X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=bc2b69854a8765add7c4956f0f7a3c23d9edf0a0;hb=de243560e2caa1d19bcbf518edfaf8b016161245;hp=d3faaebbccbca2cf53c09261b8816e417eae5e6c;hpb=8ea217f4452e34776ba294b5090827c99656cada;p=public-inbox.git
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index d3faaebb..bc2b6985 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -1,13 +1,23 @@
-# Copyright (C) 2015, all contributors
+# Copyright (C) 2015 all contributors
# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
# based on notmuch, but with no concept of folders, files or flags
+#
+# Read-only search interface for use by the web and NNTP interfaces
package PublicInbox::Search;
use strict;
use warnings;
-use PublicInbox::SearchMsg;
+
+# values for searching
+use constant TS => 0; # timestamp
+use constant NUM => 1; # NNTP article number
+use constant BYTES => 2; # :bytes as defined in RFC 3977
+use constant LINES => 3; # :lines as defined in RFC 3977
+use constant YYYYMMDD => 4; # for searching in the WWW UI
+
use Search::Xapian qw/:standard/;
-use Email::MIME;
-use PublicInbox::MID qw/mid_clean mid_compress/;
+use PublicInbox::SearchMsg;
+use PublicInbox::MIME;
+use PublicInbox::MID qw/mid_clean id_compress/;
# This is English-only, everything else is non-standard and may be confused as
# a prefix common in patch emails
@@ -15,45 +25,91 @@ our $REPLY_RE = qr/^re:\s+/i;
our $LANG = 'english';
use constant {
- TS => 0,
# SCHEMA_VERSION history
# 0 - initial
# 1 - subject_path is lower-cased
- # 2 - subject_path is mid_compress in the index, only
+ # 2 - subject_path is id_compress in the index, only
# 3 - message-ID is compressed if it includes '%' (hack!)
# 4 - change "Re: " normalization, avoid circular Reference ghosts
# 5 - subject_path drops trailing '.'
# 6 - preserve References: order in document data
# 7 - remove references and inreplyto terms
- SCHEMA_VERSION => 7,
+ # 8 - remove redundant/unneeded document data
+ # 9 - disable Message-ID compression (SHA-1)
+ # 10 - optimize doc for NNTP overviews
+ # 11 - merge threads when vivifying ghosts
+ # 12 - change YYYYMMDD value column to numeric
+ # 13 - fix threading for empty References/In-Reply-To
+ # (commit 83425ef12e4b65cdcecd11ddcb38175d4a91d5a0)
+ SCHEMA_VERSION => 13,
+
+ # n.b. FLAG_PURE_NOT is expensive not suitable for a public website
+ # as it could become a denial-of-service vector
QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD,
};
# setup prefixes
my %bool_pfx_internal = (
type => 'T', # "mail" or "ghost"
- mid => 'Q', # uniQue id (Message-ID or mid_compress)
+ thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
);
my %bool_pfx_external = (
+ # do we still need these? probably not..
path => 'XPATH',
- thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
+ mid => 'Q', # uniQue id (Message-ID)
);
my %prob_prefix = (
- subject => 'S',
+ # for mairix compatibility
+ s => 'S',
+ m => 'XMID', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+ f => 'A',
+ t => 'XTO',
+ tc => 'XTO XCC',
+ c => 'XCC',
+ tcf => 'XTO XCC A',
+ a => 'XTO XCC A',
+ b => 'XNQ XQUOT',
+ bs => 'XNQ XQUOT S',
+ n => 'XFN',
+
+ q => 'XQUOT',
+ nq => 'XNQ',
+
+ # default:
+ '' => 'XMID S A XNQ XQUOT XFN',
);
+# not documenting m: and mid: for now, the using the URLs works w/o Xapian
+our @HELP = (
+ 's:' => 'match within Subject e.g. s:"a quick brown fox"',
+ 'd:' => < 'match within message body, including text attachments',
+ 'nq:' => 'match non-quoted text within message body',
+ 'q:' => 'match quoted text within message body',
+ 'n:' => 'match filename of attachment(s)',
+ 't:' => 'match within the To header',
+ 'c:' => 'match within the Cc header',
+ 'f:' => 'match within the From header',
+ 'a:' => 'match within the To, Cc, and From headers',
+ 'tc:' => 'match within the To and Cc headers',
+ 'bs:' => 'match within the Subject and body',
+);
+chomp @HELP;
+# TODO:
+# df (filenames from diff)
+# da (diff a/ removed lines)
+# db (diff b/ added lines)
+
my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
sub xpfx { $all_pfx{$_[0]} }
-our %PFX2TERM_RMAP;
