[PATCH 1/2] www: move mirror instructions to /text/

[Eric Wong <e@80x24.org>]

This makes the mirroring and code retrieval instructions less
obstructive.  Relying on WwwText means we only use our Linkify
module to make hrefs of full URLs; making relative and shortened
hrefs off-limits; hopefully this isn't too much of a problem.

coderepo information remains duplicated on every page since
(IMHO) coderepos are an important feature; but nobody besides me
has ever bothered to configure coderepos, so I suppose it's
fine...

Suggested-by: Konstantin Ryabitsev <konstantin@linuxfoundation.org>
Link: https://public-inbox.org/meta/20210826132747.6gxuwnhftyf7c6hp@nitro.local/
---
 lib/PublicInbox/WwwListing.pm |   4 +-
 lib/PublicInbox/WwwStream.pm  | 116 +++--------------------------
 lib/PublicInbox/WwwText.pm    | 134 +++++++++++++++++++++++++++++++++-
 t/psgi_mount.t                |  11 +--
 4 files changed, 143 insertions(+), 122 deletions(-)

diff --git a/lib/PublicInbox/WwwListing.pm b/lib/PublicInbox/WwwListing.pm
index ef9048b5..c3779619 100644
--- a/lib/PublicInbox/WwwListing.pm
+++ b/lib/PublicInbox/WwwListing.pm
@@ -226,9 +226,7 @@ sub psgi_triple {
 	} else {
 		$gzf->zmore('<pre>no inboxes, yet');
 	}
-	my $out = $gzf->zflush('</pre><hr><pre>'.
-			PublicInbox::WwwStream::code_footer($ctx->{env}) .
-			'</pre></body></html>');
+	my $out = $gzf->zflush('</pre></body></html>');
 	$h->[3] = length($out);
 	[ $code, $h, [ $out ] ];
 }
diff --git a/lib/PublicInbox/WwwStream.pm b/lib/PublicInbox/WwwStream.pm
index d8142824..c960edc5 100644
--- a/lib/PublicInbox/WwwStream.pm
+++ b/lib/PublicInbox/WwwStream.pm
@@ -11,7 +11,6 @@ use v5.10.1;
 use parent qw(Exporter PublicInbox::GzipFilter);
 our @EXPORT_OK = qw(html_oneshot);
 use PublicInbox::Hval qw(ascii_html prurl ts2str);
-our $TOR_URL = 'https://www.torproject.org/';
 
 our $CODE_URL = [ qw(
 http://7fh6tueqddpjyxjmgtdiueylzoqt6pt7hec3pukyptlmohoowvhde4yd.onion/public-inbox.git
@@ -42,8 +41,6 @@ sub html_top ($) {
 	my $desc = ascii_html($ibx->description);
 	my $title = delete($ctx->{-title_html}) // $desc;
 	my $upfx = $ctx->{-upfx} || '';
-	my $help = $upfx.'_/text/help/';
-	my $color = $upfx.'_/text/color/';
 	my $atom = $ctx->{-atom} || $upfx.'new.atom';
 	my $top = "<b>$desc</b>";
 	if (my $t_max = $ctx->{-t_max}) {
@@ -54,9 +51,11 @@ sub html_top ($) {
 		$top = qq(<a\nhref="./">$top</a>);
 	}
 	my $code = $ibx->{coderepo} ? qq( / <a\nhref=#code>code</a>) : '';
-	my $links = qq(<a\nhref="$help">help</a> / ).
-			qq(<a\nhref="$color">color</a> / ).
-			qq(<a\nhref=#mirror>mirror</a>$code / ).
+	# id=mirror must exist for legacy bookmarks
+	my $links = qq(<a\nhref="${upfx}_/text/help/">help</a> / ).
+			qq(<a\nhref="${upfx}_/text/color/">color</a> / ).
+			qq(<a\nid=mirror) .
+			qq(\nhref="${upfx}_/text/mirror/">mirror</a>$code / ).
 			qq(<a\nhref="$atom">Atom feed</a>);
 	if ($ibx->isrch) {
 		my $q_val = delete($ctx->{-q_value_html}) // '';
@@ -106,109 +105,12 @@ EOF
 	@ret; # may be empty, this sub is called as an arg for join()
 }
 
