* [PATCH 1/2] t/cindex: fix test when worktree PWD is a symlink
2023-12-06 21:12 [PATCH 0/2] cindex bug fixes Eric Wong
@ 2023-12-06 21:12 ` Eric Wong
2023-12-06 21:12 ` [PATCH 2/2] cindex: avoid recursion on prune Eric Wong
1 sibling, 0 replies; 3+ messages in thread
From: Eric Wong @ 2023-12-06 21:12 UTC (permalink / raw)
To: meta
Our code aims to respect $ENV{PWD} (and therefore symlinks) as
much as possible to ensure portability across devices when repos
and indices are on portable or shared storage. Thus we can't
rely on Cwd::abs_path and ought to favor File::Spec->rel2abs
whenever absolute paths are required.
I noticed this when working on a VM where my worktree is a
symlink to a more reliable device.
---
t/cindex.t | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/t/cindex.t b/t/cindex.t
index 716e5984..15c860e1 100644
--- a/t/cindex.t
+++ b/t/cindex.t
@@ -3,7 +3,7 @@
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
use v5.12;
use PublicInbox::TestCommon;
-use Cwd qw(getcwd abs_path);
+use Cwd qw(getcwd);
use List::Util qw(sum);
use autodie qw(close mkdir open rename);
require_mods(qw(json Xapian +SCM_RIGHTS));
@@ -67,6 +67,7 @@ git gc -q
EOM
}; # /create_coderepo
+$zp = File::Spec->rel2abs($zp);
ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext",
'-g', $zp, '-g', "$tmp/wt0" ]),
'cindex external');
@@ -125,7 +126,7 @@ use_ok 'PublicInbox::CodeSearch';
my @xh_args;
my $exp = [ 'initial with NUL character', 'remove NUL character' ];
-my $zp_git = abs_path("$zp/.git");
+my $zp_git = "$zp/.git";
if ('multi-repo search') {
my $csrch = PublicInbox::CodeSearch->new("$tmp/ext");
my $mset = $csrch->mset('NUL');
^ permalink raw reply related [flat|nested] 3+ messages in thread
* [PATCH 2/2] cindex: avoid recursion on prune
2023-12-06 21:12 [PATCH 0/2] cindex bug fixes Eric Wong
2023-12-06 21:12 ` [PATCH 1/2] t/cindex: fix test when worktree PWD is a symlink Eric Wong
@ 2023-12-06 21:12 ` Eric Wong
1 sibling, 0 replies; 3+ messages in thread
From: Eric Wong @ 2023-12-06 21:12 UTC (permalink / raw)
To: meta
There's no need to recurse and trigger deep recursion warnings
when we hit a coderepo with a known hash (SHA-1 vs SHA-256).
Noticed while pruning the 1200+ repos on a git.kernel.org
mirror.
---
lib/PublicInbox/CodeSearchIdx.pm | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/lib/PublicInbox/CodeSearchIdx.pm b/lib/PublicInbox/CodeSearchIdx.pm
index 20aac584..967933f2 100644
--- a/lib/PublicInbox/CodeSearchIdx.pm
+++ b/lib/PublicInbox/CodeSearchIdx.pm
@@ -909,21 +909,23 @@ sub prep_alternate_read { # run_git cb for config extensions.objectFormat
sub prep_alternate_start {
my ($self, $git, $run_prune) = @_;
- my $o = $git->git_path('objects');
+ local $self->{xdb};
+ my ($o, $n, @ids, @fmt);
+start:
+ $o = $git->git_path('objects');
while (!-d $o) {
$git = shift(@PRUNEQ) // return;
$o = $git->git_path('objects');
}
- my $n = git_dir_hash($git->{git_dir}) % scalar(@RDONLY_XDB);
- local $self->{xdb} = $RDONLY_XDB[$n] // croak("BUG: no shard[$n]");
- my @ids = $self->docids_by_postlist('P'.$git->{git_dir});
- my @fmt = @ids ? xap_terms('H', $self->{xdb}, $ids[0]) : ();
+ $n = git_dir_hash($git->{git_dir}) % scalar(@RDONLY_XDB);
+ $self->{xdb} = $RDONLY_XDB[$n] // croak("BUG: no shard[$n]");
+ @ids = $self->docids_by_postlist('P'.$git->{git_dir});
+ @fmt = @ids ? xap_terms('H', $self->{xdb}, $ids[0]) : ();
@fmt > 1 and warn "BUG? multi `H' for shard[$n] #$ids[0]: @fmt";
if (@fmt) { # cache hit
- @PRUNEQ and
- prep_alternate_start($self, shift(@PRUNEQ), $run_prune);
prep_alternate_end $o, $fmt[0];
+ $git = shift(@PRUNEQ) and goto start;
} else { # compatibility w/ early cidx format
run_git([qw(config extensions.objectFormat)], { quiet => 1 },
\&prep_alternate_read, $self, $git, $o, $ids[0], $n,
^ permalink raw reply related [flat|nested] 3+ messages in thread