-# Copyright (C) 2014, Eric Wong <normalperson@yhbt.net> and all contributors
-# 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
+# represents a header value in various forms. Used for HTML generation
+# in our web interface(s)
package PublicInbox::Hval;
use strict;
use warnings;
-use fields qw(raw href);
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/;
+
+# User-generated content (UGC) may have excessively long lines
+# and screw up rendering on some browsers, so we use pre-wrap.
+#
+# We also force everything to the same scaled font-size because GUI
+# browsers (tested both Firefox and surf (webkit)) uses a larger font
+# for the Search <form> element than the rest of the page. Font size
+# uniformity is important to people who rely on gigantic fonts.
+# Finally, we use monospace to ensure the Search field and button
+# has the same size and spacing as everything else which is
+# <pre>-formatted anyways.
+use constant STYLE =>
+ '<style>pre{white-space:pre-wrap}' .
+ '*{font-size:100%;font-family:monospace}</style>';
my $enc_ascii = find_encoding('us-ascii');
sub new {
my ($class, $raw, $href) = @_;
- my $self = fields::new($class);
- # we never care about leading/trailing whitespace
- $raw =~ s/\A\s*//;
+ # we never care about trailing whitespace
$raw =~ s/\s*\z//;
- $self->{raw} = $raw;
- $self->{href} = defined $href ? $href : $raw;
- $self;
+ bless {
+ raw => $raw,
+ href => defined $href ? $href : $raw,
+ }, $class;
}
sub new_msgid {
- my ($class, $msgid, $no_compress) = @_;
- $msgid = mid_clean($msgid);
- $class->new($msgid, $msgid);
+ my ($class, $msgid) = @_;
+ $class->new($msgid, mid_escape($msgid));
}
sub new_oneline {
'>' => '>',
);
+$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 $_[1]) {
}
}
+sub prurl {
+ my ($env, $u) = @_;
+ index($u, '//') == 0 ? "$env->{'psgi.url_scheme'}:$u" : $u;
+}
+
+# for misguided people who believe in this stuff, give them a
+# substitution for '.'
+# ․ · 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 ($$;$) {
+ 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;