X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWwwListing.pm;h=12b0d9ad5f3f0bedae69919f3a9a4b0de557ff1f;hb=de9648ca847cf032aab6da9cac1217bf9cca9c90;hp=a416d24f0e446e27ae3c3148b061be9128ca7350;hpb=846161e3d1207d59f62b3a6718221d6f5ba2b94f;p=public-inbox.git
diff --git a/lib/PublicInbox/WwwListing.pm b/lib/PublicInbox/WwwListing.pm
index a416d24f..12b0d9ad 100644
--- a/lib/PublicInbox/WwwListing.pm
+++ b/lib/PublicInbox/WwwListing.pm
@@ -5,23 +5,11 @@
# Used by PublicInbox::WWW
package PublicInbox::WwwListing;
use strict;
-use warnings;
-use PublicInbox::Hval qw(ascii_html prurl);
+use PublicInbox::Hval qw(ascii_html prurl fmt_ts);
use PublicInbox::Linkify;
-use PublicInbox::View;
-use PublicInbox::Inbox;
+use PublicInbox::GzipFilter qw(gzf_maybe);
+use PublicInbox::ManifestJsGz;
use bytes (); # bytes::length
-use HTTP::Date qw(time2str);
-use Digest::SHA ();
-use File::Spec ();
-use IO::Compress::Gzip qw(gzip);
-*try_cat = \&PublicInbox::Inbox::try_cat;
-our $json;
-for my $mod (qw(JSON::MaybeXS JSON JSON::PP)) {
- eval "require $mod" or next;
- # ->ascii encodes non-ASCII to "\uXXXX"
- $json = $mod->new->ascii(1) and last;
-}
sub list_all_i {
my ($ibx, $arg) = @_;
@@ -39,7 +27,7 @@ sub list_all ($$$) {
sub list_match_domain_i {
my ($ibx, $arg) = @_;
my ($list, $hide_key, $re) = @$arg;
- if (!$ibx->{-hide}->{$hide_key} && grep($re, @{$ibx->{url}})) {
+ if (!$ibx->{-hide}->{$hide_key} && grep(/$re/, @{$ibx->{url}})) {
push @$list, $ibx;
}
}
@@ -59,9 +47,9 @@ sub list_404 ($$) { [] }
# TODO: +cgit
my %VALID = (
- all => *list_all,
- 'match=domain' => *list_match_domain,
- 404 => *list_404,
+ all => \&list_all,
+ 'match=domain' => \&list_match_domain,
+ 404 => \&list_404,
);
sub set_cb ($$$) {
@@ -90,7 +78,7 @@ sub new {
sub ibx_entry {
my ($mtime, $ibx, $env) = @_;
- my $ts = PublicInbox::View::fmt_ts($mtime);
+ my $ts = fmt_ts($mtime);
my $url = prurl($env, $ibx->{url});
my $tmp = <<"";
* $ts - $url
@@ -104,13 +92,15 @@ sub ibx_entry {
sub html ($$) {
my ($env, $list) = @_;
- my $title = 'public-inbox';
- my $out = '';
+ my $h = [ 'Content-Type', 'text/html; charset=UTF-8',
+ 'Content-Length', undef ];
+ my $gzf = gzf_maybe($h, $env);
+ $gzf->zmore('' .
+ 'public-inbox listing' .
+ '');
my $code = 404;
if (@$list) {
- $title .= ' - listing';
$code = 200;
-
# Schwartzian transform since Inbox->modified is expensive
@$list = sort {
$b->[0] <=> $a->[0]
@@ -118,116 +108,17 @@ sub html ($$) {
my $tmp = join("\n", map { ibx_entry(@$_, $env) } @$list);
my $l = PublicInbox::Linkify->new;
- $out = ''.$l->to_html($tmp).'
';
+ $gzf->zmore($l->to_html($tmp));
+ } else {
+ $gzf->zmore('no inboxes, yet');
}
- $out = "$title" . $out;
- $out .= ''. PublicInbox::WwwStream::code_footer($env) .
- '
';
-
- my $h = [ 'Content-Type', 'text/html; charset=UTF-8' ];
+ my $out = $gzf->zflush('
'.
+ PublicInbox::WwwStream::code_footer($env) .
