X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=547b6fbe32ac540c8eecc4e1fc386d32111df7f7;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=a4491ca1f1743484ba138db4f895f8c2e23ad147;hpb=7c5ac90b309bbe76468055e8a9289664ef2dfe37;p=public-inbox.git diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index a4491ca1..547b6fbe 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -1,44 +1,95 @@ -# Copyright (C) 2015-2019 all contributors +# Copyright (C) 2015-2021 all contributors # License: AGPL-3.0+ # 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 parent qw(Exporter); +our @EXPORT_OK = qw(retry_reopen int_val); +use List::Util qw(max); -# values for searching -use constant TS => 0; # Received: header in Unix time -use constant YYYYMMDD => 1; # Date: header for searching in the WWW UI -use constant DT => 2; # Date: YYYYMMDDHHMMSS +# values for searching, changing the numeric value breaks +# compatibility with old indices (so don't change them it) +use constant { + TS => 0, # Received: header in Unix time (IMAP INTERNALDATE) + YYYYMMDD => 1, # Date: header for searching in the WWW UI + DT => 2, # Date: YYYYMMDDHHMMSS + + # 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, +}; -use PublicInbox::SearchMsg; +use PublicInbox::Smsg; use PublicInbox::Over; -my $QP_FLAGS; -our %X = map { $_ => 0 } qw(BoolWeight Database Enquire - NumberValueRangeProcessor QueryParser Stem); +our $QP_FLAGS; +our %X = map { $_ => 0 } qw(BoolWeight Database Enquire QueryParser Stem Query); our $Xap; # 'Search::Xapian' or 'Xapian' -my $ENQ_ASCENDING; +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; - for my $x (qw(Search::Xapian Xapian)) { + # 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; - $X{$_} = $Xap.'::'.$_ for (keys %X); - # ENQ_ASCENDING doesn't seem exported by SWIG Xapian.pm, - # so lets hope this part of the ABI is stable because it's - # just an integer: - $ENQ_ASCENDING = $x eq 'Xapian' ? - 1 : Search::Xapian::ENQ_ASCENDING(); + # `version_string' was added in Xapian 1.1 + my $xver = eval('v'.eval($x.'::version_string()')) // + eval('v'.eval($x.'::xapian_version_string()')); - # for SearchMsg: - *PublicInbox::SearchMsg::sortable_unserialise = - $Xap.'::sortable_unserialise'; + # 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 @@ -56,32 +107,11 @@ sub load_xapian () { # a prefix common in patch emails our $LANG = 'english'; -use constant { - # 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 - SCHEMA_VERSION => 15, -}; - +# note: the non-X term prefix allocations are shared with +# Xapian omega, see xapian-applications/omega/docs/termprefixes.rst my %bool_pfx_external = ( 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', @@ -92,6 +122,7 @@ my %prob_prefix = ( # 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', @@ -115,6 +146,9 @@ my %prob_prefix = ( ); # 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:' => < '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', @@ -148,61 +183,72 @@ chomp @HELP; sub xdir ($;$) { my ($self, $rdonly) = @_; - if ($self->{ibx_ver} == 1) { - "$self->{inboxdir}/public-inbox/xapian" . SCHEMA_VERSION; - } else { - my $dir = "$self->{inboxdir}/xap" . SCHEMA_VERSION; - return $dir if $rdonly; - - my $shard = $self->{shard}; - defined $shard or die "shard not given"; - $dir .= "/$shard"; + if ($rdonly || !defined($self->{shard})) { + $self->{xpfx}; + } else { # v2 only: + "$self->{xpfx}/$self->{shard}"; } } -sub _xdb ($) { +# returns all shards as separate Xapian::Database objects w/o combining +sub xdb_shards_flat ($) { my ($self) = @_; - my $dir = xdir($self, 1); - my ($xdb, $slow_phrase); - my $qpf = \($self->{qp_flags} ||= $QP_FLAGS); - if ($self->{ibx_ver} >= 2) { - foreach my $shard (<$dir/*>) { - -d $shard && $shard =~ m!/[0-9]+\z! or next; - my $sub = $X{Database}->new($shard); - if ($xdb) { - $xdb->add_database($sub); - } else { - $xdb = $sub; - } - $slow_phrase ||= -f "$shard/iamchert"; - } + my $xpfx = $self->{xpfx}; + my (@xdb, $slow_phrase); + load_xapian(); + if ($xpfx =~ m/xapian${\SCHEMA_VERSION}\z/) { + @xdb = ($X{Database}->new($xpfx)); + $self->{qp_flags} |= FLAG_PHRASE() if !-f "$xpfx/iamchert"; } else { - $slow_phrase = -f "$dir/iamchert"; - $xdb = $X{Database}->new($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; } - $$qpf |= FLAG_PHRASE() unless $slow_phrase; - $xdb; + @xdb; +} + +# 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; +} + +sub mset_to_artnums { + my ($self, $mset) = @_; + my $nshard = $self->{nshard}; + [ map { mdocid($nshard, $_) } $mset->items ]; } sub xdb ($) { my ($self) = @_; - $self->{xdb} ||= do { - load_xapian(); - _xdb($self); + $self->{xdb} //= do { + $self->{qp_flags} //= $QP_FLAGS; + my @xdb = $self->xdb_shards_flat or return; + $self->{nshard} = scalar(@xdb); + my $xdb = shift @xdb; + $xdb->add_database($_) for @xdb; + $xdb; }; } sub new { my ($class, $ibx) = @_; ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx"; - my $self = bless { - inboxdir => $ibx->{inboxdir}, + my $xap = $ibx->version > 1 ? 