X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;ds=sidebyside;f=lib%2FPublicInbox%2FSearchIdx.pm;h=f14809d25fe361a827dc3f18a21e14a594594f2b;hb=55b707d788ce13696e4411389583e720ea6dab01;hp=665f673a88d9832be185d80d684467775fc1a200;hpb=c477bdd8a80eecc319b680764edfb24bd12cb7b2;p=public-inbox.git
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 665f673a..f14809d2 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2018 all contributors
+# Copyright (C) 2015-2019 all contributors
# License: AGPL-3.0+
# based on notmuch, but with no concept of folders, files or flags
#
@@ -12,14 +12,15 @@ use warnings;
use base qw(PublicInbox::Search PublicInbox::Lock);
use PublicInbox::MIME;
use PublicInbox::InboxWritable;
-use PublicInbox::MID qw/mid_clean id_compress mid_mime mids/;
+use PublicInbox::MID qw/mid_clean mid_mime mids_for_index/;
use PublicInbox::MsgIter;
use Carp qw(croak);
use POSIX qw(strftime);
use PublicInbox::OverIdx;
use PublicInbox::Spawn qw(spawn);
use PublicInbox::Git qw(git_unquote);
-
+my $X = \%PublicInbox::Search::X;
+my ($DB_CREATE_OR_OPEN, $DB_OPEN);
use constant {
BATCH_BYTES => defined($ENV{XAPIAN_FLUSH_THRESHOLD}) ?
0x7fffffff : 1_000_000,
@@ -32,7 +33,7 @@ sub new {
my ($class, $ibx, $creat, $shard) = @_;
ref $ibx or die "BUG: expected PublicInbox::Inbox object: $ibx";
my $levels = qr/\A(?:full|medium|basic)\z/;
- my $mainrepo = $ibx->{mainrepo};
+ my $inboxdir = $ibx->{inboxdir};
my $version = $ibx->{version} || 1;
my $indexlevel = 'full';
my $altid = $ibx->{altid};
@@ -49,7 +50,7 @@ sub new {
}
$ibx = PublicInbox::InboxWritable->new($ibx);
my $self = bless {
- mainrepo => $mainrepo,
+ inboxdir => $inboxdir,
-inbox => $ibx,
git => $ibx->git,
-altid => $altid,
@@ -58,7 +59,7 @@ sub new {
}, $class;
$ibx->umask_prepare;
if ($version == 1) {
- $self->{lock_path} = "$mainrepo/ssoma.lock";
+ $self->{lock_path} = "$inboxdir/ssoma.lock";
my $dir = $self->xdir;
$self->{over} = PublicInbox::OverIdx->new("$dir/over.sqlite3");
} elsif ($version == 2) {
@@ -85,17 +86,28 @@ sub _xdb_release {
undef;
}
+sub load_xapian_writable () {
+ return 1 if $X->{WritableDatabase};
+ PublicInbox::Search::load_xapian() or return;
+ my $xap = $PublicInbox::Search::Xap;
+ for (qw(Document TermGenerator WritableDatabase)) {
+ $X->{$_} = $xap.'::'.$_;
+ }
+ eval 'require '.$X->{WritableDatabase} or die;
+ *sortable_serialise = $xap.'::sortable_serialise';
+ $DB_CREATE_OR_OPEN = eval($xap.'::DB_CREATE_OR_OPEN()');
+ $DB_OPEN = eval($xap.'::DB_OPEN()');
+ 1;
+}
+
sub _xdb_acquire {
my ($self) = @_;
my $flag;
my $dir = $self->xdir;
if (need_xapian($self)) {
croak 'already acquired' if $self->{xdb};
- PublicInbox::Search::load_xapian();
- require Search::Xapian::WritableDatabase;
- $flag = $self->{creat} ?
