address review: index placeable array replacements, search past zero-length DIVIDE runs, per-part broken-table outlines

Every SORTENTSTABLE rebuilt its whole entity store, so many small tables naming one large space made import quadratic. Each space is now sorted once, by the last table naming it, which already decided its order.

Co-authored-by: Brandon Thomas <echelon@gmail.com>

crates/doc/src/array.rs

@@ -204,6 +204,23 @@ impl ArrayParams {
         self.replaced.iter().rev().find(|r| (r.i, r.j, r.level) == (i, j, level)).map_or(self.source.as_str(), |r| r.block.as_str())
     }
 
+    /// [`block_for`](Self::block_for) for many items: the replacements are indexed once (the last
+    /// entry for a place wins, as there), so each lookup is O(1) instead of a scan of `replaced`.
+    pub fn block_lookup<'a>(&'a self) -> impl Fn(u32, u32, u32) -> &'a str + 'a {
+        // Only places `items()` generates are indexed, so stray out-of-range records cost nothing.
+        let (cols, rows) = match &self.kind {
+            ArrayKind::Rect(r) => (r.cols, r.rows),
+            ArrayKind::Polar(p) => (p.items, p.rows),
+        };
+        let index: std::collections::HashMap<(u32, u32, u32), &str> = self
+            .replaced
+            .iter()
+            .filter(|r| r.i < cols && r.j < rows && r.level < self.levels)
+            .map(|r| ((r.i, r.j, r.level), r.block.as_str()))
+            .collect();
+        move |i, j, level| index.get(&(i, j, level)).copied().unwrap_or(self.source.as_str())
+    }
+
     /// The block references that make up the array block: one per item, on layer 0 with ByBlock
     /// properties so they take the array's. Handles are allocated from `d`. `None` when the
     /// parameters are not [valid](Self::is_valid).
@@ -217,9 +234,10 @@ impl ArrayParams {
             ..Common::default()
         };
         let mut out = Vec::with_capacity(items.len());
+        let block_for = self.block_lookup();
         for it in items {
             let ins = Insert {
-                block: self.block_for(it.i, it.j, it.level).to_string(),
+                block: block_for(it.i, it.j, it.level).to_string(),
                 insert: it.insert,
                 scale: Vec3::new(1.0, 1.0, 1.0),
                 rotation: it.rotation,
@@ -300,6 +318,18 @@ mod tests {
         }
     }
 
+    #[test]
+    fn block_lookup_agrees_with_block_for_and_the_last_replacement_wins() {
+        let mut p = rect(3, 2);
+        let r = |i, j, level, b: &str| ReplacedItem { i, j, level, block: b.into() };
+        p.replaced = vec![r(1, 0, 0, "A"), r(1, 0, 0, "B"), r(2, 1, 1, "C")];
+        let look = p.block_lookup();
+        for (i, j, level) in [(0, 0, 0), (1, 0, 0), (2, 1, 1), (2, 1, 0)] {
+            assert_eq!(look(i, j, level), p.block_for(i, j, level));
+        }
+        assert_eq!((look(1, 0, 0), look(0, 0, 0)), ("B", "*U1"));
+    }
+
     #[test]
     fn rect_items_go_column_row_level() {
         let items = rect(3, 2).items().unwrap_or_default();

crates/doc/src/dynblock/apply.rs

@@ -674,6 +674,10 @@ fn apply(
 /// Associative hatches of block `b` whose loop is one closed polyline of the block take its
 /// outline again (it may have been stretched).
 fn refill_hatches(b: &mut Block) {
+    // Each loop gets its own copy of the outline, so many small loops on one big outline multiply it;
+    // past this many vertices in all, the remaining loops keep the outline they have.
+    const MAX_REFILLED_VERTICES: usize = 4_000_000;
+    let mut budget = MAX_REFILLED_VERTICES;
     let outlines: HashMap<Handle, Vec<cadcraft_geom::PolyVertex>> = b
         .entities
         .iter()
@@ -689,7 +693,9 @@ fn refill_hatches(b: &mut Block) {
                 for l in &mut hh.loops {
                     if let [s] = l.sources.as_slice()
                         && let Some(vs) = outlines.get(s)
+                        && let Some(left) = budget.checked_sub(vs.len())
                     {
+                        budget = left;
                         l.vertices.clone_from(vs);
                     }
                 }