-sub code_footer ($) {
-	my ($env) = @_;
-	my $u = prurl($env, $CODE_URL);
-	my $arg = $u;
-	if ($arg =~ s!\A(https?://)([^/\.]+)\.onion/!$1\$hostname\.onion/!i) {
-		"AGPL code for this site:\n\thostname=$2\n\t" .
-		qq(torsocks git clone <a\nhref="$u">$arg</a>)
-	} else {
-		qq(AGPL code for this site: git clone <a\nhref="$u">$u</a>)
-	}
-}
-
 sub _html_end {
 	my ($ctx) = @_;
-	my $ibx = $ctx->{ibx};
-	my $desc = ascii_html($ibx->description);
-	my $s = "<a\nid=mirror>";
-	my $http = $ctx->{base_url};
-	my $dir = (split(m!/!, $http))[-1];
-	my %seen = ($http => 1);
-	if ($ibx->can('cloneurl')) { # PublicInbox::Inbox
-		$s .= "This inbox may be cloned and mirrored by anyone:</a>\n";
-		my @urls;
-		my $max = $ibx->max_git_epoch;
-		# TODO: some of these URLs may be too long and we may need to
-		# do something like code_footer() above, but these are local
-		# admin-defined
-		if (defined($max)) { # v2
-			for my $i (0..$max) {
-				# old epochs my be deleted:
-				-d "$ibx->{inboxdir}/git/$i.git" or next;
-				my $url = "$http/$i";
-				$seen{$url} = 1;
-				push @urls, "$url $dir/git/$i.git";
-			}
-			my $nr = scalar(@urls);
-			if ($nr > 1) {
-				$s .= "\n\t";
-				$s .= "# this inbox consists of $nr epochs:";
-				$urls[0] .= "\t# oldest";
-				$urls[-1] .= "\t# newest";
-			}
-		} else { # v1
-			push @urls, $http;
-		}
-		# FIXME: epoch splits can be different in other repositories,
-		# use the "cloneurl" file as-is for now:
-		for my $u (@{$ibx->cloneurl}) {
-			next if $seen{$u}++;
-			push @urls, ($u =~ /\Ahttps?:/ ?
-					qq(<a\nhref="$u">$u</a>) : $u);
-		}
-		$s .= "\n";
-		$s .= join('', map { "\tgit clone --mirror $_\n" } @urls);
-		if (my $addrs = $ibx->{address}) {
-			$addrs = join(' ', @$addrs) if ref($addrs) eq 'ARRAY';
-			my $v = defined $max ? '-V2' : '-V1';
-			$s .= <<EOF;
-
-	# If you have public-inbox 1.1+ installed, you may
-	# initialize and index your mirror using the following commands:
-	public-inbox-init $v $ibx->{name} $dir/ $http \\
-		$addrs
-	public-inbox-index $dir
-EOF
-		}
-	} else { # PublicInbox::ExtSearch
-		$s .= <<EOM;
-This is an extindex which is an amalgamation of several public-inboxes</a>
-EOM
-		my $v = $ctx->{www}->{pi_cfg}->{lc('publicInbox.wwwListing')};
-		if (($v // '') =~ /\A(?:all|match=domain)\z/) {
-			my $upfx = ($ctx->{-upfx} // ''). '../';
-			$s .= <<EOM;
-A list of them is available in the <a\nhref="$upfx">listing</a>
-EOM
-		}
-	}
-
-	my $cfg_link = ($ctx->{-upfx} // '').'_/text/config/raw';
-	$s .= <<EOF;
-
-Example <a
-href="$cfg_link">config snippet</a> for mirrors.
-EOF
-	if ($ibx->can('nntp_url')) {
-		my @nntp = map { qq(<a\nhref="$_">$_</a>) } @{$ibx->nntp_url};
-		if (@nntp) {
-			$s .= @nntp == 1 ? 'Newsgroup' : 'Newsgroups are';
-			$s .= ' available over NNTP:';
-			$s .= "\n\t" . join("\n\t", @nntp) . "\n";
-		}
-	}
-	if ($s =~ m!\b[^:]+://\w+\.onion/!) {
-		$s .= " note: .onion URLs require Tor: ";
-		$s .= qq[<a\nhref="$TOR_URL">$TOR_URL</a>];
-	}
-	'<hr><pre>'.join("\n\n",
-		$desc,
-		$s,
-		coderepos($ctx),
-		code_footer($ctx->{env})
-	).'</pre></body></html>';
+	my @cr = coderepos($ctx);
+	scalar(@cr) ?
+		'<hr><pre>'.join("\n\n", @cr).'</pre></body></html>' :
+		'</body></html>';
 }
 
