X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchMsg.pm;h=6c0780e5906424f845bafd2e3f14ed09e849e620;hb=35ff6bb106909b1c1232666a9792156dfa398ea8;hp=4c65fbe01a20fb15f36d10b3d1b3dd0cc85c6896;hpb=5f3046879e1aa713e95b46795fc49c9f83923750;p=public-inbox.git diff --git a/lib/PublicInbox/SearchMsg.pm b/lib/PublicInbox/SearchMsg.pm index 4c65fbe0..6c0780e5 100644 --- a/lib/PublicInbox/SearchMsg.pm +++ b/lib/PublicInbox/SearchMsg.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2016 all contributors +# Copyright (C) 2015-2018 all contributors # License: AGPL-3.0+ # based on notmuch, but with no concept of folders, files or flags # @@ -6,18 +6,14 @@ package PublicInbox::SearchMsg; use strict; use warnings; -use Search::Xapian; -use Date::Parse qw/str2time/; -use PublicInbox::MID qw/mid_clean/; +use PublicInbox::MID qw/mid_clean mid_mime/; use PublicInbox::Address; -our $PFX2TERM_RE = undef; +use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); sub new { my ($class, $mime) = @_; my $doc = Search::Xapian::Document->new; - $doc->add_term(PublicInbox::Search::xpfx('type') . 'mail'); - - bless { type => 'mail', doc => $doc, mime => $mime }, $class; + bless { doc => $doc, mime => $mime }, $class; } sub wrap { @@ -25,33 +21,76 @@ sub wrap { bless { doc => $doc, mime => undef, mid => $mid }, $class; } +sub get { + my ($class, $head, $db, $mid) = @_; + my $doc_id = $head->get_docid; + my $doc = $db->get_document($doc_id); + load_expand(wrap($class, $doc, $mid)) +} + sub get_val ($$) { my ($doc, $col) = @_; Search::Xapian::sortable_unserialise($doc->get_value($col)); } -sub load_doc { - my ($class, $doc) = @_; +sub to_doc_data { + my ($self, $oid, $mid0) = @_; + $oid = '' unless defined $oid; + join("\n", + $self->subject, + $self->from, + $self->references, + $self->to, + $self->cc, + $oid, + $mid0, + $self->ds, + $self->{bytes}, + $self->{lines} + ); +} + + +sub load_from_data ($$) { + my ($self) = $_[0]; # data = $_[1] + ( + $self->{subject}, + $self->{from}, + $self->{references}, + + # To: and Cc: are stored to optimize HDR/XHDR in NNTP since + # some NNTP clients will use that for message displays. + $self->{to}, + $self->{cc}, + + $self->{blob}, + $self->{mid}, + $self->{ds}, + $self->{bytes}, + $self->{lines} + ) = split(/\n/, $_[1]); +} + +sub load_expand { + my ($self) = @_; + my $doc = $self->{doc}; my $data = $doc->get_data or return; - my $ts = get_val($doc, &PublicInbox::Search::TS); + $self->{ts} = get_val($doc, &PublicInbox::Search::TS); utf8::decode($data); - my ($subj, $from, $refs, $to, $cc, $blob) = split(/\n/, $data); - bless { - doc => $doc, - subject => $subj, - ts => $ts, - from => $from, - references => $refs, - to => $to, - cc => $cc, - blob => $blob, - }, $class; + load_from_data($self, $data); + $self; +} + +sub load_doc { + my ($class, $doc) = @_; + my $self = bless { doc => $doc }, $class; + $self->load_expand; } # :bytes and :lines metadata in RFC 3977 -sub bytes ($) { get_val($_[0]->{doc}, &PublicInbox::Search::BYTES) } -sub lines ($) { get_val($_[0]->{doc}, &PublicInbox::Search::LINES) } -sub num ($) { get_val($_[0]->{doc}, &PublicInbox::Search::NUM) } +sub bytes ($) { $_[0]->{bytes} } +sub lines ($) { $_[0]->{lines} } +sub num ($) { $_[0]->{num} ||= _get_term_val($_[0], 'XNUM', qr/\AXNUM/) } sub __hdr ($$) { my ($self, $field) = @_; @@ -70,19 +109,16 @@ sub subject ($) { __hdr($_[0], 'subject') } sub to ($) { __hdr($_[0], 'to') } sub cc ($) { __hdr($_[0], 'cc') } -# no strftime, that is locale-dependent +# no strftime, that is locale-dependent and not for RFC822 my @DoW = qw(Sun Mon Tue Wed Thu Fri Sat); my @MoY = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec); sub date ($) { my ($self) = @_; - my $date = __hdr($self, 'date'); - return $date if defined $date; - my $ts = $self->{ts}; - return unless defined $ts; - my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ts); - $self->{date} = "$DoW[$wday], ". - sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000", + my $ds = $self->{ds}; + return unless defined $ds; + my ($sec, $min, $hour, $mday, $mon, $year, $wday) = gmtime($ds); + "$DoW[$wday], " . sprintf("%02d $MoY[$mon] %04d %02d:%02d:%02d +0000", $mday, $year+1900, $hour, $min, $sec); } @@ -107,15 +143,12 @@ sub from_name { sub ts { my ($self) = @_; - $self->{ts} ||= eval { str2time($self->mime->header('Date')) } || 0; + $self->{ts} ||= eval { msg_timestamp($self->{mime}->header_obj) } || 0; } -sub to_doc_data { - my ($self, $blob) = @_; - my @rows = ($self->subject, $self->from, $self->references, - $self->to, $self->cc); - push @rows, $blob if defined $blob; - join("\n", @rows); +sub ds { + my ($self) = @_; + $self->{ds} ||= eval { msg_datestamp($self->{mime}->header_obj); } || 0; } sub references { @@ -124,29 +157,17 @@ sub references { defined $x ? $x : ''; } -sub ensure_metadata { - my ($self) = @_; +sub _get_term_val ($$$) { + my ($self, $pfx, $re) = @_; my $doc = $self->{doc}; my $end = $doc->termlist_end; - - unless (defined $PFX2TERM_RE) { - my $or = join('|', keys %PublicInbox::Search::PFX2TERM_RMAP); - $PFX2TERM_RE = qr/\A($or)/; - } - - while (my ($pfx, $field) = each %PublicInbox::Search::PFX2TERM_RMAP) { - # ideally we'd move this out of the loop: - my $i = $doc->termlist_begin; - - $i->skip_to($pfx); - if ($i != $end) { - my $val = $i->get_termname; - - if ($val =~ s/$PFX2TERM_RE//o) { - $self->{$field} = $val; - } - } + my $i = $doc->termlist_begin; + $i->skip_to($pfx); + if ($i != $end) { + my $val = $i->get_termname; + $val =~ s/$re// and return $val; } + undef; } sub mid ($;$) { @@ -156,57 +177,18 @@ sub mid ($;$) { $self->{mid} = $mid; } elsif (my $rv = $self->{mid}) { $rv; + } elsif ($self->{doc}) { + $self->{mid} = _get_term_val($self, 'Q', qr/\AQ/); } else { - $self->ensure_metadata; # needed for ghosts - $self->{mid} ||= $self->_extract_mid; - } -} - -sub _extract_mid { mid_clean(mid_mime($_[0]->mime)) } - -sub blob { - my ($self, $x40) = @_; - if (defined $x40) { - $self->{blob} = $x40; - } else { - $self->{blob}; - } -} - -sub mime { - my ($self, $mime) = @_; - if (defined $mime) { - $self->{mime} = $mime; - } else { - # TODO load from git - $self->{mime}; + $self->_extract_mid; # v1 w/o Xapian } } -sub doc_id { - my ($self, $doc_id) = @_; - if (defined $doc_id) { - $self->{doc_id} = $doc_id; - } else { - # TODO load from xapian - $self->{doc_id}; - } -} +sub _extract_mid { mid_clean(mid_mime($_[0]->{mime})) } -sub thread_id { - my ($self) = @_; - my $tid = $self->{thread}; - return $tid if defined $tid; - $self->ensure_metadata; - $self->{thread}; -} +sub tid { $_[0]->{tid} } -sub path { - my ($self) = @_; - my $path = $self->{path}; - return $path if defined $path; - $self->ensure_metadata; - $self->{path}; -} +# XXX: consider removing this, we can phrase match subject +sub path { $_[0]->{path} } 1;