* [PATCH 43/52] searchidx: remove xref3 support for Xapian
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
@ 2020-10-27 7:54 3% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
It doesn't seem worth storing xref3 data in Xapian now that
the same info is in over.sqlite3.
---
lib/PublicInbox/ExtSearchIdx.pm | 10 +++--
lib/PublicInbox/SearchIdx.pm | 64 +++++++++++--------------------
lib/PublicInbox/SearchIdxShard.pm | 28 +++++++-------
lib/PublicInbox/Smsg.pm | 13 -------
t/search.t | 26 +------------
5 files changed, 46 insertions(+), 95 deletions(-)
diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index 790ee921..026e1377 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -116,9 +116,10 @@ sub do_xpost ($$) {
my $eml = $req->{eml};
if (my $new_smsg = $req->{new_smsg}) { # 'm' on cross-posted message
my $xnum = $req->{xnum};
- $idx->shard_add_xref3($docid, $xnum, $oid, $xibx, $eml);
+ $self->{oidx}->add_xref3($docid, $xnum, $oid, $xibx->eidx_key);
+ $idx->shard_add_eidx_info($docid, $oid, $xibx, $eml);
} else { # 'd'
- $idx->shard_remove_xref3($docid, $oid, $xibx, $eml);
+ $idx->shard_remove_eidx_info($docid, $oid, $xibx, $eml);
}
}
@@ -135,7 +136,10 @@ sub index_unseen ($) {
$new_smsg->{num} = $docid;
my $idx = $self->idx_shard($docid);
$self->{oidx}->add_overview($eml, $new_smsg);
- $idx->index_raw(undef, $eml, $new_smsg, $req->{ibx});
+ my $oid = $new_smsg->{blob};
+ my $ibx = delete $req->{ibx} or die 'BUG: {ibx} unset';
+ $self->{oidx}->add_xref3($docid, $req->{xnum}, $oid, $ibx->eidx_key);
+ $idx->index_raw(undef, $eml, $new_smsg, $ibx);
}
sub do_finalize ($) {
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 32fa16f5..569efbb0 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -370,8 +370,6 @@ sub add_xapian ($$$$) {
if (defined(my $eidx_key = $smsg->{eidx_key})) {
$doc->add_boolean_term('O'.$eidx_key);
- $doc->add_boolean_term('P'.
- "$eidx_key:$smsg->{num}:$smsg->{blob}");
}
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
@@ -456,57 +454,41 @@ sub _get_doc ($$$) {
}
}
-sub add_xref3 {
- my ($self, $docid, $xnum, $oid, $eidx_key, $eml) = @_;
+sub add_eidx_info {
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
term_generator($self)->set_document($doc);
$doc->add_boolean_term('O'.$eidx_key);
- $doc->add_boolean_term('P'."$eidx_key:$xnum:$oid");
index_list_id($self, $doc, $eml);
$self->{xdb}->replace_document($docid, $doc);
}
-sub remove_xref3 {
+sub remove_eidx_info {
my ($self, $docid, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
- my $xref3 = PublicInbox::Smsg::xref3(undef, $doc);
- my %x3 = map { $_ => undef } @$xref3;
- for (grep(/\A\Q$eidx_key\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
- delete $x3{$_};
- $doc->remove_term('P' . $_);
- }
- if (scalar(keys(%x3)) == 0) {
- $self->{xdb}->delete_document($docid);
- if (my $del_fh = $self->{del_fh}) { # TODO
- print $del_fh $docid, "\n" or die "E: print $!";
- }
- } else {
- if (!grep(/\A\Q$eidx_key\E:/, keys %x3)) {
- $doc->remove_term('O'.$eidx_key);
- }
- for my $l ($eml->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = lc $1;
- $doc->remove_term('G' . $lid);
-
- # nb: we don't remove the XL probabilistic terms
- # since terms may overlap if cross-posted.