+ '
');
+ $h->[3] = bytes::length($out);
[ $code, $h, [ $out ] ];
}
-sub fingerprint ($) {
- my ($git) = @_;
- # TODO: convert to qspawn for fairness when there's
- # thousands of repos
- my ($fh, $pid) = $git->popen('show-ref');
- my $dig = Digest::SHA->new(1);
- while (read($fh, my $buf, 65536)) {
- $dig->add($buf);
- }
- close $fh;
- waitpid($pid, 0);
- return if $?; # empty, uninitialized git repo
- $dig->hexdigest;
-}
-
-sub manifest_add ($$;$$) {
- my ($manifest, $ibx, $epoch, $default_desc) = @_;
- my $url_path = "/$ibx->{name}";
- my $git_dir = $ibx->{inboxdir};
- if (defined $epoch) {
- $git_dir .= "/git/$epoch.git";
- $url_path .= "/git/$epoch.git";
- }
- return unless -d $git_dir;
- my $git = PublicInbox::Git->new($git_dir);
- my $fingerprint = fingerprint($git) or return; # no empty repos
-
- chomp(my $owner = $git->qx('config', 'gitweb.owner'));
- chomp(my $desc = try_cat("$git_dir/description"));
- $owner = undef if $owner eq '';
- $desc = 'Unnamed repository' if $desc eq '';
- utf8::decode($desc);
- utf8::decode($owner);
-
- # templates/hooks--update.sample and git-multimail in git.git
- # only match "Unnamed repository", not the full contents of
- # templates/this--description in git.git
- if ($desc =~ /\AUnnamed repository/) {
- $desc = "$default_desc [epoch $epoch]" if defined($epoch);
- }
-
- my $reference;
- chomp(my $alt = try_cat("$git_dir/objects/info/alternates"));
- if ($alt) {
- # n.b.: GitPython doesn't seem to handle comments or C-quoted
- # strings like native git does; and we don't for now, either.
- my @alt = split(/\n+/, $alt);
-
- # grokmirror only supports 1 alternate for "reference",
- if (scalar(@alt) == 1) {
- my $objdir = "$git_dir/objects";
- $reference = File::Spec->rel2abs($alt[0], $objdir);
- $reference =~ s!/[^/]+/?\z!!; # basename
- }
- }
- $manifest->{-abs2urlpath}->{$git_dir} = $url_path;
- my $modified = $git->modified;
- if ($modified > $manifest->{-mtime}) {
- $manifest->{-mtime} = $modified;
- }
- $manifest->{$url_path} = {
- owner => $owner,
- reference => $reference,
- description => $desc,
- modified => $modified,
- fingerprint => $fingerprint,
- };
-}
-
-# manifest.js.gz
-sub js ($$) {
- my ($env, $list) = @_;
- # $json won't be defined if IO::Compress::Gzip is missing
- $json or return [ 404, [], [] ];
-
- my $manifest = { -abs2urlpath => {}, -mtime => 0 };
- for my $ibx (@$list) {
- if (defined(my $max = $ibx->max_git_epoch)) {
- my $desc = $ibx->description;
- for my $epoch (0..$max) {
- manifest_add($manifest, $ibx, $epoch, $desc);
- }
- } else {
- manifest_add($manifest, $ibx);
- }
- }
- my $abs2urlpath = delete $manifest->{-abs2urlpath};
- my $mtime = delete $manifest->{-mtime};
- while (my ($url_path, $repo) = each %$manifest) {
- defined(my $abs = $repo->{reference}) or next;
- $repo->{reference} = $abs2urlpath->{$abs};
- }
- my $out;
- gzip(\($json->encode($manifest)) => \$out);
- $manifest = undef;
- [ 200, [ qw(Content-Type application/gzip),
- 'Last-Modified', time2str($mtime),
- 'Content-Length', bytes::length($out) ], [ $out ] ];
-}
-
# not really a stand-alone PSGI app, but maybe it could be...
sub call {
my ($self, $env) = @_;
@@ -235,7 +126,7 @@ sub call {
if ($env->{PATH_INFO} eq '/manifest.js.gz') {
# grokmirror uses relative paths, so it's domain-dependent
my $list = $self->{manifest_cb}->($self, $env, 'manifest');
- js($env, $list);
+ PublicInbox::ManifestJsGz::response($env, $list);
} else { # /
my $list = $self->{www_cb}->($self, $env, 'www');
html($env, $list);