-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <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;
-use Search::Xapian qw/:standard/;
-require PublicInbox::View;
-use Email::MIME;
-use PublicInbox::MID qw/mid_clean mid_compressed/;
-
+use v5.10.1;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(retry_reopen int_val get_pct xap_terms);
+use List::Util qw(max);
+use POSIX qw(strftime);
+use Carp ();
+
+# values for searching, changing the numeric value breaks
+# compatibility with old indices (so don't change them it)
use constant {
- TS => 0,
- SCHEMA_VERSION => 0,
- LANG => 'english',
- QP_FLAGS => FLAG_PHRASE|FLAG_BOOLEAN|FLAG_LOVEHATE|FLAG_WILDCARD,
+ TS => 0, # Received: in Unix time (IMAP INTERNALDATE, JMAP receivedAt)
+ YYYYMMDD => 1, # redundant with DT below
+ DT => 2, # Date: YYYYMMDDHHMMSS (IMAP SENT*, JMAP sentAt)
+
+ # added for public-inbox 1.6.0+
+ BYTES => 3, # IMAP RFC822.SIZE
+ UID => 4, # IMAP UID == NNTP article number == Xapian docid
+ THREADID => 5, # RFC 8474, RFC 8621
+
+ # TODO
+ # REPLYCNT => ?, # IMAP ANSWERED
+
+ # SCHEMA_VERSION history
+ # 0 - initial
+ # 1 - subject_path is lower-cased
+ # 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
+ # 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)
+ # 14 - fix ghost root vivification
+ # 15 - see public-inbox-v2-format(5)
+ # further bumps likely unnecessary, we'll suggest in-place
+ # "--reindex" use for further fixes and tweaks:
+ #
+ # public-inbox v1.5.0 adds (still SCHEMA_VERSION=15):
+ # * "lid:" and "l:" for List-Id searches
+ #
+ # v1.6.0 adds BYTES, UID and THREADID values
+ SCHEMA_VERSION => 15,
};
-# setup prefixes
-my %bool_pfx_internal = (
- type => 'T', # "mail" or "ghost"
- mid => 'Q', # uniQue id (Message-ID or mid_compressed)
-);
+use PublicInbox::Smsg;
+use PublicInbox::Over;
+our $QP_FLAGS;
+our %X = map { $_ => 0 } qw(BoolWeight Database Enquire QueryParser Stem Query);
+our $Xap; # 'Search::Xapian' or 'Xapian'
+our $NVRP; # '$Xap::'.('NumberValueRangeProcessor' or 'NumberRangeProcessor')
+
+# ENQ_DESCENDING and ENQ_ASCENDING weren't in SWIG Xapian.pm prior to 1.4.16,
+# let's hope the ABI is stable
+our $ENQ_DESCENDING = 0;
+our $ENQ_ASCENDING = 1;
+
+sub load_xapian () {
+ return 1 if defined $Xap;
+ # n.b. PI_XAPIAN is intended for development use only. We still
+ # favor Search::Xapian since that's what's available in current
+ # Debian stable (10.x) and derived distros.
+ for my $x (($ENV{PI_XAPIAN} // 'Search::Xapian'), 'Xapian') {
+ eval "require $x";
+ next if $@;
+
+ $x->import(qw(:standard));
+ $Xap = $x;
+
+ # `version_string' was added in Xapian 1.1
+ my $xver = eval('v'.eval($x.'::version_string()')) //
+ eval('v'.eval($x.'::xapian_version_string()'));
+
+ # NumberRangeProcessor was added in Xapian 1.3.6,
+ # NumberValueRangeProcessor was removed for 1.5.0+,
+ # favor the older /Value/ variant since that's what our
+ # (currently) preferred Search::Xapian supports
+ $NVRP = $x.'::'.($x eq 'Xapian' && $xver ge v1.5 ?
+ 'NumberRangeProcessor' : 'NumberValueRangeProcessor');
+ $X{$_} = $Xap.'::'.$_ for (keys %X);
+
+ *sortable_serialise = $x.'::sortable_serialise';
+ *sortable_unserialise = $x.'::sortable_unserialise';
+ # n.b. FLAG_PURE_NOT is expensive not suitable for a public
+ # website as it could become a denial-of-service vector
+ # FLAG_PHRASE also seems to cause performance problems chert
+ # (and probably earlier Xapian DBs). glass seems fine...
+ # TODO: make this an option, maybe?
