[PATCH 12/37] view: enable naming hints for raw blob downloads

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

Meaningful names in URLs are nice, and it can make
life easier for supporting syntax-highlighting
---
 lib/PublicInbox/ViewDiff.pm | 27 +++++++++++++++++++--------
 lib/PublicInbox/ViewVCS.pm  | 32 +++++++++++++++++++++++++++-----
 2 files changed, 46 insertions(+), 13 deletions(-)

diff --git a/lib/PublicInbox/ViewDiff.pm b/lib/PublicInbox/ViewDiff.pm
index ee450fa..94f015f 100644
--- a/lib/PublicInbox/ViewDiff.pm
+++ b/lib/PublicInbox/ViewDiff.pm
@@ -2,12 +2,16 @@
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # used by PublicInbox::View
+# This adds CSS spans for diff highlighting.
+# It also generates links for ViewVCS + SolverGit to show
+# (or reconstruct) blobs.
+
 package PublicInbox::ViewDiff;
 use strict;
 use warnings;
 use base qw(Exporter);
 our @EXPORT_OK = qw(flush_diff);
-
+use URI::Escape qw(uri_escape_utf8);
 use PublicInbox::Hval qw(ascii_html);
 use PublicInbox::Git qw(git_unquote);
 
@@ -18,6 +22,7 @@ sub DSTATE_HUNK () { 3 } # /^@@ /
 sub DSTATE_CTX () { 4 } # /^ /
 sub DSTATE_ADD () { 5 } # /^\+/
 sub DSTATE_DEL () { 6 } # /^\-/
+sub UNSAFE () { "^A-Za-z0-9\-\._~/" }
 
 my $OID_NULL = '0{7,40}';
 my $OID_BLOB = '[a-f0-9]{7,40}';
@@ -40,18 +45,18 @@ sub diff_hunk ($$$$) {
 	my ($n) = ($ca =~ /^-(\d+)/);
 	$n = defined($n) ? do { ++$n; "#n$n" } : '';
 
-	my $rv = qq(@@ <a\nhref=$spfx$oid_a/s$n>$ca</a>);
+	my $rv = qq(@@ <a\nhref=$spfx$oid_a/s$dctx->{Q}$n>$ca</a>);
 
 	($n) = ($cb =~ /^\+(\d+)/);
 	$n = defined($n) ? do { ++$n; "#n$n" } : '';
 
-	$rv .= qq( <a\nhref=$spfx$oid_b/s$n>$cb</a> @@);
+	$rv .= qq( <a\nhref=$spfx$oid_b/s$dctx->{Q}$n>$cb</a> @@);
 }
 
 sub flush_diff ($$$$) {
 	my ($dst, $spfx, $linkify, $diff) = @_;
 	my $state = DSTATE_INIT;
-	my $dctx; # {}, keys: oid_a, oid_b, path_a, path_b
+	my $dctx = { Q => '' }; # {}, keys: oid_a, oid_b, path_a, path_b
 
