user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW
Date: Tue, 27 Oct 2020 07:54:49 +0000	[thread overview]
Message-ID: <20201027075453.19163-49-e@80x24.org> (raw)
In-Reply-To: <20201027075453.19163-1-e@80x24.org>

This lets us pretend an ExtSearch object is an Inbox object
in most of the existing WWW code.
---
 lib/PublicInbox/Config.pm    | 12 +++++++++
 lib/PublicInbox/ExtSearch.pm | 25 ++++++++++++++++++
 lib/PublicInbox/Inbox.pm     | 51 ++++++++++++++++++------------------
 lib/PublicInbox/WWW.pm       |  3 ++-
 4 files changed, 64 insertions(+), 27 deletions(-)

diff --git a/lib/PublicInbox/Config.pm b/lib/PublicInbox/Config.pm
index d57c361a..d425cc9b 100644
--- a/lib/PublicInbox/Config.pm
+++ b/lib/PublicInbox/Config.pm
@@ -89,6 +89,11 @@ sub lookup_name ($$) {
 	$self->{-by_name}->{$name} // _fill($self, "publicinbox.$name");
 }
 
+sub lookup_ei {
+	my ($self, $name) = @_;
+	$self->{-ei_by_name}->{$name} //= _fill_ei($self, "eindex.$name");
+}
+
 sub each_inbox {
 	my ($self, $cb, @arg) = @_;
 	# may auto-vivify if config file is non-existent:
@@ -457,6 +462,13 @@ EOF
 	$ibx
 }
 
+sub _fill_ei ($$) {
+	my ($self, $pfx) = @_;
+	require PublicInbox::ExtSearch;
+	my $d = $self->{"$pfx.topdir"};
+	defined($d) && -d $d ? PublicInbox::ExtSearch->new($d) : undef;
+}
+
 sub urlmatch {
 	my ($self, $key, $url) = @_;
 	state $urlmatch_broken; # requires git 1.8.5
diff --git a/lib/PublicInbox/ExtSearch.pm b/lib/PublicInbox/ExtSearch.pm
index 3e8ca82c..66c99eaa 100644
--- a/lib/PublicInbox/ExtSearch.pm
+++ b/lib/PublicInbox/ExtSearch.pm
@@ -3,6 +3,7 @@
 
 # Read-only external (detached) index for cross inbox search.
 # This is a read-only counterpart to PublicInbox::ExtSearchIdx
+# and behaves like PublicInbox::Inbox AND PublicInbox::Search
 package PublicInbox::ExtSearch;
 use strict;
 use v5.10.1;
@@ -21,6 +22,8 @@ sub new {
 	}, __PACKAGE__;
 }
 
+sub search { $_[0] } # self
+
 # overrides PublicInbox::Search::_xdb
 sub _xdb {
 	my ($self) = @_;
@@ -38,7 +41,29 @@ sub git {
 	$self->{git} //= PublicInbox::Git->new("$self->{topdir}/ALL.git");
 }
 
+sub mm { undef }
+
+sub altid_map { {} }
+
+sub description {
+	my ($self) = @_;
+	($self->{description} //=
+		PublicInbox::Inbox::cat_desc("$self->{topdir}/description")) //
+		'$EINDEX_DIR/description missing';
+}
+
+sub cloneurl { [] } # TODO
+
+sub base_url { 'https://example.com/TODO/' }
+sub nntp_url { [] }
+
 no warnings 'once';
 *smsg_eml = \&PublicInbox::Inbox::smsg_eml;
+*smsg_by_mid = \&PublicInbox::Inbox::smsg_by_mid;
+*msg_by_mid = \&PublicInbox::Inbox::msg_by_mid;
+*modified = \&PublicInbox::Inbox::modified;
+*recent = \&PublicInbox::Inbox::recent;
+
+*max_git_epoch = *nntp_usable = *msg_by_path = \&mm; # undef
 
 1;
diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index cd5c098a..1d18cdf1 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -225,16 +225,19 @@ sub try_cat {
 	$rv;
 }
 