- #
- # IOW, a message which has both <foo.example.com>
- # and <bar.example.com> would have overlapping
- # "XLexample" and "XLcom" as terms and which we
- # wouldn't know if they're safe to remove if we just
- # unindex <foo.example.com> while preserving
- # <bar.example.com>.
- #
- # In any case, this entire sub is will likely never
- # be needed and users using the "l:" prefix are probably
- # rarer.
- }
- $self->{xdb}->replace_document($docid, $doc);
+ $doc->remove_term('O'.$eidx_key);
+ for my $l ($eml->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->remove_term('G' . $lid);
+
+ # nb: we don't remove the XL probabilistic terms
+ # since terms may overlap if cross-posted.
+ #
+ # IOW, a message which has both <foo.example.com>
+ # and <bar.example.com> would have overlapping
+ # "XLexample" and "XLcom" as terms and which we
+ # wouldn't know if they're safe to remove if we just
+ # unindex <foo.example.com> while preserving
+ # <bar.example.com>.
+ #
+ # In any case, this entire sub is will likely never
+ # be needed and users using the "l:" prefix are probably
+ # rarer.
}
+ $self->{xdb}->replace_document($docid, $doc);
}
sub get_val ($$) {
diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index ac01340c..644d8b58 100644
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -75,15 +75,15 @@ sub shard_worker_loop ($$$$$) {
} elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) {
$self->remove_by_oid($1, $2 + 0);
} elsif ($line =~ s/\A\+X //) {
- my ($len, $docid, $xnum, $oid, $eidx_key) =
- split(/ /, $line, 5);
- $self->add_xref3($docid, $xnum, $oid, $eidx_key,
- eml($r, $len));
+ my ($len, $docid, $oid, $eidx_key) =
+ split(/ /, $line, 4);
+ $self->add_eidx_info($docid, $oid, $eidx_key,
+ eml($r, $len));
} elsif ($line =~ s/\A-X //) {
- my ($len, $docid, $xnum, $oid, $eidx_key) =
- split(/ /, $line, 5);
- $self->remove_xref3($docid, $xnum, $oid,
- $eidx_key, eml($r, $len));
+ my ($len, $docid, $oid, $eidx_key) =
+ split(/ /, $line, 4);
+ $self->remove_eidx_info($docid, $oid, $eidx_key,
+ eml($r, $len));
} else {
chomp $line;
my $eidx_key;
@@ -135,20 +135,20 @@ sub index_raw {
}
}
-sub shard_add_xref3 {
- my ($self, $docid, $xnum, $oid, $xibx, $eml) = @_;
+sub shard_add_eidx_info {
+ my ($self, $docid, $oid, $xibx, $eml) = @_;
my $eidx_key = $xibx->eidx_key;
if (my $w = $self->{w}) {
my $hdr = $eml->header_obj->as_string;
my $len = length($hdr);
- print $w "+X $len $docid $xnum $oid $eidx_key\n", $hdr or
+ print $w "+X $len $docid $oid $eidx_key\n", $hdr or
die "failed to write shard: $!";
} else {
- $self->add_xref3($docid, $xnum, $oid, $eidx_key, $eml);
+ $self->add_eidx_info($docid, $oid, $eidx_key, $eml);
}
}
-sub shard_remove_xref3 {
+sub shard_remove_eidx_info {
my ($self, $docid, $oid, $xibx, $eml) = @_;
my $eidx_key = $xibx->eidx_key;
if (my $w = $self->{w}) {
@@ -157,7 +157,7 @@ sub shard_remove_xref3 {
print $w "-X $len $docid $oid $eidx_key\n", $hdr or
die "failed to write shard: $!";
} else {
- $self->remove_xref3($docid, $oid, $eidx_key, $eml);
+ $self->remove_eidx_info($docid, $oid, $eidx_key, $eml);
}
}
diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm
index c0fd85fd..14086538 100644
--- a/lib/PublicInbox/Smsg.pm
+++ b/lib/PublicInbox/Smsg.pm
@@ -137,17 +137,4 @@ sub subject_normalized ($) {
$subj;
}