+ # or make indexlevel=medium as default
+ $QP_FLAGS = FLAG_PHRASE() | FLAG_BOOLEAN() | FLAG_LOVEHATE() |
+ FLAG_WILDCARD();
+ return 1;
+ }
+ undef;
+}
+
+# This is English-only, everything else is non-standard and may be confused as
+# a prefix common in patch emails
+our $LANG = 'english';
+# note: the non-X term prefix allocations are shared with
+# Xapian omega, see xapian-applications/omega/docs/termprefixes.rst
my %bool_pfx_external = (
- path => 'XPATH',
- thread => 'G', # newsGroup (or similar entity - e.g. a web forum name)
- references => 'XREFS',
- inreplyto => 'XIRT',
+ mid => 'Q', # Message-ID (full/exact), this is mostly uniQue
+ lid => 'G', # newsGroup (or similar entity), just inside <>
+ dfpre => 'XDFPRE',
+ dfpost => 'XDFPOST',
+ dfblob => 'XDFPRE XDFPOST',
);
+my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST';
my %prob_prefix = (
- subject => 'S',
+ # for mairix compatibility
+ s => 'S',
+ m => 'XM', # 'mid:' (bool) is exact, 'm:' (prob) can do partial
+ l => 'XL', # 'lid:' (bool) is exact, 'l:' (prob) can do partial
+ f => 'A',
+ t => 'XTO',
+ tc => 'XTO XCC',
+ c => 'XCC',
+ tcf => 'XTO XCC A',
+ a => 'XTO XCC A',
+ b => $non_quoted_body . ' XQUOT',
+ bs => $non_quoted_body . ' XQUOT S',
+ n => 'XFN',
+
+ q => 'XQUOT',
+ nq => $non_quoted_body,
+ dfn => 'XDFN',
+ dfa => 'XDFA',
+ dfb => 'XDFB',
+ dfhh => 'XDFHH',
+ dfctx => 'XDFCTX',
+
+ # default:
+ '' => 'XM S A XQUOT XFN ' . $non_quoted_body,
);
-my %all_pfx = (%bool_pfx_internal, %bool_pfx_external, %prob_prefix);
-
-sub xpfx { $all_pfx{$_[0]} }
-
-our %PFX2TERM_RMAP;
-while (my ($k, $v) = each %all_pfx) {
- next if $prob_prefix{$k};
- $PFX2TERM_RMAP{$v} = $k;
+# not documenting m: and mid: for now, the using the URLs works w/o Xapian
+# not documenting lid: for now, either, it is probably redundant with l:,
+# especially since we don't offer boolean searches for To/Cc/From
+# headers, either
+our @HELP = (
+ 's:' => 'match within Subject e.g. s:"a quick brown fox"',
+ 'd:' => <<EOF,
+match date-time range, git "approxidate" formats supported
+Open-ended ranges such as `d:last.week..' and
+`d:..2.days.ago' are supported
+EOF
+ 'b:' => 'match within message body, including text attachments',
+ 'nq:' => 'match non-quoted text within message body',
+ 'q:' => 'match quoted text within message body',
+ 'n:' => 'match filename of attachment(s)',
+ 't:' => 'match within the To header',
+ 'c:' => 'match within the Cc header',
+ 'f:' => 'match within the From header',
+ 'a:' => 'match within the To, Cc, and From headers',
+ 'tc:' => 'match within the To and Cc headers',
+ 'l:' => 'match contents of the List-Id header',
+ 'bs:' => 'match within the Subject and body',
+ 'dfn:' => 'match filename from diff',
+ 'dfa:' => 'match diff removed (-) lines',
+ 'dfb:' => 'match diff added (+) lines',
+ 'dfhh:' => 'match diff hunk header context (usually a function name)',
+ 'dfctx:' => 'match diff context lines',
+ 'dfpre:' => 'match pre-image git blob ID',
+ 'dfpost:' => 'match post-image git blob ID',
+ 'dfblob:' => 'match either pre or post-image git blob ID',
+ 'rt:' => <<EOF,
+match received time, like `d:' if sender's clock was correct
+EOF
+);
+chomp @HELP;
+
+sub xdir ($;$) {
+ my ($self, $rdonly) = @_;
+ if ($rdonly || !defined($self->{shard})) {
+ $self->{xpfx};
+ } else { # v2 + extindex only:
+ "$self->{xpfx}/$self->{shard}";
+ }
}
-my $mail_query = Search::Xapian::Query->new(xpfx('type') . 'mail');
-
-sub new {
- my ($class, $git_dir, $writable) = @_;
- # allow concurrent versions for easier rollback:
- my $dir = "$git_dir/public-inbox/xapian" . SCHEMA_VERSION;
- my $db;
-
- if ($writable) { # not used by the WWW interface
- require Search::Xapian::WritableDatabase;
- require File::Path;
- File::Path::mkpath($dir);
- $db = Search::Xapian::WritableDatabase->new($dir,
- Search::Xapian::DB_CREATE_OR_OPEN);
+# returns all shards as separate Xapian::Database objects w/o combining
+sub xdb_shards_flat ($) {
+ my ($self) = @_;
+ my $xpfx = $self->{xpfx};
+ my (@xdb, $slow_phrase);
+ load_xapian();
+ $self->{qp_flags} //= $QP_FLAGS;
