diff --git a/crates/engine/src/js.rs b/crates/engine/src/js.rs index a2c444bd6..c80537fba 100644 --- a/crates/engine/src/js.rs +++ b/crates/engine/src/js.rs @@ -289,6 +289,12 @@ pub(crate) fn page_words(text: &pdfcraft_render::PageText, info: &pdfcraft_rende .collect() } +#[cfg(test)] +thread_local! { + /// Characters read to tell underscore runs from other words. + static UNDERSCORE_CHARS_READ: std::cell::Cell = const { std::cell::Cell::new(0) }; +} + /// A page's words in reading order, their boxes mapped from view space by `map` (and ordered /// again, so that [x0, y0, x1, y1] holds whatever way `map` turns them). pub(crate) fn words_with(text: &pdfcraft_render::PageText, map: impl Fn(f32, f32) -> [f32; 2]) -> Vec<(String, [f32; 4])> { @@ -296,6 +302,8 @@ pub(crate) fn words_with(text: &pdfcraft_render::PageText, map: impl Fn(f32, f32 let mut last_line = u32::MAX; // A space glyph ends the word before it. let mut gap = false; + // Whether the last word is an underscore run (a form's blank), which other glyphs don't join. + let mut last_under = false; for (i, g) in text.glyphs.iter().enumerate() { let line = text.line_of.get(i).copied().unwrap_or(0); if g.text.trim().is_empty() { @@ -303,10 +311,9 @@ pub(crate) fn words_with(text: &pdfcraft_render::PageText, map: impl Fn(f32, f32 continue; } let under = g.text.chars().all(|c| c == '_'); - let breaks = match words.last() { - None => true, - Some((w, _)) => gap || line != last_line || text.space_before.get(i).copied().unwrap_or(false) || w.chars().all(|c| c == '_') != under, - }; + #[cfg(test)] + UNDERSCORE_CHARS_READ.with(|n| n.set(n.get() + g.text.len())); + let breaks = words.is_empty() || gap || line != last_line || text.space_before.get(i).copied().unwrap_or(false) || last_under != under; gap = false; last_line = line; match words.last_mut() { @@ -317,7 +324,10 @@ pub(crate) fn words_with(text: &pdfcraft_render::PageText, map: impl Fn(f32, f32 r[2] = r[2].max(g.rect[2]); r[3] = r[3].max(g.rect[3]); } - _ => words.push((g.text.clone(), g.rect)), + _ => { + words.push((g.text.clone(), g.rect)); + last_under = under; + } } } words @@ -409,6 +419,27 @@ impl Session { mod review_tests { use super::*; + /// A long run of underscores (a form's blank) is read in one pass: each glyph is compared with + /// the word so far without reading the word again. + #[test] + fn a_long_underscore_run_is_read_in_one_pass() { + let n = 10_000; + let glyph = |i: usize, t: &str| pdfcraft_render::TextGlyph { + text: t.into(), + rect: [i as f32, 0.0, i as f32 + 1.0, 10.0], + quad: [[0.0; 2]; 4], + direction: [1.0, 0.0], + }; + let mut glyphs: Vec<_> = (0..n).map(|i| glyph(i, "_")).collect(); + glyphs.push(glyph(n, "x")); + let text = pdfcraft_render::PageText { line_of: vec![0; glyphs.len()], space_before: vec![false; glyphs.len()], glyphs }; + UNDERSCORE_CHARS_READ.with(|c| c.set(0)); + let words = words_with(&text, |x, y| [x, y]); + assert_eq!(words.iter().map(|(w, _)| w.len()).collect::>(), [n, 1]); + let read = UNDERSCORE_CHARS_READ.with(std::cell::Cell::get); + assert!(read <= 4 * n, "{read} characters read for {n} glyphs"); + } + #[test] fn duplicate_field_names_diff_against_first_original() { let first = pdfcraft_js::FieldState::new("duplicate", pdfcraft_js::FieldType::Text, vec!["first".into()]);