-sub xref3 {
- my ($self, $doc) = @_;
- my $end = $doc->termlist_end;
- my $it = $doc->termlist_begin;
- $it->skip_to('P');
- my @ret;
- for (; $it != $end; $it++) {
- my $val = $it->get_termname;
- $val =~ s/\AP// and push @ret, $val;
- }
- \@ret;
-}
-
1;
diff --git a/t/search.t b/t/search.t
index e789b81e..da9acb07 100644
--- a/t/search.t
+++ b/t/search.t
@@ -341,14 +341,6 @@ $ibx->with_umask(sub {
my $uid = PublicInbox::SearchIdx::get_val($doc, $col);
is($uid, $smsg->{num}, 'UID column matches {num}');
is($uid, $m->get_docid, 'UID column matches docid');
-
- # check ->xref3 for external index:
- is_deeply($smsg->xref3($doc), [], 'xref3 empty by default');
- my $exp = "inbox.com.example:$uid:deadbeef";
- $doc->add_boolean_term('P'.$exp);
- is_deeply($smsg->xref3($doc), [ $exp ], 'xref3 can be set');
- $doc->remove_term('P'.$exp);
- is_deeply($smsg->xref3($doc), [], 'xref3 can be unset');
}
$mset = $ibx->search->mset('tc:list@example.com');
@@ -521,13 +513,8 @@ $ibx->with_umask(sub {
$rw_commit->();
my $doc_id = $rw->add_message(eml_load('t/data/message_embed.eml'));
ok($doc_id > 0, 'messages within messages');
-
- my $eml = PublicInbox::Eml->new(<<EOF);
-List-Id: <blahblah.example.com>
-
-EOF
- $rw->add_xref3($doc_id, 1, 'deadbeef', 'newsgroup1.example', $eml);
- $rw_commit->();
+ $rw->commit_txn_lazy;
+ $ibx->search->reopen;
my $n_test_eml = $query->('n:test.eml');
is(scalar(@$n_test_eml), 1, 'got a result');
my $n_embed2x_eml = $query->('n:embed2x.eml');
@@ -545,15 +532,6 @@ EOF
is($query->('s:"mail header experiments"')->[0]->{mid},
'20200418222508.GA13918@dcvr',
'Subject search reaches inside message/rfc822');
- is($query->('l:blahblah.example.com')->[0]->{num}, $doc_id,
- 'xref3 List-Id probabilistic works');
- is($query->('lid:blahblah.example.com')->[0]->{num}, $doc_id,
- 'xref3 List-Id boolean term works');
- $rw->remove_xref3($doc_id, 'deadbeef', 'newsgroup1.example', $eml);
- $rw->commit_txn_lazy;
- $ibx->search->reopen;
- my $res = $query->('lid:blahblah.example.com');
- is_deeply($res, [], '->remove_xref3 dropped boolean term');
});
done_testing();
^ permalink raw reply related [relevance 3%]
* [PATCH 00/52] detached external index: mostly
@ 2020-10-27 7:54 7% Eric Wong
2020-10-27 7:54 3% ` [PATCH 43/52] searchidx: remove xref3 support for Xapian Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
...and mostly wired up for WWW, but requires manual config
editing atm. Needs docs and tests, and IMAP support.
This will also form the basis of a mairix workalike client.
Not sure about the usability aspects, but I think this can
replace the need for per-inbox Xapian DBs and save a truckload
of disk space (and more importantly: cache space). Per-inbox
over.sqlite3 remains required for compatibility with NNTP/IMAP
and existing WWW code.
I don't know if the command-line tool is going to be called
public-inbox-eindex or public-inbox-extindex, but probably the
latter...
"xindex" could be confusing, and "eindex" rhymes with "reindex"
which could also be confusing. But I'm even more easily
confused than usual these days :x
Performance isn't great, it took 30+ hours to index my mirror of
lore on a SATA SSD, but the entire index is <200GB due to
deduplication between cross posts. -compact isn't working with
these indices, yet, but will sometime...
