X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=7175ddc5a2e06c078ef10f1d7875e3eebd62d709;hp=810eab85adefdaa6780e99bb6b0b297f5bd2cd7d;hb=fad9acd35e56a289ade90a62d056b2a6663d448c;hpb=761736a312a103ba522abac52a604564f9e788ce diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index 810eab85..7175ddc5 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -1,14 +1,22 @@ -# Copyright (C) 2015 all contributors -# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# Copyright (C) 2015-2018 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 constant TS => 0; + +# 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 + use Search::Xapian qw/:standard/; use PublicInbox::SearchMsg; -use Email::MIME; -use PublicInbox::MID qw/mid_clean mid_compress/; +use PublicInbox::MIME; +use PublicInbox::MID qw/id_compress/; +use PublicInbox::Over; # This is English-only, everything else is non-standard and may be confused as # a prefix common in patch emails @@ -19,108 +27,207 @@ use constant { # 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 # 8 - remove redundant/unneeded document data - # 9 - disable Message-ID compression - SCHEMA_VERSION => 9, + # 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 + SCHEMA_VERSION => 15, # 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" - thread => 'G', # newsGroup (or similar entity - e.g. a web forum name) -); - my %bool_pfx_external = ( - path => 'XPATH', - mid => 'Q', # uniQue id (Message-ID) + mid => 'Q', # Message-ID (full/exact), this is mostly uniQue ); +my $non_quoted_body = 'XNQ XDFN XDFA XDFB XDFHH XDFCTX XDFPRE XDFPOST'; my %prob_prefix = ( - subject => 'S', - s => 'S', # for mairix compatibility - m => 'Q', # 'mid' is exact, 'm' can do partial + # for mairix compatibility + s => 'S', + m => 'XM', # '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 => $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', + dfpre => 'XDFPRE', + dfpost => 'XDFPOST', + dfblob => 'XDFPRE XDFPOST', + + # 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; -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'); +# 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', + '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', +); +chomp @HELP; sub xdir { - my (undef, $git_dir) = @_; - "$git_dir/public-inbox/xapian" . SCHEMA_VERSION; + my ($self) = @_; + if ($self->{version} == 1) { + "$self->{mainrepo}/public-inbox/xapian" . SCHEMA_VERSION; + } else { + my $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION; + my $part = $self->{partition}; + defined $part or die "partition not given"; + $dir .= "/$part"; + } } sub new { - my ($class, $git_dir) = @_; - my $dir = $class->xdir($git_dir); - my $db = Search::Xapian::Database->new($dir); - bless { xdb => $db, git_dir => $git_dir }, $class; + my ($class, $mainrepo, $altid) = @_; + my $version = 1; + my $ibx = $mainrepo; + if (ref $ibx) { + $version = $ibx->{version} || 1; + $mainrepo = $ibx->{mainrepo}; + } + my $self = bless { + mainrepo => $mainrepo, + altid => $altid, + version => $version, + }, $class; + my $dir; + if ($version >= 2) { + $dir = "$self->{mainrepo}/xap" . SCHEMA_VERSION; + my $xdb; + my $parts = 0; + foreach my $part (<$dir/*>) { + -d $part && $part =~ m!/\d+\z! or next; + $parts++; + my $sub = Search::Xapian::Database->new($part); + if ($xdb) { + $xdb->add_database($sub); + } else { + $xdb = $sub; + } + } + $self->{xdb} = $xdb; + } else { + $dir = $self->xdir; + $self->{xdb} = Search::Xapian::Database->new($dir); + } + $self->{over_ro} = PublicInbox::Over->new("$dir/over.sqlite3"); + $self; } -sub reopen { $_[0]->{xdb}->reopen } +sub reopen { + my ($self) = @_; + $self->{xdb}->reopen; + $self; # make chaining easier +} # read-only sub query { my ($self, $query_string, $opts) = @_; - my $query; - $opts ||= {}; - unless ($query_string eq '') { - $query = $self->qp->parse_query($query_string, QP_FLAGS); + if ($query_string eq '' && !