rename {pi_config} fields to {pi_cfg}

[public-inbox.git] / lib / PublicInbox / Gcf2.pm

diff --git a/lib/PublicInbox/Gcf2.pm b/lib/PublicInbox/Gcf2.pm
index 6ac3aa188b9a50f32b244d5ecb799a2aa16b45b5..041dffe7d9c7b26396ab0a97f7b7deaf008c6896 100644 (file)
--- a/lib/PublicInbox/Gcf2.pm
+++ b/lib/PublicInbox/Gcf2.pm
@@ -1,11 +1,13 @@
 # Copyright (C) 2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
-#
-# git-cat-file based on libgit2
+
+# backend for a git-cat-file-workalike based on libgit2,
+# other libgit2 stuff may go here, too.
 package PublicInbox::Gcf2;
 use strict;
 use PublicInbox::Spawn qw(which popen_rd);
 use Fcntl qw(LOCK_EX);
+use IO::Handle; # autoflush
 my (%CFG, $c_src, $lockfh);
 BEGIN {
        # PublicInbox::Spawn will set PERL_INLINE_DIRECTORY
@@ -53,4 +55,56 @@ use Inline C => $c_src;
 undef $c_src;
 undef %CFG;
 undef $lockfh;
+
+sub add_alt ($$) {
+       my ($gcf2, $objdir) = @_;
+
+       # libgit2 (tested 0.27.7+dfsg.1-0.2 and 0.28.3+dfsg.1-1~bpo10+1
+       # in Debian) doesn't handle relative epochs properly when nested
+       # multiple levels.  Add all the absolute paths to workaround it,
+       # since $EXTINDEX_DIR/ALL.git/objects/info/alternates uses absolute
+       # paths to reference $V2INBOX_DIR/all.git/objects and
+       # $V2INBOX_DIR/all.git/objects/info/alternates uses relative paths
+       # to refer to $V2INBOX_DIR/git/$EPOCH.git/objects
+       #
+       # See https://bugs.debian.org/975607
+       if (open(my $fh, '<', "$objdir/info/alternates")) {
+               chomp(my @abs_alt = grep(m!^/!, <$fh>));
+               $gcf2->add_alternate($_) for @abs_alt;
+       }
+       $gcf2->add_alternate($objdir);
+}
+
+# Usage: $^X -MPublicInbox::Gcf2 -e 'PublicInbox::Gcf2::loop()'
+# (see lib/PublicInbox/Gcf2Client.pm)
+sub loop {
+       my $gcf2 = new();
+       my %seen;
+       STDERR->autoflush(1);
+       STDOUT->autoflush(1);
+
+       while (<STDIN>) {
+               chomp;
+               my ($oid, $git_dir) = split(/ /, $_, 2);
+               $seen{$git_dir}++ or add_alt($gcf2, "$git_dir/objects");
+               if (!$gcf2->cat_oid(1, $oid)) {
+                       # retry once if missing.  We only get unabbreviated OIDs
+                       # from SQLite or Xapian DBs, here, so malicious clients
+                       # can't trigger excessive retries:
+                       warn "I: $$ $oid missing, retrying in $git_dir\n";
+
+                       $gcf2 = new();
+                       %seen = ($git_dir => 1);
+                       add_alt($gcf2, "$git_dir/objects");
+
+                       if ($gcf2->cat_oid(1, $oid)) {
+                               warn "I: $$ $oid found after retry\n";
+                       } else {
+                               warn "W: $$ $oid missing after retry\n";
+                               print "$oid missing\n"; # mimic git-cat-file
+                       }
+               }
+       }
+}
+
 1;