git: add manifest_entry method

We'll be using this for MiscIdx and pre-generating the necessary
JSON for manifest.js.gz, so make it easier to share code for
generating per-repo JSON entries for grokmirror.

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 86343ac9e5a7d9b92c4ee15d79ee7c8c787735d4..917fa4a16e96b76a4a45ebd560035a4bac1b78a4 100644 (file)
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -14,10 +14,12 @@ use POSIX ();
 use IO::Handle; # ->autoflush
 use Errno qw(EINTR);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
+use File::Spec ();
 use Time::HiRes qw(stat);
 use PublicInbox::Spawn qw(popen_rd);
 use PublicInbox::Tmpfile;
 use Carp qw(croak);
+use Digest::SHA ();
 our @EXPORT_OK = qw(git_unquote git_quote);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
@@ -475,6 +477,57 @@ sub modified ($) {
        $modified || time;
 }
 
+# for grokmirror, which doesn't read gitweb.description
+# templates/hooks--update.sample and git-multimail in git.git
+# only match "Unnamed repository", not the full contents of
+# templates/this--description in git.git
+sub manifest_entry {
+       my ($self, $epoch, $default_desc) = @_;
+       my ($fh, $pid) = $self->popen('show-ref');
+       my $dig = Digest::SHA->new(1);
+       while (read($fh, my $buf, 65536)) {
+               $dig->add($buf);
+       }
+       close $fh;
+       waitpid($pid, 0);
+       return if $?; # empty, uninitialized git repo
+       my $git_dir = $self->{git_dir};
+       my $ent = {
+               fingerprint => $dig->hexdigest,
+               reference => undef,
+               modified => modified($self),
+       };
+       chomp(my $owner = $self->qx('config', 'gitweb.owner'));
+       utf8::decode($owner);
+       $ent->{owner} = $owner eq '' ? undef : $owner;
+       my $desc = '';
+       if (open($fh, '<', "$git_dir/description")) {
+               local $/ = "\n";
+               chomp($desc = <$fh>);
+               utf8::decode($desc);
+       }
+       $desc = 'Unnamed repository' if $desc eq '';
+       if (defined $epoch && $desc =~ /\AUnnamed repository/) {
+               $desc = "$default_desc [epoch $epoch]";
+       }
+       $ent->{description} = $desc;
+       if (open($fh, '<', "$git_dir/objects/info/alternates")) {
+               # n.b.: GitPython doesn't seem to handle comments or C-quoted
+               # strings like native git does; and we don't for now, either.
+               local $/ = "\n";
+               chomp(my @alt = <$fh>);
+
+               # grokmirror only supports 1 alternate for "reference",
+               if (scalar(@alt) == 1) {
+                       my $objdir = "$git_dir/objects";
+                       my $ref = File::Spec->rel2abs($alt[0], $objdir);
+                       $ref =~ s!/[^/]+/?\z!!; # basename
+                       $ent->{reference} = $ref;
+               }
+       }
+       $ent;
+}
+
 1;
 __END__
 =pod

diff --git a/lib/PublicInbox/ManifestJsGz.pm b/lib/PublicInbox/ManifestJsGz.pm
index ab1478afcc38507245a8b41b9ac0ddfcb747d5c9..3d8a38ae3ca969622e21aea7589f34102208b00a 100644 (file)
--- a/lib/PublicInbox/ManifestJsGz.pm
+++ b/lib/PublicInbox/ManifestJsGz.pm
@@ -6,15 +6,12 @@ package PublicInbox::ManifestJsGz;
 use strict;
 use v5.10.1;
 use parent qw(PublicInbox::WwwListing);
-use Digest::SHA ();
-use File::Spec ();
 use bytes (); # length
 use PublicInbox::Inbox;
 use PublicInbox::Config;
 use PublicInbox::Git;
 use IO::Compress::Gzip qw(gzip);
 use HTTP::Date qw(time2str);
-*try_cat = \&PublicInbox::Inbox::try_cat;
 
 our $json = PublicInbox::Config::json();
 
@@ -26,21 +23,6 @@ sub url_regexp {
        $ctx->SUPER::url_regexp('publicInbox.grokManifest', 'match=domain');
 }
 
