cindex: require `-g GIT_DIR' or `-r PROJECT_ROOT'

Accepting @ARGV without switches ends up being ambiguous with
optional parameters for --join and --show.  Requiring users to
specify `--join=' or `--show=' is a bit awkward (as it with
-clone --objstore= and the like, but that is historical baggage
we need to carry at this point...)

diff --git a/Documentation/public-inbox-cindex.pod b/Documentation/public-inbox-cindex.pod
index 3ff394be5cb60dda2d5af9425ec1961bb288bfc5..0c9c4bdbff03231faa7ffd55611dcedc747eb208 100644 (file)
--- a/Documentation/public-inbox-cindex.pod
+++ b/Documentation/public-inbox-cindex.pod
@@ -4,7 +4,7 @@ public-inbox-cindex - create and update search for code repositories
 
 =head1 SYNOPSIS
 
-public-inbox-cindex [OPTIONS] GIT_DIR...
+public-inbox-cindex [OPTIONS] -g GIT_DIR [-g GIT_DIR]
 
 public-inbox-cindex [OPTIONS] --update
 

diff --git a/lib/PublicInbox/CodeSearchIdx.pm b/lib/PublicInbox/CodeSearchIdx.pm
index a6cbe0b07b6d4b570c6fab51b0dea1214fca7fb9..d49e9a8dee01a1c509c145146aa60ce010c5547f 100644 (file)
--- a/lib/PublicInbox/CodeSearchIdx.pm
+++ b/lib/PublicInbox/CodeSearchIdx.pm
@@ -1131,8 +1131,6 @@ sub init_join_prefork ($) {
        } split(/,/, join(',', @$subopt));
        require PublicInbox::CidxXapHelperAux;
        require PublicInbox::XapClient;
-       my $cfg = $self->{-opt}->{-pi_cfg} // die 'BUG: -pi_cfg unset';
-       $self->{-cfg_f} = $cfg->{-f} = rel2abs_collapsed($cfg->{-f});
        my @unknown;
        my $pfx = $JOIN{prefixes} // 'patchid';
        for (split /\+/, $pfx) {
@@ -1223,7 +1221,8 @@ sub cidx_run { # main entry point
                                $PublicInbox::SearchIdx::BATCH_BYTES;
        local $MAX_SIZE = $self->{-opt}->{max_size};
        local $self->{PENDING} = {}; # used by PublicInbox::CidxXapHelperAux
-       local $self->{-cfg_f};
+       my $cfg = $self->{-opt}->{-pi_cfg} // die 'BUG: -pi_cfg unset';
+       $self->{-cfg_f} = $cfg->{-f} = rel2abs_collapsed($cfg->{-f});
        if (grep { $_ } @{$self->{-opt}}{qw(prune join)}) {
                require File::Temp;
                $TMPDIR = File::Temp->newdir('cidx-all-git-XXXX', TMPDIR => 1);

diff --git a/script/public-inbox-cindex b/script/public-inbox-cindex
index 97890c1bd730328de7994da205656b1023710ed5..a015d7a4f06769f7f65a5845f03c97510fc0506c 100755 (executable)
--- a/script/public-inbox-cindex
+++ b/script/public-inbox-cindex
@@ -4,8 +4,8 @@
 use v5.12;
 use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
 my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
-usage: public-inbox-cindex [options] GIT_DIR...
-usage: public-inbox-cindex [options] --project-list=FILE PROJECT_ROOT
+usage: public-inbox-cindex [options] -g GIT_DIR...
+usage: public-inbox-cindex [options] --project-list=FILE -r PROJECT_ROOT
 
   Create and update search indices for code repos
 
@@ -29,7 +29,8 @@ GetOptions($opt, qw(quiet|q verbose|v+ reindex jobs|j=i fsync|sync! dangerous
                indexlevel|index-level|L=s join:s@
                batch_size|batch-size=s max_size|max-size=s
                include|I=s@ only=s@ all show:s@
-               project-list=s exclude=s@
+               project-list=s exclude=s@ project-root|r=s
+               git-dir|g=s@
                sort-parallel=s sort-compress-program=s sort-buffer-size=s
                d=s update|u scan! prune dry-run|n C=s@ help|h))
        or die $help;
@@ -50,23 +51,36 @@ PublicInbox::Admin::progress_prepare($opt);
 my $env = PublicInbox::Admin::index_prepare($opt, $cfg);
 %ENV = (%ENV, %$env) if $env;
 
