diff --git a/crates/export/src/as_html.rs b/crates/export/src/as_html.rs index 45f6ecafca..8c250ca484 100644 --- a/crates/export/src/as_html.rs +++ b/crates/export/src/as_html.rs @@ -14,16 +14,33 @@ 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, [`LONGEST_TAG`] characters at most. Anything else names no language. +/// hyphens, [`LONGEST_TAG`] characters at most. A singleton (one letter or digit) starts an +/// extension, or with `x` private use, and needs a subtag after it. 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() <= 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())); - well_formed.then_some(tag) + if tag.len() > LONGEST_TAG || !(2..=3).contains(&primary.len()) || !primary.bytes().all(|b| b.is_ascii_alphabetic()) { + return None; + } + // In private use every subtag is data, one character long or not. + let (mut private, mut singleton) = (false, false); + for s in subtags { + if !(1..=8).contains(&s.len()) || !s.bytes().all(|b| b.is_ascii_alphanumeric()) { + return None; + } + if s.len() == 1 && !private { + if singleton { + return None; + } + private = s.eq_ignore_ascii_case("x"); + singleton = true; + } else { + singleton = false; + } + } + (!singleton).then_some(tag) } pub(crate) fn esc(s: &str) -> String { diff --git a/crates/export/src/tests.rs b/crates/export/src/tests.rs index ba5f95f66d..5820fc57bc 100644 --- a/crates/export/src/tests.rs +++ b/crates/export/src/tests.rs @@ -265,6 +265,8 @@ fn word_and_html_take_the_documents_language() { assert!(styles(Some(long)).contains(&format!("")), "{long}"); assert!(html_with_language(&pages, "Report", Some(long)).contains(&format!("")), "{long}"); let too_long = format!("en{}", "-abcdefgh".repeat(29)); + // Private use takes one-character subtags. + assert!(html_with_language(&pages, "Report", Some("en-x-a-b")).contains("")); for lang in [ None, Some(""), @@ -274,6 +276,10 @@ fn word_and_html_take_the_documents_language() { Some("bulg-BG"), Some("bg--BG"), Some("bg-"), + Some("en-x"), + Some("en-a"), + Some("en-a-x-private"), + Some("en-US-u-ca-x"), Some("en-US-abcdefghi"), Some(too_long.as_str()), Some("en-\"x\""),