-# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2014-2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
#
# represents a header value in various forms. Used for HTML generation
# in our web interface(s)
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/;
-
-# 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>';
+our @EXPORT_OK = qw/ascii_html obfuscate_addrs to_filename src_escape/;
my $enc_ascii = find_encoding('us-ascii');
$class->new($raw);
}
+# some of these overrides are standard C escapes so they're
+# easy-to-understand when rendered.
+my %escape_sequence = (
+ "\x00" => '\\0', # NUL
+ "\x07" => '\\a', # bell
+ "\x08" => '\\b', # backspace
+ "\x09" => "\t", # obvious to show as-is
+ "\x0a" => "\n", # obvious to show as-is
+ "\x0b" => '\\v', # vertical tab
+ "\x0c" => '\\f', # form feed
+ "\x0d" => '\\r', # carriage ret (not preceding \n)
+ "\x1b" => '^[', # ASCII escape (mutt seems to escape this way)
+ "\x7f" => '\\x7f', # DEL
+);
+
my %xhtml_map = (
'"' => '"',
'&' => '&',
);
$xhtml_map{chr($_)} = 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)
-$xhtml_map{"\x7f"} = '\\x7f'; # DEL
+%xhtml_map = (%xhtml_map, %escape_sequence);
+
+sub src_escape ($) {
+ $_[0] =~ s/\r\n/\n/sg;
+ $_[0] =~ s/([\x7f\x00-\x1f])/$xhtml_map{$1}/sge;
+ $_[0] = $enc_ascii->encode($_[0], Encode::HTMLCREF);
+}
sub ascii_html {
my ($s) = @_;
# ․ · and ͺ were also candidates:
# https://public-inbox.org/meta/20170615015250.GA6484@starla/
# However, • was chosen to make copy+paste errors more obvious
-sub obfuscate_addrs ($) { $_[0] =~ s/(\S+@[^\.]+)\./$1•/g }
+sub obfuscate_addrs ($$;$) {
+ my $ibx = $_[0];
+ my $repl = $_[2] || '•';
+ 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;