crates/doc/src/tables.rs

@@ -491,11 +491,18 @@ impl DimStyle {
         use serde_json::Value;
         let mut rejected = Vec::new();
         let Ok(mut cur) = serde_json::to_value(&*self) else { return src.keys().cloned().collect() };
+        // Spellings of one field (`DIMPOST`, `dimpost`, `textPrefix`…): only the last is applied, so
+        // the style is checked once per field, not once per spelling (each check copies its strings).
+        let last_spelling: std::collections::HashMap<&str, &String> =
+            src.keys().filter_map(|k| DimStyle::field_name(k).filter(|f| *f != "name").map(|f| (f, k))).collect();
         for (k, v) in src {
             let Some(field) = DimStyle::field_name(k).filter(|f| *f != "name") else {
                 rejected.push(k.clone());
                 continue;
             };
+            if last_spelling.get(field) != Some(&k) {
+                continue;
+            }
             let Some(obj) = cur.as_object_mut() else { break };
             let Some(old) = obj.get(field).cloned() else {
                 rejected.push(k.clone());

crates/doc/src/tests.rs

@@ -709,3 +709,14 @@ fn space_names_its_tab() {
     assert_eq!(p.layout(), Some("Sheet A"));
     assert_eq!(p.tab_name(), "Sheet A");
 }
+
+/// Several spellings of one DIM field apply once, the last in the map's order, and none is rejected.
+#[test]
+fn dim_style_spellings_of_one_field_apply_once() {
+    let mut st = DimStyle::default();
+    let m = serde_json::json!({ "textHeight": 2.5, "TEXTHEIGHT": 3.5, "DIMTXT": 4.5 });
+    let m = m.as_object().unwrap();
+    let want = m.values().next_back().and_then(serde_json::Value::as_f64).unwrap();
+    assert!(st.apply_fields(m).is_empty());
+    assert_eq!(st.text_height, want);
+}

crates/engine/src/cmd/array/edit.rs

@@ -188,8 +188,9 @@ fn item_at(d: &Drawing, h: Handle, at: Vec2, tol: f64) -> Option<(u32, u32, u32)
     let mut best: Option<((u32, u32, u32), f64)> = None;
     // Each block's own extents, measured once.
     let mut extents: HashMap<String, (Vec2, Bounds2)> = HashMap::new();
+    let block_for = p.block_lookup();
     for it in p.items()? {
-        let name = p.block_for(it.i, it.j, it.level);
+        let name = block_for(it.i, it.j, it.level);
         let (base, local) = match extents.get(name) {
             Some(x) => *x,
             None => {

crates/engine/src/cmd/curves.rs

@@ -453,14 +453,32 @@ impl Chain {
     }
     /// Point and unit tangent at arc length `d` from the start (clamped).
     pub fn at_length(&self, d: f64) -> Option<(Vec2, Vec2)> {
-        let mut acc = 0.0;
-        for s in &self.segs {
-            let l = s.len();
-            if d <= acc + l + 1e-12 && l > 0.0 {
-                let t = ((d - acc) / l).clamp(0.0, 1.0);
-                return Some((s.at(t), s.tangent(t)));
-            }
-            acc += l;
+        self.at_length_in(&self.end_lengths(), d)
+    }
+    /// The arc length from the chain's start to the end of each segment, for [`Self::at_length_in`].
+    pub fn end_lengths(&self) -> Vec<f64> {
+        self.segs
+            .iter()
+            .scan(0.0, |acc, s| {
+                *acc += s.len();
+                Some(*acc)
+            })
+            .collect()
+    }
+    /// [`Self::at_length`] with the segment end lengths computed once (`ends` from
+    /// [`Self::end_lengths`]), so many samples along one chain each cost a binary search.
+    pub fn at_length_in(&self, ends: &[f64], d: f64) -> Option<(Vec2, Vec2)> {
+        let first = ends.partition_point(|e| d > e + 1e-12);
+        // A segment of no length can't hold the point; the next one that has length does.
+        // `ends` never decreases, so the first segment past `first` with length is found by search
+        // (a run of zero-length segments can be long) instead of a scan.
+        let base = first.checked_sub(1).and_then(|p| ends.get(p)).copied().unwrap_or(0.0);
+        let i = first + ends.get(first..).unwrap_or_default().partition_point(|e| *e <= base);
+        let i = (i < self.segs.len()).then_some(i);
+        if let Some(s) = i.and_then(|i| self.segs.get(i)) {
+            let start = i.and_then(|i| i.checked_sub(1)).and_then(|p| ends.get(p)).copied().unwrap_or(0.0);
+            let t = ((d - start) / s.len()).clamp(0.0, 1.0);
+            return Some((s.at(t), s.tangent(t)));
         }
         self.segs.last().map(|s| (s.end(), s.tangent(1.0)))
     }
@@ -640,6 +658,34 @@ pub fn reverse_vertices(vs: &[PolyVertex], closed: bool) -> Vec<PolyVertex> {
 mod tests {
     use super::*;
 
