From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 13/34] search: revert to using 'Q' as a uniQue id per-Xapian conventions
Date: Tue, 6 Mar 2018 08:42:21 +0000 [thread overview]
Message-ID: <20180306084242.19988-14-e@80x24.org> (raw)
In-Reply-To: <20180306084242.19988-1-e@80x24.org>
'Q' is merely a convention in the Xapian world, and is close
enough to unique for practical purposes, so stop using XMID
and gain a little more term length as a result.
---
lib/PublicInbox/ExtMsg.pm | 2 +-
lib/PublicInbox/Search.pm | 8 ++++----
lib/PublicInbox/SearchIdx.pm | 8 ++++----
lib/PublicInbox/SearchIdxSkeleton.pm | 2 +-
lib/PublicInbox/SearchMsg.pm | 2 +-
5 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm
index 90d68db..f3076a3 100644
--- a/lib/PublicInbox/ExtMsg.pm
+++ b/lib/PublicInbox/ExtMsg.pm
@@ -46,7 +46,7 @@ sub ext_msg {
}
# try to find the URL with Xapian to avoid forking
- my $doc_id = eval { $s->find_first_doc_id('XMID' . $mid) };
+ my $doc_id = eval { $s->find_first_doc_id('Q' . $mid) };
if ($@) {
# xapian not configured properly for this repo
push @nox, $other;
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index c074410..74f406a 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -56,7 +56,7 @@ my %bool_pfx_internal = (
);
my %bool_pfx_external = (
- mid => 'XMID', # Message-ID (full/exact)
+ mid => 'Q', # Message-ID (full/exact), this is mostly uniQue
);
my %prob_prefix = (
@@ -333,7 +333,7 @@ sub lookup_skeleton {
my ($self, $mid) = @_;
my $skel = $self->{skel} or return lookup_message($self, $mid);
$mid = mid_clean($mid);
- my $term = 'XMID' . $mid;
+ my $term = 'Q' . $mid;
my $smsg;
my $beg = $skel->postlist_begin($term);
if ($beg != $skel->postlist_end($term)) {
@@ -352,7 +352,7 @@ sub lookup_message {
my ($self, $mid) = @_;
$mid = mid_clean($mid);
- my $doc_id = $self->find_first_doc_id('XMID' . $mid);
+ my $doc_id = $self->find_first_doc_id('Q' . $mid);
my $smsg;
if (defined $doc_id) {
# raises on error:
@@ -377,7 +377,7 @@ sub each_smsg_by_mid {
my $xdb = $self->{xdb};
# XXX retry_reopen isn't necessary for V2Writable, but the PSGI
# interface will need it...
- my ($head, $tail) = $self->find_doc_ids('XMID' . $mid);
+ my ($head, $tail) = $self->find_doc_ids('Q' . $mid);
for (; $head->nequal($tail); $head->inc) {
my $doc_id = $head->get_docid;
my $doc = $xdb->get_document($doc_id);
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 57aed75..61dc057 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -19,7 +19,7 @@ use POSIX qw(strftime);
require PublicInbox::Git;
use constant {
- MAX_MID_SIZE => 244, # max term size - 1 in Xapian
+ MAX_MID_SIZE => 244, # max term size (Xapian limitation) - length('Q')
PERM_UMASK => 0,
OLD_PERM_GROUP => 1,
OLD_PERM_EVERYBODY => 2,
@@ -302,7 +302,7 @@ sub add_message {
}
$smsg = PublicInbox::SearchMsg->new($mime);
my $doc = $smsg->{doc};
- $doc->add_term('XMID' . $mid);
+ $doc->add_term('Q' . $mid);
my $subj = $smsg->subject;
my $xpath;
@@ -404,7 +404,7 @@ sub remove_message {
$mid = mid_clean($mid);
eval {
- my ($head, $tail) = $self->find_doc_ids('XMID' . $mid);
+ my ($head, $tail) = $self->find_doc_ids('Q' . $mid);
if ($head->equal($tail)) {
warn "cannot remove non-existent <$mid>\n";
}
@@ -721,7 +721,7 @@ sub create_ghost {
my $tid = $self->next_thread_id;
my $doc = Search::Xapian::Document->new;
- $doc->add_term('XMID' . $mid);
+ $doc->add_term('Q' . $mid);
$doc->add_term('G' . $tid);
$doc->add_term('T' . 'ghost');
diff --git a/lib/PublicInbox/SearchIdxSkeleton.pm b/lib/PublicInbox/SearchIdxSkeleton.pm
index aa2713f..333f965 100644
--- a/lib/PublicInbox/SearchIdxSkeleton.pm
+++ b/lib/PublicInbox/SearchIdxSkeleton.pm
@@ -107,7 +107,7 @@ sub index_skeleton_real ($$) {
}
my $doc = $smsg->{doc};
$doc->add_term('XPATH' . $xpath) if defined $xpath;
- $doc->add_term('XMID' . $mid);
+ $doc->add_term('Q' . $mid);
PublicInbox::SearchIdx::add_values($doc, $values);
$doc->set_data($doc_data);
$smsg->{ts} = $ts;
diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm
index 941bfd2..014f490 100644
--- a/lib/PublicInbox/SearchMsg.pm
+++ b/lib/PublicInbox/SearchMsg.pm
@@ -154,7 +154,7 @@ sub mid ($;$) {
} elsif (my $rv = $self->{mid}) {
$rv;
} else {
- $self->{mid} = _get_term_val($self, 'XMID', qr/\AXMID/) ||