-require PublicInbox::CodeSearchIdx; # unstable internal API
 my @git_dirs;
-if (defined(my $pl = $opt->{'project-list'})) {
-       my $pfx = shift @ARGV // die <<EOM;
+require PublicInbox::CodeSearchIdx; # unstable internal API
+if (@ARGV) {
+       my @g = map { "-g $_" } @ARGV;
+       die <<EOM;
+Specify git directories with `-g' (or --git-dir=): @g
+Or use --project-list=... and --project-root=...
+EOM
+} elsif (defined(my $pl = $opt->{'project-list'})) {
+       my $pfx = $opt->{'project-root'} // die <<EOM;
 PROJECTS_ROOT required for --project-list
 EOM
-       @ARGV and die <<EOM;
---project-list does not accept additional directories
-(@ARGV)
-beyond `$pfx'
+       $opt->{'git-dir'} and die <<EOM;
+--project-list does not accept additional --git-dir directories
+(@{$opt->{'git-dir'}})
 EOM
        open my $fh, '<', $pl or die "open($pl): $!\n";
        chomp(@git_dirs = <$fh>);
-       $_ = PublicInbox::Admin::resolve_git_dir("$pfx/$_") for @git_dirs;
+       $pfx .= '/';
+       $pfx =~ tr!/!/!s;
+       substr($_, 0, 0, $pfx) for @git_dirs;
+} elsif (my $gd = $opt->{'git-dir'}) {
+       @git_dirs = @$gd;
+} elsif (grep defined, @$opt{qw(show update prune)}) {
 } else {
-       @git_dirs = map { PublicInbox::Admin::resolve_git_dir($_) } @ARGV;
+       warn "No --git-dir= nor --project-list= + --project-root= specified\n";
+       die $help;
 }
+
+$_ = PublicInbox::Admin::resolve_git_dir($_) for @git_dirs;
 if (defined $cidx_dir) { # external index
        die "`%' is not allowed in $cidx_dir\n" if $cidx_dir =~ /\%/;
        my $cidx = PublicInbox::CodeSearchIdx->new($cidx_dir, $opt);

diff --git a/t/cindex-join.t b/t/cindex-join.t
index ac90cd6481f794bb6399e409863f7f9eb8579afd..c2e85332446ad94b5469fcc757b45fd61b46a712 100644 (file)
--- a/t/cindex-join.t
+++ b/t/cindex-join.t
@@ -70,7 +70,7 @@ my $cidxdir = "$tmpdir/cidx";
 my $rdr = { 1 => \my $cout, 2 => \my $cerr };
 ok run_script([qw(-cindex -v --all --show=join_data),
                '--join=aggressive,dt:..2022-12-01',
-               '-d', $cidxdir, values %code ],
+               '-d', $cidxdir, map { ('-g', $_) } values %code ],
                $env, $rdr), 'initial join inboxes w/ coderepos';
 my $out = PublicInbox::Config->json->decode($cout);
 is($out->{join_data}->{dt}->[0], '19700101'.'000000',
@@ -79,4 +79,9 @@ is($out->{join_data}->{dt}->[0], '19700101'.'000000',
 ok run_script([qw(-cindex -v --all -u --join --show),
                '-d', $cidxdir], $env, $rdr), 'incremental --join';
 
+ok run_script([qw(-cindex -v --no-scan --show),
+               '-d', $cidxdir], $env, $rdr), 'show';
+$out = PublicInbox::Config->json->decode($cout);
+is ref($out->{join_data}), 'HASH', 'got hash join data';
+is $cerr, '', 'no warnings or errors in stderr w/ --show';
 done_testing;

diff --git a/t/cindex.t b/t/cindex.t
index 29d88ca8a4baa148cf1d37aae41dec9e22bc621e..0193cf1811d526305fd12ef36d729256cdc3b841 100644 (file)
--- a/t/cindex.t
+++ b/t/cindex.t
@@ -33,7 +33,7 @@ git gc -q
 EOM
 }; # /create_coderepo
 
-ok(run_script([qw(-cindex --dangerous -q), "$tmp/wt0"]), 'cindex internal');
+ok(run_script([qw(-cindex --dangerous -q -g), "$tmp/wt0"]), 'cindex internal');
 {
        my $exists = -e "$tmp/wt0/.git/public-inbox-cindex/cidx.lock";
        my @st = stat(_);
@@ -67,13 +67,14 @@ git gc -q
 EOM
 }; # /create_coderepo
 
-ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext", $zp, "$tmp/wt0"]),
+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", $zp, "$tmp/wt0"]), 'cindex external medium');
+       "$tmp/med", '-g', $zp, '-g', "$tmp/wt0"]), 'cindex external medium');
 
 
 SKIP: {
@@ -228,7 +229,7 @@ SKIP: { # --prune
 
 File::Path::remove_tree("$tmp/ext");
 mkdir("$tmp/ext", 0707);
-ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext", $zp]),
+ok(run_script([qw(-cindex --dangerous -q -d), "$tmp/ext", '-g', $zp]),
        'external on existing dir');
 {
        my @st = stat("$tmp/ext/cidx.lock");

diff --git a/t/xap_helper.t b/t/xap_helper.t
index ee25b2dc4913161dc1be6393730f5842ab8029ae..37679ae909ebfa1441aa5d3f75e7031d56d5d0da 100644 (file)
--- a/t/xap_helper.t
+++ b/t/xap_helper.t
@@ -20,10 +20,10 @@ my $crepo = create_coderepo 'for-cindex', sub {
        xsys_e([qw(git init -q --bare)]);
        xsys_e([qw(git fast-import --quiet)], undef, { 0 => $fi_fh });
        chdir($dh);
-       run_script([qw(-cindex --dangerous -L medium --no-fsync -q -j1), $d])
+       run_script([qw(-cindex --dangerous -L medium --no-fsync -q -j1), '-g', $d])
                or xbail '-cindex internal';
        run_script([qw(-cindex --dangerous -L medium --no-fsync -q -j3 -d),
-               "$d/cidx-ext", $d]) or xbail '-cindex "external"';
+               "$d/cidx-ext", '-g', $d]) or xbail '-cindex "external"';
 };
 $dh = $fi_fh = undef;