X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FOverIdx.pm;h=0a4eb39e0a9d112260eb417c035846c5bac5e7e4;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=6f0477f0a7150587e4b64a0bf0470736b8caba75;hpb=7f4a11a6499aade26b418b7ae13cd12859f75bdd;p=public-inbox.git

diff --git a/lib/PublicInbox/OverIdx.pm b/lib/PublicInbox/OverIdx.pm
index 6f0477f0..0a4eb39e 100644
--- a/lib/PublicInbox/OverIdx.pm
+++ b/lib/PublicInbox/OverIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # for XOVER, OVER in NNTP, and feeds/homepage/threads in PSGI
@@ -79,6 +79,11 @@ SELECT $id_col FROM $tbl WHERE $val_col = ? LIMIT 1
 	}
 }
 
+sub ibx_id {
+	my ($self, $eidx_key) = @_;
+	id_for($self, 'inboxes', 'ibx_id', eidx_key => $eidx_key);
+}
+
 sub sid {
 	my ($self, $path) = @_;
 	return unless defined $path && $path ne '';
@@ -170,8 +175,14 @@ sub _resolve_mid_to_tid {
 		$$tid = $cur_tid;
 	} else { # rethreading, queue up dead ghosts
 		$$tid = next_tid($self);
-		my $num = $smsg->{num};
-		push(@{$self->{-ghosts_to_delete}}, $num) if $num < 0;
+		my $n = $smsg->{num};
+		if ($n > 0) {
+			$self->{dbh}->prepare_cached(<<'')->execute($$tid, $n);
+UPDATE over SET tid = ? WHERE num = ?
+
+		} elsif ($n < 0) {
+			push(@{$self->{-ghosts_to_delete}}, $n);
+		}
 	}
 	1;
 }
@@ -261,21 +272,27 @@ sub subject_path ($) {
 	lc($subj);
 }
 
+sub ddd_for ($) {
+	my ($smsg) = @_;
+	my $dd = $smsg->to_doc_data;
+	utf8::encode($dd);
+	compress($dd);
+}
+
 sub add_overview {
 	my ($self, $eml, $smsg) = @_;
 	$smsg->{lines} = $eml->body_raw =~ tr!\n!\n!;
 	my $mids = mids_for_index($eml);
 	my $refs = parse_references($smsg, $eml, $mids);
+	$mids->[0] //= $smsg->{mid} //= $eml->{-lei_fake_mid};
+	$smsg->{mid} //= '';
 	my $subj = $smsg->{subject};
 	my $xpath;
 	if ($subj ne '') {
 		$xpath = subject_path($subj);
 		$xpath = id_compress($xpath);
 	}
-	my $dd = $smsg->to_doc_data;
-	utf8::encode($dd);
-	$dd = compress($dd);
-	add_over($self, $smsg, $mids, $refs, $xpath, $dd);
+	add_over($self, $smsg, $mids, $refs, $xpath, ddd_for($smsg));
 }
 
 sub _add_over {
@@ -294,7 +311,7 @@ sub _add_over {
 		}
 	} elsif ($n < 0) { # ghost
 		$$old_tid //= $cur_valid ? $cur_tid : next_tid($self);
-		link_refs($self, $refs, $$old_tid);
+		$$old_tid = link_refs($self, $refs, $$old_tid);
 		delete_by_num($self, $n);
 		$$v++;
 	}
@@ -379,13 +396,12 @@ sub create_tables {
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS over (
-	num INTEGER NOT NULL,
-	tid INTEGER NOT NULL,
-	sid INTEGER,
-	ts INTEGER,
-	ds INTEGER,
-	ddd VARBINARY, /* doc-data-deflated */
-	UNIQUE (num)
+	num INTEGER PRIMARY KEY NOT NULL, /* NNTP article number == IMAP UID */
+	tid INTEGER NOT NULL, /* THREADID (IMAP REFERENCES threading, JMAP) */
+	sid INTEGER, /* Subject ID (IMAP ORDEREDSUBJECT "threading") */
+	ts INTEGER, /* IMAP INTERNALDATE (Received: header, git commit time) */
+	ds INTEGER, /* RFC-2822 sent Date: header, git author time */
+	ddd VARBINARY /* doc-data-deflated (->to_doc_data, ->load_from_data) */
 )
 