+    /// The indexed lookup gives the point and tangent a scan from the start gives, also past the
+    /// ends and over a segment of no length.
+    #[test]
+    fn at_length_in_matches_a_scan() {
+        let l = |a: (f64, f64), b: (f64, f64)| Segment::Line(Line::new(Vec2::new(a.0, a.1), Vec2::new(b.0, b.1)));
+        let c = Chain {
+            segs: vec![l((0.0, 0.0), (0.0, 0.0)), l((0.0, 0.0), (4.0, 0.0)), l((4.0, 0.0), (4.0, 0.0)), l((4.0, 0.0), (4.0, 3.0))],
+            closed: false,
+        };
+        let ends = c.end_lengths();
+        for d in [-1.0, 0.0, 1.5, 4.0, 4.0 + 1e-13, 5.0, 7.0, 9.0] {
+            // The scan this replaced.
+            let mut acc = 0.0;
+            let mut want = c.segs.last().map(|s| (s.end(), s.tangent(1.0)));
+            for s in &c.segs {
+                let len = s.len();
+                if d <= acc + len + 1e-12 && len > 0.0 {
+                    let t = ((d - acc) / len).clamp(0.0, 1.0);
+                    want = Some((s.at(t), s.tangent(t)));
+                    break;
+                }
+                acc += len;
+            }
+            assert_eq!(c.at_length_in(&ends, d), want, "d = {d}");
+            assert_eq!(c.at_length(d), want);
+        }
+    }
+
     #[test]
     fn arc_builders() {
         let a = arc_sca(Vec2::new(1.0, 0.0), Vec2::ZERO, std::f64::consts::FRAC_PI_2).unwrap();

crates/engine/src/cmd/draw2/divide.rs

@@ -36,16 +36,18 @@ fn check_block(s: &Session, b: Option<&str>) -> Result<()> {
 pub(crate) fn divide_points(c: &Chain, n: usize) -> Vec<(Vec2, Vec2)> {
     let l = c.len();
     let range = if c.closed { 0..n } else { 1..n };
-    range.filter_map(|i| c.at_length(l * i as f64 / n as f64)).collect()
+    let ends = c.end_lengths();
+    range.filter_map(|i| c.at_length_in(&ends, l * i as f64 / n as f64)).collect()
 }
 
 pub(crate) fn measure_points(c: &Chain, step: f64) -> Vec<(Vec2, Vec2)> {
     let l = c.len();
+    let ends = c.end_lengths();
     let mut out = Vec::new();
     let mut k = 1usize;
     while (k as f64) * step < l - 1e-9 && out.len() < MAX_GEN {
         let d = k as f64 * step;
-        out.extend(c.at_length(d));
+        out.extend(c.at_length_in(&ends, d));
         k += 1;
     }
     out

crates/engine/src/cmd/draw2/revcloud.rs

@@ -58,8 +58,9 @@ pub(crate) fn cloud_vertices(boundary: &[Vec2], arc_len: f64, per_edge: bool, re
             closed: true,
         };
         let k = ((perim / arc_len).round() as usize).clamp(3, MAX_GEN);
+        let ends = chain.end_lengths();
         for j in 0..k {
-            out.extend(chain.at_length(perim * j as f64 / k as f64).map(|x| x.0));
+            out.extend(chain.at_length_in(&ends, perim * j as f64 / k as f64).map(|x| x.0));
         }
     }
     let b = if reverse { -0.5 } else { 0.5 };

