* [PATCH 23/23] search: add mset_to_artnums method
2020-08-20 20:24 7% [PATCH 00/23] indexing: --skip-docdata + speedups Eric Wong
@ 2020-08-20 20:24 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-08-20 20:24 UTC (permalink / raw)
To: meta
We can avoid importing mdocid() in several places by using
this method, simplifying callers.
---
lib/PublicInbox/ExtMsg.pm | 4 +---
lib/PublicInbox/IMAP.pm | 4 +---
lib/PublicInbox/Mbox.pm | 7 ++-----
lib/PublicInbox/Search.pm | 6 ++++++
lib/PublicInbox/SearchView.pm | 6 ++----
5 files changed, 12 insertions(+), 15 deletions(-)
diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm
index 5c23dc31..65892161 100644
--- a/lib/PublicInbox/ExtMsg.pm
+++ b/lib/PublicInbox/ExtMsg.pm
@@ -11,7 +11,6 @@ use warnings;
use PublicInbox::Hval qw(ascii_html prurl mid_href);
use PublicInbox::WwwStream qw(html_oneshot);
use PublicInbox::Smsg;
-use PublicInbox::Search qw(mdocid);
our $MIN_PARTIAL_LEN = 16;
# TODO: user-configurable
@@ -61,7 +60,6 @@ sub search_partial ($$) {
}
}
- my $n = $srch->{nshard} // 1;
foreach my $m (@try) {
# If Xapian can't handle the wildcard since it
# has too many results. $@ can be
@@ -70,7 +68,7 @@ sub search_partial ($$) {
my $mset = eval { $srch->query($m, $opt) } or next;
my @mids = map {
$_->{mid}
- } @{$ibx->over->get_all(map { mdocid($n, $_) } $mset->items)};
+ } @{$ibx->over->get_all(@{$srch->mset_to_artnums($mset)})};
return \@mids if scalar(@mids);
}
}
diff --git a/lib/PublicInbox/IMAP.pm b/lib/PublicInbox/IMAP.pm
index 562c59d4..abdb8fec 100644
--- a/lib/PublicInbox/IMAP.pm
+++ b/lib/PublicInbox/IMAP.pm
@@ -40,7 +40,6 @@ use PublicInbox::Syscall qw(EPOLLIN EPOLLONESHOT);
use PublicInbox::GitAsyncCat;
use Text::ParseWords qw(parse_line);
use Errno qw(EAGAIN);
-use PublicInbox::Search qw(mdocid);
use PublicInbox::IMAPsearchqp;
my $Address;
@@ -1188,9 +1187,8 @@ sub refill_xap ($$$$) {
my ($beg, $end) = @$range_info;
my $srch = $self->{ibx}->search;
my $opt = { mset => 2, limit => 1000 };
- my $nshard = $srch->{nshard} // 1;
my $mset = $srch->query("$q uid:$beg..$end", $opt);
- @$uids = map { mdocid($nshard, $_) } $mset->items;
+ @$uids = @{$srch->mset_to_artnums($mset)};
if (@$uids) {
$range_info->[0] = $uids->[-1] + 1; # update $beg
return; # possibly more
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 0fa9a38d..873ff7be 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -10,7 +10,6 @@ use PublicInbox::MID qw/mid_escape/;
use PublicInbox::Hval qw/to_filename/;
use PublicInbox::Smsg;
use PublicInbox::Eml;
-use PublicInbox::Search qw(mdocid);
# called by PSGI server as body response
# this gets called twice for every message, once to return the header,
@@ -217,8 +216,7 @@ sub results_cb {
my $mset = $srch->query($ctx->{query}, $ctx->{qopts});
my $size = $mset->size or return;
$ctx->{qopts}->{offset} += $size;
- my $nshard = $srch->{nshard} // 1;
- $ctx->{ids} = [ map { mdocid($nshard, $_) } $mset->items ];
+ $ctx->{ids} = $srch->mset_to_artnums($mset);
}
}
@@ -234,8 +232,7 @@ sub mbox_all {
return [404, [qw(Content-Type text/plain)],
["No results found\n"]];
$ctx->{query} = $query;
- my $nshard = $srch->{nshard} // 1;
- $ctx->{ids} = [ map { mdocid($nshard, $_) } $mset->items ];
+ $ctx->{ids} = $srch->mset_to_artnums($mset);
require PublicInbox::MboxGz;
PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, 'results-'.$query);
}
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 1c648299..c18e19d4 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -219,6 +219,12 @@ sub mdocid {
int(($docid - 1) / $nshard) + 1;
}
+sub mset_to_artnums {
+ my ($self, $mset) = @_;
+ my $nshard = $self->{nshard} // 1;
+ [ map { mdocid($nshard, $_) } $mset->items ];
+}
+
sub xdb ($) {
my ($self) = @_;
$self->{xdb} ||= do {
diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm
index ef1b9767..aa8fa037 100644
--- a/lib/PublicInbox/SearchView.pm
+++ b/lib/PublicInbox/SearchView.pm
@@ -91,9 +91,8 @@ sub mset_summary {
my $pfx = ' ' x $pad;
my $res = \($ctx->{-html_tip});
my $ibx = $ctx->{-inbox};