'xap' : 'public-inbox/xapian'; + bless { + xpfx => "$ibx->{inboxdir}/$xap" . SCHEMA_VERSION, altid => $ibx->{altid}, - ibx_ver => $ibx->version, }, $class; - my $dir = xdir($self, 1); - $self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3"); - $self; } sub reopen { @@ -214,30 +260,24 @@ sub reopen { } # read-only -sub query { +sub mset { my ($self, $query_string, $opts) = @_; $opts ||= {}; - if ($query_string eq '' && !$opts->{mset}) { - $self->{over_ro}->recent($opts); - } else { - my $qp = qp($self); - my $qp_flags = $self->{qp_flags}; - my $query = $qp->parse_query($query_string, $qp_flags); - $opts->{relevance} = 1 unless exists $opts->{relevance}; - _do_enquire($self, $query, $opts); - } + my $qp = $self->{qp} //= qparse_new($self); + my $query = $qp->parse_query($query_string, $self->{qp_flags}); + _do_enquire($self, $query, $opts); } sub retry_reopen { - my ($self, $cb, $arg) = @_; + my ($self, $cb, @arg) = @_; for my $i (1..10) { if (wantarray) { my @ret; - eval { @ret = $cb->($arg) }; + eval { @ret = $cb->($self, @arg) }; return @ret unless $@; } else { my $ret; - eval { $ret = $cb->($arg) }; + eval { $ret = $cb->($self, @arg) }; return $ret unless $@; } # Exception: The revision being read has been discarded - @@ -257,54 +297,87 @@ sub retry_reopen { sub _do_enquire { my ($self, $query, $opts) = @_; - retry_reopen($self, \&_enquire_once, [ $self, $query, $opts ]); + retry_reopen($self, \&_enquire_once, $query, $opts); +} + +# returns true if all docs have the THREADID value +sub has_threadid ($) { + my ($self) = @_; + (xdb($self)->get_metadata('has_threadid') // '') eq '1'; } sub _enquire_once { # retry_reopen callback - my ($self, $query, $opts) = @{$_[0]}; + my ($self, $query, $opts) = @_; 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); $opts ||= {}; my $desc = !$opts->{asc}; - if (($opts->{mset} || 0) == 2) { + my $rel = $opts->{relevance} // 0; + if ($rel == -1) { # ORDER BY docid/UID + $enquire->set_weighting_scheme($X{BoolWeight}->new); $enquire->set_docid_order($ENQ_ASCENDING); + } elsif ($rel == 0) { + $enquire->set_sort_by_value_then_relevance(TS, $desc); + } elsif ($rel == -2) { $enquire->set_weighting_scheme($X{BoolWeight}->new); - } elsif ($opts->{relevance}) { + $enquire->set_docid_order($ENQ_DESCENDING); + } else { # rel > 0 $enquire->set_sort_by_relevance_then_value(TS, $desc); - } else { - $enquire->set_sort_by_value_then_relevance(TS, $desc); } - 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::from_mitem($_) } $mset->items; - return \@msgs unless wantarray; - - ($mset->get_matches_estimated, \@msgs) + + # `mairix -t / --threads' or JMAP collapseThreads + if ($opts->{thread} && 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}; + 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; } # read-write sub stemmer { $X{Stem}->new($LANG) } # read-only -sub qp { +sub qparse_new ($) { my ($self) = @_; - my $qp = $self->{query_parser}; - return $qp if $qp; my $xdb = xdb($self); - # new parser - $qp = $X{QueryParser}->new; + my $qp = $X{QueryParser}->new; $qp->set_default_op(OP_AND()); $qp->set_database($xdb); - $qp->set_stemmer($self->stemmer); + $qp->set_stemmer(stemmer($self)); $qp->set_stemming_strategy(STEM_SOME()); - $qp->set_max_wildcard_expansion(100); - my $nvrp = $X{NumberValueRangeProcessor}; - $qp->add_valuerangeprocessor($nvrp->new(YYYYMMDD, 'd:')); - $qp->add_valuerangeprocessor($nvrp->new(DT, 'dt:')); + 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, 'bytes:')); + $cb->($qp, $NVRP->new(TS, 'ts:')); + $cb->($qp, $NVRP->new(UID, 'uid:')); while (my ($name, $prefix) = each %bool_pfx_external) { $qp->add_boolean_prefix($name, $_) foreach split(/ /, $prefix); @@ -313,9 +386,11 @@ sub qp { # 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} ||= []; + 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:", <add_prefix($name, $_) foreach split(/ /, $prefix); } - - $self->{query_parser} = $qp; + $qp; } sub help { my ($self) = @_; - $self->qp; # parse altids + $self->{qp} //= qparse_new($self); # parse altids my @ret = @HELP; if (my $user_pfx = $self->{-user_pfx}) { push @ret, @$user_pfx; @@ -344,4 +418,10 @@ sub help { \@ret; } +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 +} + 1;