reply: follow obfuscation rules for HTML in sh args

[public-inbox.git] / lib / PublicInbox / Hval.pm

diff --git a/lib/PublicInbox/Hval.pm b/lib/PublicInbox/Hval.pm
index d295f5ce3d29fb8d783e2550e75975fe237fcba7..d65ab3217c915a18db892e226a87af7594a2fe53 100644 (file)
--- a/lib/PublicInbox/Hval.pm
+++ b/lib/PublicInbox/Hval.pm
@@ -7,14 +7,14 @@ package PublicInbox::Hval;
 use strict;
 use warnings;
 use Encode qw(find_encoding);
-use URI::Escape qw(uri_escape_utf8);
-use PublicInbox::MID qw/mid_clean/;
+use PublicInbox::MID qw/mid_clean mid_escape/;
+use base qw/Exporter/;
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename/;
 
 # for user-generated content (UGC) which may have excessively long lines
 # and screw up rendering on some browsers.  This is the only CSS style
 # feature we use.
 use constant STYLE => '<style>pre{white-space:pre-wrap}</style>';
-use constant PRE => "<pre\nstyle=\"white-space:pre-wrap\">"; # legacy
 
 my $enc_ascii = find_encoding('us-ascii');
 
@@ -30,9 +30,8 @@ sub new {
 }
 
 sub new_msgid {
-       my ($class, $msgid, $no_compress) = @_;
-       $msgid = mid_clean($msgid);
-       $class->new($msgid, $msgid);
+       my ($class, $msgid) = @_;
+       $class->new($msgid, mid_escape($msgid));
 }
 
 sub new_oneline {
@@ -51,15 +50,28 @@ my %xhtml_map = (
        '>' => '&gt;',
 );
 
+$xhtml_map{chr($_)} = sprintf('\\x%02x', $_) for (0..31);
+# some of these overrides are standard C escapes so they're
+# easy-to-understand when rendered.
+$xhtml_map{"\x00"} = '\\0'; # NUL
+$xhtml_map{"\x07"} = '\\a'; # bell
+$xhtml_map{"\x08"} = '\\b'; # backspace
+$xhtml_map{"\x09"} = "\t"; # obvious to show as-is
+$xhtml_map{"\x0a"} = "\n"; # obvious to show as-is
+$xhtml_map{"\x0b"} = '\\v'; # vertical tab
+$xhtml_map{"\x0c"} = '\\f'; # form feed
+$xhtml_map{"\x0d"} = '\\r'; # carriage ret (not preceding \n)
+$xhtml_map{"\x1b"} = '^['; # ASCII escape (mutt seems to escape this way)
+$xhtml_map{"\x7f"} = '\\x7f'; # DEL
+
 sub ascii_html {
        my ($s) = @_;
        $s =~ s/\r\n/\n/sg; # fixup bad line endings
-       $s =~ s/([<>&'"])/$xhtml_map{$1}/ge;
+       $s =~ s/([<>&'"\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
        $enc_ascii->encode($s, Encode::HTMLCREF);
 }
 
 sub as_html { ascii_html($_[0]->{raw}) }
-sub as_href { ascii_html(uri_escape_utf8($_[0]->{href})) }
 
 sub raw {
        if (defined $_[1]) {
@@ -69,4 +81,40 @@ sub raw {
        }
 }
 
+sub prurl {
+       my ($env, $u) = @_;
+       index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
+}
+
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# &#8228; &#183; and &#890; were also candidates:
+#   https://public-inbox.org/meta/20170615015250.GA6484@starla/
+# However, &#8226; was chosen to make copy+paste errors more obvious
+sub obfuscate_addrs ($$;$) {
+       my $ibx = $_[0];
+       my $repl = $_[2] || '&#8226;';
+       my $re = $ibx->{-no_obfuscate_re}; # regex of domains
+       my $addrs = $ibx->{-no_obfuscate}; # { adddress => 1 }
+       $_[1] =~ s/(([\w\.\+=\-]+)\@([\w\-]+\.[\w\.\-]+))/
+               my ($addr, $user, $domain) = ($1, $2, $3);
+               if ($addrs->{$addr} || ((defined $re && $domain =~ $re))) {
+                       $addr;
+               } else {
+                       $domain =~ s!([^\.]+)\.!$1$repl!;
+                       $user . '@' . $domain
+               }
+               /sge;
+}
+
+# like format_sanitized_subject in git.git pretty.c with '%f' format string
+sub to_filename ($) {
+       my ($s, undef) = split(/\n/, $_[0]);
+       $s =~ s/[^A-Za-z0-9_\.]+/-/g;
+       $s =~ tr/././s;
+       $s =~ s/[\.\-]+\z//;
+       $s =~ s/\A[\.\-]+//;
+       $s
+}
+
 1;