diff options
Diffstat (limited to 't/cindex.t')
-rw-r--r-- | t/cindex.t | 302 |
1 files changed, 302 insertions, 0 deletions
diff --git a/t/cindex.t b/t/cindex.t new file mode 100644 index 00000000..90236287 --- /dev/null +++ b/t/cindex.t @@ -0,0 +1,302 @@ +#!perl -w +# Copyright (C) all contributors <meta@public-inbox.org> +# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> +use v5.12; +use PublicInbox::TestCommon; +use Cwd qw(getcwd); +use List::Util qw(sum); +use autodie qw(close mkdir open rename); +require_mods(qw(json Xapian +SCM_RIGHTS)); +use_ok 'PublicInbox::CodeSearchIdx'; +use PublicInbox::Import; +my ($tmp, $for_destroy) = tmpdir(); +my $pwd = getcwd(); +my @unused_keys = qw(last_commit has_threadid skip_docdata); +local $ENV{PI_CONFIG} = '/dev/null'; +# local $ENV{TAIL_ALL} = $ENV{TAIL_ALL} // 1; # while features are unstable +my $opt = { 1 => \(my $cidx_out), 2 => \(my $cidx_err) }; + +# I reworked CodeSearchIdx->shard_worker to handle empty trees +# in the initial commit generated by cvs2svn for xapian.git +create_coderepo 'empty-tree-root-0600', tmpdir => "$tmp/wt0", sub { + xsys_e([qw(/bin/sh -c), <<'EOM']); +git init -q && +git config core.sharedRepository 0600 +tree=$(git mktree </dev/null) && +head=$(git symbolic-ref HEAD) && +cmt=$(echo 'empty root' | git commit-tree $tree) && +git update-ref $head $cmt && +echo hi >f && +git add f && +git commit -q -m hi && +git gc -q +EOM +}; # /create_coderepo + +ok(run_script([qw(-cindex --dangerous -q -g), "$tmp/wt0"]), 'cindex internal'); +{ + my $exists = -e "$tmp/wt0/.git/public-inbox-cindex/cidx.lock"; + my @st = stat(_); + ok($exists, 'internal dir created'); + is($st[2] & 0600, 0600, 'mode respects core.sharedRepository'); + @st = stat("$tmp/wt0/.git/public-inbox-cindex"); + is($st[2] & 0700, 0700, 'dir mode respects core.sharedRepository'); +} + +# it's possible for git to emit NUL characters in diffs +# (see c4201214cbf10636e2c1ab9131573f735b42c8d4 in linux.git) +my $zp = create_coderepo 'NUL in patch', sub { + my $src = PublicInbox::IO::try_cat("$pwd/COPYING"); + xsys_e([qw(git init -q)]); + + # needs to be further than FIRST_FEW_BYTES (8000) in git.git + $src =~ s/\b(Limitation of Liability\.)\n\n/$1\n\0\n/s or + xbail "BUG: no `\\n\\n' in $pwd/COPYING"; + + PublicInbox::IO::write_file '>', 'f', $src; + xsys_e([qw(/bin/sh -c), <<'EOM']); +git add f && +git commit -q -m 'initial with NUL character' +EOM + $src =~ s/\n\0\n/\n\n/ or xbail "BUG: no `\\n\\0\\n'"; + PublicInbox::IO::write_file '>', 'f', $src; + xsys_e([qw(/bin/sh -c), <<'EOM']); +git add f && +git commit -q -m 'remove NUL character' && +git gc -q +EOM +}; # /create_coderepo + +$zp = File::Spec->rel2abs($zp); +ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext", + '-g', $zp, '-g', "$tmp/wt0" ]), + 'cindex external'); +ok(-e "$tmp/ext/cidx.lock", 'external dir created'); +ok(!-d "$zp/.git/public-inbox-cindex", 'no cindex in original coderepo'); + +ok(run_script([qw(-cindex -L medium --dangerous -q -d), + "$tmp/med", '-g', $zp, '-g', "$tmp/wt0"]), 'cindex external medium'); + + +SKIP: { + have_xapian_compact 2; + ok(run_script([qw(-compact -q), "$tmp/ext"]), 'compact on full'); + ok(run_script([qw(-compact -q), "$tmp/med"]), 'compact on medium'); +} + +my $no_metadata_set = sub { + my ($i, $extra, $xdb) = @_; + for my $xdb (@$xdb) { + for my $k (@unused_keys, @$extra) { + is($xdb->get_metadata($k) // '', '', + "metadata $k unset in shard #$i"); + } + ++$i; + } +}; + +{ + my $mid_size = sum(map { -s $_ } glob("$tmp/med/cidx*/*/*")); + my $full_size = sum(map { -s $_ } glob("$tmp/ext/cidx*/*/*")); + ok($full_size > $mid_size, 'full size > mid size') or + diag "full=$full_size mid=$mid_size"; + for my $l (qw(med ext)) { + ok(run_script([qw(-cindex -q --reindex -u -d), "$tmp/$l"]), + "reindex $l"); + } + $mid_size = sum(map { -s $_ } glob("$tmp/med/cidx*/*/*")); + $full_size = sum(map { -s $_ } glob("$tmp/ext/cidx*/*/*")); + ok($full_size > $mid_size, 'full size > mid size after reindex') or + diag "full=$full_size mid=$mid_size"; + my $csrch = PublicInbox::CodeSearch->new("$tmp/med"); + my ($xdb0, @xdb) = $csrch->xdb_shards_flat; + $no_metadata_set->(0, [], [ $xdb0 ]); + is($xdb0->get_metadata('indexlevel'), 'medium', + 'indexlevel set in shard #0'); + $no_metadata_set->(1, ['indexlevel'], \@xdb); + + ok(run_script([qw(-cindex -q -L full --reindex -u -d), "$tmp/med"]), + 'reindex medium as full'); + @xdb = $csrch->xdb_shards_flat; + $no_metadata_set->(0, ['indexlevel'], \@xdb); +} + +use_ok 'PublicInbox::CodeSearch'; + + +my @xh_args; +my $exp = [ 'initial with NUL character', 'remove NUL character' ]; +my $zp_git = "$zp/.git"; +if ('multi-repo search') { + my $csrch = PublicInbox::CodeSearch->new("$tmp/ext"); + my $mset = $csrch->mset('NUL'); + is(scalar($mset->items), 2, 'got results'); + my @have = sort(map { $_->get_document->get_data } $mset->items); + is_xdeeply(\@have, $exp, 'got expected subjects'); + + $mset = $csrch->mset('NUL', { git_dir => "$tmp/wt0/.git" }); + is(scalar($mset->items), 0, 'no results with other GIT_DIR'); + + $mset = $csrch->mset('NUL', { git_dir => $zp_git }); + @have = sort(map { $_->get_document->get_data } $mset->items); + is_xdeeply(\@have, $exp, 'got expected subjects w/ GIT_DIR filter'); + my @xdb = $csrch->xdb_shards_flat; + $no_metadata_set->(0, ['indexlevel'], \@xdb); + @xh_args = $csrch->xh_args; +} + +my $test_xhc = sub { + my ($xhc) = @_; + my $csrch = PublicInbox::CodeSearch->new("$tmp/ext"); + my $impl = $xhc->{impl}; + my ($r, @l); + $r = $xhc->mkreq([], qw(mset -c -g), $zp_git, @xh_args, 'NUL'); + chomp(@l = <$r>); + like shift(@l), qr/\bmset\.size=2\b/, "got expected header $impl"; + my %docid2data; + my @got = sort map { + my ($docid, $pct, $rank, @extra) = split /\0/; + ok $pct >= 0 && $pct <= 100, 'pct in range'; + ok $rank >= 0 && $rank <= 100000, 'rank ok'; + is scalar(@extra), 0, 'no extra fields'; + $docid2data{$docid} = + $csrch->xdb->get_document($docid)->get_data; + } @l; + is_deeply(\@got, $exp, "expected doc_data $impl"); + + $r = $xhc->mkreq([], qw(mset -c -g), "$tmp/wt0/.git", @xh_args, 'NUL'); + chomp(@l = <$r>); + like shift(@l), qr/\bmset.size=0\b/, "got miss in wrong dir $impl"; + is_deeply(\@l, [], "no extra lines $impl"); + + while (my ($did, $expect) = each %docid2data) { + is_deeply($csrch->xdb->get_document($did)->get_data, + $expect, "docid=$did data matches"); + } + ok(!$xhc->{io}->close, "$impl close"); + is($?, 66 << 8, "got EX_NOINPUT from $impl exit"); +}; + +SKIP: { + require_mods('+SCM_RIGHTS', 1); + require PublicInbox::XapClient; + my $xhc = PublicInbox::XapClient::start_helper('-j0'); + my $csrch = PublicInbox::CodeSearch->new("$tmp/ext"); + $test_xhc->($xhc, $csrch); + skip 'PI_NO_CXX set', 1 if $ENV{PI_NO_CXX}; + $xhc->{impl} =~ /Cxx/ or + skip 'C++ compiler or xapian development libs missing', 1; + skip 'TEST_XH_CXX_ONLY set', 1 if $ENV{TEST_XH_CXX_ONLY}; + local $ENV{PI_NO_CXX} = 1; # force XS or SWIG binding test + $xhc = PublicInbox::XapClient::start_helper('-j0'); + $test_xhc->($xhc, $csrch); +} + +if ('--update') { + my $csrch = PublicInbox::CodeSearch->new("$tmp/ext"); + my $mset = $csrch->mset('dfn:for-update'); + is(scalar($mset->items), 0, 'no result before