-# Copyright (C) 2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2019-2021 all contributors <meta@public-inbox.org>
# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
# I have no idea how stable or safe this is for handling untrusted
# wrapper for SWIG-generated highlight.pm bindings
package PublicInbox::HlMod;
use strict;
-use warnings;
+use v5.10.1;
use highlight; # SWIG-generated stuff
+use PublicInbox::Hval qw(src_escape ascii_html);
my $hl;
sub _parse_filetypes ($) {
- my $ft_conf = $_[0]->searchFile('filetypes.conf') or
+ my $ft_conf = $_[0]->getFiletypesConfPath('filetypes') or
die 'filetypes.conf not found by highlight';
open my $fh, '<', $ft_conf or die "failed to open($ft_conf): $!";
local $/;
(\%ext2lang, \@shebang);
}
-# We only need one instance, so we don't need to do
-# highlight::CodeGenerator::deleteInstance
+# We only need one instance
sub new {
my ($class) = @_;
$hl ||= do {
sub do_hl_lang {
my ($self, $str, $lang) = @_;
- my $dir = $self->{-dir};
my $langpath;
-
if (defined $lang) {
- $langpath = $dir->getLangPath("$lang.lang") or return;
- $lang = undef unless -f $langpath
- }
- unless (defined $lang) {
- $lang = _shebang2lang($self, $str) or return;
- $langpath = $dir->getLangPath("$lang.lang") or return;
- return unless -f $langpath
+ $langpath = $self->{-dir}->getLangPath("$lang.lang") or return;
+ undef $lang unless -f $langpath;
}
- my $gen = $self->{$langpath} ||= do {
- my $g = highlight::CodeGenerator::getInstance($highlight::HTML);
- $g->setFragmentCode(1); # generate html fragment
+ $lang //= _shebang2lang($self, $str) // return;
+ $langpath = $self->{-dir}->getLangPath("$lang.lang") or return;
+ return unless -f $langpath;
- # whatever theme works
- my $themepath = $dir->getThemePath('print.theme');
- $g->initTheme($themepath);
- $g->loadLanguage($langpath);
- $g->setEncoding('utf-8');
- $g;
- };
+ my $g = highlight::CodeGenerator::getInstance($highlight::HTML);
+ $g->setFragmentCode(1); # generate html fragment
+ # whatever theme works
+ $g->initTheme($self->{-dir}->getThemePath('print.theme'));
+ $g->loadLanguage($langpath);
+ $g->setEncoding('utf-8');
# we assume $$str is valid UTF-8, but the SWIG binding doesn't
# know that, so ensure it's marked as UTF-8 even if it isnt...
- my $out = $gen->generateString($$str);
+ my $out = $g->generateString($$str);
+ highlight::CodeGenerator::deleteInstance($g);
utf8::decode($out);
+ src_escape($out);
\$out;
}
+# Highlight text, but support Markdown "```$LANG" notation
+# while preserving WYSIWYG of plain-text documentation.
+# This is NOT to be enabled by default or encouraged for parsing
+# emails, since it is NOT stable and can lead to standards
+# proliferation of email.
+sub do_hl_text {
+ my ($self, $str) = @_;
+
+ $$str = join('', map {
+ if (/\A(``` ?)(\w+)\s*?\n(.+)(^```\s*)\z/sm) {
+ my ($pfx, $lang, $code, $post) = ($1, $2, $3, $4);
+ my $hl = do_hl_lang($self, \$code, $lang) || \$code;
+ $pfx . $lang . "\n" . $$hl . $post;
+ } else {
+ ascii_html($_);
+ }
+ } split(/(^``` ?\w+\s*?\n.+?^```\s*$)/sm, $$str));
+}
+
1;