 	$dbh->do('CREATE INDEX IF NOT EXISTS idx_tid ON over (tid)');
@@ -406,13 +422,13 @@ CREATE TABLE IF NOT EXISTS counter (
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS subject (
 	sid INTEGER PRIMARY KEY AUTOINCREMENT,
-	path VARCHAR(40) NOT NULL,
+	path VARCHAR(40) NOT NULL, /* SHA-1 of normalized subject */
 	UNIQUE (path)
 )
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS id2num (
-	id INTEGER NOT NULL,
+	id INTEGER NOT NULL, /* <=> msgid.id */
 	num INTEGER NOT NULL,
 	UNIQUE (id, num)
 )
@@ -423,7 +439,7 @@ CREATE TABLE IF NOT EXISTS id2num (
 
 	$dbh->do(<<'');
 CREATE TABLE IF NOT EXISTS msgid (
-	id INTEGER PRIMARY KEY AUTOINCREMENT,
+	id INTEGER PRIMARY KEY AUTOINCREMENT, /* <=> id2num.id */
 	mid VARCHAR(244) NOT NULL,
 	UNIQUE (mid)
 )
@@ -459,10 +475,14 @@ sub dbh_close {
 
 sub create {
 	my ($self) = @_;
-	unless (-r $self->{filename}) {
+	my $fn = $self->{filename} // do {
+		Carp::confess('BUG: no {filename}') unless $self->{dbh};
+		return;
+	};
+	unless (-r $fn) {
 		require File::Path;
 		require File::Basename;
-		File::Path::mkpath(File::Basename::dirname($self->{filename}));
+		File::Path::mkpath(File::Basename::dirname($fn));
 	}
 	# create the DB:
 	PublicInbox::Over::dbh($self);
@@ -512,4 +532,172 @@ EOM
 	$pr->("I: rethread culled $total ghosts\n") if $pr && $total;
 }
 
