search: support "patchid:" prefix (git patch-id --stable)

[public-inbox.git] / lib / PublicInbox / SearchIdx.pm

diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index bebe904b783a990491c41ac1a8cd667a1530d733..53ec23a5c50c4facfcf1977ea04f2fa4498d8805 100644 (file)
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2015-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 # 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;
@@ -30,6 +31,7 @@ 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:
@@ -115,7 +117,10 @@ 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 +144,12 @@ 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 +237,8 @@ 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);
@@ -259,6 +268,7 @@ sub index_diff ($$$) {
                } elsif (m!^diff --git "?[^/]+/.+ "?[^/]+/.+\z!) {
                        # wait until "---" and "+++" to capture filenames
                        $in_diff = 1;
+                       push @xnq, $_;
                # traditional diff:
                } elsif (m/^diff -(.+) (\S+) (\S+)$/) {
                        my ($opt, $fa, $fb) = ($1, $2, $3);
@@ -269,12 +279,12 @@ sub index_diff ($$$) {
                                                        $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+)/) {
@@ -340,6 +350,20 @@ 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
@@ -451,10 +475,9 @@ 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 +541,12 @@ 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 +823,7 @@ 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 +919,20 @@ 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);