Fix UTF-8 double encoding in #!vim perl blocks

[Copilot]

UTF-8 characters in #!vim perl code blocks were displaying as « instead of « due to double encoding. =begin perl blocks rendered correctly.

Root Cause

In inc/WWW-AdventCalendar/lib/WWW/AdventCalendar/Article.pm:

$body = Encode::encode('utf-8', $body);              # Line 121: encode for Pod::Elemental
my $document = Pod::Elemental->read_string($body);
# ... transformers process content ...
$body = $document->as_pod_string;                    # Line 140: returns UTF-8 bytes
$parser->parse_string_document( Encode::encode('utf-8', $body) );  # Line 149: re-encodes!

as_pod_string returns UTF-8 bytes, which were then re-encoded, turning c2 ab (UTF-8 for «) into c3 82 c2 ab (displays as «).

Changes

Decode UTF-8 bytes back to characters after transformation, before passing to Pod::Simple::XHTML:

$body = $document->as_pod_string;
$body = Encode::decode('utf-8', $body);  # Decode bytes → characters
$parser->parse_string_document( $body ); # Pass characters (expects strings, not bytes)

This ensures content is encoded exactly once.

Modified Files

• inc/WWW-AdventCalendar submodule commit updated
  • lib/WWW/AdventCalendar/Article.pm: Added decode step, removed redundant encode

Fixes #541 (related to #505)

[!WARNING]

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• cpanmin.us
  • Triggering command: curl -L REDACTED (dns block)
• esm.ubuntu.com
  • Triggering command: /usr/lib/apt/methods/https (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

---

This section details on the original issue you should resolve

<issue_title>UTF-8 is double encoded in #!vim perl</issue_title> <issue_description>As can be seen in 2024-12-15, UTF-8 encoded characters are displayed correctly in =begin perl, but they're double encoded in #!vim perl:

=begin perl

      ok( headerOK( $str ), "«$str» is OK" );

renders «$str» correctly, but

    #!vim perl

          debug "«$firstLine» is proper markdown ho, ho, ho";

shows as

debug "«$firstLine» is proper markdown ho, ho, ho";

</issue_description>

Comments on the Issue (you are @copilot in this section)

@oalders Related to perladvent/Perl-Advent#505 @oalders Maybe it shouldn't have been closed. 😄 I guess there's an ongoing issue here. The `vim` syntax highlight is nice because you can choose an arbitrary language, but it sometimes does wacky things with Perl. This would all be easier if we just used Markdown, but I guess Pod is part of the charm.

If you feel inclined to send a PR with more fixes, I'm happy to merge!</comment_new>

• Fixes perladvent/Perl-Advent#530

---

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.