X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FSearchIdx.pm;h=bdb84fc73dacf7bbfb1d463d386cdf466f1749ce;hb=840785917bc74c8e7df226463144185294047d75;hp=bebe904b783a990491c41ac1a8cd667a1530d733;hpb=a9ccb76649432e8fb17a8cf1189ac65de1da2d81;p=public-inbox.git diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm index bebe904b..bdb84fc7 100644 --- a/lib/PublicInbox/SearchIdx.pm +++ b/lib/PublicInbox/SearchIdx.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2015-2021 all contributors +# Copyright (C) all contributors # License: AGPL-3.0+ # based on notmuch, but with no concept of folders, files # @@ -18,9 +18,10 @@ use PublicInbox::MsgIter; use PublicInbox::IdxStack; use Carp qw(croak carp); use POSIX qw(strftime); +use Fcntl qw(SEEK_SET); use Time::Local qw(timegm); use PublicInbox::OverIdx; -use PublicInbox::Spawn qw(spawn nodatacow_dir); +use PublicInbox::Spawn qw(spawn); use PublicInbox::Git qw(git_unquote); use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp); use PublicInbox::Address; @@ -30,13 +31,13 @@ our @EXPORT_OK = qw(log2stack is_ancestor check_size prepare_stack my $X = \%PublicInbox::Search::X; our ($DB_CREATE_OR_OPEN, $DB_OPEN); our $DB_NO_SYNC = 0; +our $DB_DANGEROUS = 0; our $BATCH_BYTES = $ENV{XAPIAN_FLUSH_THRESHOLD} ? 0x7fffffff : # assume a typical 64-bit system has 8x more RAM than a # typical 32-bit system: (($Config{ptrsize} >= 8 ? 8192 : 1024) * 1024); - use constant DEBUG => !!$ENV{DEBUG}; - +my $BASE85 = qr/\A[a-zA-Z0-9\!\#\$\%\&\(\)\*\+\-;<=>\?\@\^_`\{\|\}\~]+\z/; my $xapianlevels = qr/\A(?:full|medium)\z/; my $hex = '[a-f0-9]'; my $OID = $hex .'{40,}'; @@ -115,7 +116,10 @@ sub load_xapian_writable () { my $ver = (eval($xap.'::major_version()') << 16) | (eval($xap.'::minor_version()') << 8) | eval($xap.'::revision()'); - $DB_NO_SYNC = 0x4 if $ver >= 0x10400; + if ($ver >= 0x10400) { + $DB_NO_SYNC = 0x4; + $DB_DANGEROUS = 0x10; + } # Xapian v1.2.21..v1.2.24 were missing close-on-exec on OFD locks $X->{CLOEXEC_UNSET} = 1 if $ver >= 0x010215 && $ver <= 0x010218; 1; @@ -139,8 +143,12 @@ sub idx_acquire { if (!-d $dir && (!$is_shard || ($is_shard && need_xapian($self)))) { File::Path::mkpath($dir); - nodatacow_dir($dir); + require PublicInbox::Syscall; + PublicInbox::Syscall::nodatacow_dir($dir); $self->{-set_has_threadid_once} = 1; + if (($self->{ibx} // $self->{eidx})->{-dangerous}) { + $flag |= $DB_DANGEROUS; + } } } return unless defined $flag; @@ -228,8 +236,8 @@ sub index_old_diff_fn { # 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); + my @fa = split(m'/', $fa); + my @fb = split(m'/', $fb); while (scalar(@fa) && scalar(@fb)) { $fa = join('/', @fa); $fb = join('/', @fb); @@ -249,37 +257,59 @@ sub index_diff ($$$) { my ($self, $txt, $doc) = @_; my %seen; my $in_diff; - my @xnq; - my $xnq = \@xnq; - foreach (split(/\n/, $txt)) { - if ($in_diff && s/^ //) { # diff context + my $xnq = []; + my @l = split(/\n/, $$txt); + undef $$txt; + while (defined($_ = shift @l)) { + if ($in_diff && /^GIT binary patch/) { + push @$xnq, $_; + while (@l && $l[0] =~ /^(?:literal|delta) /) { + # TODO allow searching by size range? + # allows searching by exact size via: + # "literal $SIZE" or "delta $SIZE" + push @$xnq, shift(@l); + + # skip base85 and empty lines + while (@l && ($l[0] =~ /$BASE85/o || + $l[0] !~ /\S/)) { + shift @l; + } + # loop hits trailing "literal 0\nHcmV?d00001\n" + } + } elsif ($in_diff && s/^ //) { # diff context index_diff_inc($self, $_, 'XDFCTX', $xnq); } elsif (/^-- $/) { # email signature begins $in_diff = undef; - } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) { - # wait until "---" and "+++" to capture filenames + } elsif (m!^diff --git ("?[^/]+/.+) ("?[^/]+/.+)\z!) { + # capture filenames here for binary diffs: + my ($fa, $fb) = ($1, $2); + push @$xnq, $_; $in_diff = 1; + $fa = (split(m'/', git_unquote($fa), 2))[1]; + $fb = (split(m'/', git_unquote($fb), 2))[1]; + $seen{$fa}++ or index_diff_inc($self, $fa, 'XDFN', $xnq); + $seen{$fb}++ or index_diff_inc($self, $fb, 'XDFN', $xnq); # traditional diff: } elsif (m/^diff -(.