+# used for cross-inbox search
+sub eidx_prep ($) {
+	my ($self) = @_;
+	$self->{-eidx_prep} //= do {
+		my $dbh = $self->dbh;
+		$dbh->do(<<"");
+INSERT OR IGNORE INTO counter (key) VALUES ('eidx_docid')
+
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS inboxes (
+	ibx_id INTEGER PRIMARY KEY AUTOINCREMENT,
+	eidx_key VARCHAR(255) NOT NULL, /* {newsgroup} // {inboxdir} */
+	UNIQUE (eidx_key)
+)
+
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS xref3 (
+	docid INTEGER NOT NULL, /* <=> over.num */
+	ibx_id INTEGER NOT NULL, /* <=> inboxes.ibx_id */
+	xnum INTEGER NOT NULL, /* NNTP article number in ibx */
+	oidbin VARBINARY NOT NULL, /* 20-byte SHA-1 or 32-byte SHA-256 */
+	UNIQUE (docid, ibx_id, xnum, oidbin)
+)
+
+	$dbh->do('CREATE INDEX IF NOT EXISTS idx_docid ON xref3 (docid)');
+
+	# performance critical, this is not UNIQUE since we may need to
+	# tolerate some old bugs from indexing mirrors
+	$dbh->do('CREATE INDEX IF NOT EXISTS idx_nntp ON '.
+		'xref3 (oidbin,xnum,ibx_id)');
+
+		$dbh->do(<<'');
+CREATE TABLE IF NOT EXISTS eidx_meta (
+	key VARCHAR(255) PRIMARY KEY,
+	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
+)
+
+		$dbh;
+	};
+}
+
+sub eidx_meta { # requires transaction
+	my ($self, $key, $val) = @_;
+
+	my $sql = 'SELECT val FROM eidx_meta WHERE key = ? LIMIT 1';
+	my $dbh = $self->{dbh};
+	defined($val) or return $dbh->selectrow_array($sql, undef, $key);
+
+	my $prev = $dbh->selectrow_array($sql, undef, $key);
+	if (defined $prev) {
+		$sql = 'UPDATE eidx_meta SET val = ? WHERE key = ?';
+		$dbh->do($sql, undef, $val, $key);
+	} else {
+		$sql = 'INSERT INTO eidx_meta (key,val) VALUES (?,?)';
+		$dbh->do($sql, undef, $key, $val);
+	}
+	$prev;
+}
+
+sub eidx_max {
+	my ($self) = @_;
+	get_counter($self->{dbh}, 'eidx_docid');
+}
+
+sub add_xref3 {
+	my ($self, $docid, $xnum, $oidhex, $eidx_key) = @_;
+	begin_lazy($self);
+	my $ibx_id = ibx_id($self, $eidx_key);
+	my $oidbin = pack('H*', $oidhex);
+	my $sth = $self->{dbh}->prepare_cached(<<'');
+INSERT OR IGNORE INTO xref3 (docid, ibx_id, xnum, oidbin) VALUES (?, ?, ?, ?)
+
+	$sth->bind_param(1, $docid);
+	$sth->bind_param(2, $ibx_id);
+	$sth->bind_param(3, $xnum);
+	$sth->bind_param(4, $oidbin, SQL_BLOB);
+	$sth->execute;
+}
+
+# returns remaining reference count to $docid
+sub remove_xref3 {
+	my ($self, $docid, $oidhex, $eidx_key, $rm_eidx_info) = @_;
+	begin_lazy($self);
+	my $oidbin = pack('H*', $oidhex);
+	my ($sth, $ibx_id);
+	if (defined $eidx_key) {
+		$ibx_id = ibx_id($self, $eidx_key);
+		$sth = $self->{dbh}->prepare_cached(<<'');
+DELETE FROM xref3 WHERE docid = ? AND ibx_id = ? AND oidbin = ?
+
+		$sth->bind_param(1, $docid);
+		$sth->bind_param(2, $ibx_id);
+		$sth->bind_param(3, $oidbin, SQL_BLOB);
+	} else {
+		$sth = $self->{dbh}->prepare_cached(<<'');
+DELETE FROM xref3 WHERE docid = ? AND oidbin = ?
+
+		$sth->bind_param(1, $docid);
+		$sth->bind_param(2, $oidbin, SQL_BLOB);
+	}
+	$sth->execute;
+	$sth = $self->{dbh}->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE docid = ?
+
+	$sth->execute($docid);
+	my $nr = $sth->fetchrow_array;
+	if ($nr == 0) {
+		delete_by_num($self, $docid);
+	} elsif (defined($ibx_id) && $rm_eidx_info) {
+		# if deduplication rules in ContentHash change, it's
+		# possible a docid can have multiple rows with the
+		# same ibx_id.  This governs whether or not we call
+		# ->shard_remove_eidx_info in ExtSearchIdx.
+		$sth = $self->{dbh}->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE docid = ? AND ibx_id = ?
+
+		$sth->execute($docid, $ibx_id);
+		my $count = $sth->fetchrow_array;
+		$$rm_eidx_info = ($count == 0);
+	}
+	$nr;
+}
+
+# for when an xref3 goes missing, this does NOT update {ts}
+sub update_blob {
+	my ($self, $smsg, $oidhex) = @_;
+	my $sth = $self->{dbh}->prepare(<<'');
+UPDATE over SET ddd = ? WHERE num = ?
+
+	$smsg->{blob} = $oidhex;
+	$sth->bind_param(1, ddd_for($smsg), SQL_BLOB);
+	$sth->bind_param(2, $smsg->{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 = ?
+
+}
+
+sub blob_exists {
+	my ($self, $oidhex) = @_;
+	my $sth = $self->dbh->prepare_cached(<<'', undef, 1);
+SELECT COUNT(*) FROM xref3 WHERE oidbin = ?
+
+	$sth->bind_param(1, pack('H*', $oidhex), SQL_BLOB);
+	$sth->execute;
+	$sth->fetchrow_array;
+}
+
 1;