-# Copyright (C) 2015-2020 all contributors <meta@public-inbox.org>
+# 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
#
package PublicInbox::Search;
use strict;
use parent qw(Exporter);
-our @EXPORT_OK = qw(retry_reopen int_val);
+our @EXPORT_OK = qw(retry_reopen int_val get_pct xap_terms);
use List::Util qw(max);
+use POSIX qw(strftime);
# values for searching, changing the numeric value breaks
# compatibility with old indices (so don't change them it)
}
}
-sub xdb_sharded {
+# returns all shards as separate Xapian::Database objects w/o combining
+sub xdb_shards_flat ($) {
my ($self) = @_;
- opendir(my $dh, $self->{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;
+ my $xpfx = $self->{xpfx};
my (@xdb, $slow_phrase);
- for (0..$last) {
- my $shard_dir = "$self->{xpfx}/$_";
- if (-d $shard_dir && -r _) {
+ load_xapian();
+ $self->{qp_flags} //= $QP_FLAGS;
+ if ($xpfx =~ m/xapian${\SCHEMA_VERSION}\z/) {
+ @xdb = ($X{Database}->new($xpfx));
+ $self->{qp_flags} |= FLAG_PHRASE() if !-f "$xpfx/iamchert";
+ } else {
+ 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";
- } else { # gaps from missing epochs throw off mdocid()
- warn "E: $shard_dir missing or unreadable\n";
- return;
}
+ $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
}
- $self->{qp_flags} |= FLAG_PHRASE() if !$slow_phrase;
- $self->{nshard} = scalar(@xdb);
- my $xdb = shift @xdb;
- $xdb->add_database($_) for @xdb;
- $xdb;
-}
-
-sub _xdb {
- my ($self) = @_;
- my $dir = xdir($self, 1);
- $self->{qp_flags} //= $QP_FLAGS;
- if ($self->{ibx_ver} >= 2) {
- xdb_sharded($self);
- } else {
- $self->{qp_flags} |= FLAG_PHRASE() if !-f "$dir/iamchert";
- $X{Database}->new($dir);
- }
+ @xdb;
}
# v2 Xapian docids don't conflict, so they're identical to
sub mset_to_artnums {
my ($self, $mset) = @_;
- my $nshard = $self->{nshard} // 1;
+ my $nshard = $self->{nshard};
[ map { mdocid($nshard, $_) } $mset->items ];
}
sub xdb ($) {
my ($self) = @_;
$self->{xdb} //= do {
- load_xapian();
- $self->_xdb;
+ my @xdb = $self->xdb_shards_flat or return;
+ $self->{nshard} = scalar(@xdb);
+ my $xdb = shift @xdb;
+ $xdb->add_database($_) for @xdb;
+ $xdb;
};
}
-sub xpfx_init ($) {
- my ($self) = @_;
- if ($self->{ibx_ver} == 1) {
- $self->{xpfx} .= '/public-inbox/xapian' . SCHEMA_VERSION;
- } else {
- $self->{xpfx} .= '/xap'.SCHEMA_VERSION;
- }
-}
-
sub new {
my ($class, $ibx) = @_;
ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
- my $self = bless {
- xpfx => $ibx->{inboxdir}, # for xpfx_init
+ my $xap = $ibx->version > 1 ? 'xap' : 'public-inbox/xapian';
+ bless {
+ xpfx => "$ibx->{inboxdir}/$xap" . SCHEMA_VERSION,
altid => $ibx->{altid},
- ibx_ver => $ibx->version,
}, $class;
- xpfx_init($self);
- $self;
}
sub reopen {
$self; # make chaining easier
}
+# Convert git "approxidate" ranges to something usable with our
+# Xapian indices. At the moment, Xapian only offers a C++-only API
+# and neither the SWIG nor XS bindings allow us to use custom code
+# to parse dates (and libgit2 doesn't expose git__date_parse, either,
+# so we're running git-rev-parse(1)).
+sub date_range {
+ my ($git, $pfx, $range) = @_;
+ # are we inside a parenthesized statement?