-my %meta_pfx = (mid => 1, thread => 1, path => 1);
-while (my ($k, $v) = each %all_pfx) {
- $PFX2TERM_RMAP{$v} = $k if $meta_pfx{$k};
-}
-
my $mail_query = Search::Xapian::Query->new(xpfx('type') . 'mail');
sub xdir {
@@ -62,10 +118,10 @@ sub xdir {
}
sub new {
- my ($class, $git_dir) = @_;
+ my ($class, $git_dir, $altid) = @_;
my $dir = $class->xdir($git_dir);
my $db = Search::Xapian::Database->new($dir);
- bless { xdb => $db, git_dir => $git_dir }, $class;
+ bless { xdb => $db, git_dir => $git_dir, altid => $altid }, $class;
}
sub reopen { $_[0]->{xdb}->reopen }
@@ -73,17 +129,15 @@ sub reopen { $_[0]->{xdb}->reopen }
# read-only
sub query {
my ($self, $query_string, $opts) = @_;
- my $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ my $query;
$opts ||= {};
- $opts->{relevance} = 1;
- $self->do_enquire($query, $opts);
-}
+ unless ($query_string eq '') {
+ $query = $self->qp->parse_query($query_string, QP_FLAGS);
+ $opts->{relevance} = 1 unless exists $opts->{relevance};
+ }
-sub get_subject_path {
- my ($self, $path, $opts) = @_;
- my $query = $self->qp->parse_query("path:".mid_compress($path), 0);
- $self->do_enquire($query, $opts);
+ _do_enquire($self, $query, $opts);
}
sub get_thread {
@@ -91,30 +145,66 @@ sub get_thread {
my $smsg = eval { $self->lookup_message($mid) };
return { total => 0, msgs => [] } unless $smsg;
- my $qp = $self->qp;
- my $qtid = $qp->parse_query('thread:'.$smsg->thread_id, 0);
- my $qsub = $qp->parse_query('path:'.mid_compress($smsg->path), 0);
- my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
- $self->do_enquire($query, $opts);
+ my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id);
+ my $path = $smsg->path;
+ if (defined $path && $path ne '') {
+ my $path = id_compress($smsg->path);
+ my $qsub = Search::Xapian::Query->new(xpfx('path').$path);
+ $qtid = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
+ }
+ $opts ||= {};
+ $opts->{limit} ||= 1000;
+
+ # always sort threads by timestamp, this makes life easier
+ # for the threading algorithm (in SearchThread.pm)
+ $opts->{asc} = 1;
+
+ _do_enquire($self, $qtid, $opts);
+}
+
+sub retry_reopen {
+ my ($self, $cb) = @_;
+ my $ret;
+ for (1..10) {
+ eval { $ret = $cb->() };
+ return $ret unless $@;
+ # Exception: The revision being read has been discarded -
+ # you should call Xapian::Database::reopen()
+ if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') {
+ reopen($self);
+ } else {
+ die;
+ }
+ }
}
-# private subs below
+sub _do_enquire {
+ my ($self, $query, $opts) = @_;
+ retry_reopen($self, sub { _enquire_once($self, $query, $opts) });
+}
-sub do_enquire {
+sub _enquire_once {
my ($self, $query, $opts) = @_;
my $enquire = $self->enquire;
-
- $query = Search::Xapian::Query->new(OP_AND, $query, $mail_query);
+ if (defined $query) {
+ $query = Search::Xapian::Query->new(OP_AND,$query,$mail_query);
+ } else {
+ $query = $mail_query;
+ }
$enquire->set_query($query);
+ $opts ||= {};
+ my $desc = !$opts->{asc};
if ($opts->{relevance}) {
- $enquire->set_sort_by_relevance_then_value(TS, 0);
+ $enquire->set_sort_by_relevance_then_value(TS, $desc);
+ } elsif ($opts->{num}) {
+ $enquire->set_sort_by_value(NUM, 0);
} else {
- $enquire->set_sort_by_value(TS, 0);
+ $enquire->set_sort_by_value_then_relevance(TS, $desc);
}
- $opts ||= {};
my $offset = $opts->{offset} || 0;
my $limit = $opts->{limit} || 50;
my $mset = $enquire->get_mset($offset, $limit);
+ return $mset if $opts->{mset};
my @msgs = map {
PublicInbox::SearchMsg->load_doc($_->get_document);
} $mset->items;
@@ -138,32 +228,55 @@ sub qp {
$qp->set_database($self->{xdb});
$qp->set_stemmer($self->stemmer);
$qp->set_stemming_strategy(STEM_SOME);
- $qp->add_valuerangeprocessor($self->ts_range_processor);
- $qp->add_valuerangeprocessor($self->date_range_processor);
+ $qp->add_valuerangeprocessor(
+ Search::Xapian::NumberValueRangeProcessor->new(YYYYMMDD, 'd:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
$qp->add_boolean_prefix($name, $prefix);
}
+ # we do not actually create AltId objects,
+ # just parse the spec to avoid the extra DB handles for now.