crates/engine/src/cmd/modify2/patharray.rs

@@ -34,10 +34,12 @@ pub(crate) fn arraypath(
         _ => (6, if c.closed { l / 6.0 } else { l / 5.0 }),
     };
     crate::cmd::array::check_size(s, n as u64, objs.len())?;
-    let Some((p0, t0)) = c.at_length(0.0) else { return Ok(Vec::new()) };
+    // Segment end lengths once: each sample is then a binary search, not a scan from the start.
+    let ends = c.end_lengths();
+    let Some((p0, t0)) = c.at_length_in(&ends, 0.0) else { return Ok(Vec::new()) };
     let mut out = Vec::new();
     for i in 1..n {
-        let Some((p, t)) = c.at_length(step * i as f64) else { continue };
+        let Some((p, t)) = c.at_length_in(&ends, step * i as f64) else { continue };
         let mut m = Mat3::translate(p - p0);
         if align {
             m = Mat3::rotate_about(p, t.angle() - t0.angle()).then_before(m);

crates/io/src/dxf_read/document.rs

@@ -333,7 +333,17 @@ pub(super) fn apply_sortents(
     paper_for: &HashMap<String, String>,
     first_layout: &str,
 ) {
-    for (owner, map) in tables {
+    // Each sort rebuilds its whole space, so a space named by many tables is sorted once, by the
+    // last of them (which decided its order anyway); repeated tables made import quadratic.
+    let target = |owner: &String| {
+        let up = brs.get(owner)?.to_ascii_uppercase();
+        Some(if up.starts_with("*PAPER_SPACE") { paper_for.get(&up).cloned().unwrap_or_else(|| first_layout.to_string()) + "\0paper" } else { up })
+    };
+    let last: HashMap<String, usize> = tables.iter().enumerate().filter_map(|(i, (owner, _))| Some((target(owner)?, i))).collect();
+    for (i, (owner, map)) in tables.iter().enumerate() {
+        if target(owner).and_then(|t| last.get(&t)) != Some(&i) {
+            continue;
+        }
         let Some(name) = brs.get(owner) else { continue };
         let up = name.to_ascii_uppercase();
         // A sort handle of 0 draws last (ezdxf `reorder`, which notes AutoCAD defines it, undocumented).

crates/io/src/dxf_read/entities.rs

@@ -299,7 +299,9 @@ pub(super) fn acad_table(tags: &[Tag], table_cells_left: &mut usize) -> Table {
     // Large declared sizes must be backed by cell records (no allocation from a bare count).
     let n_cells = tail.iter().filter(|x| x.code == 171).count();
     let declared = rows.saturating_mul(cols);
-    if declared > MAX_CELLS || (declared > 10_000 && n_cells < declared) {
+    // A table with no rows or no columns has no cells: keep neither dimension, so its row heights
+    // and column widths (allocated per dimension, outside the cell budget) are not allocated.
+    if declared == 0 || declared > MAX_CELLS || (declared > 10_000 && n_cells < declared) {
         rows = 0;
         cols = 0;
     }

crates/io/src/tests.rs

@@ -337,6 +337,42 @@ fn entity_transparency_roundtrips_as_group_440() {
     assert_eq!(d.model.iter().map(|e| e.common.transparency).collect::<Vec<_>>(), [Transparency::ByLayer, Transparency::Percent(90)]);
 }
 
