Save form data in XFA datasets when pdf is a mix of acroforms and xfa (#12344)

* Move display/xml_parser.js in shared to use it in worker

* Save form data in XFA datasets when pdf is a mix of acroforms and xfa

Co-authored-by: Brendan Dahl <brendan.dahl@gmail.com>

src/shared/util.js

@@ -910,6 +910,73 @@ const createObjectURL = (function createObjectURLClosure() {
   };
 })();
 
+/**
+ * AcroForm field names use an array like notation to refer to
+ * repeated XFA elements e.g. foo.bar[nnn].
+ * see: XFA Spec Chapter 3 - Repeated Elements
+ *
+ * @param {string} path - XFA path name.
+ * @returns {Array} - Array of Objects with the name and pos of
+ * each part of the path.
+ */
+function parseXFAPath(path) {
+  const positionPattern = /(.+)\[([0-9]+)\]$/;
+  return path.split(".").map(component => {
+    const m = component.match(positionPattern);
+    if (m) {
+      return { name: m[1], pos: parseInt(m[2], 10) };
+    }
+    return { name: component, pos: 0 };
+  });
+}
+
+const XMLEntities = {
+  /* < */ 0x3c: "&lt;",
+  /* > */ 0x3e: "&gt;",
+  /* & */ 0x26: "&amp;",
+  /* " */ 0x22: "&quot;",
+  /* ' */ 0x27: "&apos;",
+};
+
+function encodeToXmlString(str) {
+  const buffer = [];
+  let start = 0;
+  for (let i = 0, ii = str.length; i < ii; i++) {
+    const char = str.codePointAt(i);
+    if (0x20 <= char && char <= 0x7e) {
+      // ascii
+      const entity = XMLEntities[char];
+      if (entity) {
+        if (start < i) {
+          buffer.push(str.substring(start, i));
+        }
+        buffer.push(entity);
+        start = i + 1;
+      }
+    } else {
+      if (start < i) {
+        buffer.push(str.substring(start, i));
+      }
+      buffer.push(`&#x${char.toString(16).toUpperCase()};`);
+      if (char > 0xd7ff && (char < 0xe000 || char > 0xfffd)) {
+        // char is represented by two u16
+        i++;
+      }
+      start = i + 1;
+    }
+  }
+
+  if (buffer.length === 0) {
+    return str;
+  }
+
+  if (start < str.length) {
+    buffer.push(str.substring(start, str.length));
+  }
+
+  return buffer.join("");
+}
+
 export {
   BaseException,
   FONT_IDENTITY_MATRIX,
@@ -947,6 +1014,7 @@ export {
   createPromiseCapability,
   createObjectURL,
   escapeString,
+  encodeToXmlString,
   getModificationDate,
   getVerbosityLevel,
   info,
@@ -959,6 +1027,7 @@ export {
   createValidAbsoluteUrl,
   IsLittleEndianCached,
   IsEvalSupportedCached,
+  parseXFAPath,
   removeNullCharacters,
   setVerbosityLevel,
   shadow,