- Search::Xapian::DB_CREATE_OR_OPEN() :
- Search::Xapian::DB_OPEN();
+ load_xapian_writable();
+ $flag = $self->{creat} ? $DB_CREATE_OR_OPEN : $DB_OPEN;
}
if ($self->{creat}) {
require File::Path;
@@ -108,7 +120,7 @@ sub _xdb_acquire {
}
}
return unless defined $flag;
- my $xdb = eval { Search::Xapian::WritableDatabase->new($dir, $flag) };
+ my $xdb = eval { ($X->{WritableDatabase})->new($dir, $flag) };
if ($@) {
die "Failed opening $dir: ", $@;
}
@@ -117,20 +129,29 @@ sub _xdb_acquire {
sub add_val ($$$) {
my ($doc, $col, $num) = @_;
- $num = Search::Xapian::sortable_serialise($num);
+ $num = sortable_serialise($num);
$doc->add_value($col, $num);
}
-sub index_text ($$$$)
-{
- my ($self, $field, $n, $text) = @_;
- my $tg = $self->term_generator;
+sub term_generator ($) { # write-only
+ my ($self) = @_;
+
+ $self->{term_generator} //= do {
+ my $tg = $X->{TermGenerator}->new;
+ $tg->set_stemmer($self->stemmer);
+ $tg;
+ }
+}
+
+sub index_text ($$$$) {
+ my ($self, $text, $wdf_inc, $prefix) = @_;
+ my $tg = term_generator($self); # man Search::Xapian::TermGenerator
if ($self->{indexlevel} eq 'full') {
- $tg->index_text($field, $n, $text);
+ $tg->index_text($text, $wdf_inc, $prefix);
$tg->increase_termpos;
} else {
- $tg->index_text_without_positions($field, $n, $text);
+ $tg->index_text_without_positions($text, $wdf_inc, $prefix);
}
}
@@ -141,18 +162,18 @@ sub index_users ($$) {
my $to = $smsg->to;
my $cc = $smsg->cc;
- $self->index_text($from, 1, 'A'); # A - author
- $self->index_text($to, 1, 'XTO') if $to ne '';
- $self->index_text($cc, 1, 'XCC') if $cc ne '';
+ index_text($self, $from, 1, 'A'); # A - author
+ index_text($self, $to, 1, 'XTO') if $to ne '';
+ index_text($self, $cc, 1, 'XCC') if $cc ne '';
}
sub index_diff_inc ($$$$) {
my ($self, $text, $pfx, $xnq) = @_;
if (@$xnq) {
- $self->index_text(join("\n", @$xnq), 1, 'XNQ');
+ index_text($self, join("\n", @$xnq), 1, 'XNQ');
@$xnq = ();
}
- $self->index_text($text, 1, $pfx);
+ index_text($self, $text, 1, $pfx);
}
sub index_old_diff_fn {
@@ -167,7 +188,7 @@ sub index_old_diff_fn {
$fb = join('/', @fb);
if ($fa eq $fb) {
unless ($seen->{$fa}++) {
- $self->index_diff_inc($fa, 'XDFN', $xnq);
+ index_diff_inc($self, $fa, 'XDFN', $xnq);
}
return 1;
}
@@ -178,22 +199,22 @@ sub index_old_diff_fn {
}
sub index_diff ($$$) {
- my ($self, $lines, $doc) = @_;
+ my ($self, $txt, $doc) = @_;
my %seen;
my $in_diff;
my @xnq;
my $xnq = \@xnq;
- foreach (@$lines) {
+ foreach (split(/\n/, $txt)) {
if ($in_diff && s/^ //) { # diff context
- $self->index_diff_inc($_, 'XDFCTX', $xnq);
+ index_diff_inc($self, $_, 'XDFCTX', $xnq);
} 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];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
$fn = (split('/', git_unquote($fb), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
$in_diff = 1;
# traditional diff:
} elsif (m/^diff -(.+) (\S+) (\S+)$/) {
@@ -201,26 +222,28 @@ sub index_diff ($$$) {
push @xnq, $_;
# only support unified:
next unless $opt =~ /[uU]/;
- $in_diff = $self->index_old_diff_fn(\%seen, $fa, $fb,
+ $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb,
$xnq);
} elsif (m!^--- ("?a/.+)!) {
- my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ my $fn = $1;
+ $fn = (split('/', git_unquote($fn), 2))[1];
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
$in_diff = 1;
} elsif (m!^\+\+\+ ("?b/.+)!) {
- my $fn = (split('/', git_unquote($1), 2))[1];
- $seen{$fn}++ or $self->index_diff_inc($fn, 'XDFN', $xnq);
+ my $fn = $1;
+ $fn = (split('/', git_unquote($fn), 2))[1];
+ $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq);
$in_diff = 1;
} elsif (/^--- (\S+)/) {
$in_diff = $1;
push @xnq, $_;
} elsif (defined $in_diff && /^\+\+\+ (\S+)/) {
- $in_diff = $self->index_old_diff_fn(\%seen, $in_diff, $1,
- $xnq);
+ $in_diff = index_old_diff_fn($self, \%seen, $in_diff,
+ $1, $xnq);
} elsif ($in_diff && s/^\+//) { # diff added
- $self->index_diff_inc($_, 'XDFB', $xnq);
+ index_diff_inc($self, $_, 'XDFB', $xnq);
} elsif ($in_diff && s/^-//) { # diff removed
- $self->index_diff_inc($_, 'XDFA', $xnq);
+ index_diff_inc($self, $_, 'XDFA', $xnq);
} elsif (m!^index ([a-f0-9]+)\.\.([a-f0-9]+)!) {
my ($ba, $bb) = ($1, $2);
index_git_blob_id($doc, 'XDFPRE', $ba);
@@ -230,7 +253,7 @@ sub index_diff ($$$) {
# traditional diff w/o -p
} elsif (/^@@ (?:\S+) (?:\S+) @@\s*(\S+.*)$/) {
# hunk header context
- $self->index_diff_inc($1, 'XDFHH', $xnq);
+ index_diff_inc($self, $1, 'XDFHH', $xnq);
# ignore the following lines:
} elsif (/^(?:dis)similarity index/ ||
/^(?:old|new) mode/ ||
@@ -241,7 +264,9 @@ sub index_diff ($$$) {
/^Binary files .* differ/) {
push @xnq, $_;
} elsif ($_ eq '') {
- $in_diff = undef;
+ # possible to be in diff context, some mail may be
+ # stripped by MUA or even GNU diff(1). "git apply"
+ # treats a bare "\n" as diff context, too
} else {
push @xnq, $_;
warn "non-diff line: $_\n" if DEBUG && $_ ne '';
@@ -249,30 +274,45 @@ sub index_diff ($$$) {
}
}
- $self->index_text(join("\n", @xnq), 1, 'XNQ');
+ index_text($self, join("\n", @xnq), 1, 'XNQ');
}
sub index_body ($$$) {
- my ($self, $lines, $doc) = @_;
- my $txt = join("\n", @$lines);
+ my ($self, $txt, $doc) = @_;