$opts->{mset}) { + $self->{over_ro}->recent($opts); + } else { + my $query = $self->qp->parse_query($query_string, QP_FLAGS); $opts->{relevance} = 1 unless exists $opts->{relevance}; + _do_enquire($self, $query, $opts); } +} - $self->do_enquire($query, $opts); +sub get_thread { + my ($self, $mid, $prev) = @_; + $self->{over_ro}->get_thread($mid, $prev); } -sub get_subject_path { - my ($self, $path, $opts) = @_; - my $q = Search::Xapian::Query->new(xpfx("path").mid_compress($path)); - $self->do_enquire($q, $opts); +sub retry_reopen { + my ($self, $cb) = @_; + for my $i (1..10) { + if (wantarray) { + my @ret; + eval { @ret = $cb->() }; + return @ret unless $@; + } else { + my $ret; + 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') { + warn "reopen try #$i on $@\n"; + reopen($self); + } else { + warn "ref: ", ref($@), "\n"; + die; + } + } + die "Too many Xapian database modifications in progress\n"; } -sub get_thread { - my ($self, $mid, $opts) = @_; - my $smsg = eval { $self->lookup_message($mid) }; - - return { total => 0, msgs => [] } unless $smsg; - my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id); - my $path = mid_compress($smsg->path); - my $qsub = Search::Xapian::Query->new(xpfx('path').$path); - my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub); - $self->do_enquire($query, $opts); +sub _do_enquire { + my ($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; - if (defined $query) { - $query = Search::Xapian::Query->new(OP_AND,$query,$mail_query); - } else { - $query = $mail_query; - } + my $enquire = enquire($self); $enquire->set_query($query); $opts ||= {}; my $desc = !$opts->{asc}; - if ($opts->{relevance}) { + if (($opts->{mset} || 0) == 2) { + $enquire->set_docid_order(Search::Xapian::ENQ_ASCENDING()); + $enquire->set_weighting_scheme(Search::Xapian::BoolWeight->new); + delete $self->{enquire}; + } elsif ($opts->{relevance}) { $enquire->set_sort_by_relevance_then_value(TS, $desc); } else { $enquire->set_sort_by_value_then_relevance(TS, $desc); @@ -132,8 +239,9 @@ sub do_enquire { my @msgs = map { PublicInbox::SearchMsg->load_doc($_->get_document); } $mset->items; + return \@msgs unless wantarray; - { total => $mset->get_matches_estimated, msgs => \@msgs } + ($mset->get_matches_estimated, \@msgs) } # read-write @@ -152,74 +260,62 @@ 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:')); + $qp->add_valuerangeprocessor( + Search::Xapian::NumberValueRangeProcessor->new(DT, 'dt:')); while (my ($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 date_range_processor { - $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS); +# only used for NNTP server +sub query_xover { + my ($self, $beg, $end, $offset) = @_; + $self->{over_ro}->query_xover($beg, $end, $offset); } -sub lookup_message { - my ($self, $mid) = @_; - $mid = mid_clean($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); - } - $smsg; -} - -sub find_unique_doc_id { - my ($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"; - $rv; +sub query_ts { + my ($self, $ts, $prev) = @_; + $self->{over_ro}->query_ts($ts, $prev); } -# returns begin and end PostingIterator -sub find_doc_ids { - my ($self, $term, $value) = @_; - - $self->find_doc_ids_for_term(xpfx($term) . $value); +sub lookup_article { + my ($self, $num) = @_; + $self->{over_ro}->get_art($num); } -# 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)); +sub next_by_mid { + my ($self, $mid, $id, $prev) = @_; + $self->{over_ro}->next_by_mid($mid, $id, $prev); } # normalize subjects so they are suitable as pathnames for URLs +# XXX: consider for removal sub subject_path { my $subj = pop; $subj = subject_normalized($subj); @@ -237,35 +333,19 @@ 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;