Merge PR #2679: fix(annot): percent-encode non-ASCII bytes written into link /URI

crates/annot/src/links.rs

@@ -178,6 +178,19 @@ fn write_style(d: &mut Dict, s: &LinkStyle) {
     d.set(b"H".to_vec(), Object::name(s.highlight.code()));
 }
 
+/// Bytes of `u` as a 7-bit ASCII URI string (§12.6.4.8).
+fn uri_bytes(u: &str) -> Vec<u8> {
+    let mut out = Vec::with_capacity(u.len());
+    for &b in u.as_bytes() {
+        if (0x21..=0x7e).contains(&b) {
+            out.push(b);
+        } else {
+            out.extend_from_slice(format!("%{b:02X}").as_bytes());
+        }
+    }
+    out
+}
+
 fn write_action(doc: &Document, d: &mut Dict, a: &LinkAction) -> Result<(), AnnotError> {
     match a {
         LinkAction::Page(p) => {
@@ -194,7 +207,7 @@ fn write_action(doc: &Document, d: &mut Dict, a: &LinkAction) -> Result<(), Anno
             let mut act = Dict::new();
             act.set(b"S".to_vec(), Object::name("URI"));
             // URIs are 7-bit ASCII strings (§12.6.4.8).
-            act.set(b"URI".to_vec(), PdfString::literal(u.as_bytes().to_vec()));
+            act.set(b"URI".to_vec(), PdfString::literal(uri_bytes(u)));
             d.set(b"A".to_vec(), Object::Dict(act));
         }
         LinkAction::Other(_) => {}

crates/annot/src/tests.rs

@@ -588,6 +588,25 @@ fn links_are_added_edited_listed_and_removed() {
     assert!(links::add(&mut doc, 0, [0.0, 0.0, 1.0, 1.0], &LinkAction::Page(0), &LinkStyle::default()).is_err(), "too small");
 }
 
+#[test]
+fn link_uri_is_percent_encoded_to_7_bit_ascii() {
+    use crate::links::{self, LinkAction, LinkStyle};
+    let mut doc = fixture();
+    for url in ["https://example.com/ação", "https://example.com/a%20b"] {
+        links::add(&mut doc, 0, [10.0, 10.0, 110.0, 30.0], &LinkAction::Uri(url.into()), &LinkStyle::default()).unwrap();
+    }
+    let doc = reopen(&doc);
+    let urls: Vec<String> = links::list(&doc)
+        .into_iter()
+        .filter_map(|link| match link.action {
+            LinkAction::Uri(url) => Some(url),
+            _ => None,
+        })
+        .collect();
+    assert_eq!(urls, ["https://example.com/a%C3%A7%C3%A3o", "https://example.com/a%20b"]);
+    assert!(urls.iter().all(|url| url.is_ascii()));
+}
+
 #[test]
 fn link_edit_rejects_non_finite_and_overflowed_rectangles_without_mutating_the_pdf() {
     use crate::links::{self, LinkAction, LinkStyle};