update'); + + my $e = \%PublicInbox::TestCommon::COMMIT_ENV; + xsys_e([qw(/bin/sh -c), <<'EOM'], $e, { -C => "$tmp/wt0" }); +>for-update && git add for-update && git commit -q -m updated +EOM + ok(run_script([qw(-cindex -qu -d), "$tmp/ext"]), '-cindex -u'); + $mset = $csrch->reopen->mset('dfn:for-update'); + is(scalar($mset->items), 1, 'got updated result'); + + ok(run_script([qw(-cindex -qu --reindex -d), "$tmp/ext"]), 'reindex'); + $mset = $csrch->reopen->mset('dfn:for-update'); + is(scalar($mset->items), 1, 'same result after reindex'); +} + +SKIP: { # --prune + require_cmd($ENV{XAPIAN_DELVE} || 'xapian-delve', 1); + require_git v2.6, 1; + my $csrch = PublicInbox::CodeSearch->new("$tmp/ext"); + is(scalar($csrch->mset('s:hi')->items), 1, 'got hit'); + + rename("$tmp/wt0/.git", "$tmp/wt0/.giit"); + ok(run_script([qw(-cindex -q --prune -d), "$tmp/ext"], undef, $opt), + 'prune'); + is(${$opt->{2}}, '', 'nothing in stderr') or diag explain($opt); + $csrch->reopen; + is(scalar($csrch->mset('s:hi')->items), 0, 'hit pruned'); + + rename("$tmp/wt0/.giit", "$tmp/wt0/.git"); + ok(run_script([qw(-cindex -qu -d), "$tmp/ext"]), 'update'); + $csrch->reopen; + is(scalar($csrch->mset('s:hi')->items), 0, + 'hit stays pruned since GIT_DIR was previously pruned'); + isnt(scalar($csrch->mset('s:NUL')->items), 0, + 'prune did not clobber entire index'); +} + +File::Path::remove_tree("$tmp/ext"); +mkdir("$tmp/ext", 0707); +ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext", '-g', $zp]), + 'external on existing dir'); +{ + my @st = stat("$tmp/ext/cidx.lock"); + is($st[2] & 0777, 0604, 'created lock respects odd permissions'); +} + +ok(run_script([qw(-xcpdb), "$tmp/ext"]), 'xcpdb upgrade'); +ok(run_script([qw(-xcpdb -R4), "$tmp/ext"]), 'xcpdb reshard'); + +SKIP: { + have_xapian_compact 2; + ok(run_script([qw(-xcpdb -R2 --compact), "$tmp/ext"]), + 'xcpdb reshard+compact'); + ok(run_script([qw(-xcpdb --compact), "$tmp/ext"]), 'xcpdb compact'); +}; + +SKIP: { + require_cmd('join', 1); + my $basic = create_inbox 'basic', indexlevel => 'basic', sub { + my ($im, $ibx) = @_; + $im->add(eml_load('t/plack-qp.eml')); + }; + my $env = { PI_CONFIG => "$tmp/pi_config" }; + PublicInbox::IO::write_file '>', $env->{PI_CONFIG}, <<EOM; +[publicinbox "basictest"] + inboxdir = $basic->{inboxdir} + address = basic\@example.com +EOM + my $cmd = [ qw(-cindex -u --all -d), "$tmp/ext", + '--join=aggressive,dt:19700101000000..now', + '-I', $basic->{inboxdir} ]; + $cidx_out = $cidx_err = ''; + ok(run_script($cmd, $env, $opt), 'join w/o search'); + like($cidx_err, qr/W: \Q$basic->{inboxdir}\E not indexed for search/s, + 'non-Xapian-enabled inbox noted'); +} + +# we need to support blank sections for a top-level repos +# (e.g. <https://example.com/my-project> +# git.kernel.org could use "pub" as section name, though, since all git repos +# are currently under //git.kernel.org/pub/**/* +{ + mkdir(my $d = "$tmp/blanksection"); + my $cfg = cfg_new($d, <<EOM); +[cindex ""] + topdir = $tmp/ext + localprefix = $tmp +EOM + my $csrch = $cfg->lookup_cindex(''); + is ref($csrch), 'PublicInbox::CodeSearch', 'codesearch w/ blank name'; + is_deeply $csrch->{localprefix}, [ "$tmp" ], 'localprefix respected'; + my $nr = 0; + $cfg->each_cindex(sub { + my ($cs, @rest) = @_; + is $cs->{topdir}, $csrch->{topdir}, 'each_cindex works'; + is_deeply \@rest, [ '.' ], 'got expected arg'; + ++$nr; + }, '.'); + is $nr, 1, 'iterated through cindices'; + my $oid = 'dba13ed2ddf783ee8118c6a581dbf75305f816a3'; + my $mset = $csrch->mset("dfpost:$oid"); + is $mset->size, 1, 'got result from full OID search'; +} + +done_testing; |