#
# Indexes mail with Xapian and our (SQLite-based) ::Msgmap for use
# with the web and NNTP interfaces. This index maintains thread
-# relationships for use by Mail::Thread. This writes to the search
-# index.
+# relationships for use by PublicInbox::SearchThread.
+# This writes to the search index.
package PublicInbox::SearchIdx;
use strict;
use warnings;
use Fcntl qw(:flock :DEFAULT);
-use Email::MIME;
+use PublicInbox::MIME;
use Email::MIME::ContentType;
$Email::MIME::ContentType::STRICT_PARAMS = 0;
use base qw(PublicInbox::Search);
use Carp qw(croak);
use POSIX qw(strftime);
require PublicInbox::Git;
-*xpfx = *PublicInbox::Search::xpfx;
-use constant MAX_MID_SIZE => 244; # max term size - 1 in Xapian
use constant {
+ MAX_MID_SIZE => 244, # max term size - 1 in Xapian
PERM_UMASK => 0,
OLD_PERM_GROUP => 1,
OLD_PERM_EVERYBODY => 2,
PERM_GROUP => 0660,
PERM_EVERYBODY => 0664,
+ BATCH_BYTES => 1_000_000,
+ DEBUG => !!$ENV{DEBUG},
};
+my %GIT_ESC = (
+ a => "\a",
+ b => "\b",
+ f => "\f",
+ n => "\n",
+ r => "\r",
+ t => "\t",
+ v => "\013",
+);
+
+sub git_unquote ($) {
+ my ($s) = @_;
+ return $s unless ($s =~ /\A"(.*)"\z/);
+ $s = $1;
+ $s =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g;
+ $s =~ s/\\([0-7]{1,3})/chr(oct($1))/ge;
+ $s;
+}
+
sub new {
my ($class, $inbox, $creat) = @_;
my $git_dir = $inbox;
require File::Path;
_lock_acquire($self);
File::Path::mkpath($dir);
- $self->{batch_size} = 100;
$flag = Search::Xapian::DB_CREATE_OR_OPEN;
}
$self->{xdb} = Search::Xapian::WritableDatabase->new($dir, $flag);
$smsg->{mime}->body_raw =~ tr!\n!\n!);
my $yyyymmdd = strftime('%Y%m%d', gmtime($ts));
- $doc->add_value(&PublicInbox::Search::YYYYMMDD, $yyyymmdd);
+ add_val($doc, PublicInbox::Search::YYYYMMDD, $yyyymmdd);
}
sub index_users ($$) {
$tg->increase_termpos;
}
+sub index_text_inc ($$$) {
+ my ($tg, $text, $pfx) = @_;
+ $tg->index_text($text, 1, $pfx);
+ $tg->increase_termpos;
+}
+
+sub index_old_diff_fn {
+ my ($tg, $seen, $fa, $fb) = @_;
+
+ # no renames or space support for traditional diffs,
+ # find the number of leading common paths to strip:
+ my @fa = split('/', $fa);
+ my @fb = split('/', $fb);
+ while (scalar(@fa) && scalar(@fb)) {
+ $fa = join('/', @fa);
+ $fb = join('/', @fb);
+ if ($fa eq $fb) {
+ index_text_inc($tg, $fa,'XDFN') unless $seen->{$fa}++;
+ return 1;
+ }
+ shift @fa;
+ shift @fb;
+ }
+ 0;
+}
+
+sub index_diff ($$$) {
+ my ($tg, $lines, $doc) = @_;
+ my %seen;
+ my $in_diff;
+ foreach (@$lines) {
+ if ($in_diff && s/^ //) { # diff context
+ index_text_inc($tg, $_, 'XDFCTX');
+ } elsif (/^-- $/) { # email signature begins
+ $in_diff = undef;
+ } elsif (m!^diff --git ("?a/.+) ("?b/.+)\z!) {
+ my ($fa, $fb) = ($1, $2);
+ my $fn = (split('/', git_unquote($fa), 2))[1];
+ index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+ $fn = (split('/', git_unquote($fb), 2))[1];
+ index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+ $in_diff = 1;
+ # traditional diff:
+ } elsif (m/^diff -(.+) (\S+) (\S+)$/) {
+ my ($opt, $fa, $fb) = ($1, $2, $3);
+ # only support unified:
+ next unless $opt =~ /[uU]/;
+ $in_diff = index_old_diff_fn($tg, \%seen, $fa, $fb);
+ } elsif (m!^--- ("?a/.+)!) {
+ my $fn = (split('/', git_unquote($1), 2))[1];
+ index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+ $in_diff = 1;
+ } elsif (m!^\+\+\+ ("?b/.+)!) {
+ my $fn = (split('/', git_unquote($1), 2))[1];
+ index_text_inc($tg, $fn, 'XDFN') unless $seen{$fn}++;
+ $in_diff = 1;
+ } elsif (/^--- (\S+)/) {
+ $in_diff = $1;
+ } elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
+ $in_diff = index_old_diff_fn($tg, \%seen, $in_diff, $1);
+ } elsif ($in_diff && s/^\+//) { # diff added
+ index_text_inc($tg, $_, 'XDFB');
+ } elsif ($in_diff && s/^-//) { # diff removed
+ index_text_inc($tg, $_, 'XDFA');
+ } elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
+ my ($ba, $bb) = ($1, $2);
+ index_git_blob_id($doc, 'XDFPRE', $ba);
+ index_git_blob_id($doc, 'XDFPOST', $bb);
+ $in_diff = 1;
+ } elsif (/^@@ (?:\S+) (?:\S+) @@\s*$/) {
+ # traditional diff w/o -p
+ } elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
+ # hunk header context
+ index_text_inc($tg, $1, 'XDFHH');
+ # ignore the following lines:
+ } elsif (/^(?:dis)similarity index/) {
+ } elsif (/^(?:old|new) mode/) {
+ } elsif (/^(?:deleted|new) file mode/) {
+ } elsif (/^(?:copy|rename) (?:from|to) /) {
+ } elsif (/^(?:dis)?similarity index /) {
+ } elsif (/^\\ No newline at end of file/) {
+ } elsif (/^Binary files .* differ/) {
+ } elsif ($_ eq '') {
+ $in_diff = undef;
+ } else {
+ warn "non-diff line: $_\n" if DEBUG && $_ ne '';
+ $in_diff = undef;
+ }
+ }
+}
+
+sub index_body ($$$) {
+ my ($tg, $lines, $doc) = @_;
+ my $txt = join("\n", @$lines);
+ $tg->index_text($txt, !!$doc, $doc ? 'XNQ' : 'XQUOT');
+ $tg->increase_termpos;
+ # does it look like a diff?
+ if ($doc && $txt =~ /^(?:diff|---|\+\+\+) /ms) {
+ $txt = undef;
+ index_diff($tg, $lines, $doc);
+ }
+ @$lines = ();
+}
+
sub add_message {
my ($self, $mime, $bytes, $num, $blob) = @_; # mime = Email::MIME object
my $db = $self->{xdb};
my ($doc_id, $old_tid);
my $mid = mid_clean(mid_mime($mime));
- my $ct_msg = $mime->header('Content-Type') || 'text/plain';
eval {
die 'Message-ID too long' if length($mid) > MAX_MID_SIZE;
if ($smsg) {
# convert a ghost to a regular message
# it will also clobber any existing regular message
- $doc_id = $smsg->doc_id;
+ $doc_id = $smsg->{doc_id};
$old_tid = $smsg->thread_id;
}
$smsg = PublicInbox::SearchMsg->new($mime);
my $doc = $smsg->{doc};
- $doc->add_term(xpfx('mid') . $mid);
+ $doc->add_term('Q' . $mid);
my $subj = $smsg->subject;
if ($subj ne '') {
my $path = $self->subject_path($subj);
- $doc->add_term(xpfx('path') . id_compress($path));
+ $doc->add_term('XPATH' . id_compress($path));
}
add_values($smsg, $bytes, $num);
msg_iter($mime, sub {
my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || $ct_msg;
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ $tg->index_text($fn, 1, 'XFN');
+ }
- # account for filter bugs...
- $ct =~ m!\btext/plain\b!i or return;
+ return if $ct =~ m!\btext/x?html\b!i;
+
+ my $s = eval { $part->body_str };
+ if ($@) {
+ if ($ct =~ m!\btext/plain\b!i) {
+ # Try to assume UTF-8 because Alpine
+ # seems to do wacky things and set
+ # charset=X-UNKNOWN
+ $part->charset_set('UTF-8');
+ $s = eval { $part->body_str };
+ $s = $part->body if $@;
+ }
+ }
+ defined $s or return;
my (@orig, @quot);
my $body = $part->body;
- $part->body_set('');
my @lines = split(/\n/, $body);
while (defined(my $l = shift @lines)) {
if ($l =~ /^>/) {
+ index_body($tg, \@orig, $doc) if @orig;
push @quot, $l;
} else {
+ index_body($tg, \@quot, 0) if @quot;
push @orig, $l;
}
}
- if (@quot) {
- my $s = join("\n", @quot);
- @quot = ();
- $tg->index_text($s, 0, 'XQUOT');
- $tg->increase_termpos;
- }
- if (@orig) {
- my $s = join("\n", @orig);
- @orig = ();
- $tg->index_text($s, 1, 'XNQ');
- $tg->increase_termpos;
- }
+ index_body($tg, \@quot, 0) if @quot;
+ index_body($tg, \@orig, $doc) if @orig;
});
link_message($self, $smsg, $old_tid);
$mid = mid_clean($mid);
eval {
- $doc_id = $self->find_unique_doc_id('mid', $mid);
- $db->delete_document($doc_id) if defined $doc_id;
+ $doc_id = $self->find_unique_doc_id('Q' . $mid);
+ if (defined $doc_id) {
+ $db->delete_document($doc_id);
+ } else {
+ warn "cannot remove non-existent <$mid>\n";
+ }
};
if ($@) {