if ($doc) {
# does it look like a diff?
if ($txt =~ /^(?:diff|---|\+\+\+) /ms) {
- $txt = undef;
- $self->index_diff($lines, $doc);
+ index_diff($self, $txt, $doc);
} else {
- $self->index_text($txt, 1, 'XNQ');
+ index_text($self, $txt, 1, 'XNQ');
}
} else {
- $self->index_text($txt, 0, 'XQUOT');
+ index_text($self, $txt, 0, 'XQUOT');
}
- @$lines = ();
}
-sub add_xapian ($$$$$) {
+sub index_xapian { # msg_iter callback
+ my ($part, $depth, @idx) = @{$_[0]};
+ my ($self, $doc) = @{$_[1]};
+ my $ct = $part->content_type || 'text/plain';
+ my $fn = $part->filename;
+ if (defined $fn && $fn ne '') {
+ index_text($self, $fn, 1, 'XFN');
+ }
+
+ my ($s, undef) = msg_part_text($part, $ct);
+ defined $s or return;
+
+ # split off quoted and unquoted blocks:
+ my @sections = split(/((?:^>[^\n]*\n)+)/sm, $s);
+ $part = $s = undef;
+ index_body($self, $_, /\A>/ ? 0 : $doc) for @sections;
+}
+
+sub add_xapian ($$$$$$) {
my ($self, $mime, $num, $oid, $mids, $mid0) = @_;
my $smsg = PublicInbox::SearchMsg->new($mime);
- my $doc = Search::Xapian::Document->new;
+ my $doc = $X->{Document}->new;
my $subj = $smsg->subject;
add_val($doc, PublicInbox::Search::TS(), $smsg->ts);
my @ds = gmtime($smsg->ds);
@@ -281,46 +321,21 @@ sub add_xapian ($$$$$) {
my $dt = strftime('%Y%m%d%H%M%S', @ds);
add_val($doc, PublicInbox::Search::DT(), $dt);
- my $tg = $self->term_generator;
+ my $tg = term_generator($self);
$tg->set_document($doc);
- $self->index_text($subj, 1, 'S') if $subj;
- $self->index_users($smsg);
-
- msg_iter($mime, sub {
- my ($part, $depth, @idx) = @{$_[0]};
- my $ct = $part->content_type || 'text/plain';
- my $fn = $part->filename;
- if (defined $fn && $fn ne '') {
- $self->index_text($fn, 1, 'XFN');
- }
-
- my ($s, undef) = msg_part_text($part, $ct);
- defined $s or return;
-
- my (@orig, @quot);
- my @lines = split(/\n/, $s);
- while (defined(my $l = shift @lines)) {
- if ($l =~ /^>/) {
- $self->index_body(\@orig, $doc) if @orig;
- push @quot, $l;
- } else {
- $self->index_body(\@quot, 0) if @quot;
- push @orig, $l;
- }
- }
- $self->index_body(\@quot, 0) if @quot;
- $self->index_body(\@orig, $doc) if @orig;
- });
+ index_text($self, $subj, 1, 'S') if $subj;
+ index_users($self, $smsg);
+ msg_iter($mime, \&index_xapian, [ $self, $doc ]);
foreach my $mid (@$mids) {
- $self->index_text($mid, 1, 'XM');
+ index_text($self, $mid, 1, 'XM');
# because too many Message-IDs are prefixed with
# "Pine.LNX."...
if ($mid =~ /\w{12,}/) {
my @long = ($mid =~ /(\w{3,}+)/g);
- $self->index_text(join(' ', @long), 1, 'XM');
+ index_text($self, join(' ', @long), 1, 'XM');
}
}
$smsg->{to} = $smsg->{cc} = '';
@@ -341,18 +356,27 @@ sub add_xapian ($$$$$) {
$self->{xdb}->replace_document($num, $doc);
}
+sub _msgmap_init ($) {
+ my ($self) = @_;
+ die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1;
+ $self->{mm} //= eval {
+ require PublicInbox::Msgmap;
+ PublicInbox::Msgmap->new($self->{inboxdir}, 1);
+ };
+}
+
sub add_message {
# mime = Email::MIME object
my ($self, $mime, $bytes, $num, $oid, $mid0) = @_;
- my $mids = mids($mime->header_obj);
- $mid0 = $mids->[0] unless defined $mid0; # v1 compatibility
- unless (defined $num) { # v1
- $self->_msgmap_init;
- $num = index_mm($self, $mime);
- }
+ my $mids = mids_for_index($mime->header_obj);
+ $mid0 //= $mids->[0]; # v1 compatibility
+ $num //= do { # v1
+ _msgmap_init($self);
+ index_mm($self, $mime);
+ };
eval {
if (need_xapian($self)) {
- $self->add_xapian($mime, $num, $oid, $mids, $mid0)
+ add_xapian($self, $mime, $num, $oid, $mids, $mid0);
}
if (my $over = $self->{over}) {
$over->add_overview($mime, $bytes, $num, $oid, $mid0);
@@ -382,7 +406,7 @@ sub batch_do {
my ($head, $tail) = $self->find_doc_ids($termval);
return if $head == $tail;
my @ids;
- for (; $head != $tail && @ids < $batch_size; $head->inc) {
+ for (; $head != $tail && @ids < $batch_size; $head++) {
push @ids, $head->get_docid;
}
$cb->(\@ids);
@@ -409,7 +433,7 @@ sub remove_message {
batch_do($self, 'Q' . $mid, sub {
my ($ids) = @_;
$db->delete_document($_) for @$ids;
- $nr = scalar @$ids;
+ $nr += scalar @$ids;
});
};
if ($@) {
@@ -437,7 +461,7 @@ sub remove_by_oid {
# there is only ONE element in @delete unless we
# have bugs in our v2writable deduplication check
my @delete;
- for (; $head != $tail; $head->inc) {
+ for (; $head != $tail; $head++) {
my $docid = $head->get_docid;
my $doc = $db->get_document($docid);
my $smsg = PublicInbox::SearchMsg->wrap($mid);
@@ -450,18 +474,6 @@ sub remove_by_oid {
scalar(@delete);
}
-sub term_generator { # write-only
- my ($self) = @_;
-
- my $tg = $self->{term_generator};
- return $tg if $tg;
-
- $tg = Search::Xapian::TermGenerator->new;
- $tg->set_stemmer($self->stemmer);
-
- $self->{term_generator} = $tg;
-}
-
sub index_git_blob_id {
my ($doc, $pfx, $objid) = @_;
@@ -590,6 +602,7 @@ sub read_log {
$newest ||= $latest;
}
}
+ close($log) or die "git log failed: \$?=$?";
# get the leftovers
foreach my $blob (keys %D) {
my $mime = do_cat_mail($git, $blob, \$bytes) or next;
@@ -598,15 +611,6 @@ sub read_log {
$batch_cb->($nr, $latest, $newest);
}
-sub _msgmap_init {
- my ($self) = @_;
- die "BUG: _msgmap_init is only for v1\n" if $self->{version} != 1;
- $self->{mm} ||= eval {
- require PublicInbox::Msgmap;
- PublicInbox::Msgmap->new($self->{mainrepo}, 1);
- };
-}
-
sub _git_log {
my ($self, $opts, $range) = @_;
my $git = $self->{git};
@@ -632,7 +636,7 @@ sub _git_log {
--no-notes --no-color --no-renames
--diff-filter=AM), $range);
++$fcount while <$fh>;
- close $fh;
+ close $fh or die "git log failed: \$?=$?";
my $high = $self->{mm}->num_highwater;
$pr->("$fcount\n") if $pr; # continue previous line
$self->{ntodo} = $fcount;
@@ -713,7 +717,10 @@ sub _index_sync {
my $xdb = $self->begin_txn_lazy;
my $mm = _msgmap_init($self);
do {
- $xlog = undef;
+ if ($xlog) {
+ close($xlog) or die "git log failed: \$?=$?";
+ $xlog = undef;
+ }
$last_commit = _last_x_commit($self, $mm);
$lx = reindex_from($opts->{reindex}, $last_commit);