Compare commits

...
Author SHA1 Message Date
Abimael MartellandClaude Fable 5 59b3fcd9e6 fix(markdown): lowercase-initial short fragments are not headings
A lowercase-initial one-or-two-word "heading" is a mid-sentence
fragment beside display math ("or inversely", "and therefore") — real
headings that short start uppercase. Measured as spurious headings on
academic docs (opendataloader MHS via fire-pdf's coverage_fallback
path, ENG-5029).

Extends is_heading_fragment, so both bold-heading call sites get the
gate. Corpus sweep (708 opendataloader + ParseBench PDFs): 33 docs
change, all lowercase-fragment demotions from `##`/`#` to plain or
bold ("## caldera" -> "**caldera**", "## of quorum.\"" ->
"**of quorum.\"**") — no real heading is lowercase-initial and that
short in either corpus.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L3U6BKYCS73DVA83odAfYB
2026-07-11 13:09:10 -07:00
+19
View File
@@ -174,6 +174,21 @@ pub(crate) fn is_toc_marker_heading(text: &str) -> bool {
pub(crate) fn is_heading_fragment(text: &str) -> bool {
let t = text.trim_end();
// A lowercase-initial one-or-two-word "heading" is a mid-sentence
// fragment beside display math ("or inversely", "and therefore") —
// real headings that short start uppercase. Measured as spurious
// headings on academic docs (fire-pdf ENG-5029 / opendataloader MHS).
{
let words: Vec<&str> = t.split_whitespace().collect();
if words.len() <= 2 {
if let Some(first_alpha) = t.chars().find(|c| c.is_alphabetic()) {
if first_alpha.is_lowercase() {
return true;
}
}
}
}
fn is_equation_number(s: &str) -> bool {
s.strip_prefix('(')
.and_then(|r| r.strip_suffix(')'))
@@ -460,6 +475,10 @@ mod tests {
#[test]
fn heading_fragments() {
// Equation lead-ins: colon ending + inline equation reference
assert!(is_heading_fragment("or inversely"));
assert!(is_heading_fragment("and therefore"));
assert!(!is_heading_fragment("Introduction"));
assert!(!is_heading_fragment("iPhone Sales Strategy Overview")); // 4 words, exempt
assert!(is_heading_fragment("Rearranging Equation (8) gives:"));
// Display-equation neighbours ending in an equation number
assert!(is_heading_fragment("S = kB ln W, (2)"));