From 7281c5c492f9d6bbd585da9f061d19819d952352 Mon Sep 17 00:00:00 2001
From: Eric Wong <e@80x24.org>
Date: Tue, 15 Dec 2020 02:02:16 +0000
Subject: extindex: preliminary --reindex support

--reindex allows us to catch missed and stale messages due to
-extindex vs -index races prior to commit 02b2fcc46f364b51
("extsearchidx: enforce -index before -extindex").

We'll also rely on reindex to internally deal with v1/v2 inbox
removals and partial-unindexing of messages which are only
removed from one inbox out of many.

This reindex design is completely different than how normal
v1/v2 inbox reindex operates due to extindex having multiple
histories to work with.  Instead of scanning git history, this
relies exclusively on comparing over.sqlite3 contents between
the v1/v2 inboxes and the extindex.

Changes to Xapian behavior also get picked up, now.  Xapian indexing
is handled by workers with minimal IPC to the parent process.
This results in more read I/O but fewer writes when dealing
with cross-posted messages.

Changes to $smsg->populate and --rethread still need further
work.
---
 lib/PublicInbox/OverIdx.pm | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

(limited to 'lib/PublicInbox/OverIdx.pm')

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 38552247..4a39bf53 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -563,6 +563,15 @@ CREATE TABLE IF NOT EXISTS eidx_meta (
 	val VARCHAR(255) NOT NULL
 )
 
+		# A queue of current docids which need reindexing.
+		# eidxq persists across aborted -extindex invocations
+		# Currently used for "-extindex --reindex" for Xapian
+		# data, but may be used in more places down the line.
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS eidxq (
+	docid INTEGER PRIMARY KEY NOT NULL
+)
+
 		$dbh;
 	};
 }
@@ -661,4 +670,18 @@ UPDATE over SET ddd = ? WHERE num = ?
 	$sth->execute;
 }
 
+sub eidxq_add {
+	my ($self, $docid) = @_;
+	$self->dbh->prepare_cached(<<'')->execute($docid);
+INSERT OR IGNORE INTO eidxq (docid) VALUES (?)
+
+}
+
+sub eidxq_del {
+	my ($self, $docid) = @_;
+	$self->dbh->prepare_cached(<<'')->execute($docid);
+DELETE FROM eidxq WHERE docid = ?
+
+}
+
 1;
-- 
cgit v1.2.3-24-ge0c7