-sub fingerprint ($) {
-       my ($git) = @_;
-       # TODO: convert to qspawn for fairness when there's
-       # thousands of repos
-       my ($fh, $pid) = $git->popen('show-ref');
-       my $dig = Digest::SHA->new(1);
-       while (read($fh, my $buf, 65536)) {
-               $dig->add($buf);
-       }
-       close $fh;
-       waitpid($pid, 0);
-       return if $?; # empty, uninitialized git repo
-       $dig->hexdigest;
-}
-
 sub manifest_add ($$;$$) {
        my ($ctx, $ibx, $epoch, $default_desc) = @_;
        my $url_path = "/$ibx->{name}";
@@ -51,48 +33,13 @@ sub manifest_add ($$;$$) {
        }
        return unless -d $git_dir;
        my $git = PublicInbox::Git->new($git_dir);
-       my $fingerprint = fingerprint($git) or return; # no empty repos
-
-       chomp(my $owner = $git->qx('config', 'gitweb.owner'));
-       chomp(my $desc = try_cat("$git_dir/description"));
-       utf8::decode($owner);
-       utf8::decode($desc);
-       $owner = undef if $owner eq '';
-       $desc = 'Unnamed repository' if $desc eq '';
-
-       # templates/hooks--update.sample and git-multimail in git.git
-       # only match "Unnamed repository", not the full contents of
-       # templates/this--description in git.git
-       if ($desc =~ /\AUnnamed repository/) {
-               $desc = "$default_desc [epoch $epoch]" if defined($epoch);
-       }
-
-       my $reference;
-       chomp(my $alt = try_cat("$git_dir/objects/info/alternates"));
-       if ($alt) {
-               # n.b.: GitPython doesn't seem to handle comments or C-quoted
-               # strings like native git does; and we don't for now, either.
-               my @alt = split(/\n+/, $alt);
-
-               # grokmirror only supports 1 alternate for "reference",
-               if (scalar(@alt) == 1) {
-                       my $objdir = "$git_dir/objects";
-                       $reference = File::Spec->rel2abs($alt[0], $objdir);
-                       $reference =~ s!/[^/]+/?\z!!; # basename
-               }
-       }
+       my $ent = $git->manifest_entry($epoch, $default_desc) or return;
        $ctx->{-abs2urlpath}->{$git_dir} = $url_path;
-       my $modified = $git->modified;
+       my $modified = $ent->{modified};
        if ($modified > ($ctx->{-mtime} // 0)) {
                $ctx->{-mtime} = $modified;
        }
-       $ctx->{manifest}->{$url_path} = {
-               owner => $owner,
-               reference => $reference,
-               description => $desc,
-               modified => $modified,
-               fingerprint => $fingerprint,
-       };
+       $ctx->{manifest}->{$url_path} = $ent;
 }
 
 sub ibx_entry {

diff --git a/t/www_listing.t b/t/www_listing.t
index 4309a5e17ba24e176409937b21e7475e95a65ed1..636133715eb1f4cbe5c93ac56197c9d29430727e 100644 (file)
--- a/t/www_listing.t
+++ b/t/www_listing.t
@@ -21,8 +21,7 @@ use_ok 'PublicInbox::Git';
 my ($tmpdir, $for_destroy) = tmpdir();
 my $bare = PublicInbox::Git->new("$tmpdir/bare.git");
 PublicInbox::Import::init_bare($bare->{git_dir});
-is(PublicInbox::ManifestJsGz::fingerprint($bare), undef,
-       'empty repo has no fingerprint');
+is($bare->manifest_entry, undef, 'empty repo has no manifest entry');
 {
        my $fi_data = './t/git.fast-import-data';
        open my $fh, '<', $fi_data or die "open $fi_data: $!";
@@ -31,7 +30,7 @@ is(PublicInbox::ManifestJsGz::fingerprint($bare), undef,
                'fast-import');
 }
 
-like(PublicInbox::ManifestJsGz::fingerprint($bare), qr/\A[a-f0-9]{40}\z/,
+like($bare->manifest_entry->{fingerprint}, qr/\A[a-f0-9]{40}\z/,
        'got fingerprint with non-empty repo');
 
 sub tiny_test {