X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSmsg.pm;h=b132381b4ab2c3a93fd78b1fe042d1710a2c3fe8;hb=5198c976ce8b1954f0f76a0da152cc434411f147;hp=5eb0723f4257995832b7ba21c6fe8218f9f48a4e;hpb=33ce2aa920d9ebffb0affcb216ebf03320c7492d;p=public-inbox.git diff --git a/lib/PublicInbox/Smsg.pm b/lib/PublicInbox/Smsg.pm index 5eb0723f..b132381b 100644 --- a/lib/PublicInbox/Smsg.pm +++ b/lib/PublicInbox/Smsg.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2020 all contributors +# Copyright (C) 2015-2021 all contributors # License: AGPL-3.0+ # # A small/skeleton/slim representation of a message. @@ -9,38 +9,23 @@ # large threads in our WWW UI and the NNTP range responses. package PublicInbox::Smsg; use strict; -use warnings; -use base qw(Exporter); +use v5.10.1; +use parent qw(Exporter); our @EXPORT_OK = qw(subject_normalized); -use PublicInbox::MID qw/mid_clean mid_mime/; +use PublicInbox::MID qw(mids references); use PublicInbox::Address; use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); -use Time::Local qw(timegm); -sub new { - my ($class, $mime) = @_; - bless { mime => $mime }, $class; -} - -sub wrap { - my ($class, $mid) = @_; - bless { mid => $mid }, $class; -} - -sub get_val ($$) { - my ($doc, $col) = @_; - # sortable_unserialise is defined by PublicInbox::Search::load_xapian() - sortable_unserialise($doc->get_value($col)); -} +sub oidbin { pack('H*', $_[0]->{blob}) } sub to_doc_data { my ($self) = @_; join("\n", - $self->subject, - $self->from, - $self->references, - $self->to, - $self->cc, + $self->{subject}, + $self->{from}, + $self->{references} // '', + $self->{to}, + $self->{cc}, $self->{blob}, $self->{mid}, $self->{bytes} // '', @@ -50,6 +35,7 @@ sub to_doc_data { sub load_from_data ($$) { my ($self) = $_[0]; # data = $_[1] + utf8::decode($_[1]); ( $self->{subject}, $self->{from}, @@ -70,122 +56,95 @@ sub load_from_data ($$) { ) = split(/\n/, $_[1]); } -sub load_expand { - my ($self, $doc) = @_; - my $data = $doc->get_data or return; - $self->{ts} = get_val($doc, PublicInbox::Search::TS()); - my $dt = get_val($doc, PublicInbox::Search::DT()); - my ($yyyy, $mon, $dd, $hh, $mm, $ss) = unpack('A4A2A2A2A2A2', $dt); - $self->{ds} = timegm($ss, $mm, $hh, $dd, $mon - 1, $yyyy); - utf8::decode($data); - load_from_data($self, $data); - $self; -} - sub psgi_cull ($) { my ($self) = @_; - from_name($self); # fill in {from_name} so we can delete {from} # drop NNTP-only fields which aren't relevant to PSGI results: # saves ~80K on a 200 item search result: - delete @$self{qw(from ts to cc bytes lines)}; + # TODO: we may need to keep some of these for JMAP... + my ($f) = delete @$self{qw(from tid to cc bytes lines)}; + # ghosts don't have ->{from} + $self->{from_name} = join(', ', PublicInbox::Address::names($f // '')); $self; } -# Only called by PSGI interface, not NNTP -sub from_mitem { - my ($mitem, $srch) = @_; - return $srch->retry_reopen(\&from_mitem, $mitem) if $srch; - my $self = bless {}, __PACKAGE__; - psgi_cull(load_expand($self, $mitem->get_document)); -} - -# :bytes and :lines metadata in RFC 3977 -sub bytes ($) { $_[0]->{bytes} } -sub lines ($) { $_[0]->{lines} } - -sub __hdr ($$) { - my ($self, $field) = @_; - my $val = $self->{$field}; - return $val if defined $val; - - my $mime = $self->{mime} or return; - my @raw = $mime->header($field); - $val = join(', ', @raw); - $val =~ tr/\t\n/ /; - $val =~ tr/\r//d; - $self->{$field} = $val; +sub parse_references ($$$) { + my ($smsg, $hdr, $mids) = @_; + my $refs = references($hdr); + push(@$refs, @$mids) if scalar(@$mids) > 1; + return $refs if scalar(@$refs) == 0; + + # prevent circular references here: + my %seen = ( ($smsg->{mid} // '') => 1 ); + my @keep; + foreach my $ref (@$refs) { + if (length($ref) > PublicInbox::MID::MAX_MID_SIZE) { + warn "References: <$ref> too long, ignoring\n"; + next; + } + $seen{$ref} //= push(@keep, $ref); + } + $smsg->{references} = '<'.join('> <', @keep).'