X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FSearch.pm;h=bc2b69854a8765add7c4956f0f7a3c23d9edf0a0;hp=856c8c144c8ea1afcb4d0cae2a736ffad4e955ef;hb=de243560e2caa1d19bcbf518edfaf8b016161245;hpb=748ae0cdc29f05fdd76389b651287c5abc60ad8c diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm index 856c8c14..bc2b6985 100644 --- a/lib/PublicInbox/Search.pm +++ b/lib/PublicInbox/Search.pm @@ -12,10 +12,11 @@ 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 PublicInbox::SearchMsg; -use Email::MIME; +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 @@ -36,7 +37,11 @@ use constant { # 8 - remove redundant/unneeded document data # 9 - disable Message-ID compression (SHA-1) # 10 - optimize doc for NNTP overviews - SCHEMA_VERSION => 10, + # 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 @@ -50,26 +55,61 @@ my %bool_pfx_internal = ( ); my %bool_pfx_external = ( + # do we still need these? probably not.. path => 'XPATH', mid => 'Q', # uniQue id (Message-ID) ); 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 => '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 $mail_query = Search::Xapian::Query->new(xpfx('type') . 'mail'); sub xdir { @@ -78,10 +118,10 @@ sub xdir { } sub new { - my ($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 } @@ -106,30 +146,43 @@ sub get_thread { return { total => 0, msgs => [] } unless $smsg; my $qtid = Search::Xapian::Query->new(xpfx('thread').$smsg->thread_id); - my $path = id_compress($smsg->path); - my $qsub = Search::Xapian::Query->new(xpfx('path').$path); - my $query = Search::Xapian::Query->new(OP_OR, $qtid, $qsub); + 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 ||= {}; $opts->{limit} ||= 1000; - _do_enquire($self, $query, $opts); + + # always sort threads by timestamp, this makes life easier + # for the threading algorithm (in SearchThread.pm) + $opts->{asc} = 1; + + _do_enquire($self, $qtid, $opts); } -sub _do_enquire { - my ($self, $query, $opts) = @_; +sub retry_reopen { + my ($self, $cb) = @_; my $ret; for (1..10) { - eval { $ret = _enquire_once($self, $query, $opts) }; + eval { $ret = $cb->() }; return $ret unless $@; # Exception: The revision being read has been discarded - # you should call Xapian::Database::reopen() - if (index($@, 'Xapian::Database::reopen') >= 0) { + if (ref($@) eq 'Search::Xapian::DatabaseModifiedError') { reopen($self); } else { - die $@; + die; } } } +sub _do_enquire { + my ($self, $query, $opts) = @_; + retry_reopen($self, sub { _enquire_once($self, $query, $opts) }); +} + sub _enquire_once { my ($self, $query, $opts) = @_; my $enquire = $self->enquire; @@ -175,28 +228,37 @@ 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 date_range_processor { - $_[0]->{drp} ||= Search::Xapian::DateValueRangeProcessor->new(TS); -} - sub num_range_processor { $_[0]->{nrp} ||= Search::Xapian::NumberValueRangeProcessor->new(NUM); } @@ -222,11 +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) = @_; @@ -258,6 +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); @@ -275,35 +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;