+ if ($xpfx =~ m!/xapian[0-9]+\z!) {
+ @xdb = ($X{Database}->new($xpfx));
+ $self->{qp_flags} |= FLAG_PHRASE() if !-f "$xpfx/iamchert";
} else {
- $db = Search::Xapian::Database->new($dir);
+ opendir(my $dh, $xpfx) or return (); # not initialized yet
+ # We need numeric sorting so shard[0] is first for reading
+ # Xapian metadata, if needed
+ my $last = max(grep(/\A[0-9]+\z/, readdir($dh))) // return ();
+ for (0..$last) {
+ my $shard_dir = "$self->{xpfx}/$_";
+ push @xdb, $X{Database}->new($shard_dir);
+ $slow_phrase ||= -f "$shard_dir/iamchert";
+ }
+ $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
}
- bless { xdb => $db, git_dir => $git_dir }, $class;
+ @xdb;
}
-sub reopen { $_[0]->{xdb}->reopen }
-
-sub add_message {
- my ($self, $mime) = @_; # mime = Email::MIME object
- my $db = $self->{xdb};
-
- my $doc_id;
- my $mid = mid_clean($mime->header('Message-ID'));
- $mid = mid_compressed($mid);
- my $was_ghost = 0;
- my $ct_msg = $mime->header('Content-Type') || 'text/plain';
- my $enc_msg = PublicInbox::View::enc_for($ct_msg);
-
- $db->begin_transaction;
- eval {
- my $smsg = $self->lookup_message($mid);
- my $doc;
-
- if ($smsg) {
- $smsg->ensure_metadata;
- # convert a ghost to a regular message
- # it will also clobber any existing regular message
- $smsg->mime($mime);
- $doc = $smsg->{doc};
-
- my $type = xpfx('type');
- eval {
- $doc->remove_term($type . 'ghost');
- $was_ghost = 1;
- };
-
- # probably does not exist:
- eval { $doc->remove_term($type . 'mail') };
- $doc->add_term($type . 'mail');
- } else {
- $smsg = PublicInbox::SearchMsg->new($mime);
- $doc = $smsg->{doc};
- $doc->add_term(xpfx('mid') . $mid);
- }
-
- my $subj = $smsg->subject;
-
- if (length $subj) {
- $doc->add_term(xpfx('subject') . $subj);
-
- my $path = subject_path($subj);
- $doc->add_term(xpfx('path') . $path);
- }
-
- my $from = $smsg->from_name;
- my $date = $smsg->date;
- my $ts = Search::Xapian::sortable_serialise($smsg->ts);
- $doc->add_value(PublicInbox::Search::TS, $ts);
-
- $doc->set_data($smsg->to_doc_data);
-
- my $tg = $self->term_generator;
+# v2 Xapian docids don't conflict, so they're identical to
+# NNTP article numbers and IMAP UIDs.
+# https://trac.xapian.org/wiki/FAQ/MultiDatabaseDocumentID
+sub mdocid {
+ my ($nshard, $mitem) = @_;
+ my $docid = $mitem->get_docid;
+ int(($docid - 1) / $nshard) + 1;
+}
- $tg->set_document($doc);
- $tg->index_text($subj, 1, 'S') if $subj;
- $tg->increase_termpos;
- $tg->index_text($subj) if $subj;
- $tg->increase_termpos;
+sub mset_to_artnums {
+ my ($self, $mset) = @_;
+ my $nshard = $self->{nshard};
+ [ map { mdocid($nshard, $_) } $mset->items ];
+}
- $tg->index_text($smsg->from->format);
- $tg->increase_termpos;
+sub xdb ($) {
+ my ($self) = @_;
+ $self->{xdb} // do {
+ my @xdb = $self->xdb_shards_flat or return;
+ $self->{nshard} = scalar(@xdb);
+ my $xdb = shift @xdb;
+ $xdb->add_database($_) for @xdb;
+ $self->{xdb} = $xdb;
+ };
+}
- $mime->walk_parts(sub {
- my ($part) = @_;
- return if $part->subparts; # walk_parts already recurses
- my $ct = $part->content_type || $ct_msg;
+sub new {
+ my ($class, $ibx) = @_;
+ ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
+ my $xap = $ibx->version > 1 ? 'xap' : 'public-inbox/xapian';
+ my $xpfx = "$ibx->{inboxdir}/$xap".SCHEMA_VERSION;
+ my $self = bless { xpfx => $xpfx }, $class;
+ $self->{altid} = $ibx->{altid} if defined($ibx->{altid});
+ $self;
+}
- # account for filter bugs...
- $ct =~ m!\btext/plain\b!i or return;
+sub reopen {
+ my ($self) = @_;
+ if (my $xdb = $self->{xdb}) {
+ $xdb->reopen;
+ }
+ $self; # make chaining easier
+}
- my $enc = PublicInbox::View::enc_for($ct, $enc_msg);
- my (@orig, @quot);
- foreach my $l (split(/\n/, $enc->decode($part->body))) {
- if ($l =~ /^\s*>/) {
- push @quot, $l;
- } else {
- push @orig, $l;
+# Convert git "approxidate" ranges to something usable with our
+# Xapian indices. At the moment, Xapian only offers a C++-only API
+# and neither the SWIG nor XS bindings allow us to use custom code
+# to parse dates (and libgit2 doesn't expose git__date_parse, either,
+# so we're running git-rev-parse(1)).
