user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@yhbt.net>
To: meta@public-inbox.org
Subject: [PATCH 4/5] search: support downloading mboxes results with full thread
Date: Sat, 22 Aug 2020 06:06:26 +0000	[thread overview]
Message-ID: <20200822060627.15595-5-e@yhbt.net> (raw)
In-Reply-To: <20200822060627.15595-1-e@yhbt.net>

Finally, the addition of THREADID for collapsing results
in Xapian lets us emulate the "mairix --threads" feature.
That is, instead of returning only the matching messages,
the entire thread is included in the downloaded mbox.gz

This requires a "public-inbox-index --reindex" to be usable.
---
 lib/PublicInbox/Mbox.pm        | 54 +++++++++++++++++++++++++++-------
 lib/PublicInbox/Over.pm        | 29 ++++++++++++++++++
 lib/PublicInbox/Search.pm      |  4 +++
 lib/PublicInbox/SearchQuery.pm |  8 +++--
 lib/PublicInbox/SearchView.pm  | 21 ++++++++-----
 5 files changed, 95 insertions(+), 21 deletions(-)

diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 873ff7be..c9b11c21 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -167,13 +167,13 @@ sub thread_mbox {
 sub emit_range {
 	my ($ctx, $range) = @_;
 
-	my $query;
+	my $q;
 	if ($range eq 'all') { # TODO: YYYY[-MM]
-		$query = '';
+		$q = '';
 	} else {
 		return [404, [qw(Content-Type text/plain)], []];
 	}
-	mbox_all($ctx, $query);
+	mbox_all($ctx, { q => $q });
 }
 
 sub all_ids_cb {
@@ -220,21 +220,55 @@ sub results_cb {
 	}
 }
 
-sub mbox_all {
-	my ($ctx, $query) = @_;
+sub results_thread_cb {
+	my ($ctx) = @_;
 
-	return mbox_all_ids($ctx) if $query eq '';
-	my $qopts = $ctx->{qopts} = { mset => 2 }; # order by docid
+	my $over = $ctx->{-inbox}->over or return;
+	while (1) {
+		while (defined(my $num = shift(@{$ctx->{xids}}))) {
+			my $smsg = $over->get_art($num) or next;
+			return $smsg;
+		}
+
+		# refills ctx->{xids}
+		next if $over->expand_thread($ctx);
+
+		# refill result set
+		my $srch = $ctx->{-inbox}->search(undef, $ctx) or return;
+		my $mset = $srch->query($ctx->{query}, $ctx->{qopts});
+		my $size = $mset->size or return;
+		$ctx->{qopts}->{offset} += $size;
+		$ctx->{ids} = $srch->mset_to_artnums($mset);
+	}
+
+}
+
+sub mbox_all {
+	my ($ctx, $q) = @_;
+	my $q_string = $q->{'q'};
+	return mbox_all_ids($ctx) if $q_string !~ /\S/;
 	my $srch = $ctx->{-inbox}->search or
 		return PublicInbox::WWW::need($ctx, 'Search');
-	my $mset = $srch->query($query, $qopts);
+	my $over = $ctx->{-inbox}->over or
+		return PublicInbox::WWW::need($ctx, 'Overview');
+
+	my $qopts = $ctx->{qopts} = { mset => 2 }; # order by docid
+	$qopts->{thread} = 1 if $q->{t};
+	my $mset = $srch->query($q_string, $qopts);
 	$qopts->{offset} = $mset->size or
 			return [404, [qw(Content-Type text/plain)],
 				["No results found\n"]];
-	$ctx->{query} = $query;
+	$ctx->{query} = $q_string;
 	$ctx->{ids} = $srch->mset_to_artnums($mset);
 	require PublicInbox::MboxGz;
-	PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, 'results-'.$query);
+	my $fn;
+	if ($q->{t}) {
+		$fn = 'results-thread-'.$q_string;
+		PublicInbox::MboxGz::mbox_gz($ctx, \&results_thread_cb, $fn);
+	} else {
+		$fn = 'results-'.$q_string;
+		PublicInbox::MboxGz::mbox_gz($ctx, \&results_cb, $fn);
+	}
 }
 
 1;
diff --git a/lib/PublicInbox/Over.pm b/lib/PublicInbox/Over.pm
index 34d0b05d..fba58d17 100644
--- a/lib/PublicInbox/Over.pm
+++ b/lib/PublicInbox/Over.pm
@@ -179,6 +179,35 @@ ORDER BY $sort_col DESC
 	($nr, $msgs);
 }
 
+# strict `tid' matches, only, for thread-expanded mbox.gz search results
+# and future CLI interface
+# returns true if we have IDs, undef if not
+sub expand_thread {
+	my ($self, $ctx) = @_;
+	my $dbh = $self->connect;
+	do {
+		defined(my $num = $ctx->{ids}->[0]) or return;
+		my ($tid) = $dbh->selectrow_array(<<'', undef, $num);
+SELECT tid FROM over WHERE num = ?
+
+		if (defined($tid)) {
+			my $sql = <<'';
+SELECT num FROM over WHERE tid = ? AND num > ?
+ORDER BY num ASC LIMIT 1000
+
+			my $xids = $dbh->selectcol_arrayref($sql, undef, $tid,
+							$ctx->{prev} // 0);
+			if (scalar(@$xids)) {
+				$ctx->{prev} = $xids->[-1];
+				$ctx->{xids} = $xids;
+				return 1; # success
+			}
+		}
+		$ctx->{prev} = 0;
+		shift @{$ctx->{ids}};
+	} while (1);
+}
+
 sub recent {
 	my ($self, $opts, $after, $before) = @_;
 	my ($s, @v);
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 4cfb7b38..bc820b64 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -326,6 +326,10 @@ sub _enquire_once { # retry_reopen callback
 	} else {
 		$enquire->set_sort_by_value_then_relevance(TS, $desc);
 	}
+
+	# `mairix -t / --threads' or JMAP collapseThreads
+	$enquire->set_collapse_key(THREADID) if $opts->{thread};
+
 	my $offset = $opts->{offset} || 0;
 	my $limit = $opts->{limit} || 50;
 	my $mset = $enquire->get_mset($offset, $limit);
diff --git a/lib/PublicInbox/SearchQuery.pm b/lib/PublicInbox/SearchQuery.pm
index ce1eae12..6724ae39 100644
--- a/lib/PublicInbox/SearchQuery.pm
+++ b/lib/PublicInbox/SearchQuery.pm
@@ -12,7 +12,8 @@ our $LIM = 200;
 sub new {
 	my ($class, $qp) = @_;
 