+sub cat_desc ($) {
+	my $desc = try_cat($_[0]);
+	local $/ = "\n";
+	chomp $desc;
+	utf8::decode($desc);
+	$desc =~ s/\s+/ /smg;
+	$desc eq '' ? undef : $desc;
+}
+
 sub description {
 	my ($self) = @_;
-	($self->{description} //= do {
-		my $desc = try_cat("$self->{inboxdir}/description");
-		local $/ = "\n";
-		chomp $desc;
-		utf8::decode($desc);
-		$desc =~ s/\s+/ /smg;
-		$desc eq '' ? undef : $desc;
-	}) // '($INBOX_DIR/description missing)';
+	($self->{description} //= cat_desc("$self->{inboxdir}/description")) //
+		'($INBOX_DIR/description missing)';
 }
 
 sub cloneurl {
@@ -342,39 +345,35 @@ sub smsg_eml {
 	$eml;
 }
 
-sub mid2num($$) {
-	my ($self, $mid) = @_;
-	my $mm = mm($self) or return;
-	$mm->num_for($mid);
-}
-
 sub smsg_by_mid ($$) {
 	my ($self, $mid) = @_;
-	my $over = over($self) or return;
-	# favor the Message-ID we used for the NNTP article number:
-	defined(my $num = mid2num($self, $mid)) or return;
-	my $smsg = $over->get_art($num) or return;
-	PublicInbox::Smsg::psgi_cull($smsg);
+	my $over = $self->over or return;
+	my $smsg;
+	if (my $mm = $self->mm) {
+		# favor the Message-ID we used for the NNTP article number:
+		defined(my $num = $mm->num_for($mid)) or return;
+		$smsg = $over->get_art($num);
+	} else {
+		my ($id, $prev);
+		$smsg = $over->next_by_mid($mid, \$id, \$prev);
+	}
+	$smsg ? PublicInbox::Smsg::psgi_cull($smsg) : undef;
 }
 
 sub msg_by_mid ($$) {
 	my ($self, $mid) = @_;
-
-	over($self) or
-		return msg_by_path($self, mid2path($mid));
-
 	my $smsg = smsg_by_mid($self, $mid);
-	$smsg ? msg_by_smsg($self, $smsg) : undef;
+	$smsg ? msg_by_smsg($self, $smsg) : msg_by_path($self, mid2path($mid));
 }
 
 sub recent {
 	my ($self, $opts, $after, $before) = @_;
-	over($self)->recent($opts, $after, $before);
+	$self->over->recent($opts, $after, $before);
 }
 
 sub modified {
 	my ($self) = @_;
-	if (my $over = over($self)) {
+	if (my $over = $self->over) {
 		my $msgs = $over->recent({limit => 1});
 		if (my $smsg = $msgs->[0]) {
 			return $smsg->{ts};
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index e3b589cb..cdbcff1e 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -210,7 +210,8 @@ sub news_cgit_fallback ($) {
 # returns undef if valid, array ref response if invalid
 sub invalid_inbox ($$) {
 	my ($ctx, $inbox) = @_;
-	my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox);
+	my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox) //
+			$ctx->{www}->{pi_config}->lookup_ei($inbox);
 	if (defined $ibx) {
 		$ctx->{-inbox} = $ibx;
 		return;