+# This replaces things we need to send to $git->date_parse with
+# "\0".$strftime_format.['+'|$idx]."\0" placeholders
+sub date_parse_prepare {
+ my ($to_parse, $pfx, $range) = @_;
+ # are we inside a parenthesized statement?
+ my $end = $range =~ s/([\)\s]*)\z// ? $1 : '';
+ my @r = split(/\.\./, $range, 2);
+
+ # expand "d:20101002" => "d:20101002..20101003" and like
+ # n.b. git doesn't do YYYYMMDD w/o '-', it needs YYYY-MM-DD
+ # We upgrade "d:" to "dt:" to iff using approxidate
+ if ($pfx eq 'd') {
+ my $fmt = "\0%Y%m%d";
+ if (!defined($r[1])) {
+ if ($r[0] =~ /\A([0-9]{4})([0-9]{2})([0-9]{2})\z/) {
+ push @$to_parse, "$1-$2-$3";
+ # we could've handled as-is, but we need
+ # to parse anyways for "d+" below
+ } else {
+ push @$to_parse, $r[0];
+ if ($r[0] !~ /\A[0-9]{4}-[0-9]{2}-[0-9]{2}\z/) {
+ $pfx = 'dt';
+ $fmt = "\0%Y%m%d%H%M%S";
}
}
- if (@quot) {
- $tg->index_text(join("\n", @quot), 0);
- $tg->increase_termpos;
+ $r[0] = "$fmt+$#$to_parse\0";
+ $r[1] = "$fmt+\0";
+ } else {
+ for my $x (@r) {
+ next if $x eq '' || $x =~ /\A[0-9]{8}\z/;
+ push @$to_parse, $x;
+ if ($x !~ /\A[0-9]{4}-[0-9]{2}-[0-9]{2}\z/) {
+ $pfx = 'dt';
+ }
+ $x = "$fmt$#$to_parse\0";
}
- if (@orig) {
- $tg->index_text(join("\n", @orig));
- $tg->increase_termpos;
+ if ($pfx eq 'dt') {
+ for (@r) {
+ s/\0%Y%m%d/\0%Y%m%d%H%M%S/;
+ s/\A([0-9]{8})\z/${1}000000/;
+ }
}
- });
-
- if ($was_ghost) {
- $doc_id = $smsg->doc_id;
- $self->link_message($smsg, 0);
- $db->replace_document($doc_id, $doc);
+ }
+ } elsif ($pfx eq 'dt') {
+ if (!defined($r[1])) { # git needs gaps and not /\d{14}/
+ if ($r[0] =~ /\A([0-9]{4})([0-9]{2})([0-9]{2})
+ ([0-9]{2})([0-9]{2})([0-9]{2})\z/x) {
+ push @$to_parse, "$1-$2-$3 $4:$5:$6";
+ } else {
+ push @$to_parse, $r[0];
+ }
+ $r[0] = "\0%Y%m%d%H%M%S$#$to_parse\0";
+ $r[1] = "\0%Y%m%d%H%M%S+\0";
} else {
- $self->link_message($smsg, 0);
- $doc_id = $db->add_document($doc);
+ for my $x (@r) {
+ next if $x eq '' || $x =~ /\A[0-9]{14}\z/;
+ push @$to_parse, $x;
+ $x = "\0%Y%m%d%H%M%S$#$to_parse\0";
+ }
}
- };
-
- if ($@) {
- warn "failed to index message <$mid>: $@\n";
- $db->cancel_transaction;
- } else {
- $db->commit_transaction;
+ } else { # "rt", let git interpret "YYYY", deal with Y10K later :P
+ for my $x (@r) {
+ next if $x eq '' || $x =~ /\A[0-9]{5,}\z/;
+ push @$to_parse, $x;
+ $x = "\0%s$#$to_parse\0";
+ }
+ $r[1] //= "\0%s+\0"; # add 1 day
}
- $doc_id;
+ "$pfx:".join('..', @r).$end;
}
-# returns deleted doc_id on success, undef on missing
-sub remove_message {
- my ($self, $mid) = @_;
- my $db = $self->{xdb};
- my $doc_id;
- $mid = mid_clean($mid);
- $mid = mid_compressed($mid);
-
- $db->begin_transaction;
- eval {
- $doc_id = $self->find_unique_doc_id('mid', $mid);
- $db->delete_document($doc_id) if defined $doc_id;
- };
+sub date_parse_finalize {
+ my ($git, $to_parse) = @_;
+ # git-rev-parse can handle any number of args up to system
+ # limits (around (4096*32) bytes on Linux).
+ my @r = $git->date_parse(@$to_parse);
+ # n.b. git respects TZ, times stored in SQLite/Xapian are always UTC,
+ # and gmtime doesn't seem to do the right thing when TZ!=UTC
+ my ($i, $t);
+ $_[2] =~ s/\0(%[%YmdHMSs]+)([0-9\+]+)\0/
+ $t = $2 eq '+' ? ($r[$i]+86400) : $r[$i=$2+0];
+ $1 eq '%s' ? $t : strftime($1, gmtime($t))/sge;
+}
- if ($@) {
- warn "failed to remove message <$mid>: $@\n";
- $db->cancel_transaction;
- } else {
- $db->commit_transaction;
- }
- $doc_id;
+# n.b. argv never has NUL, though we'll need to filter it out
+# if this $argv isn't from a command execution
+sub query_argv_to_string {
+ my (undef, $git, $argv) = @_;
+ my $to_parse;
+ my $tmp = join(' ', map {;
+ if (s!\b(d|rt|dt):(\S+)\z!date_parse_prepare(
+ $to_parse //= [], $1, $2)!sge) {
+ $_;
+ } elsif (/\s/) {
+ s/(.*?)\b(\w+:)// ? qq{$1$2"$_"} : qq{"$_"};
+ } else {
+ $_
+ }
+ } @$argv);
+ date_parse_finalize($git, $to_parse, $tmp) if $to_parse;
+ $tmp
+}
+
+# this is for the WWW "q=" query parameter and "lei q --stdin"
+# it can't do d:"5 days ago", but it will do d:5.days.ago
+sub query_approxidate {
+ my (undef, $git) = @_; # $_[2] = $query_string (modified in-place)
+ my $DQ = qq<"\x{201c}\x{201d}>; # Xapian can use curly quotes
+ $_[2] =~ tr/\x00/ /; # Xapian doesn't do NUL, we use it as a placeholder
+ my ($terms, $phrase, $to_parse);
+ $_[2] =~ s{([^$DQ]*)([$DQ][^$DQ]*[$DQ])?}{
+ ($terms, $phrase) = ($1, $2);
+ $terms =~ s!\b(d|rt|dt):(\S+)!
+ date_parse_prepare($to_parse //= [], $1, $2)!sge;
+ $terms.($phrase // '');
+ }sge;
+ date_parse_finalize($git, $to_parse, $_[2]) if $to_parse;
}
# read-only
-sub query {
+sub mset {
my ($self, $query_string, $opts) = @_;
- my $query = $self->qp->parse_query($query_string, QP_FLAGS);
-
- $query = Search::Xapian::Query->new(OP_AND, $mail_query, $query);
- $self->do_enquire($query, $opts);
+ $opts ||= {};
+ my $qp = $self->{qp} //= $self->qparse_new;
+ my $query = $qp->parse_query($query_string, $self->{qp_flags});
+ _do_enquire($self, $query, $opts);
}
-# given a message ID, get replies to a message
-sub get_replies {
- my ($self, $mid, $opts) = @_;
- $mid = mid_clean($mid);
- $mid = mid_compressed($mid);
- my $qp = $self->qp;
- my $irt = $qp->parse_query("inreplyto:$mid", 0);
- my $ref = $qp->parse_query("references:$mid", 0);
- my $query = Search::Xapian::Query->new(OP_OR, $irt, $ref);
-
- $self->do_enquire($query);
+sub retry_reopen {
+ my ($self, $cb, @arg) = @_;
+ for my $i (1..10) {
+ if (wantarray) {
+ my @ret = eval { $cb->($self, @arg) };
+ return @ret unless $@;
+ } else {
+ my $ret = eval { $cb->($self, @arg) };
+ return $ret unless $@;
+ }
+ # Exception: The revision being read has been discarded -
+ # you should call Xapian::Database::reopen()
+ if (ref($@) =~ /\bDatabaseModifiedError\b/) {
+ reopen($self);
+ } else {
+ # let caller decide how to spew, because ExtMsg queries
+ # get wonky and trigger:
+ # "something terrible happened at .../Xapian/Enquire.pm"
+ Carp::croak($@);
+ }
+ }
+ Carp::croak("Too many Xapian database modifications in progress\n");
}
-sub get_thread {
- my ($self, $mid, $opts) = @_;
- my $smsg = eval { $self->lookup_message($mid) };
-
- return { count => 0, msgs => [] } unless $smsg;
- my $qp = $self->qp;
- my $qtid = $qp->parse_query('thread:'.$smsg->thread_id);
- my $qsub = $qp->parse_query('path:'.$smsg->path);
- my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub);
- $self->do_enquire($query);
+sub _do_enquire {
+ my ($self, $query, $opts) = @_;
+ retry_reopen($self, \&_enquire_once, $query, $opts);
}
-# private subs below
+# returns true if all docs have the THREADID value
+sub has_threadid ($) {
+ my ($self) = @_;
+ (xdb($self)->get_metadata('has_threadid') // '') eq '1';
+}
-sub do_enquire {
+sub _enquire_once { # retry_reopen callback
my ($self, $query, $opts) = @_;
- my $enquire = $self->enquire;
-
+ my $xdb = xdb($self);
+ if (defined(my $eidx_key = $opts->{eidx_key})) {
+ $query = $X{Query}->new(OP_FILTER(), $query, 'O'.$eidx_key);
+ }
+ if (defined(my $uid_range = $opts->{uid_range})) {
+ my $range = $X{Query}->new(OP_VALUE_RANGE(), UID,
+ sortable_serialise($uid_range->[0]),
+ sortable_serialise($uid_range->[1]));
+ $query = $X{Query}->new(OP_FILTER(), $query, $range);
+ }
+ my $enquire = $X{Enquire}->new($xdb);
$enquire->set_query($query);
- $enquire->set_sort_by_relevance_then_value(TS, 0);
$opts ||= {};
- my $offset = $opts->{offset} || 0;
- my $limit = $opts->{limit} || 50;
- my $mset = $enquire->get_mset($offset, $limit);
- my @msgs = map {
- PublicInbox::SearchMsg->load_doc($_->get_document);
- } $mset->items;
-
- { count => $mset->get_matches_estimated, msgs => \@msgs }
-}
-
-# read-write
-sub stemmer { Search::Xapian::Stem->new(LANG) }
-
-# read-only
-sub qp {
- my ($self) = @_;
-
- my $qp = $self->{query_parser};
- return $qp if $qp;
-
- # new parser
- $qp = Search::Xapian::QueryParser->new;
- $qp->set_default_op(OP_AND);
- $qp->set_database($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);
-
- while (my ($name, $prefix) = each %bool_pfx_external) {
- $qp->add_boolean_prefix($name, $prefix);
+ my $rel = $opts->{relevance} // 0;
+ if ($rel == -2) { # ORDER BY docid/UID (highest first)
+ $enquire->set_weighting_scheme($X{BoolWeight}->new);
+ $enquire->set_docid_order($ENQ_DESCENDING);
+ } elsif ($rel == -1) { # ORDER BY docid/UID (lowest first)
+ $enquire->set_weighting_scheme($X{BoolWeight}->new);
+ $enquire->set_docid_order($ENQ_ASCENDING);
+ } elsif ($rel == 0) {
+ $enquire->set_sort_by_value_then_relevance(TS, !$opts->{asc});
+ } else { # rel > 0
+ $enquire->set_sort_by_relevance_then_value(TS, !$opts->{asc});
}
- while (my ($name, $prefix) = each %prob_prefix) {
- $qp->add_prefix($name, $prefix);
+ # `mairix -t / --threads' or JMAP collapseThreads
+ if ($opts->{threads} && has_threadid($self)) {
+ $enquire->set_collapse_key(THREADID);
}
-
- $self->{query_parser} = $qp;
+ $enquire->get_mset($opts->{offset} || 0, $opts->{limit} || 50);
}
-sub term_generator { # write-only
- my ($self) = @_;
-
- my $tg = $self->{term_generator};
- return $tg if $tg;
-
- $tg = Search::Xapian::TermGenerator->new;
- $tg->set_stemmer($self->stemmer);
-
- $self->{term_generator} = $tg;
+sub mset_to_smsg {
+ my ($self, $ibx, $mset) = @_;
+ my $nshard = $self->{nshard};
+ my $i = 0;
+ my %order = map { mdocid($nshard, $_) => ++$i } $mset->items;
+ my @msgs = sort {
+ $order{$a->{num}} <=> $order{$b->{num}}
+ } @{$ibx->over->get_all(keys %order)};
+ wantarray ? ($mset->get_matches_estimated, \@msgs) : \@msgs;
}
-sub next_doc_id { $_[0]->{xdb}->get_lastdocid + 1 }
+# read-write
+sub stemmer { $X{Stem}->new($LANG) }
-# increments last_thread_id counter
-# returns a 64-bit integer represented as a hex string
-sub next_thread_id {
+# read-only
+sub qparse_new {
my ($self) = @_;
- my $db = $self->{xdb};
- my $last_thread_id = int($db->get_metadata('last_thread_id') || 0);
-
- $db->set_metadata('last_thread_id', ++$last_thread_id);
-
- $last_thread_id;
-}
-
-sub ts_range_processor {
- $_[0]->{tsrp} ||= Search::Xapian::NumberValueRangeProcessor->new(TS);
-}
-
-sub date_range_processor {
- $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS);
-}
-sub link_message {
- my ($self, $smsg, $is_ghost) = @_;
+ my $xdb = xdb($self);
+ my $qp = $X{QueryParser}->new;
+ $qp->set_default_op(OP_AND());
+ $qp->set_database($xdb);
+ $qp->set_stemmer(stemmer($self));
+ $qp->set_stemming_strategy(STEM_SOME());
+ my $cb = $qp->can('set_max_wildcard_expansion') //
+ $qp->can('set_max_expansion'); # Xapian 1.5.0+
+ $cb->($qp, 100);
+ $cb = $qp->can('add_valuerangeprocessor') //
+ $qp->can('add_rangeprocessor'); # Xapian 1.5.0+
+ $cb->($qp, $NVRP->new(YYYYMMDD, 'd:'));
+ $cb->($qp, $NVRP->new(DT, 'dt:'));
+
+ # for IMAP, undocumented for WWW and may be split off go away
+ $cb->($qp, $NVRP->new(BYTES, 'z:'));
+ $cb->($qp, $NVRP->new(TS, 'rt:'));
+ $cb->($qp, $NVRP->new(UID, 'uid:'));
- if ($is_ghost) {
- $smsg->ensure_metadata;
- } else {
- $self->link_message_to_parents($smsg);