More changes on the way, still trying fix my brain and get
through this year...
Eric Wong (52):
doc/standards: add RFCs for URL schemes
search: hoist out _xdb_sharded for v2 inboxes
extsearch: start mocking out
searchidx: expose INDEXLEVELS as `our'
v2writable: add git method
v2writable: make OO calls to last_commit-related methods
search: xdb_sharded: make this a public method for ExtSearch
searchidx: introduce "xref3" concept
v2writable: prepare initialization for external indices
v2writable: hoist out write_alternates
searchidxshard: allow msgref to be undef
v2writable: idx_shard: simplify callers
v2writable: count_shards: allow working without {ibx}
overidx: introduce changes for external index
v2: some changes for ExtSearchIdx compatibility
inboxwritable: eidx_key for external index
v2writable: rename remaining "remote" terminology
v2writable: checkpoint: account for lack of {mm}
extsearchidx: initial implementation
searchidx: index eidx_key as a boolean term
searchidx: xref3 delete support
searchidxshard: special init for eidx
searchidx: put {ibx} into $sync state
searchidx: log2stack: simplify callers
v2writable: more generic sync setup code
v2writable: allow OO method references
v2writable: rename {v2w} field to {self}
v2writable: make *last_commits and sync_prepare OO methods
v2writable: move size check init to sync_prepare
extsearchidx: more compatibility with V2Writable callers
v2writable: reduce scope of epoch-aware code
extsearchidx: remove {unindex_range} field
v2writable: pass oid to uindex_oid
extsearchidx: sync unit updates
searchidx: export prepare_stack
extsearchidx: sync updates
searchidx: reduce inbox-dependency, wrap ->with_umask
searchidx: favor $sync->{ibx} (over $self->{ibx})
Makefile.PL: do not build manpage if POD is missing
script: add preliminary eindex implementation
index: eindex wiring
over: store xref3 data in over.sqlite3
searchidx: remove xref3 support for Xapian
t/extsearch.t: verify results and xref3 ordering
t/v2writable: remove pointless ->barrier call
extsearch: wire up smsg_eml
extsearchidx: handle edits
extsearch: wire up remaining Inbox-like methods for WWW
searchidx: ignore exceptions from ->remove_term
extsearchidx: set current_info in warning callbacks
extsearchidx: support --batch-size checkpoints
searchidxshard: make warnings with eidx_key less confusing
Documentation/standards.perl | 3 +
MANIFEST | 4 +
Makefile.PL | 16 +-
lib/PublicInbox/Config.pm | 12 +
lib/PublicInbox/ExtSearch.pm | 69 +++++
lib/PublicInbox/ExtSearchIdx.pm | 404 ++++++++++++++++++++++++++++++
lib/PublicInbox/Inbox.pm | 53 ++--
lib/PublicInbox/InboxWritable.pm | 23 ++
lib/PublicInbox/Over.pm | 19 ++
lib/PublicInbox/OverIdx.pm | 122 ++++++++-
lib/PublicInbox/Search.pm | 62 ++---
lib/PublicInbox/SearchIdx.pm | 135 +++++++---
lib/PublicInbox/SearchIdxShard.pm | 77 +++++-
lib/PublicInbox/V2Writable.pm | 310 ++++++++++++-----------
lib/PublicInbox/WWW.pm | 3 +-
lib/PublicInbox/Xapcmd.pm | 2 +-
script/public-inbox-eindex | 43 ++++
script/public-inbox-index | 3 +-
t/extsearch.t | 75 ++++++
t/over.t | 24 ++
t/search.t | 2 -
t/v2writable.t | 3 +-
22 files changed, 1204 insertions(+), 260 deletions(-)
create mode 100644 lib/PublicInbox/ExtSearch.pm
create mode 100644 lib/PublicInbox/ExtSearchIdx.pm
create mode 100644 script/public-inbox-eindex
create mode 100644 t/extsearch.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27 7:54 3% ` [PATCH 43/52] searchidx: remove xref3 support for Xapian Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).