+ my $end = $range =~ s/([\)\s]*)\z// ? $1 : '';
+ my @r = split(/\.\./, $range, 2);
+
+ # expand "d:20101002" => "d:20101002..20101003" and like
+ # n.b. git doesn't do YYYYMMDD w/o '-', it needs YYYY-MM-DD
+ if ($pfx eq 'd') {
+ if (!defined($r[1])) {
+ $r[0] =~ s/\A([0-9]{4})([0-9]{2})([0-9]{2})\z/$1-$2-$3/;
+ $r[0] = $git->date_parse($r[0]);
+ $r[1] = $r[0] + 86400;
+ for my $x (@r) {
+ $x = strftime('%Y%m%d', gmtime($x));
+ }
+ } else {
+ for my $x (@r) {
+ next if $x eq '' || $x =~ /\A[0-9]{8}\z/;
+ $x = strftime('%Y%m%d',
+ gmtime($git->date_parse($x)));
+ }
+ }
+ } elsif ($pfx eq 'dt') {
+ if (!defined($r[1])) { # git needs gaps and not /\d{14}/
+ $r[0] =~ s/\A([0-9]{4})([0-9]{2})([0-9]{2})
+ ([0-9]{2})([0-9]{2})([0-9]{2})\z
+ /$1-$2-$3 $4:$5:$6/x;
+ $r[0] = $git->date_parse($r[0]);
+ $r[1] = $r[0] + 86400;
+ for my $x (@r) {
+ $x = strftime('%Y%m%d%H%M%S', gmtime($x));
+ }
+ } else {
+ for my $x (@r) {
+ next if $x eq '' || $x =~ /\A[0-9]{14}\z/;
+ $x = strftime('%Y%m%d%H%M%S',
+ gmtime($git->date_parse($x)));
+ }
+ }
+ } 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/;
+ $x = $git->date_parse($x);
+ }
+ $r[1] //= $r[0] + 86400;
+ }
+ "$pfx:".join('..', @r).$end;
+}
+
+sub query_argv_to_string {
+ my (undef, $git, $argv) = @_;
+ join(' ', map {;
+ if (s!\b(d|rt|dt):(.+)\z!date_range($git, $1, $2)!sge) {
+ $_;
+ } else {
+ /\s/ ? (s/\A(\w+:)// ? qq{$1"$_"} : qq{"$_}) : $_
+ }
+ } @$argv);
+}
+
# read-only
sub mset {
my ($self, $query_string, $opts) = @_;
}
# `mairix -t / --threads' or JMAP collapseThreads
- if ($opts->{thread} && has_threadid($self)) {
+ if ($opts->{threads} && has_threadid($self)) {
$enquire->set_collapse_key(THREADID);
}
$enquire->get_mset($opts->{offset} || 0, $opts->{limit} || 50);
sub mset_to_smsg {
my ($self, $ibx, $mset) = @_;
- my $nshard = $self->{nshard} // 1;
+ my $nshard = $self->{nshard};
my $i = 0;
my %order = map { mdocid($nshard, $_) => ++$i } $mset->items;
my @msgs = sort {
# for IMAP, undocumented for WWW and may be split off go away
$cb->($qp, $NVRP->new(BYTES, 'bytes:'));
- $cb->($qp, $NVRP->new(TS, 'ts:'));
+ $cb->($qp, $NVRP->new(TS, 'rt:'));
$cb->($qp, $NVRP->new(UID, 'uid:'));
while (my ($name, $prefix) = each %bool_pfx_external) {
sortable_unserialise($val) + 0; # PV => IV conversion
}
+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 xap_terms ($$;@) {
+ my ($pfx, $xdb_or_doc, @docid) = @_; # @docid may be empty ()
+ my %ret;
+ eval {
+ 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 = $cur->get_termname;
+ if (index($tn, $pfx) == 0) {
+ $ret{substr($tn, length($pfx))} = undef;
+ }
+ }
+ };
+ \%ret;
+}
+
1;