From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 1/4] hval: routines for attribute escaping
Date: Fri, 1 Feb 2019 08:55:05 +0000 [thread overview]
Message-ID: <20190201085508.24003-2-e@80x24.org> (raw)
In-Reply-To: <20190201085508.24003-1-e@80x24.org>
We'll use HTML attributes + anchor links to link to filenames
in coming commits.
---
lib/PublicInbox/Hval.pm | 35 +++++++++++++++++++++++++++++++++--
t/hval.t | 14 ++++++++++++--
2 files changed, 45 insertions(+), 4 deletions(-)
diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index 53810b3..95a0f70 100644
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -9,8 +9,8 @@ use warnings;
use Encode qw(find_encoding);
use PublicInbox::MID qw/mid_clean mid_escape/;
use base qw/Exporter/;
-our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape/;
-
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape
+ to_attr from_attr/;
my $enc_ascii = find_encoding('us-ascii');
sub new {
@@ -122,4 +122,35 @@ sub to_filename ($) {
$s
}
+# convert a filename (or any string) to HTML attribute
+
+my %ESCAPES = map { chr($_) => sprintf('::%02x', $_) } (0..255);
+$ESCAPES{'/'} = ':'; # common
+
+sub to_attr ($) {
+ my ($str) = @_;
+
+ # git would never do this to us:
+ return if index($str, '//') >= 0;
+
+ my $first = '';
+ if ($str =~ s/\A([^A-Ya-z])//ms) { # start with a letter
+ $first = sprintf('Z%02x', ord($1));
+ }
+ $str =~ s/([^A-Za-z0-9_\.\-])/$ESCAPES{$1}/egms;
+ $first . $str;
+}
+
+# reverse the result of to_attr
+sub from_attr ($) {
+ my ($str) = @_;
+ my $first = '';
+ if ($str =~ s/\AZ([a-f0-9]{2})//ms) {
+ $first = chr(hex($1));
+ }
+ $str =~ s!::([a-f0-9]{2})!chr(hex($1))!egms;
+ $str =~ tr!:!/!;
+ $first . $str;
+}
+
1;
diff --git a/t/hval.t b/t/hval.t
index bfc9a85..f93d6be 100644
--- a/t/hval.t
+++ b/t/hval.t
@@ -1,9 +1,9 @@
-# Copyright (C) 2017-2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2017-2019 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
use strict;
use warnings;
use Test::More;
-use_ok 'PublicInbox::Hval';
+use_ok 'PublicInbox::Hval', qw(from_attr to_attr);
my $ibx = {
-no_obfuscate_re => qr/(?:example\.com)\z/i,
@@ -47,4 +47,14 @@ my $s = "\0\x07\n";
PublicInbox::Hval::src_escape($s);
is($s, "\\0\\a\n", 'src_escape works as intended');
+foreach my $s ('Hello/World.pm', 'Zcat', 'hello world.c', 'Eléanor', '$at') {
+ my $attr = to_attr($s);
+ is(from_attr($attr), $s, "$s => $attr => $s round trips");
+}
+
+{
+ my $bad = to_attr('foo//bar');
+ ok(!$bad, 'double-slash rejected');
+}
+
done_testing();
--
EW
next prev parent reply other threads:[~2019-02-01 8:55 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-02-01 8:55 [PATCH 0/4] viewvcs: Atom bugfix + diffstat anchors Eric Wong
2019-02-01 8:55 ` Eric Wong [this message]
2019-02-01 8:55 ` [PATCH 2/4] viewdiff: diffstat links to diff anchors Eric Wong
2019-02-01 8:55 ` [PATCH 3/4] view: diffstat anchors for multi-message/attachment views Eric Wong
2019-02-01 8:55 ` [PATCH 4/4] view: fix broken hunk header hrefs in Atom feeds Eric Wong
Reply instructions:
You may reply publicly 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: http://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=20190201085508.24003-2-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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).