* [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
@ 2020-10-27 7:54 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
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;
^ permalink raw reply related [relevance 6%]
* [PATCH 00/52] detached external index: mostly
@ 2020-10-27 7:54 7% Eric Wong
2020-10-27 7:54 6% ` [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW 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 6% ` [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW 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).