+/// Several SORTENTSTABLEs for one space sort it once, in the last table's order.
+#[test]
+fn repeated_sortents_tables_use_the_last() {
+    let table =
+        |a: u32, b: u32| format!("0\nSORTENTSTABLE\n5\n{:X}\n100\nAcDbSortentsTable\n330\n1F\n331\nA\n5\n{a:X}\n331\nB\n5\n{b:X}\n", 0x100 + a);
+    let mut t = String::from(
+        "0\nSECTION\n2\nTABLES\n0\nTABLE\n2\nBLOCK_RECORD\n0\nBLOCK_RECORD\n5\n1F\n2\n*Model_Space\n0\nENDTAB\n0\nENDSEC\n\
+         0\nSECTION\n2\nENTITIES\n0\nLINE\n5\nA\n330\n1F\n10\n0\n20\n0\n11\n1\n21\n1\n0\nLINE\n5\nB\n330\n1F\n10\n0\n20\n0\n11\n2\n21\n2\n0\nENDSEC\n\
+         0\nSECTION\n2\nOBJECTS\n0\nDICTIONARY\n5\nC\n",
+    );
+    for _ in 0..1000 {
+        t.push_str(&table(2, 1));
+    }
+    t.push_str(&table(1, 2));
+    t.push_str("0\nENDSEC\n0\nEOF\n");
+    let d = read(t.as_bytes(), "s.dxf").unwrap();
+    assert_eq!(d.model.iter().map(|e| e.handle.0).collect::<Vec<_>>(), [0xA, 0xB]);
+    let reversed = t.replacen(&table(1, 2), &table(2, 1), 1);
+    let d = read(reversed.as_bytes(), "s.dxf").unwrap();
+    assert_eq!(d.model.iter().map(|e| e.handle.0).collect::<Vec<_>>(), [0xB, 0xA]);
+}
+
+/// A table declaring 10 000 rows and no columns (or the reverse) is read as an empty table.
+#[test]
+fn table_with_an_empty_dimension_allocates_nothing() {
+    for (rows, cols) in [(10_000, 0), (0, 10_000)] {
+        let t = format!("0\nSECTION\n2\nENTITIES\n0\nACAD_TABLE\n100\nAcDbTable\n91\n{rows}\n92\n{cols}\n0\nENDSEC\n0\nEOF\n");
+        let d = read(t.as_bytes(), "t.dxf").unwrap();
+        let tables: Vec<_> = d.model.iter().filter_map(|e| if let EntityKind::Table(t) = &e.kind { Some(t) } else { None }).collect();
+        assert_eq!(tables.len(), 1, "the table is read");
+        for t in tables {
+            assert!(t.row_heights.is_empty() && t.col_widths.is_empty() && t.cells.is_empty());
+        }
+    }
+}
+
 /// Many distinct layer, linetype and style names (in the tables and on entities) read in linear
 /// time, with the duplicate rules kept: first LTYPE wins, last STYLE wins, layers case-insensitive.
 #[test]

crates/render/src/table.rs

@@ -133,6 +133,20 @@ pub fn table_geometry(d: &Drawing, t: &Table) -> TableGeom {
     if parts.len() <= 1 {
         return layout(d, t);
     }
+    // Every part is laid out and kept, so the cells of all of them count together (a header repeated
+    // on each part adds to each); past the limit only the table's outline is drawn.
+    let cols = t.col_widths.len().min(10_000);
+    let total: usize = parts.iter().map(|p| p.rows.len().min(10_000).saturating_mul(cols)).fold(0, usize::saturating_add);
+    if total > MAX_LAYOUT_CELLS {
+        // One outline per part, at the part's origin and as tall as its displayed rows.
+        let w = edges(&t.col_widths, cols).last().copied().unwrap_or(0.0);
+        let mut g = TableGeom::default();
+        for p in parts {
+            let h: f64 = p.rows.iter().take(10_000).map(|r| t.row_heights.get(*r).copied().filter(|v| v.is_finite()).unwrap_or(0.0)).sum();
+            outline_box(&mut g, p.origin, w, h);
+        }
+        return g;
+    }
     let mut g = TableGeom::default();
     for p in parts {
         let mut pg = layout(d, &part_table(t, &p.rows, p.origin));
@@ -156,16 +170,20 @@ fn part_table(t: &Table, rows: &[usize], origin: Vec2) -> Table {
     // Otherwise `layout` renders an outline, so materialising millions of empty cells here would be
     // wasted work an attacker can trigger with a compact dimension array (CWE-789).
     if rows.len().min(10_000).saturating_mul(cols) <= MAX_LAYOUT_CELLS {
+        // `run[i]`: how many rows from part row `i` follow one another in the table, found once so a
+        // merge is cut by a lookup, not by walking the rows it spans.
+        let mut run = vec![1u32; rows.len()];
+        for i in (0..rows.len().saturating_sub(1)).rev() {
+            if rows.get(i + 1).zip(rows.get(i)).is_some_and(|(next, this)| *next == this + 1) {
+                run[i] = run.get(i + 1).copied().unwrap_or(0).saturating_add(1);
+            }
+        }
         for (i, row) in cells.iter_mut().enumerate() {
             row.resize_with(cols, Default::default);
             for cell in row.iter_mut() {
                 if let Some((rs, cs)) = cell.merged {
                     // Rows of the merge that follow in this part.
-                    let start = rows.get(i).copied().unwrap_or(0);
-                    let mut n = 1u32;
-                    while n < rs && rows.get(i + n as usize).is_some_and(|r| *r == start + n as usize) {
-                        n += 1;
-                    }
+                    let n = rs.max(1).min(run.get(i).copied().unwrap_or(1));
                     cell.merged = (n > 1 || cs > 1).then_some((n, cs));
                 }
             }
@@ -186,6 +204,27 @@ fn part_table(t: &Table, rows: &[usize], origin: Vec2) -> Table {
     }
 }
 