+) (\S+) (\S+)$/) { my ($opt, $fa, $fb) = ($1, $2, $3); - push @xnq, $_; + push @$xnq, $_; # only support unified: next unless $opt =~ /[uU]/; $in_diff = index_old_diff_fn($self, \%seen, $fa, $fb, $xnq); } elsif (m!^--- ("?[^/]+/.+)!) { my $fn = $1; - $fn = (split('/', git_unquote($fn), 2))[1]; + $fn = (split(m'/', git_unquote($fn), 2))[1]; $seen{$fn}++ or index_diff_inc($self, $fn, 'XDFN', $xnq); $in_diff = 1; } elsif (m!^\+\+\+ ("?[^/]+/.+)!) { my $fn = $1; - $fn = (split('/', git_unquote($fn), 2))[1]; + $fn = (split(m'/', 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, $_; + $in_diff = $1; # old diff filename + push @$xnq, $_; } elsif (defined $in_diff && /^\+\+\+ (\S+)/) { $in_diff = index_old_diff_fn($self, \%seen, $in_diff, $1, $xnq); @@ -305,19 +335,19 @@ sub index_diff ($$$) { /^(?:dis)?similarity index / || /^\\ No newline at end of file/ || /^Binary files .* differ/) { - push @xnq, $_; + push @$xnq, $_; } elsif ($_ eq '') { # 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, $_; + push @$xnq, $_; warn "non-diff line: $_\n" if DEBUG && $_ ne ''; $in_diff = undef; } } - index_text($self, join("\n", @xnq), 1, 'XNQ'); + index_text($self, join("\n", @$xnq), 1, 'XNQ'); } sub index_xapian { # msg_iter callback @@ -340,6 +370,20 @@ sub index_xapian { # msg_iter callback defined $s or return; $_[0]->[0] = $part = undef; # free memory + if ($s =~ /^(?:diff|---|\+\+\+) /ms) { + open(my $fh, '+>:utf8', undef) or die "open: $!"; + open(my $eh, '+>', undef) or die "open: $!"; + $fh->autoflush(1); + print $fh $s or die "print: $!"; + sysseek($fh, 0, SEEK_SET) or die "sysseek: $!"; + my $id = ($self->{ibx} // $self->{eidx})->git->qx( + [qw(patch-id --stable)], + {}, { 0 => $fh, 2 => $eh }); + $id =~ /\A([a-f0-9]{40,})/ and $doc->add_term('XDFID'.$1); + seek($eh, 0, SEEK_SET) or die "seek: $!"; + while (<$eh>) { warn $_ } + } + # split off quoted and unquoted blocks: my @sections = PublicInbox::MsgIter::split_quotes($s); undef $s; # free memory @@ -349,7 +393,7 @@ sub index_xapian { # msg_iter callback } else { # does it look like a diff? if ($txt =~ /^(?:diff|---|\+\+\+) /ms) { - index_diff($self, $txt, $doc); + index_diff($self, \$txt, $doc); } else { index_text($self, $txt, 1, 'XNQ'); } @@ -451,10 +495,9 @@ sub add_xapian ($$$$) { sub _msgmap_init ($) { my ($self) = @_; die "BUG: _msgmap_init is only for v1\n" if $self->{ibx}->version != 1; - $self->{mm} //= eval { + $self->{mm} //= do { require PublicInbox::Msgmap; - my $rw = $self->{ibx}->{-no_fsync} ? 2 : 1; - PublicInbox::Msgmap->new($self->{ibx}->{inboxdir}, $rw); + PublicInbox::Msgmap->new_file($self->{ibx}, 1); }; } @@ -518,6 +561,12 @@ sub add_eidx_info { $self->{xdb}->replace_document($docid, $doc); } +sub get_terms { + my ($self, $pfx, $docid) = @_; + begin_txn_lazy($self); + xap_terms($pfx, $self->{xdb}, $docid); +} + sub remove_eidx_info { my ($self, $docid, $eidx_key, $eml) = @_; begin_txn_lazy($self); @@ -794,6 +843,7 @@ sub v1_checkpoint ($$;$) { ${$sync->{max}} = $self->{batch_bytes}; $self->{mm}->{dbh}->commit; + eval { $self->{mm}->{dbh}->do('PRAGMA optimize') }; my $xdb = $self->{xdb}; if ($newest && $xdb) { my $cur = $xdb->get_metadata('last_commit'); @@ -889,20 +939,20 @@ sub log2stack ($$$) { push @cmd, "--$k=$v"; } my $fh = $git->popen(@cmd, $range); - my ($at, $ct, $stk, $cmt); - while (<$fh>) { + my ($at, $ct, $stk, $cmt, $l); + while (defined($l = <$fh>)) { return if $sync->{quit}; - if (/\A([0-9]+)-([0-9]+)-($OID)$/o) { + if ($l =~ /\A([0-9]+)-([0-9]+)-($OID)$/o) { ($at, $ct, $cmt) = ($1 + 0, $2 + 0, $3); $stk //= PublicInbox::IdxStack->new($cmt); - } elsif (/$del/) { + } elsif ($l =~ /$del/) { my $oid = $1; if ($D) { # reindex case $D->{pack('H*', $oid)}++; } else { # non-reindex case: $stk->push_rec('d', $at, $ct, $oid, $cmt); } - } elsif (/$add/) { + } elsif ($l =~ /$add/) { my $oid = $1; if ($D) { my $oid_bin = pack('H*', $oid);