* [PATCH 08/52] searchidx: introduce "xref3" concept
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
@ 2020-10-27 7:54 4% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
This will be used to track cross-posted messages in the
external/detached index.
---
lib/PublicInbox/SearchIdx.pm | 78 ++++++++++++++++++++++++++-----
lib/PublicInbox/SearchIdxShard.pm | 53 ++++++++++++++++++---
lib/PublicInbox/Smsg.pm | 13 ++++++
t/search.t | 28 +++++++++--
4 files changed, 150 insertions(+), 22 deletions(-)
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index af707ced..283bdd6c 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -325,6 +325,16 @@ sub index_xapian { # msg_iter callback
}
}
+sub index_list_id ($$$) {
+ my ($self, $doc, $hdr) = @_;
+ for my $l ($hdr->header_raw('List-Id')) {
+ $l =~ /<([^>]+)>/ or next;
+ my $lid = lc $1;
+ $doc->add_boolean_term('G' . $lid);
+ index_text($self, $lid, 1, 'XL'); # probabilistic
+ }
+}
+
sub index_ids ($$$$) {
my ($self, $doc, $hdr, $mids) = @_;
for my $mid (@$mids) {
@@ -338,12 +348,7 @@ sub index_ids ($$$$) {
}
}
$doc->add_boolean_term('Q' . $_) for @$mids;
- for my $l ($hdr->header_raw('List-Id')) {
- $l =~ /<([^>]+)>/ or next;
- my $lid = lc $1;
- $doc->add_boolean_term('G' . $lid);
- index_text($self, $lid, 1, 'XL'); # probabilistic
- }
+ index_list_id($self, $doc, $hdr);
}
sub add_xapian ($$$$) {
@@ -363,6 +368,10 @@ sub add_xapian ($$$$) {
$tg->set_document($doc);
index_headers($self, $smsg);
+ if (my $ng_or_dir = $self->{ng_or_dir}) { # external index
+ $doc->add_boolean_term('P'.
+ "$ng_or_dir:$smsg->{num}:$smsg->{blob}");
+ }
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
@@ -436,6 +445,56 @@ sub add_message {
$smsg->{num};
}
+sub _get_doc ($$$) {
+ my ($self, $docid, $oid) = @_;
+ my $doc = eval { $self->{xdb}->get_document($docid) };
+ $doc // do {
+ warn "E: $@\n" if $@;
+ warn "E: #$docid $oid missing in Xapian\n";
+ undef;
+ }
+}
+
+sub add_xref3 {
+ my ($self, $docid, $xnum, $oid, $ng_or_dir, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ term_generator($self)->set_document($doc);
+ $doc->add_boolean_term('P'."$ng_or_dir:$xnum:$oid");
+ index_list_id($self, $doc, $eml);
+ $self->{xdb}->replace_document($docid, $doc);
+}
+
+sub remove_xref3 {
+ my ($self, $docid, $oid, $ng_or_dir, $eml) = @_;
+ begin_txn_lazy($self);
+ my $doc = _get_doc($self, $docid, $oid) or return;
+ my $xref3 = PublicInbox::Smsg::xref3(undef, $doc);
+ for (grep(/\A\Q$ng_or_dir\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
+ $doc->remove_term('P' . $_);
+ }
+ 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 ($$) {
my ($doc, $col) = @_;
sortable_unserialise($doc->get_value($col));
@@ -457,12 +516,7 @@ sub xdb_remove {
my ($self, $oid, @removed) = @_;
my $xdb = $self->{xdb} or return;
for my $num (@removed) {
- my $doc = eval { $xdb->get_document($num) };
- unless ($doc) {
- warn "E: $@\n" if $@;
- warn "E: #$num $oid missing in Xapian\n";
- next;
- }
+ my $doc = _get_doc($self, $num, $oid) or next;
my $smsg = smsg_from_doc($doc);
my $blob = $smsg->{blob}; # may be undef if --skip-docdata
if (!defined($blob) || $blob eq $oid) {
diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index f23d23d0..8e24aa1b 100644
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -7,6 +7,7 @@ package PublicInbox::SearchIdxShard;
use strict;
use v5.10.1;
use parent qw(PublicInbox::SearchIdx);
+use bytes qw(length);
use IO::Handle (); # autoflush
use PublicInbox::Eml;
@@ -47,6 +48,13 @@ sub spawn_worker {
close $r or die "failed to close: $!";
}
+sub eml ($$) {
+ my ($r, $len) = @_;
+ my $n = read($r, my $bref, $len) or die "read: $!\n";
+ $n == $len or die "short read: $n != $len\n";
+ PublicInbox::Eml->new(\$bref);
+}
+
# this reads all the writes to $self->{w} from the parent process
sub shard_worker_loop ($$$$$) {
my ($self, $v2w, $r, $shard, $bnote) = @_;
@@ -65,25 +73,32 @@ sub shard_worker_loop ($$$$$) {
die "write failed for barrier $!\n";
} elsif ($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, $ng_or_dir) =
+ split(/ /, $line, 5);
+ $self->add_xref3($docid, $xnum, $oid, $ng_or_dir,
+ eml($r, $len));
+ } elsif ($line =~ s/\A-X //) {
+ my ($len, $docid, $xnum, $oid, $ng_or_dir) =
+ split(/ /, $line, 5);
+ $self->remove_xref3($docid, $xnum, $oid,
+ $ng_or_dir, eml($r, $len));
} else {
chomp $line;