 	foreach my $s (@$diff) {
 		if ($s =~ /^ /) {
@@ -67,7 +72,7 @@ sub flush_diff ($$$$) {
 				$$dst .= '</span>';
 			}
 			$$dst .= $s;
-		} elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!x) {
+		} elsif ($s =~ m!^diff --git ($PATH_A) ($PATH_B)$!) {
 			if ($state != DSTATE_HEAD) {
 				my ($pa, $pb) = ($1, $2);
 				$$dst .= '</span>' if $state != DSTATE_INIT;
@@ -75,15 +80,21 @@ sub flush_diff ($$$$) {
 				$state = DSTATE_HEAD;
 				$pa = (split('/', git_unquote($pa), 2))[1];
 				$pb = (split('/', git_unquote($pb), 2))[1];
-				$dctx = { path_a => $pa, path_b => $pb };
+				$dctx = {
+					Q => "?b=".uri_escape_utf8($pb, UNSAFE),
+				};
+				if ($pa ne $pb) {
+					$dctx->{Q} .=
+					     "&a=".uri_escape_utf8($pa, UNSAFE);
+				}
 			}
 			$$dst .= to_html($linkify, $s);
 		} elsif ($s =~ s/^(index $OID_NULL\.\.)($OID_BLOB)\b//o) {
-			$$dst .= qq($1<a\nhref=$spfx$2/s>$2</a>);
+			$$dst .= qq($1<a\nhref=$spfx$2/s$dctx->{Q}>$2</a>);
 			$$dst .= to_html($linkify, $s) ;
 		} elsif ($s =~ s/^index ($OID_NULL)(\.\.$OID_BLOB)\b//o) {
 			$$dst .= 'index ';
-			$$dst .= qq(<a\nhref=$spfx$1/s>$1</a>$2);
+			$$dst .= qq(<a\nhref=$spfx$1/s$dctx->{Q}>$1</a>$2);
 			$$dst .= to_html($linkify, $s);
 		} elsif ($s =~ /^index ($OID_BLOB)\.\.($OID_BLOB)/o) {
 			$dctx->{oid_a} = $1;
diff --git a/lib/PublicInbox/ViewVCS.pm b/lib/PublicInbox/ViewVCS.pm
index 49fb1c5..90c0907 100644
--- a/lib/PublicInbox/ViewVCS.pm
+++ b/lib/PublicInbox/ViewVCS.pm
@@ -2,6 +2,17 @@
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # show any VCS object, similar to "git show"
+# FIXME: we only show blobs for now
+#
+# This can use a "solver" to reconstruct blobs based on git
+# patches (with abbreviated OIDs in the header).  However, the
+# abbreviated OIDs must match exactly what's in the original
+# email (unless a normal code repo already has the blob).
+#
+# In other words, we can only reliably reconstruct blobs based
+# on links generated by ViewDiff (and only if the emailed
+# patches apply 100% cleanly to published blobs).
+
 package PublicInbox::ViewVCS;
 use strict;
 use warnings;
@@ -9,7 +20,7 @@ use Encode qw(find_encoding);
 use PublicInbox::SolverGit;
 use PublicInbox::WwwStream;
 use PublicInbox::Linkify;
-use PublicInbox::Hval qw(ascii_html);
+use PublicInbox::Hval qw(ascii_html to_filename);
 my %QP_MAP = ( A => 'oid_a', B => 'oid_b', a => 'path_a', b => 'path_b' );
 my $max_size = 1024 * 1024; # TODO: configurable
 my $enc_utf8 = find_encoding('UTF-8');
@@ -63,8 +74,18 @@ sub show ($$;$) {
 		return html_page($ctx, 500, \$log);
 	}
 
-	if (index($$blob, "\0") >= 0) {
-		$log = "<pre>$oid $type $size bytes (binary)</pre>" . $log;
+	my $binary = index($$blob, "\0") >= 0;
+	if ($fn) {
+		my $h = [ 'Content-Length', $size, 'Content-Type' ];
+		push(@$h, ($binary ? 'application/octet-stream' : 'text/plain'));
+		return [ 200, $h, [ $$blob ]];
+	}
+
+	my $path = to_filename($di->{path_b} || $hints->{path_b} || 'blob');
+	my $raw_link = "(<a\nhref=_$path>raw</a>)";
+	if ($binary) {
+		$log = "<pre>$oid $type $size bytes (binary)" .
+			" $raw_link</pre>" . $log;
 		return html_page($ctx, 200, \$log);
 	}
 
@@ -73,13 +94,14 @@ sub show ($$;$) {
 	my $pad = length($nl);
 
 	# using some of the same CSS class names and ids as cgit
-	$log = "<pre>$oid $type $size bytes</pre><hr /><table\nclass=blob>".
+	$log = "<pre>$oid $type $size bytes $raw_link</pre>" .
+		"<hr /><table\nclass=blob>".
 		"<tr><td\nclass=linenumbers><pre>" . join('', map {
 			sprintf("<a id=n$_ href=#n$_>% ${pad}u</a>\n", $_)
 		} (1..$nl)) . '</pre></td>' .
 		'<td><pre> </pre></td>'. # pad for non-CSS users
 		"<td\nclass=lines><pre><code>" .  ascii_html($$blob) .
-		'</pre></td></tr></table>' . $log;
+		'</code></pre></td></tr></table>' . $log;
 
 	html_page($ctx, 200, \$log);
 }
-- 
EW