+ if (my $altid = $self->{altid}) {
+ my $user_pfx = $self->{-user_pfx} ||= [];
+ for (@$altid) {
+ # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ /\Aserial:(\w+):/ or next;
+ my $pfx = $1;
+ push @$user_pfx, "$pfx:", < XGMANE
+ $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
+ }
+ chomp @$user_pfx;
+ }
+
while (my ($name, $prefix) = each %prob_prefix) {
- $qp->add_prefix($name, $prefix);
+ $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
}
$self->{query_parser} = $qp;
}
-sub ts_range_processor {
- $_[0]->{tsrp} ||= Search::Xapian::NumberValueRangeProcessor->new(TS);
+sub num_range_processor {
+ $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM);
}
-sub date_range_processor {
- $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
+# only used for NNTP server
+sub query_xover {
+ my ($self, $beg, $end, $offset) = @_;
+ my $qp = Search::Xapian::QueryParser->new;
+ $qp->set_database($self->{xdb});
+ $qp->add_valuerangeprocessor($self->num_range_processor);
+ my $query = $qp->parse_query("$beg..$end", QP_FLAGS);
+
+ _do_enquire($self, $query, {num => 1, limit => 200, offset => $offset});
}
sub lookup_message {
my ($self, $mid) = @_;
$mid = mid_clean($mid);
- $mid = mid_compress($mid);
my $doc_id = $self->find_unique_doc_id('mid', $mid);
my $smsg;
@@ -171,11 +284,19 @@ sub lookup_message {
# raises on error:
my $doc = $self->{xdb}->get_document($doc_id);
$smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $smsg->doc_id($doc_id);
+ $smsg->{doc_id} = $doc_id;
}
$smsg;
}
+sub lookup_mail { # no ghosts!
+ my ($self, $mid) = @_;
+ retry_reopen($self, sub {
+ my $smsg = lookup_message($self, $mid) or return;
+ PublicInbox::SearchMsg->load_doc($smsg->{doc});
+ });
+}
+
sub find_unique_doc_id {
my ($self, $term, $value) = @_;
@@ -207,6 +328,7 @@ sub find_doc_ids_for_term {
}
# normalize subjects so they are suitable as pathnames for URLs
+# XXX: consider for removal
sub subject_path {
my $subj = pop;
$subj = subject_normalized($subj);
@@ -224,35 +346,19 @@ sub subject_normalized {
$subj;
}
-# for doc data
-sub subject_summary {
- my $subj = pop;
- my $max = 68;
- if (length($subj) > $max) {
- my @subj = split(/\s+/, $subj);
- $subj = '';
- my $l;
-
- while ($l = shift @subj) {
- my $new = $subj . $l . ' ';
- last if length($new) >= $max;
- $subj = $new;
- }
- if ($subj ne '') {
- my $r = scalar @subj ? ' ...' : '';
- $subj =~ s/ \z/$r/s;
- } else {
- # subject has one REALLY long word, and NOT spam? wtf
- @subj = ($l =~ /\A(.{1,72})/);
- $subj = $subj[0] . ' ...';
- }
- }
- $subj;
-}
-
sub enquire {
my ($self) = @_;
$self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
}
+sub help {
+ my ($self) = @_;
+ $self->qp; # parse altids
+ my @ret = @HELP;
+ if (my $user_pfx = $self->{-user_pfx}) {
+ push @ret, @$user_pfx;
+ }
+ \@ret;
+}
+
1;