# n.b. $mid may contain spaces(!)
- my ($to_read, $bytes, $num, $blob, $ds, $ts, $tid, $mid)
+ my ($len, $bytes, $num, $oid, $ds, $ts, $tid, $mid)
= split(/ /, $line, 8);
$self->begin_txn_lazy;
- my $n = read($r, my $msg, $to_read) or die "read: $!\n";
- $n == $to_read or die "short read: $n != $to_read\n";
- my $mime = PublicInbox::Eml->new(\$msg);
my $smsg = bless {
bytes => $bytes,
num => $num + 0,
- blob => $blob,
+ blob => $oid,
mid => $mid,
tid => $tid,
ds => $ds,
ts => $ts,
}, 'PublicInbox::Smsg';
- $self->add_message($mime, $smsg);
+ $self->add_message(eml($r, $len), $smsg);
}
}
$self->worker_done;
@@ -107,6 +122,32 @@ sub index_raw {
}
}
+sub shard_add_xref3 {
+ my ($self, $docid, $xnum, $oid, $xibx, $eml) = @_;
+ my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir};
+ if (my $w = $self->{w}) {
+ my $hdr = $eml->header_obj->as_string;
+ my $len = length($hdr);
+ print $w "+X $len $docid $xnum $oid $ng_or_dir\n", $hdr or
+ die "failed to write shard: $!";
+ } else {
+ $self->add_xref3($docid, $xnum, $oid, $ng_or_dir, $eml);
+ }
+}
+
+sub shard_remove_xref3 {
+ my ($self, $docid, $oid, $xibx, $eml) = @_;
+ my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir};
+ if (my $w = $self->{w}) {
+ my $hdr = $eml->header_obj->as_string;
+ my $len = length($hdr);
+ print $w "-X $len $docid $oid $ng_or_dir\n", $hdr or
+ die "failed to write shard: $!";
+ } else {
+ $self->remove_xref3($docid, $oid, $ng_or_dir, $eml);
+ }
+}
+
sub atfork_child {
close $_[0]->{w} or die "failed to close write pipe: $!\n";
}
diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm
index 14086538..c0fd85fd 100644
--- a/lib/PublicInbox/Smsg.pm
+++ b/lib/PublicInbox/Smsg.pm
@@ -137,4 +137,17 @@ sub subject_normalized ($) {
$subj;
}
+sub xref3 {
+ my ($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 a66aec36..e789b81e 100644
--- a/t/search.t
+++ b/t/search.t
@@ -341,6 +341,14 @@ $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');
@@ -513,8 +521,13 @@ $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');
- $rw->commit_txn_lazy;
- $ibx->search->reopen;
+
+ my $eml = PublicInbox::Eml->new(<<EOF);
+List-Id: <blahblah.example.com>
+
+EOF
+ $rw->add_xref3($doc_id, 1, 'deadbeef', 'newsgroup1.example', $eml);
+ $rw_commit->();
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');
@@ -532,8 +545,15 @@ $ibx->with_umask(sub {
is($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();
-
-1;
^ permalink raw reply related [relevance 4%]
* [PATCH 00/52] detached external index: mostly
@ 2020-10-27 7:54 7% Eric Wong
2020-10-27 7:54 4% ` [PATCH 08/52] searchidx: introduce "xref3" concept 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 4% ` [PATCH 08/52] searchidx: introduce "xref3" concept 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).