my ($self, $smsg, $old_tid) = @_;
my $doc = $smsg->{doc};
my $mid = $smsg->mid;
- my $mime = $smsg->mime;
+ my $mime = $smsg->{mime};
my $hdr = $mime->header_obj;
- my $refs = $hdr->header_raw('References');
- my @refs = $refs ? ($refs =~ /<([^>]+)>/g) : ();
- if (my $irt = $hdr->header_raw('In-Reply-To')) {
- # last References should be $irt
- # we will de-dupe later
- push @refs, mid_clean($irt);
- }
+
+ # last References should be IRT, but some mail clients do things
+ # out of order, so trust IRT over References iff IRT exists
+ my @refs = ($hdr->header_raw('References'),
+ $hdr->header_raw('In-Reply-To'));
+ @refs = ((join(' ', @refs)) =~ /<([^>]+)>/g);
my $tid;
if (@refs) {
push @refs, $ref;
}
}
+
if (@refs) {
$smsg->{references} = '<'.join('> <', @refs).'>';
merge_threads($self, $tid, $ptid);
}
} else {
- $tid = $self->next_thread_id;
+ $tid = defined $old_tid ? $old_tid : $self->next_thread_id;
}
- $doc->add_term(xpfx('thread') . $tid);
+ $doc->add_term('G' . $tid);
}
sub index_blob {
$self->add_message($mime, $bytes, $num, $blob);
}
+sub index_git_blob_id {
+ my ($doc, $pfx, $objid) = @_;
+
+ my $len = length($objid);
+ for (my $len = length($objid); $len >= 7; ) {
+ $doc->add_term($pfx.$objid);
+ $objid = substr($objid, 0, --$len);
+ }
+}
+
sub unindex_blob {
my ($self, $mime) = @_;
my $mid = eval { mid_clean(mid_mime($mime)) };
my $str = $git->cat_file($blob, $sizeref);
# fixup bugs from import:
$$str =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
- Email::MIME->new($str);
+ PublicInbox::MIME->new($str);
};
$@ ? undef : $mime;
}
with_umask($self, sub { $self->_index_sync($opts) });
}
+sub batch_adjust ($$$$) {
+ my ($max, $bytes, $batch_cb, $latest) = @_;
+ $$max -= $bytes;
+ if ($$max <= 0) {
+ $$max = BATCH_BYTES;
+ $batch_cb->($latest, 1);
+ }
+}
+
sub rlog {
my ($self, $log, $add_cb, $del_cb, $batch_cb) = @_;
my $hex = '[a-f0-9]';
my $git = $self->{git};
my $latest;
my $bytes;
- my $max = $self->{batch_size}; # may be undef
+ my $max = BATCH_BYTES;
local $/ = "\n";
my $line;
while (defined($line = <$log>)) {
if ($line =~ /$addmsg/o) {
my $blob = $1;
my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ batch_adjust(\$max, $bytes, $batch_cb, $latest);
$add_cb->($self, $mime, $bytes, $blob);
} elsif ($line =~ /$delmsg/o) {
my $blob = $1;
- my $mime = do_cat_mail($git, $blob) or next;
+ my $mime = do_cat_mail($git, $blob, \$bytes) or next;
+ batch_adjust(\$max, $bytes, $batch_cb, $latest);
$del_cb->($self, $mime);
} elsif ($line =~ /^commit ($h40)/o) {
- if (defined $max && --$max <= 0) {
- $max = $self->{batch_size};
- $batch_cb->($latest, 1);
- }
$latest = $1;
}
}
my $tid = $self->next_thread_id;
my $doc = Search::Xapian::Document->new;
- $doc->add_term(xpfx('mid') . $mid);
- $doc->add_term(xpfx('thread') . $tid);
- $doc->add_term(xpfx('type') . 'ghost');
+ $doc->add_term('Q' . $mid);
+ $doc->add_term('G' . $tid);
+ $doc->add_term('T' . 'ghost');
my $smsg = PublicInbox::SearchMsg->wrap($doc, $mid);
$self->{xdb}->add_document($doc);
sub merge_threads {
my ($self, $winner_tid, $loser_tid) = @_;
return if $winner_tid == $loser_tid;
- my ($head, $tail) = $self->find_doc_ids('thread', $loser_tid);
- my $thread_pfx = xpfx('thread');
+ my ($head, $tail) = $self->find_doc_ids('G' . $loser_tid);
my $db = $self->{xdb};
for (; $head != $tail; $head->inc) {
my $docid = $head->get_docid;
my $doc = $db->get_document($docid);
- $doc->remove_term($thread_pfx . $loser_tid);
- $doc->add_term($thread_pfx . $winner_tid);
+ $doc->remove_term('G' . $loser_tid);
+ $doc->add_term('G' . $winner_tid);
$db->replace_document($docid, $doc);
}
}
my $rv = eval { $cb->() };
my $err = $@;
umask $old;
- die $err if $@;
+ die $err if $err;
$rv;
}