- my $nshard = $ibx->search->{nshard} // 1;
my $obfs_ibx = $ibx->{obfuscate} ? $ibx : undef;
- my @nums = map { mdocid($nshard, $_) } $mset->items;
+ my @nums = @{$ibx->search->mset_to_artnums($mset)};
my %num2msg = map { $_->{num} => $_ } @{$ibx->over->get_all(@nums)};
foreach my $m ($mset->items) {
@@ -316,8 +315,7 @@ sub ctx_prepare {
sub adump {
my ($cb, $mset, $q, $ctx) = @_;
- my $nshard = $ctx->{-inbox}->search->{nshard} // 1;
- $ctx->{ids} = [ map { mdocid($nshard, $_) } $mset->items ];
+ $ctx->{ids} = $ctx->{-inbox}->search->mset_to_artnums($mset);
$ctx->{search_query} = $q; # used by WwwAtomStream::atom_header
PublicInbox::WwwAtomStream->response($ctx, 200, \&adump_i);
}
^ permalink raw reply related [relevance 6%]
* [PATCH 00/23] indexing: --skip-docdata + speedups
@ 2020-08-20 20:24 7% Eric Wong
2020-08-20 20:24 6% ` [PATCH 23/23] search: add mset_to_artnums method Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-08-20 20:24 UTC (permalink / raw)
To: meta
Some miscellaneous help and cleanup things, too.
Document data is no longer read from Xapian by read-only
daemons; that data is redundant given over.sqlite3 always
exists. This should should improve page cache hit rates for
over.sqlite3 by a small bit. Being able to mass load a bunch of
rows from SQLite speeds up the default search summary view by
~10%, too.
--skip-docdata option to -init and -index can avoid writing
Xapian document data, saving ~1.5% in Xapian space overhead
(and associated I/O and page cache overheads). It breaks
rollbacks to old versions, though, so it won't be the default.
Eric Wong (23):
doc: note -compact and -xcpdb are rarely used
admin: progress shows the inbox being indexed
compact: support --help/-? and perform lazy loading
init: support --help and -?
init: support --newsgroup option
init: drop -N alias for --skip-artnum
search: v2: ensure shards are numerically sorted
xapcmd: simplify {reindex} parameter passing
www: reduce long-lived PublicInbox::Search references
search: improve comments around constants
search: export mdocid subroutine
searchquery: split off from searchview
search: make qparse_new an internal function
smsg: reduce utf8::decode call sites
searchview: use over.sqlite3 instead of Xapian docdata
searchview: speed up search summary by ~10%
searchview: convert nested and Atom display to over.sqlite3
extmsg: avoid using Xapian docdata
mbox: avoid Xapian docdata in search results
smsg: remove from_mitem
t/nntpd-v2: set PI_TEST_VERSION=2 properly
init+index: support --skip-docdata for Xapian
search: add mset_to_artnums method
Documentation/public-inbox-compact.pod | 5 +
Documentation/public-inbox-config.pod | 2 +-
Documentation/public-inbox-index.pod | 8 ++
Documentation/public-inbox-init.pod | 37 +++++++-
Documentation/public-inbox-xcpdb.pod | 3 +
MANIFEST | 1 +
lib/PublicInbox/Admin.pm | 15 ++-
lib/PublicInbox/ExtMsg.pm | 19 ++--
lib/PublicInbox/IMAP.pm | 5 +-
lib/PublicInbox/Inbox.pm | 11 ++-
lib/PublicInbox/Mbox.pm | 24 +++--
lib/PublicInbox/Over.pm | 28 +++---
lib/PublicInbox/Search.pm | 125 ++++++++++++++-----------
lib/PublicInbox/SearchIdx.pm | 35 +++++--
lib/PublicInbox/SearchIdxShard.pm | 2 +-
lib/PublicInbox/SearchQuery.pm | 53 +++++++++++
lib/PublicInbox/SearchView.pm | 90 ++++--------------
lib/PublicInbox/Smsg.pm | 10 +-
lib/PublicInbox/Xapcmd.pm | 20 ++--
script/public-inbox-compact | 39 ++++++--
script/public-inbox-convert | 3 +-
script/public-inbox-index | 7 +-
script/public-inbox-init | 101 +++++++++++++-------
t/imapd.t | 6 +-
t/inbox_idle.t | 2 +-
t/index-git-times.t | 11 ++-
t/init.t | 17 +++-
t/nntpd-v2.t | 2 +-
t/nntpd.t | 9 +-
t/search.t | 34 ++++---
30 files changed, 437 insertions(+), 287 deletions(-)
create mode 100644 lib/PublicInbox/SearchQuery.pm
^ 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 --
2020-08-20 20:24 7% [PATCH 00/23] indexing: --skip-docdata + speedups Eric Wong
2020-08-20 20:24 6% ` [PATCH 23/23] search: add mset_to_artnums method 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).