+ $self->{mid} = _get_term_val($self, 'Q', qr/\AQ/) ||
$self->_extract_mid;
}
}
--
EW
next prev parent reply other threads:[~2018-03-06 8:42 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-06 8:42 [v2 PATCH 00/34] duplicate handling, smaller Xapian DBs, date fixes Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 01/34] v2writable: delete ::Import obj when ->done Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 02/34] search: remove informational "warning" message Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 03/34] searchidx: add PID to error message when die-ing Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 04/34] content_id: special treatment for Message-Id headers Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 05/34] evcleanup: disable outside of daemon Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 06/34] v2writable: deduplicate detection on add Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 07/34] evcleanup: do not create event loop if nothing was registered Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 08/34] mid: add `mids' and `references' methods for extraction Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 09/34] content_id: use `mids' and `references' for MID extraction Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 10/34] searchidx: use new `references' method for parsing References Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 11/34] content_id: no need to be human-friendly Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 12/34] v2writable: inject new Message-IDs on true duplicates Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` Eric Wong (Contractor, The Linux Foundation) [this message]
2018-03-06 8:42 ` [PATCH 14/34] searchidx: support indexing multiple MIDs Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 15/34] mid: be strict with References, but loose on Message-Id Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 16/34] searchidx: avoid excessive XNQ indexing with diffs Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 17/34] searchidxskeleton: add a note about locking Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 18/34] v2writable: generated Message-ID goes first Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 19/34] searchidx: use add_boolean_term for internal terms Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 20/34] searchidx: add NNTP article number as a searchable term Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 21/34] mid: truncate excessively long MIDs early Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 22/34] nntp: use NNTP article numbers for lookups Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 23/34] nntp: fix NEWNEWS command Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 24/34] searchidx: store the primary MID in doc data for NNTP Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 25/34] import: consolidate object info for v2 imports Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 26/34] v2: avoid redundant/repeated configs for git partition repos Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 27/34] INSTALL: document more optional dependencies Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 28/34] search: favor skeleton DB for lookup_mail Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 29/34] search: each_smsg_by_mid uses skeleton if available Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 30/34] v2writable: remove unnecessary skeleton commit Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 31/34] favor Received: date over Date: header globally Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 32/34] import: fall back to Sender for extracting name and email Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 33/34] scripts/import_vger_from_mbox: perform mboxrd or mboxo escaping Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:42 ` [PATCH 34/34] v2writable: detect and use previous partition count Eric Wong (Contractor, The Linux Foundation)
2018-03-06 8:53 ` [v2 PATCH 00/34] duplicate handling, smaller Xapian DBs, date fixes 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=20180306084242.19988-14-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.
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).