user/dev discussion of public-inbox itself
 help / color / mirror / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 23/23] search: add mset_to_artnums method
Date: Thu, 20 Aug 2020 20:24:57 +0000
Message-ID: <20200820202457.21042-24-e@yhbt.net> (raw)
In-Reply-To: <20200820202457.21042-1-e@yhbt.net>

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);
 }

      parent reply	other threads:[~2020-08-20 20:25 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-20 20:24 [PATCH 00/23] indexing: --skip-docdata + speedups Eric Wong
2020-08-20 20:24 ` [PATCH 01/23] doc: note -compact and -xcpdb are rarely used Eric Wong
2020-08-20 20:24 ` [PATCH 02/23] admin: progress shows the inbox being indexed Eric Wong
2020-08-20 20:24 ` [PATCH 03/23] compact: support --help/-? and perform lazy loading Eric Wong
2020-08-20 20:24 ` [PATCH 04/23] init: support --help and -? Eric Wong
2020-08-20 20:24 ` [PATCH 05/23] init: support --newsgroup option Eric Wong
2020-08-20 21:10   ` Eric Wong
2020-08-20 20:24 ` [PATCH 06/23] init: drop -N alias for --skip-artnum Eric Wong
2020-08-20 20:24 ` [PATCH 07/23] search: v2: ensure shards are numerically sorted Eric Wong
2020-08-20 20:24 ` [PATCH 08/23] xapcmd: simplify {reindex} parameter passing Eric Wong
2020-08-20 20:24 ` [PATCH 09/23] www: reduce long-lived PublicInbox::Search references Eric Wong
2020-08-20 20:24 ` [PATCH 10/23] search: improve comments around constants Eric Wong
2020-08-20 20:24 ` [PATCH 11/23] search: export mdocid subroutine Eric Wong
2020-08-20 20:24 ` [PATCH 12/23] searchquery: split off from searchview Eric Wong
2020-08-20 20:24 ` [PATCH 13/23] search: make qparse_new an internal function Eric Wong
2020-08-20 20:24 ` [PATCH 14/23] smsg: reduce utf8::decode call sites Eric Wong
2020-08-20 20:24 ` [PATCH 15/23] searchview: use over.sqlite3 instead of Xapian docdata Eric Wong
2020-08-20 20:24 ` [PATCH 16/23] searchview: speed up search summary by ~10% Eric Wong
2020-08-20 20:24 ` [PATCH 17/23] searchview: convert nested and Atom display to over.sqlite3 Eric Wong
2020-08-20 20:24 ` [PATCH 18/23] extmsg: avoid using Xapian docdata Eric Wong
2020-08-20 20:24 ` [PATCH 19/23] mbox: avoid Xapian docdata in search results Eric Wong
2020-08-20 20:24 ` [PATCH 20/23] smsg: remove from_mitem Eric Wong
2020-08-20 20:24 ` [PATCH 21/23] t/nntpd-v2: set PI_TEST_VERSION=2 properly Eric Wong
2020-08-20 20:24 ` [PATCH 22/23] init+index: support --skip-docdata for Xapian Eric Wong
2020-08-20 20:24 ` Eric Wong [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200820202457.21042-24-e@yhbt.net \
    --to=e@yhbt.net \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

user/dev discussion of public-inbox itself

This inbox may be cloned and mirrored by anyone:

	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V1 meta meta/ https://public-inbox.org/meta \
		meta@public-inbox.org
	public-inbox-index meta

Example config snippet for mirrors.
Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.io/gmane.mail.public-inbox.general
 note: .onion URLs require Tor: https://www.torproject.org/

code repositories for the project(s) associated with this inbox:

	https://80x24.org/public-inbox.git

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git