fix(xfa): scripts come only from the XDP's own packets and quote the date pattern (#5987)

The template (and the saved form state) was found anywhere under the XDP root, so a
template-shaped element inside imported datasets could supply the form and its event
scripts. A date field's pattern went into AFDate_FormatEx/KeystrokeEx string literals
unescaped.

crates/xfa/src/parse.rs

@@ -746,10 +746,12 @@ pub fn parse(xml: &str) -> Result<(Template, Vec<String>), XfaError> {
             && n.tag_name().name() == "template"
             && (n.tag_name().namespace().is_some_and(|ns| ns.contains("xfa-template")) || children(*n, "subform").next().is_some())
     };
+    // The template is a packet of the XDP itself, a child of its root: one nested deeper is
+    // data (an imported dataset, say), which must not supply the form's scripts.
     let template = if is_template(&root) {
         root
     } else {
-        root.descendants().find(is_template).ok_or_else(|| XfaError::Malformed("no <template> element".into()))?
+        root.children().find(is_template).ok_or_else(|| XfaError::Malformed("no <template> element".into()))?
     };
     let mut warnings = Vec::new();
     let sf = children(template, "subform").next().ok_or_else(|| XfaError::Malformed("the template has no root subform".into()))?;
@@ -760,7 +762,7 @@ pub fn parse(xml: &str) -> Result<(Template, Vec<String>), XfaError> {
     }
     // The form packet beside the template holds the state the form was saved in.
     let saved = root
-        .descendants()
+        .children()
         .find(|n| n.is_element() && n.tag_name().name() == "form" && n.tag_name().namespace().is_some_and(|ns| ns.contains("xfa-form")));
     if let Some(saved_root) = saved.and_then(|f| children(f, "subform").next()) {
         if let Some(p) = saved_root.attribute("presence") {

crates/xfa/src/pdf.rs

@@ -17,7 +17,9 @@ mod strip;
 
 pub use common::jpeg_size;
 pub(crate) use common::rounded;
-use common::{all_faces, content_hash, empty_form, hex32, jpeg_info, js_action, n, parse_hex32, rgb, rgb_array, standard_font, state_name};
+use common::{
+    all_faces, content_hash, empty_form, hex32, jpeg_info, js_action, js_string, n, parse_hex32, rgb, rgb_array, standard_font, state_name,
+};
 pub(crate) use strip::USAGE_RIGHTS_REMOVED;
 use strip::drop_usage_rights;
 pub use strip::{Stripped, XfaShape, existing_layout, strip, xfa_shape};
@@ -205,8 +207,9 @@ impl Emitter<'_> {
                 }
                 if let WidgetKind::Date(pattern) = &w.kind {
                     let mut aa = Dict::new();
-                    aa.set(b"F".to_vec(), js_action(&format!("AFDate_FormatEx(\"{pattern}\");")));
-                    aa.set(b"K".to_vec(), js_action(&format!("AFDate_KeystrokeEx(\"{pattern}\");")));
+                    let pattern = js_string(pattern);
+                    aa.set(b"F".to_vec(), js_action(&format!("AFDate_FormatEx({pattern});")));
+                    aa.set(b"K".to_vec(), js_action(&format!("AFDate_KeystrokeEx({pattern});")));
                     d.set(b"AA".to_vec(), Object::Dict(aa));
                 }
             }

crates/xfa/src/pdf/common.rs

@@ -192,9 +192,41 @@ pub(super) fn empty_form(doc: &mut Document, w: f64, h: f64) -> Object {
     Object::Ref(doc.add(Object::Stream(Stream::from_raw(d, Vec::new()))))
 }
 
+/// `s` as a JavaScript string literal, quotes included: a quote, a backslash or a line break in
+/// it stays text instead of ending the string and running as code.
+pub(super) fn js_string(s: &str) -> String {
+    let mut out = String::with_capacity(s.len() + 2);
+    out.push('"');
+    for c in s.chars() {
+        match c {
+            '"' | '\\' => {
+                out.push('\\');
+                out.push(c);
+            }
+            c if c.is_control() || c == '\u{2028}' || c == '\u{2029}' => out.push_str(&format!("\\u{:04x}", u32::from(c))),
+            c => out.push(c),
+        }
+    }
+    out.push('"');
+    out
+}
+
 pub(super) fn js_action(js: &str) -> Object {
     let mut a = Dict::new();
     a.set(b"S".to_vec(), Object::name("JavaScript"));
     a.set(b"JS".to_vec(), Object::String(PdfString::literal(js.as_bytes().to_vec())));
     Object::Dict(a)
 }
+
+#[cfg(test)]
+mod js_string_tests {
+    use super::js_string;
+
+    /// A date pattern that tries to close the string and run code stays one string literal.
+    #[test]
+    fn a_pattern_cannot_leave_its_string() {
+        assert_eq!(js_string("yyyy-mm-dd"), "\"yyyy-mm-dd\"");
+        assert_eq!(js_string("x\");app.alert(1);//"), "\"x\\\");app.alert(1);//\"");
+        assert_eq!(js_string("a\\\nb\u{2028}"), "\"a\\\\\\u000ab\\u2028\"");
+    }
+}

crates/xfa/src/tests.rs

@@ -4531,3 +4531,13 @@ fn a_container_is_as_wide_as_a_turned_draw_stands() {
         assert!((got - right).abs() < 0.01, "{rotate}: the neighbour stands {got} right of the anchor, not {right}");
     }
 }
+
+/// Only a template that is a packet of the XDP is the form's: one inside imported data (a
+/// dataset holding XML that looks like a template) is not read, and neither are its scripts.
+#[test]
+fn a_template_inside_the_data_is_not_the_form() {
+    let nested = "<xdp:xdp xmlns:xdp=\"http://ns.adobe.com/xdp/\"><xfa:datasets xmlns:xfa=\"http://www.xfa.org/schema/xfa-data/1.0/\"><xfa:data><template xmlns=\"http://www.xfa.org/schema/xfa-template/3.3/\"><subform name=\"evil\"><event activity=\"initialize\"><script>xfa.host.messageBox(1)</script></event></subform></template></xfa:data></xfa:datasets></xdp:xdp>";
+    assert!(parse(nested).is_err(), "no template packet");
+    let real = "<xdp:xdp xmlns:xdp=\"http://ns.adobe.com/xdp/\"><template xmlns=\"http://www.xfa.org/schema/xfa-template/3.3/\"><subform name=\"form1\"/></template></xdp:xdp>";
+    assert_eq!(parse(real).unwrap().0.root.common.name.as_deref(), Some("form1"));
+}