+ while (my ($name, $prefix) = each %bool_pfx_external) {
+ $qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix);
}
-}
-sub link_message_to_parents {
- my ($self, $smsg) = @_;
- my $doc = $smsg->{doc};
- my $mid = mid_compressed($smsg->mid);
- my $mime = $smsg->mime;
- my $refs = $mime->header('References');
- my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
- my $irt = $mime->header('In-Reply-To');
- if ($irt) {
- if ($irt =~ /<([^>]+)>/) {
- $irt = $1;
+ # 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) {
+ # $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ # note: Xapian supports multibyte UTF-8, /^[0-9]+$/,
+ # and '_' with prefixes matching \w+
+ /\Aserial:(\w+):/ or next;
+ my $pfx = $1;
+ push @$user_pfx, "$pfx:", <<EOF;
+alternate serial number e.g. $pfx:12345 (boolean)
+EOF
+ # gmane => XGMANE
+ $qp->add_boolean_prefix($pfx, 'X'.uc($pfx));
}
- push @refs, $irt;
+ chomp @$user_pfx;
}
- my $tid;
- if (@refs) {
- @refs = map { mid_compressed($_) } @refs;
- my %uniq;
- @refs = grep { !$uniq{$_}++ } @refs; # uniq
-
- $doc->add_term(xpfx('inreplyto') . $refs[-1]);
-
- my $ref_pfx = xpfx('references');
-
- # first ref *should* be the thread root,
- # but we can never trust clients to do the right thing
- my $ref = shift @refs;
- $doc->add_term($ref_pfx . $ref);
- $tid = $self->_resolve_mid_to_tid($ref);
-
- # the rest of the refs should point to this tid:
- foreach $ref (@refs) {
- $doc->add_term($ref_pfx . $ref);
- my $ptid = $self->_resolve_mid_to_tid($ref);
- if ($tid ne $ptid) {
- $self->merge_threads($tid, $ptid);
- }
- }
- } else {
- $tid = $self->next_thread_id;
+ while (my ($name, $prefix) = each %prob_prefix) {
+ $qp->add_prefix($name, $_) foreach split(/ /, $prefix);
}
- $doc->add_term(xpfx('thread') . $tid);
+ $qp;
}
-sub lookup_message {
- my ($self, $mid) = @_;
- $mid = mid_clean($mid);
- $mid = mid_compressed($mid);
-
- my $doc_id = $self->find_unique_doc_id('mid', $mid);
- my $smsg;
- if (defined $doc_id) {
- # raises on error:
- my $doc = $self->{xdb}->get_document($doc_id);
- $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $smsg->doc_id($doc_id);
+sub help {
+ my ($self) = @_;
+ $self->{qp} //= $self->qparse_new; # parse altids
+ my @ret = @HELP;
+ if (my $user_pfx = $self->{-user_pfx}) {
+ push @ret, @$user_pfx;
}
- $smsg;
+ \@ret;
}
-sub find_unique_doc_id {
- my ($self, $term, $value) = @_;
-
- my ($begin, $end) = $self->find_doc_ids($term, $value);
-
- return undef if $begin->equal($end); # not found
-
- my $rv = $begin->get_docid;
-
- # sanity check
- $begin->inc;
- $begin->equal($end) or die "Term '$term:$value' is not unique\n";
- $rv;
+sub int_val ($$) {
+ my ($doc, $col) = @_;
+ my $val = $doc->get_value($col) or return; # undefined is '' in Xapian
+ sortable_unserialise($val) + 0; # PV => IV conversion
}
-# returns begin and end PostingIterator
-sub find_doc_ids {
- my ($self, $term, $value) = @_;
-
- $self->find_doc_ids_for_term(xpfx($term) . $value);
-}
-
-# returns begin and end PostingIterator
-sub find_doc_ids_for_term {
- my ($self, $term) = @_;
- my $db = $self->{xdb};
-
- ($db->postlist_begin($term), $db->postlist_end($term));
-}
-
-# this will create a ghost as necessary
-sub _resolve_mid_to_tid {
- my ($self, $mid) = @_;
-
- my $smsg = $self->lookup_message($mid) || $self->create_ghost($mid);
- $smsg->thread_id;
-}
-
-sub create_ghost {
- my ($self, $mid, $tid) = @_;
-
- $mid = mid_compressed($mid);
- $tid = $self->next_thread_id unless defined $tid;
-
- my $doc = Search::Xapian::Document->new;
- $doc->add_term(xpfx('mid') . $mid);
- $doc->add_term(xpfx('thread') . $tid);
- $doc->add_term(xpfx('type') . 'ghost');
-
- my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
- $self->link_message($smsg, 1);
- $self->{xdb}->add_document($doc);
-
- $smsg;
+sub get_pct ($) { # mset item
+ # Capped at "99%" since "100%" takes an extra column in the
+ # thread skeleton view. <xapian/mset.h> says the value isn't
+ # very meaningful, anyways.
