user/dev discussion of public-inbox itself
 help / color / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 12/37] view: enable naming hints for raw blob downloads
Date: Mon, 21 Jan 2019 20:52:28 +0000
Message-ID: <20190121205253.10455-13-e@80x24.org> (raw)
In-Reply-To: <20190121205253.10455-1-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


  parent reply index

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-21 20:52 [PATCH 00/37] viewvcs: diff highlighting and more Eric Wong
2019-01-21 20:52 ` [PATCH 01/37] view: disable bold in topic display Eric Wong
2019-01-21 20:52 ` [PATCH 02/37] hval: force monospace for <form> elements, too Eric Wong
2019-01-21 20:52 ` [PATCH 03/37] t/perf-msgview: add test to check msg_html performance Eric Wong
2019-01-21 20:52 ` [PATCH 04/37] solver: initial Perl implementation Eric Wong
2019-01-21 20:52 ` [PATCH 05/37] git: support multiple URL endpoints Eric Wong
2019-01-21 20:52 ` [PATCH 06/37] git: add git_quote Eric Wong
2019-01-21 20:52 ` [PATCH 07/37] git: check saves error on disambiguation Eric Wong
2019-01-21 20:52 ` [PATCH 08/37] solver: various bugfixes and cleanups Eric Wong
2019-01-21 20:52 ` [PATCH 09/37] view: wire up diff and vcs viewers with solver Eric Wong
2019-01-21 20:52 ` [PATCH 10/37] git: disable abbreviations with cat-file hints Eric Wong
2019-01-21 20:52 ` [PATCH 11/37] solver: operate directly on git index Eric Wong
2019-01-21 20:52 ` Eric Wong [this message]
2019-01-21 20:52 ` [PATCH 13/37] git: support 'ambiguous' result from --batch-check Eric Wong
2019-01-21 20:52 ` [PATCH 14/37] solver: more verbose blob resolution Eric Wong
2019-01-21 20:52 ` [PATCH 15/37] solver: break up patch application steps Eric Wong
2019-01-21 20:52 ` [PATCH 16/37] solver: switch patch application to use a callback Eric Wong
2019-01-21 20:52 ` [PATCH 17/37] solver: simplify control flow for initial loop Eric Wong
2019-01-21 20:52 ` [PATCH 18/37] solver: break @todo loop into a callback Eric Wong
2019-01-21 20:52 ` [PATCH 19/37] solver: note the synchronous nature of index preparation Eric Wong
2019-01-21 20:52 ` [PATCH 20/37] solver: add a TODO note about making this fully evented Eric Wong
2019-01-21 20:52 ` [PATCH 21/37] view: enforce trailing slash for /$INBOX/$OID/s/ endpoints Eric Wong
2019-01-21 20:52 ` [PATCH 22/37] solver: restore diagnostics and deal with CRLF Eric Wong
2019-01-21 20:52 ` [PATCH 23/37] www: admin-configurable CSS via "publicinbox.css" Eric Wong
2019-01-21 20:52 ` [PATCH 24/37] $INBOX/_/text/color/ and sample user-side CSS Eric Wong
2019-01-21 20:52 ` [PATCH 25/37] viewdiff: support diff-highlighting w/o coderepo Eric Wong
2019-01-21 20:52 ` [PATCH 26/37] viewdiff: cleanup state transitions a bit Eric Wong
2019-01-21 20:52 ` [PATCH 27/37] viewdiff: quote attributes for Atom feed Eric Wong
2019-01-21 20:52 ` [PATCH 28/37] t/check-www-inbox: use xmlstarlet to validate Atom if available Eric Wong
2019-01-21 20:52 ` [PATCH 29/37] viewdiff: do not link to 0{7,40} blobs (again) Eric Wong
2019-01-21 20:52 ` [PATCH 30/37] viewvcs: disable white-space prewrap in blob view Eric Wong
2019-01-21 20:52 ` [PATCH 31/37] solver: force quoted-printable bodies to LF Eric Wong
2019-01-21 20:52 ` [PATCH 32/37] solver: remove extra "^index $OID..$OID" line Eric Wong
2019-01-21 20:52 ` [PATCH 33/37] config: each_inbox iteration preserves config order Eric Wong
2019-01-21 20:52 ` [PATCH 34/37] t/check-www-inbox: warn on missing Content-Type Eric Wong
2019-01-21 20:52 ` [PATCH 35/37] highlight: initial wrapper and PSGI service Eric Wong
2019-01-21 20:52 ` [PATCH 36/37] hval: split out escape sequences to a separate table Eric Wong
2019-01-21 20:52 ` [PATCH 37/37] t/check-www-inbox: trap SIGINT for File::Temp destruction Eric Wong

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190121205253.10455-13-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror https://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox