ];
 		} else {
 			my $e_uri = $ibx_uri->clone;
 			my ($epath) = ($d =~ m!(/git/[0-9]+\.git)\z!);
@@ -182,6 +204,10 @@ 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);
 	}