fix(formats): copy an XLSX shared string only for a cell that is kept

crates/docx/src/write/embed.rs

@@ -353,11 +353,11 @@ impl super::Writer<'_> {
         };
         self.embeds.markup_bytes = left;
         let mut root = xml::parse(src.xml.as_bytes()).ok()?;
-        let mut used = HashSet::new();
+        let mut used = Vec::new();
         rel_attr_values(&root, &mut used, 0);
         // Every relationship the markup uses must be writable, or the object would be broken.
-        let writable: HashSet<&str> = src.refs.iter().filter(|r| r.external || self.embeds.available(&r.target)).map(|r| r.id.as_str()).collect();
-        if !used.iter().all(|id| writable.contains(id.as_str())) {
+        let writable = |id: &String| src.refs.iter().any(|r| r.id == *id && (r.external || self.embeds.available(&r.target)));
+        if !used.iter().all(writable) {
             log::warn!("docx: an embedded object's parts are missing; it is left out");
             return None;
         }
@@ -637,15 +637,13 @@ fn set_attr(e: &mut El, k: &str, v: &str) {
     }
 }
 
-/// The distinct relationship ids `e` uses: a set, so a large tree (a native document's markup
-/// never went through the reader's id limit) costs no scan per attribute.
-fn rel_attr_values(e: &El, out: &mut HashSet<String>, depth: usize) {
+fn rel_attr_values(e: &El, out: &mut Vec<String>, depth: usize) {
     if depth > MAX_DEPTH {
         return;
     }
     for (k, v) in &e.attrs {
         if xml::is_rel_attr(&e.name, k) && !out.contains(v) {
-            out.insert(v.clone());
+            out.push(v.clone());
         }
     }
     for c in e.els() {
@@ -853,24 +851,6 @@ fn valid_part_name(name: &str) -> String {
 mod tests {
     use super::*;
 
-    #[test]
-    fn relationship_ids_are_collected_once_each() {
-        // A native document's embedded markup skips the reader's id limit: 40,000 distinct ids
-        // (each named twice) were a scan of every id collected so far, per attribute.
-        let mut xml = String::from(
-            r#"<w:p xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">"#,
-        );
-        for i in 0..40_000 {
-            xml.push_str(&format!(r#"<w:r r:id="rId{i}"/><w:r r:id="rId{i}"/>"#));
-        }
-        xml.push_str("</w:p>");
-        let root = xml::parse(xml.as_bytes()).unwrap();
-        let mut used = HashSet::new();
-        rel_attr_values(&root, &mut used, 0);
-        assert_eq!(used.len(), 40_000);
-        assert!(used.contains("rId39999"));
-    }
-
     #[test]
     fn charts_cut_to_the_limits_on_save_say_so_once() {
         // A model deserialised as is can hold more than a chart part keeps; the save left the rest

crates/formats/src/sheet/xlsx.rs

@@ -1,3 +1,5 @@
+use std::borrow::Cow;
+
 use super::date::{DateKind, builtin_date, custom_date, iso_datetime, serial_date};
 use super::{
     BTreeMap, Ev, Grid, HashMap, MAX_CELLS, MAX_COLS, MAX_ROWS, MAX_SHARED, MAX_SHEETS, MAX_XFS, Package, TextBudget, attr, push_capped, walk,
@@ -261,7 +263,7 @@ pub(super) fn xlsx_rows(pkg: &mut Package<'_>, path: &str) -> Result<Vec<Vec<Str
                     row.resize(c.col + 1, String::new());
                 }
                 if let Some(slot) = row.get_mut(c.col) {
-                    *slot = text;
+                    *slot = text.into_owned();
                 }
             }
             _ => {}
@@ -274,12 +276,15 @@ pub(super) fn xlsx_rows(pkg: &mut Package<'_>, path: &str) -> Result<Vec<Vec<Str
     Ok(grid.rows)
 }
 
-fn xlsx_value(c: &XCell, shared: &[String], formats: &[Option<DateKind>], date1904: bool) -> String {
+/// A cell's text: a shared string borrowed, so a cell the sheet then refuses (past the text
+/// budget, the columns or the rows) costs no copy of it.
+fn xlsx_value<'a>(c: &XCell, shared: &'a [String], formats: &[Option<DateKind>], date1904: bool) -> Cow<'a, str> {
     let v = c.value.trim();
     let kind = c.kind.trim();
     if kind.eq_ignore_ascii_case("s") {
-        v.parse::<usize>().ok().and_then(|i| shared.get(i)).cloned().unwrap_or_default()
-    } else if kind.eq_ignore_ascii_case("inlineStr") {
+        return Cow::Borrowed(v.parse::<usize>().ok().and_then(|i| shared.get(i)).map_or("", String::as_str));
+    }
+    Cow::Owned(if kind.eq_ignore_ascii_case("inlineStr") {
         if c.inline.is_empty() { c.value.clone() } else { c.inline.clone() }
     } else if kind.eq_ignore_ascii_case("str") || kind.eq_ignore_ascii_case("e") {
         c.value.clone()
@@ -290,12 +295,12 @@ fn xlsx_value(c: &XCell, shared: &[String], formats: &[Option<DateKind>], date19
     } else if v.is_empty() {
         c.inline.clone()
     } else {
-        let Ok(x) = v.parse::<f64>() else { return v.to_string() };
+        let Ok(x) = v.parse::<f64>() else { return Cow::Owned(v.to_string()) };
         match formats.get(c.style).copied().flatten() {
             Some(kind) => serial_date(x, date1904, kind).unwrap_or_else(|| number(x)),
             None => number(x),
         }
-    }
+    })
 }
 
 /// A number as a spreadsheet shows it in General format: up to 15 significant digits, no