+ my $n = $_[0]->get_percent;
+ $n > 99 ? 99 : $n;
}
-sub merge_threads {
- my ($self, $winner_tid, $loser_tid) = @_;
- my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
- my $thread_pfx = xpfx('thread');
- my $db = $self->{xdb};
-
- for (; $head != $tail; $head->inc) {
- my $docid = $head->get_docid;
- my $doc = $db->get_document($docid);
- $doc->remove_term($thread_pfx . $loser_tid);
- $doc->add_term($thread_pfx . $winner_tid);
- $db->replace_document($docid, $doc);
+sub xap_terms ($$;@) {
+ my ($pfx, $xdb_or_doc, @docid) = @_; # @docid may be empty ()
+ my %ret;
+ my $end = $xdb_or_doc->termlist_end(@docid);
+ my $cur = $xdb_or_doc->termlist_begin(@docid);
+ for (; $cur != $end; $cur++) {
+ $cur->skip_to($pfx);
+ last if $cur == $end;
+ my $tn = $cur->get_termname;
+ $ret{substr($tn, length($pfx))} = undef if !index($tn, $pfx);
}
+ wantarray ? sort(keys(%ret)) : \%ret;
}
-# normalize subjects so they are suitable as pathnames for URLs
-sub subject_path {
- my ($subj) = @_;
-
- $subj =~ s/\A\s+//;
- $subj =~ s/\s+\z//;
- $subj =~ s/^(?:re|aw):\s*//i; # remove reply prefix (aw: German)
- $subj =~ s![^a-zA-Z0-9_\.~/\-]+!_!g;
- $subj;
-}
-
-sub do_cat_mail {
- my ($git, $blob) = @_;
- my $mime = eval {
- my $str = $git->cat_file($blob);
- Email::MIME->new($str);
- };
- $@ ? undef : $mime;
-}
-
-sub index_blob {
- my ($self, $git, $blob) = @_;
- my $mime = do_cat_mail($git, $blob) or return;
- eval { $self->add_message($mime) };
- warn "W: index_blob $blob: $@\n" if $@;
-}
-
-sub unindex_blob {
- my ($self, $git, $blob) = @_;
- my $mime = do_cat_mail($git, $blob) or return;
- my $mid = $mime->header('Message-ID');
- eval { $self->remove_message($mid) } if defined $mid;
- warn "W: unindex_blob $blob: $@\n" if $@;
-}
-
-sub enquire {
- my ($self) = @_;
- $self->{enquire} ||= Search::Xapian::Enquire->new($self->{xdb});
-}
-
-# indexes all unindexed messages
-sub index_sync {
- my ($self, $git) = @_;
- my $db = $self->{xdb};
- my $latest = $db->get_metadata('last_commit');
- my $range = length $latest ? "$latest..HEAD" : 'HEAD';
- $latest = undef;
-
- my $hex = '[a-f0-9]';
- my $h40 = $hex .'{40}';
- my $addmsg = qr!^:000000 100644 \S+ ($h40) A\t${hex}{2}/${hex}{38}$!;
- my $delmsg = qr!^:100644 000000 ($h40) \S+ D\t${hex}{2}/${hex}{38}$!;
-
- # get indexed messages
- my @cmd = ('git', "--git-dir=$git->{git_dir}", "log",
- qw/--reverse --no-notes --no-color --raw -r --no-abbrev/,
- $range);
-
- my $pid = open(my $log, '-|', @cmd) or
- die('open` '.join(' ', @cmd) . " pipe failed: $!\n");
- my $last;
- while (my $line = <$log>) {
- if ($line =~ /$addmsg/o) {
- $self->index_blob($git, $1);
- } elsif ($line =~ /$delmsg/o) {
- $self->unindex_blob($git, $1);
- } elsif ($line =~ /^commit ($h40)/o) {
- my $commit = $1;
- if (defined $latest) {
- $db->set_metadata('last_commit', $latest)
- }
- $latest = $commit;
- }
- }
- close $log;
- $db->set_metadata('last_commit', $latest) if defined $latest;
+# get combined docid from over.num:
+# (not generic Xapian, only works with our sharding scheme)
+sub num2docid ($$) {
+ my ($self, $num) = @_;
+ my $nshard = $self->{nshard};
+ ($num - 1) * $nshard + $num % $nshard + 1;
}
1;