 # callback for HTTP.pm (and any other PSGI servers)
diff --git a/lib/PublicInbox/WwwText.pm b/lib/PublicInbox/WwwText.pm
index 47310258..858fc2f7 100644
--- a/lib/PublicInbox/WwwText.pm
+++ b/lib/PublicInbox/WwwText.pm
@@ -7,7 +7,7 @@ use strict;
 use v5.10.1;
 use PublicInbox::Linkify;
 use PublicInbox::WwwStream;
-use PublicInbox::Hval qw(ascii_html);
+use PublicInbox::Hval qw(ascii_html prurl);
 use URI::Escape qw(uri_escape_utf8);
 use PublicInbox::GzipFilter qw(gzf_maybe);
 our $QP_URL = 'https://xapian.org/docs/queryparser.html';
@@ -23,7 +23,7 @@ sub get_text {
 	my ($ctx, $key) = @_;
 	my $code = 200;
 
-	$key = 'help' if !defined $key; # this 302s to _/text/help/
+	$key //= 'help'; # this 302s to _/text/help/
 
 	# get the raw text the same way we get mboxrds
 	my $raw = ($key =~ s!/raw\z!!);
@@ -240,12 +240,138 @@ EOS
 	1;
 }
 
+sub coderepos_raw ($$) {
+	my ($ctx, $top_url) = @_;
+	my $cr = $ctx->{ibx}->{coderepo} // return ();
+	my $cfg = $ctx->{www}->{pi_cfg};
+	my @ret;
+	for my $cr_name (@$cr) {
+		$ret[0] //= <<EOF;
+code repositories for project(s) associated with this inbox:
+EOF
+		my $urls = $cfg->get_all("coderepo.$cr_name.cgiturl");
+		if ($urls) {
+			for (@$urls) {
+				# relative or absolute URL?, prefix relative
+				# "foo.git" with appropriate number of "../"
+				my $u = m!\A(?:[a-z\+]+:)?//!i ? $_ :
+					$top_url.$_;
+				$ret[0] .= "\n\t" . prurl($ctx->{env}, $u);
+			}
+		} else {
+			$ret[0] .= qq[\n\t$cr_name.git (no URL configured)];
+		}
+	}
+	@ret; # may be empty, this sub is called as an arg for join()
+}
+
+sub _mirror_help ($$) {
+	my ($ctx, $txt) = @_;
+	my $ibx = $ctx->{ibx};
+	my $base_url = $ibx->base_url($ctx->{env});
+	chop $base_url; # no trailing slash for "git clone"
+	my $dir = (split(m!/!, $base_url))[-1];
+	my %seen = ($base_url => 1);
+	my $top_url = $base_url;
+	$top_url =~ s!/[^/]+\z!/!;
+	$$txt .= "public-inbox mirroring instructions\n\n";
+	if ($ibx->can('cloneurl')) { # PublicInbox::Inbox
+		$$txt .= "This inbox may be cloned and mirrored by anyone:\n";
+		my @urls;
+		my $max = $ibx->max_git_epoch;
+		# TODO: some of these URLs may be too long and we may need to
+		# do something like code_footer() above, but these are local
+		# admin-defined
+		if (defined($max)) { # v2
+			for my $i (0..$max) {
+				# old epochs my be deleted:
+				-d "$ibx->{inboxdir}/git/$i.git" or next;
+				my $url = "$base_url/$i";
+				$seen{$url} = 1;
+				push @urls, "$url $dir/git/$i.git";
+			}
+			my $nr = scalar(@urls);
+			if ($nr > 1) {
+				$$txt .= "\n\t";
+				$$txt .= "# this inbox consists of $nr epochs:";
+				$urls[0] .= " # oldest";
+				$urls[-1] .= " # newest";
+			}
+		} else { # v1
+			push @urls, $base_url;
+		}
+		# FIXME: epoch splits can be different in other repositories,
+		# use the "cloneurl" file as-is for now:
+		for my $u (@{$ibx->cloneurl}) {
+			next if $seen{$u}++;
+			push @urls, $u;
+		}
+		$$txt .= "\n";
