* [PATCH 1/2] searchidx: simplify ghost creation
2016-06-21 4:28 [PATCH 0/2] searchidx: fix ghost vivification Eric Wong
@ 2016-06-21 4:28 ` Eric Wong
2016-06-21 4:28 ` [PATCH 2/2] searchidx: merge old thread id from ghosts Eric Wong
1 sibling, 0 replies; 4+ messages in thread
From: Eric Wong @ 2016-06-21 4:28 UTC (permalink / raw)
To: meta
Remove some worthless parameters and redundant no-ops
to make the next (important) patch easier-to-review.
---
lib/PublicInbox/SearchIdx.pm | 20 ++++----------------
1 file changed, 4 insertions(+), 16 deletions(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index a259d86..3134687 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -150,11 +150,11 @@ sub add_message {
if ($was_ghost) {
$doc_id = $smsg->doc_id;
- $self->link_message($smsg, 0);
+ $self->link_message($smsg);
$doc->set_data($smsg->to_doc_data);
$db->replace_document($doc_id, $doc);
} else {
- $self->link_message($smsg, 0);
+ $self->link_message($smsg);
$doc->set_data($smsg->to_doc_data);
$doc_id = $db->add_document($doc);
}
@@ -211,16 +211,6 @@ sub next_thread_id {
}
sub link_message {
- my ($self, $smsg, $is_ghost) = @_;
-
- if ($is_ghost) {
- $smsg->ensure_metadata;
- } else {
- $self->link_message_to_parents($smsg);
- }
-}
-
-sub link_message_to_parents {
my ($self, $smsg) = @_;
my $doc = $smsg->{doc};
my $mid = $smsg->mid;
@@ -414,17 +404,15 @@ sub _resolve_mid_to_tid {
}
sub create_ghost {
- my ($self, $mid, $tid) = @_;
-
- $tid = $self->next_thread_id unless defined $tid;
+ my ($self, $mid) = @_;
+ my $tid = $self->next_thread_id;
my $doc = Search::Xapian::Document->new;
$doc->add_term(xpfx('mid') . $mid);
$doc->add_term(xpfx('thread') . $tid);
$doc->add_term(xpfx('type') . 'ghost');
my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $self->link_message($smsg, 1);
$self->{xdb}->add_document($doc);
$smsg;
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH 2/2] searchidx: merge old thread id from ghosts
2016-06-21 4:28 [PATCH 0/2] searchidx: fix ghost vivification Eric Wong
2016-06-21 4:28 ` [PATCH 1/2] searchidx: simplify ghost creation Eric Wong
@ 2016-06-21 4:28 ` Eric Wong
2016-06-21 21:26 ` Eric Wong
1 sibling, 1 reply; 4+ messages in thread
From: Eric Wong @ 2016-06-21 4:28 UTC (permalink / raw)
To: meta
We failed to discard old thread IDs when vivifying ghosts
due to out-of-order message arrival. This rectifies the
failure and will trigger a re-index.
---
lib/PublicInbox/Search.pm | 3 ++-
lib/PublicInbox/SearchIdx.pm | 5 +++--
2 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 8c0bab1..bf50365 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -36,7 +36,8 @@ use constant {
# 8 - remove redundant/unneeded document data
# 9 - disable Message-ID compression (SHA-1)
# 10 - optimize doc for NNTP overviews
- SCHEMA_VERSION => 10,
+ # 11 - merge threads when vivifying ghosts
+ SCHEMA_VERSION => 11,
# n.b. FLAG_PURE_NOT is expensive not suitable for a public website
# as it could become a denial-of-service vector
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 3134687..58eccc1 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -150,7 +150,7 @@ sub add_message {
if ($was_ghost) {
$doc_id = $smsg->doc_id;
- $self->link_message($smsg);
+ $self->link_message($smsg, $smsg->thread_id);
$doc->set_data($smsg->to_doc_data);
$db->replace_document($doc_id, $doc);
} else {
@@ -211,7 +211,7 @@ sub next_thread_id {
}
sub link_message {
- my ($self, $smsg) = @_;
+ my ($self, $smsg, $old_tid) = @_;
my $doc = $smsg->{doc};
my $mid = $smsg->mid;
my $mime = $smsg->mime;
@@ -247,6 +247,7 @@ sub link_message {
# but we can never trust clients to do the right thing
my $ref = shift @refs;
$tid = $self->_resolve_mid_to_tid($ref);
+ $self->merge_threads($tid, $old_tid) if defined $old_tid;
# the rest of the refs should point to this tid:
foreach $ref (@refs) {
^ permalink raw reply related [flat|nested] 4+ messages in thread