fetch: ignore non-writable epoch dirs

[public-inbox.git] / lib / PublicInbox / Fetch.pm

diff --git a/lib/PublicInbox/Fetch.pm b/lib/PublicInbox/Fetch.pm
index 184b4f26319f1f01ddf846a97ae0a3612bffeb3c..0bd6502cd6660d6fd577b01374e1b43b98e534c1 100644 (file)
--- a/lib/PublicInbox/Fetch.pm
+++ b/lib/PublicInbox/Fetch.pm
@@ -15,9 +15,9 @@ use File::Temp ();
 
 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 +41,9 @@ 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) {
@@ -53,8 +52,9 @@ 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) {
@@ -96,7 +96,7 @@ 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: $dir missing remote.origin.url\n";
@@ -108,6 +108,10 @@ sub do_fetch { # main entry point
                my ($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
+                               $skip->{$nr} = 1;
+                               next;
+                       }
                        if (defined(my $url = remote_url($lei, $edir))) {
                                $git_url = $url;
                                $epoch = $nr;
@@ -116,6 +120,8 @@ sub do_fetch { # main entry point
                                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
@@ -132,7 +138,10 @@ EOM
                # 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 $code\n";
        }
@@ -140,8 +149,10 @@ EOM
                defined($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;
        } else {
                $git_dir[0] = $dir;
        }
@@ -153,9 +164,9 @@ 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!);