  parent reply	other threads:[~2020-10-27  7:55 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-27  7:54 [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27  7:54 ` [PATCH 01/52] doc/standards: add RFCs for URL schemes Eric Wong
2020-11-05  7:54   ` [PATCH v2] " Eric Wong
2020-10-27  7:54 ` [PATCH 02/52] search: hoist out _xdb_sharded for v2 inboxes Eric Wong
2020-10-27  7:54 ` [PATCH 03/52] extsearch: start mocking out Eric Wong
2020-10-27  7:54 ` [PATCH 04/52] searchidx: expose INDEXLEVELS as `our' Eric Wong
2020-10-27  7:54 ` [PATCH 05/52] v2writable: add git method Eric Wong
2020-10-27  7:54 ` [PATCH 06/52] v2writable: make OO calls to last_commit-related methods Eric Wong
2020-10-27  7:54 ` [PATCH 07/52] search: xdb_sharded: make this a public method for ExtSearch Eric Wong
2020-10-27  7:54 ` [PATCH 08/52] searchidx: introduce "xref3" concept Eric Wong
2020-10-27  7:54 ` [PATCH 09/52] v2writable: prepare initialization for external indices Eric Wong
2020-10-27  7:54 ` [PATCH 10/52] v2writable: hoist out write_alternates Eric Wong
2020-10-27  7:54 ` [PATCH 11/52] searchidxshard: allow msgref to be undef Eric Wong
2020-10-27  7:54 ` [PATCH 12/52] v2writable: idx_shard: simplify callers Eric Wong
2020-10-27  7:54 ` [PATCH 13/52] v2writable: count_shards: allow working without {ibx} Eric Wong
2020-10-27  7:54 ` [PATCH 14/52] overidx: introduce changes for external index Eric Wong
2020-10-27  7:54 ` [PATCH 15/52] v2: some changes for ExtSearchIdx compatibility Eric Wong
2020-10-27  7:54 ` [PATCH 16/52] inboxwritable: eidx_key for external index Eric Wong
2020-10-27  7:54 ` [PATCH 17/52] v2writable: rename remaining "remote" terminology Eric Wong
2020-10-27  7:54 ` [PATCH 18/52] v2writable: checkpoint: account for lack of {mm} Eric Wong
2020-10-27  7:54 ` [PATCH 19/52] extsearchidx: initial implementation Eric Wong
2020-10-27  7:54 ` [PATCH 20/52] searchidx: index eidx_key as a boolean term Eric Wong
2020-10-27  7:54 ` [PATCH 21/52] searchidx: xref3 delete support Eric Wong
2020-10-27  7:54 ` [PATCH 22/52] searchidxshard: special init for eidx Eric Wong
2020-10-27  7:54 ` [PATCH 23/52] searchidx: put {ibx} into $sync state Eric Wong
2020-10-27  7:54 ` [PATCH 24/52] searchidx: log2stack: simplify callers Eric Wong
2020-10-27  7:54 ` [PATCH 25/52] v2writable: more generic sync setup code Eric Wong
2020-10-27  7:54 ` [PATCH 26/52] v2writable: allow OO method references Eric Wong
2020-10-27  7:54 ` [PATCH 27/52] v2writable: rename {v2w} field to {self} Eric Wong
2020-10-27  7:54 ` [PATCH 28/52] v2writable: make *last_commits and sync_prepare OO methods Eric Wong
2020-10-27  7:54 ` [PATCH 29/52] v2writable: move size check init to sync_prepare Eric Wong
2020-10-27  7:54 ` [PATCH 30/52] extsearchidx: more compatibility with V2Writable callers Eric Wong
2020-10-27  7:54 ` [PATCH 31/52] v2writable: reduce scope of epoch-aware code Eric Wong
2020-10-27  7:54 ` [PATCH 32/52] extsearchidx: remove {unindex_range} field Eric Wong
2020-10-27  7:54 ` [PATCH 33/52] v2writable: pass oid to uindex_oid Eric Wong
2020-10-27  7:54 ` [PATCH 34/52] extsearchidx: sync unit updates Eric Wong
2020-10-27  7:54 ` [PATCH 35/52] searchidx: export prepare_stack Eric Wong
2020-10-27  7:54 ` [PATCH 36/52] extsearchidx: sync updates Eric Wong
2020-10-27  7:54 ` [PATCH 37/52] searchidx: reduce inbox-dependency, wrap ->with_umask Eric Wong
2020-10-27  7:54 ` [PATCH 38/52] searchidx: favor $sync->{ibx} (over $self->{ibx}) Eric Wong
2020-10-27  7:54 ` [PATCH 39/52] Makefile.PL: do not build manpage if POD is missing Eric Wong
2020-10-27  7:54 ` [PATCH 40/52] script: add preliminary eindex implementation Eric Wong
2020-10-27  7:54 ` [PATCH 41/52] index: eindex wiring Eric Wong
2020-10-27  7:54 ` [PATCH 42/52] over: store xref3 data in over.sqlite3 Eric Wong
2020-10-27  7:54 ` [PATCH 43/52] searchidx: remove xref3 support for Xapian Eric Wong
2020-10-27  7:54 ` [PATCH 44/52] t/extsearch.t: verify results and xref3 ordering Eric Wong
2020-10-27  7:54 ` [PATCH 45/52] t/v2writable: remove pointless ->barrier call Eric Wong
2020-10-27  7:54 ` [PATCH 46/52] extsearch: wire up smsg_eml Eric Wong
2020-10-27  7:54 ` [PATCH 47/52] extsearchidx: handle edits Eric Wong
2020-10-27  7:54 ` Eric Wong [this message]
2020-10-27  7:54 ` [PATCH 49/52] searchidx: ignore exceptions from ->remove_term Eric Wong
2020-10-27  7:54 ` [PATCH 50/52] extsearchidx: set current_info in warning callbacks Eric Wong
2020-10-27  7:54 ` [PATCH 51/52] extsearchidx: support --batch-size checkpoints Eric Wong
2020-11-03  9:08   ` Eric Wong
2020-10-27  7:54 ` [PATCH 52/52] searchidxshard: make warnings with eidx_key less confusing Eric Wong
2020-10-27 12:08 ` [PATCH 00/52] detached external index: mostly Konstantin Ryabitsev
2020-11-10 18:53 ` detached external index: performance note Eric Wong

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=20201027075453.19163-49-e@80x24.org \
    --to=e@80x24.org \
    --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).