+/// The table's outline alone, for a table too large to lay out.
+fn outline(t: &Table) -> TableGeom {
+    let rows = t.row_heights.len().min(10_000);
+    let cols = t.col_widths.len().min(10_000);
+    let (w, h) = (edges(&t.col_widths, cols).last().copied().unwrap_or(0.0), edges(&t.row_heights, rows).last().copied().unwrap_or(0.0));
+    let mut g = TableGeom::default();
+    outline_box(&mut g, t.insert.xy(), w, h);
+    g
+}
+
+/// The four sides of a `w` by `h` box hanging down from `o`.
+fn outline_box(g: &mut TableGeom, o: Vec2, w: f64, h: f64) {
+    let p = |x: f64, y: f64| o + Vec2::new(x, -y);
+    let corners = [p(0.0, 0.0), p(w, 0.0), p(w, h), p(0.0, h), p(0.0, 0.0)];
+    for s in corners.windows(2) {
+        if let [a, b] = s {
+            g.lines.push(TableLine { a: *a, b: *b, color: Color::ByBlock, lineweight: Lineweight::ByBlock });
+        }
+    }
+}
+
 /// Lay out one part.
 fn layout(d: &Drawing, t: &Table) -> TableGeom {
     let st = table_style_of(d, t);
@@ -203,14 +242,7 @@ fn layout(d: &Drawing, t: &Table) -> TableGeom {
     }
     let cov = coverage(t);
     if rows.saturating_mul(cols) > MAX_LAYOUT_CELLS || cov.is_err() {
-        let (w, h) = (x_at(cols), y_at(rows));
-        let corners = [p(0.0, 0.0), p(w, 0.0), p(w, h), p(0.0, h), p(0.0, 0.0)];
-        for s in corners.windows(2) {
-            if let [a, b] = s {
-                g.lines.push(TableLine { a: *a, b: *b, color: Color::ByBlock, lineweight: Lineweight::ByBlock });
-            }
-        }
-        return g;
+        return outline(t);
     }
     let k = style_scale(&st, t);
     // Cell styles by name, scaled to the table.

crates/render/src/tests.rs

@@ -1148,3 +1148,25 @@ fn without_linetypes_every_line_is_drawn_whole() {
     let drawn = build(&drawing("DASHED"), &Space::Model, &Options::default());
     assert!(drawn.prims.len() > 2 * continuous.prims.len(), "drawn with its linetype: {} primitives", drawn.prims.len());
 }
+
+/// A broken table whose parts, with their repeated labels, together hold more cells than a table may
+/// lay out is drawn as its outline, though the table's own cells are within the limit.
+#[test]
+fn broken_table_cells_count_across_its_parts() {
+    let d = Drawing::new_imperial();
+    let t = cadcraft_doc::Table {
+        col_widths: vec![1.0; 600],
+        row_heights: vec![1.0; 1000],
+        title: true,
+        header: true,
+        breaks: Some(cadcraft_doc::TableBreak { enabled: true, height: 3.0, ..Default::default() }),
+        ..Default::default()
+    };
+    assert!(t.parts().len() > 500 && 1000 * 600 <= crate::MAX_LAYOUT_CELLS);
+    let g = crate::table_geometry(&d, &t);
+    let parts = t.parts();
+    assert_eq!((g.lines.len(), g.texts.len(), g.fills.len()), (4 * parts.len(), 0, 0));
+    // Each part's box starts at its own origin.
+    let top = |i: usize| g.lines[4 * i].a;
+    assert!((0..parts.len()).all(|i| top(i) == parts[i].origin));
+}