Compare commits

...
3 changed files with 28 additions and 7 deletions
+2 -1
View File
File diff suppressed because one or more lines are too long
+25 -5
View File
@@ -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 = Vec::new();
let mut used = HashSet::new();
rel_attr_values(&root, &mut used, 0);
// Every relationship the markup uses must be writable, or the object would be broken.
let writable = |id: &String| src.refs.iter().any(|r| r.id == *id && (r.external || self.embeds.available(&r.target)));
if !used.iter().all(writable) {
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())) {
log::warn!("docx: an embedded object's parts are missing; it is left out");
return None;
}
@@ -637,13 +637,15 @@ fn set_attr(e: &mut El, k: &str, v: &str) {
}
}
fn rel_attr_values(e: &El, out: &mut Vec<String>, depth: usize) {
/// 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) {
if depth > MAX_DEPTH {
return;
}
for (k, v) in &e.attrs {
if xml::is_rel_attr(&e.name, k) && !out.contains(v) {
out.push(v.clone());
out.insert(v.clone());
}
}
for c in e.els() {
@@ -851,6 +853,24 @@ 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
+1 -1
View File
File diff suppressed because one or more lines are too long