From 0cae1c518b863ab660272b375710a3261e1a3c34 Mon Sep 17 00:00:00 2001
From: oracola91 <118899664+oracola91@users.noreply.github.com>
Date: Tue, 3 Nov 2026 00:10:15 +0200
Subject: [PATCH] A language tag longer than 35 characters is still a tag

BCP 47 sets no maximum length; 35 characters is only the least a protocol
must hold. A well formed tag such as en-US-u-ca-gregory-nu-latn-co-phonebk
was left out of both exports. The bound is now 255, kept only so a PDF's
/Lang can't put an unbounded string in the file.
---
 crates/export/src/as_html.rs | 8 ++++++--
 crates/export/src/tests.rs   | 7 ++++++-
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/crates/export/src/as_html.rs b/crates/export/src/as_html.rs
index 6ae767d09c..45f6ecafca 100644
--- a/crates/export/src/as_html.rs
+++ b/crates/export/src/as_html.rs
@@ -8,14 +8,18 @@ pub(crate) fn allowed(c: char) -> bool {
     matches!(c, '\t' | '\n' | '\r') || !(c.is_ascii_control() || c == '\u{FFFE}' || c == '\u{FFFF}')
 }
 
+/// The longest language tag the exports write. BCP 47 sets no maximum (35 characters is only
+/// the least a protocol must hold), so this bounds only what a PDF's `/Lang` can put in a file.
+const LONGEST_TAG: usize = 255;
+
 /// `lang` when it is a well formed language tag (BCP 47, as a PDF's `/Lang` holds one): a primary
 /// language of two or three letters, then subtags of one to eight letters or digits, joined by
-/// hyphens, 35 characters at most. Anything else names no language.
+/// hyphens, [`LONGEST_TAG`] characters at most. Anything else names no language.
 pub(crate) fn language_tag(lang: Option<&str>) -> Option<&str> {
     let tag = lang?.trim();
     let mut subtags = tag.split('-');
     let primary = subtags.next()?;
-    let well_formed = tag.len() <= 35
+    let well_formed = tag.len() <= LONGEST_TAG
         && (2..=3).contains(&primary.len())
         && primary.bytes().all(|b| b.is_ascii_alphabetic())
         && subtags.all(|s| (1..=8).contains(&s.len()) && s.bytes().all(|b| b.is_ascii_alphanumeric()));
diff --git a/crates/export/src/tests.rs b/crates/export/src/tests.rs
index d62148aaf2..ba5f95f66d 100644
--- a/crates/export/src/tests.rs
+++ b/crates/export/src/tests.rs
@@ -260,6 +260,11 @@ fn word_and_html_take_the_documents_language() {
     assert!(styles(Some("ar-EG")).contains(&defaults("<w:lang w:bidi=\"ar-EG\"/>")), "right-to-left text");
     assert!(styles(Some("HE")).contains("<w:lang w:bidi=\"HE\"/>"), "right-to-left text");
     assert!(html_with_language(&pages, "Report", Some("bg-BG")).starts_with("<!DOCTYPE html>\n<html lang=\"bg-BG\">\n"));
+    // A tag longer than 35 characters is still a tag.
+    let long = "en-US-u-ca-gregory-nu-latn-co-phonebk";
+    assert!(styles(Some(long)).contains(&format!("<w:lang w:val=\"{long}\"/>")), "{long}");
+    assert!(html_with_language(&pages, "Report", Some(long)).contains(&format!("<html lang=\"{long}\">")), "{long}");
+    let too_long = format!("en{}", "-abcdefgh".repeat(29));
     for lang in [
         None,
         Some(""),
@@ -270,7 +275,7 @@ fn word_and_html_take_the_documents_language() {
         Some("bg--BG"),
         Some("bg-"),
         Some("en-US-abcdefghi"),
-        Some("en-abcdefgh-abcdefgh-abcdefgh-abcdefgh"),
+        Some(too_long.as_str()),
         Some("en-\"x\""),
         Some("1a-BG"),
         Some("\u{431}\u{433}-BG"),