>' if @keep; + \@keep; +} + +# used for v2, Import and v1 non-SQLite WWW code paths +sub populate { + my ($self, $hdr, $sync) = @_; + for my $f (qw(From To Cc Subject)) { + my @all = $hdr->header($f); + my $val = join(', ', @all); + $val =~ tr/\r//d; + # MIME decoding can create NULs, replace them with spaces + # to protect git and NNTP clients + $val =~ tr/\0\t\n/ /; + + # lower-case fields for read-only stuff + $self->{lc($f)} = $val; + + # Capitalized From/Subject for git-fast-import + next if $f eq 'To' || $f eq 'Cc'; + if (scalar(@all) > 1) { + $val = $all[0]; + $val =~ tr/\r//d; + $val =~ tr/\0\t\n/ /; + } + $self->{$f} = $val if $val ne ''; + } + $sync //= {}; + my @ds = msg_datestamp($hdr, $sync->{autime} // $self->{ds}); + my @ts = msg_timestamp($hdr, $sync->{cotime} // $self->{ts}); + $self->{-ds} = \@ds; + $self->{-ts} = \@ts; + $self->{ds} //= $ds[0]; # no zone + $self->{ts} //= $ts[0]; + $self->{mid} //= mids($hdr)->[0]; } -sub subject ($) { __hdr($_[0], 'subject') } -sub to ($) { __hdr($_[0], 'to') } -sub cc ($) { __hdr($_[0], 'cc') } - # 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 ($) { +sub date ($) { # for NNTP my ($self) = @_; 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, $sec); - } -sub from ($) { +sub internaldate { # for IMAP my ($self) = @_; - my $from = __hdr($self, 'from'); - if (defined $from && !defined $self->{from_name}) { - my @n = PublicInbox::Address::names($from); - $self->{from_name} = join(', ', @n); - } - $from; -} - -sub from_name { - my ($self) = @_; - my $from_name = $self->{from_name}; - return $from_name if defined $from_name; - $self->from; - $self->{from_name}; -} - -sub ts { - my ($self) = @_; - $self->{ts} ||= eval { msg_timestamp($self->{mime}->header_obj) } || 0; -} - -sub ds { - my ($self) = @_; - $self->{ds} ||= eval { msg_datestamp($self->{mime}->header_obj); } || 0; -} - -sub references { - my ($self) = @_; - my $x = $self->{references}; - defined $x ? $x : ''; -} - -sub mid ($;$) { - my ($self, $mid) = @_; - - if (defined $mid) { - $self->{mid} = $mid; - } elsif (defined(my $rv = $self->{mid})) { - $rv; - } else { - die "NO {mime} for mid\n" unless $self->{mime}; - $self->_extract_mid; # v1 w/o Xapian - } + my ($sec, $min, $hour, $mday, $mon, $year) = gmtime($self->{ts} // 0); + sprintf("%02d-$MoY[$mon]-%04d %02d:%02d:%02d +0000", + $mday, $year+1900, $hour, $min, $sec); } -sub _extract_mid { mid_clean(mid_mime($_[0]->{mime})) } - our $REPLY_RE = qr/^re:\s+/i; +# TODO: see RFC 5256 sec 2.1 "Base Subject" and evaluate compatibility +# w/ existing indices... sub subject_normalized ($) { my ($subj) = @_; $subj =~ s/\A\s+//s; # no leading space @@ -196,4 +155,17 @@ sub subject_normalized ($) { $subj; } +# returns the number of bytes to add if given a non-CRLF arg +sub crlf_adjust ($) { + if (index($_[0], "\r\n") < 0) { + # common case is LF-only, every \n needs an \r; + # so favor a cheap tr// over an expensive m//g + $_[0] =~ tr/\n/\n/; + } else { # count number of '\n' w/o '\r', expensive: + scalar(my @n = ($_[0] =~ m/(?{bytes} = $_[2] + crlf_adjust($_[1]) } + 1;