+		$$txt .= join('', map { "\tgit clone --mirror $_\n" } @urls);
+		if (my $addrs = $ibx->{address}) {
+			$addrs = join(' ', @$addrs) if ref($addrs) eq 'ARRAY';
+			my $v = defined $max ? '-V2' : '-V1';
+			$$txt .= <<EOF;
+
+	# If you have public-inbox 1.1+ installed, you may
+	# initialize and index your mirror using the following commands:
+	public-inbox-init $v $ibx->{name} $dir/ $base_url \\
+		$addrs
+	public-inbox-index $dir
+EOF
+		}
+	} else { # PublicInbox::ExtSearch
+		$$txt .= <<EOM;
+This is an extindex which is an amalgamation of several public-inboxes.
+Each public-inbox needs to be mirrored individually.
+EOM
+		my $v = $ctx->{www}->{pi_cfg}->{lc('publicInbox.wwwListing')};
+		if (($v // '') =~ /\A(?:all|match=domain)\z/) {
+			$$txt .= <<EOM;
+A list of them is available at $top_url
+EOM
+		}
+	}
+	my $cfg_link = "$base_url/_/text/config/raw";
+	$$txt .= <<EOF;
+
+Example config snippet for mirrors: $cfg_link
+EOF
+	if ($ibx->can('nntp_url')) {
+		my $nntp = $ibx->nntp_url;
+		if (scalar @$nntp) {
+			$$txt .= "\n";
+			$$txt .= @$nntp == 1 ? 'Newsgroup' : 'Newsgroups are';
+			$$txt .= ' available over NNTP:';
+			$$txt .= "\n\t" . join("\n\t", @$nntp) . "\n";
+		}
+	}
+	if ($$txt =~ m!\b[^:]+://\w+\.onion/!) {
+		$$txt .= <<EOM
+
+note: .onion URLs require Tor: https://www.torproject.org/
+
+EOM
+	}
+	my $code_url = prurl($ctx->{env}, $PublicInbox::WwwStream::CODE_URL);
+	$$txt .= join("\n\n",
+		coderepos_raw($ctx, $top_url), # may be empty
+		"AGPL code for this site:\n\tgit clone $code_url");
+	1;
+}
+
 sub _default_text ($$$$) {
 	my ($ctx, $key, $hdr, $txt) = @_;
-	return _colors_help($ctx, $txt) if $key eq 'color';
-	$key eq 'config' and return $ctx->{ibx}->can('cloneurl') ?
+	if ($key eq 'mirror') {
+		return _mirror_help($ctx, $txt);
+	} elsif ($key eq 'color') {
+		return _colors_help($ctx, $txt);
+	} elsif ($key eq 'config') {
+		return $ctx->{ibx}->can('cloneurl') ?
 			inbox_config($ctx, $hdr, $txt) :
 			extindex_config($ctx, $hdr, $txt);
+	}
+
 	return if $key ne 'help'; # TODO more keys?
 
 	my $ibx = $ctx->{ibx};
diff --git a/t/psgi_mount.t b/t/psgi_mount.t
index e9547c15..7c5487f3 100644
--- a/t/psgi_mount.t
+++ b/t/psgi_mount.t
@@ -48,14 +48,9 @@ test_psgi($app, sub {
 	unlike($res->content, qr!\b\Qhttp://[^/]+/test/\E!,
 		'No URLs which are not mount-aware');
 
-	$res = $cb->(GET('/a/test/new.html'));
-	like($res->content, qr!git clone --mirror http://[^/]+/a/test\b!,
-		'clone URL in new.html is mount-aware');
-
-	$res = $cb->(GET('/a/test/blah%40example.com/'));
-	is($res->code, 200, 'OK with URLMap mount');
-	like($res->content, qr!git clone --mirror http://[^/]+/a/test\b!,
-		'clone URL in /$INBOX/$MESSAGE_ID/ is mount-aware');
+	$res = $cb->(GET('/a/test/_/text/mirror/'));
+	like($res->content, qr!git clone --mirror\s+.*?http://[^/]+/a/test\b!s,
+		'clone URL in /text/mirror is mount-aware');
 
 	$res = $cb->(GET('/a/test/blah%40example.com/raw'));
 	is($res->code, 200, 'OK with URLMap mount');