-	my $r = $qp->{r};
+	my $r = $qp->{r}; # relevance
+	my $t = $qp->{t}; # collapse threads
 	my ($l) = (($qp->{l} || '') =~ /([0-9]+)/);
 	$l = $LIM if !$l || $l > $LIM;
 	bless {
@@ -21,6 +22,7 @@ sub new {
 		o => (($qp->{o} || '0') =~ /(-?[0-9]+)/),
 		l => $l,
 		r => (defined $r && $r ne '0'),
+		t => (defined $t && $t ne '0'),
 	}, $class;
 }
 
@@ -41,8 +43,8 @@ sub qs_html {
 	if (my $l = $self->{l}) {
 		$qs .= "&amp;l=$l" unless $l == $LIM;
 	}
-	if (my $r = $self->{r}) {
-		$qs .= "&amp;r";
+	for my $bool (qw(r t)) {
+		$qs .= "&amp;$bool" if $self->{$bool};
 	}
 	if (my $x = $self->{x}) {
 		$qs .= "&amp;x=$x" if ($x eq 't' || $x eq 'A' || $x eq 'm');
diff --git a/lib/PublicInbox/SearchView.pm b/lib/PublicInbox/SearchView.pm
index 75e2d39d..dd69564a 100644
--- a/lib/PublicInbox/SearchView.pm
+++ b/lib/PublicInbox/SearchView.pm
@@ -19,10 +19,12 @@ my %rmap_inc;
 sub mbox_results {
 	my ($ctx) = @_;
 	my $q = PublicInbox::SearchQuery->new($ctx->{qp});
-	my $x = $q->{x};
+	if ($ctx->{env}->{'psgi.input'}->read(my $buf, 3)) {
+		$q->{t} = 1 if $buf =~ /\Ax=[^0]/;
+	}
 	require PublicInbox::Mbox;
-	return PublicInbox::Mbox::mbox_all($ctx, $q->{'q'}) if $x eq 'm';
-	sres_top_html($ctx);
+	$q->{x} eq 'm' ? PublicInbox::Mbox::mbox_all($ctx, $q) :
+			sres_top_html($ctx);
 }
 
 sub sres_top_html {
@@ -46,6 +48,7 @@ sub sres_top_html {
 		offset => $o,
 		mset => 1,
 		relevance => $q->{r},
+		thread => $q->{t},
 		asc => $asc,
 	};
 	my ($mset, $total, $err, $html);
@@ -151,7 +154,7 @@ sub err_txt {
 
 sub search_nav_top {
 	my ($mset, $q, $ctx) = @_;
-	my $m = $q->qs_html(x => 'm', r => undef);
+	my $m = $q->qs_html(x => 'm', r => undef, t => undef);
 	my $rv = qq{<form\naction="?$m"\nmethod="post"><pre>};
 	my $initial_q = $ctx->{-uxs_retried};
 	if (defined $initial_q) {
@@ -186,10 +189,12 @@ sub search_nav_top {
 	}
 	my $A = $q->qs_html(x => 'A', r => undef);
 	$rv .= qq{|<a\nhref="?$A">Atom feed</a>]} .
-		qq{\n\t\t\t\t\t\tdownload: } .
-		# lynx seems to require a name=, here, so just use 'z'
-		qq{<input\ntype=submit\nname=z\nvalue="mbox.gz"/>} .
-		q{</pre></form><pre>};
+		qq{\n\t\t\tdownload mbox.gz: } .
+		# we set name=z w/o using it since it seems required for
+		# lynx (but works fine for w3m).
+		qq{<input\ntype=submit\nname=z\nvalue="results only"/>|} .
+		qq{<input\ntype=submit\nname=x\nvalue="full threads"/>} .
+		qq{</pre></form><pre>};
 }
 
 sub search_nav_bot {

  parent reply	other threads:[~2020-08-22  6:06 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-22  6:06 [PATCH 0/5] "mairix -t" workalike for mbox.gz downloads Eric Wong
2020-08-22  6:06 ` [PATCH 1/5] searchidxshard: clear $msgref buffer properly Eric Wong
2020-08-22  6:06 ` [PATCH 2/5] searchidx: put all shard-related stuff in SearchIdxShard.pm Eric Wong
2020-08-22  6:06 ` [PATCH 3/5] searchidx: index THREADID in Xapian Eric Wong
2020-08-22  6:06 ` Eric Wong [this message]
2020-08-22  6:06 ` [PATCH 5/5] mbox: disable "&t" on existing Xapian until full reindex Eric Wong
2020-08-22  6:39   ` Eric Wong
2020-08-22  6:42 ` [PATCH 0/5] "mairix -t" workalike for mbox.gz downloads Eric Wong
2020-08-22 20:12   ` Kyle Meyer
2020-08-22 20:30     ` Eric Wong
2020-08-22 21:04       ` Kyle Meyer

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=20200822060627.15595-5-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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).