Improve handling of named destinations in out-of-order NameTrees (PR 10274 follow-up)

According to the specification, see https://web.archive.org/web/20210404042322if_/https://www.adobe.com/content/dam/acom/en/devnet/acrobat/pdfs/PDF32000_2008.pdf#G6.2384179, the keys of a NameTree/NumberTree should be ordered.
For corrupt PDF files, which violate this assumption, it's thus possible that trying to lookup a single entry fails.

Previously, in PR 10274, we implemented a fallback that only applies to the "bottom" node of a NameTree/NumberTree, which in general might not actually help for sufficiently corrupt NameTree/NumberTree data.
Instead we remove the current *limited* fallback from `NameOrNumberTree.get`, and defer to the call-site to handle this case explicitly e.g. by using `NameOrNumberTree.getAll` for data where that makes sense. For well-formed documents, these changes should *not* lead to any additional data fetching/parsing.

Finally, as part of these changes, the validation of named destination data is improved in the `Catalog` and a new unit-test is also added.

src/core/catalog.js

@@ -53,7 +53,10 @@ import { MetadataParser } from "./metadata_parser.js";
 import { StructTreeRoot } from "./struct_tree.js";
 
 function fetchDestination(dest) {
-  return isDict(dest) ? dest.get("D") : dest;
+  if (dest instanceof Dict) {
+    dest = dest.get("D");
+  }
+  return Array.isArray(dest) ? dest : null;
 }
 
 class Catalog {
@@ -515,22 +518,41 @@ class Catalog {
       dests = Object.create(null);
     if (obj instanceof NameTree) {
       for (const [key, value] of obj.getAll()) {
-        dests[key] = fetchDestination(value);
+        const dest = fetchDestination(value);
+        if (dest) {
+          dests[key] = dest;
+        }
       }
     } else if (obj instanceof Dict) {
       obj.forEach(function (key, value) {
-        if (value) {
+        const dest = fetchDestination(value);
-          dests[key] = fetchDestination(value);
+        if (dest) {
+          dests[key] = dest;
         }
       });
     }
     return shadow(this, "destinations", dests);
   }
 
-  getDestination(destinationId) {
+  getDestination(id) {
     const obj = this._readDests();
-    if (obj instanceof NameTree || obj instanceof Dict) {
+    if (obj instanceof NameTree) {
-      return fetchDestination(obj.get(destinationId) || null);
+      const dest = fetchDestination(obj.get(id));
+      if (dest) {
+        return dest;
+      }
+      // Fallback to checking the *entire* NameTree, in an attempt to handle
+      // corrupt PDF documents with out-of-order NameTrees (fixes issue 10272).
+      const allDest = this.destinations[id];
+      if (allDest) {
+        warn(`Found "${id}" at an incorrect position in the NameTree.`);
+        return allDest;
+      }
+    } else if (obj instanceof Dict) {
+      const dest = fetchDestination(obj.get(id));
+      if (dest) {
+        return dest;
+      }
     }
     return null;
   }

src/core/name_number_tree.js

@@ -13,7 +13,7 @@
  * limitations under the License.
  */
 
-import { FormatError, info, unreachable, warn } from "../shared/util.js";
+import { FormatError, unreachable, warn } from "../shared/util.js";
 import { isDict, RefSet } from "./primitives.js";
 
 /**
@@ -133,23 +133,6 @@ class NameOrNumberTree {
           return xref.fetchIfRef(entries[m + 1]);
         }
       }
-
-      // Fallback to an exhaustive search, in an attempt to handle corrupt
-      // PDF files where keys are not correctly ordered (fixes issue 10272).
-      info(
-        `Falling back to an exhaustive search, for key "${key}", ` +
-          `in "${this._type}" tree.`
-      );
-      for (let m = 0, mm = entries.length; m < mm; m += 2) {
-        const currentKey = xref.fetchIfRef(entries[m]);
-        if (currentKey === key) {
-          warn(
-            `The "${key}" key was found at an incorrect, ` +
-              `i.e. out-of-order, position in "${this._type}" tree.`
-          );
-          return xref.fetchIfRef(entries[m + 1]);
-        }
-      }
     }
     return null;
   }

src/display/api.js

@@ -730,8 +730,9 @@ class PDFDocumentProxy {
 
   /**
    * @param {string} id - The named destination to get.
-   * @returns {Promise<Array<any>>} A promise that is resolved with all
+   * @returns {Promise<Array<any> | null>} A promise that is resolved with all
-   *   information of the given named destination.
+   *   information of the given named destination, or `null` when the named
+   *   destination is not present in the PDF file.
    */
   getDestination(id) {
     return this._transport.getDestination(id);

test/pdfs/issue10272.pdf.link

@@ -0,0 +1 @@
+https://github.com/mozilla/pdf.js/files/2598691/ATS_TEST_PVC_2_1.pdf

test/test_manifest.json

@@ -917,6 +917,12 @@
        "link": true,
        "type": "load"
     },
+    {  "id": "issue10272",
+       "file": "pdfs/issue10272.pdf",
+       "md5": "bf3b2f74c6878d38a70dc0825f1b9a02",
+       "link": true,
+       "type": "other"
+    },
     {  "id": "issue10388",
        "file": "pdfs/issue10388_reduced.pdf",
        "md5": "62a6b2adbea1535432bd94a3516e2d4c",

test/unit/api_spec.js

@@ -669,6 +669,24 @@ describe("api", function () {
       await loadingTask.destroy();
     });
 
+    it("gets a destination, from out-of-order /Names (NameTree) dictionary (issue 10272)", async function () {
+      if (isNodeJS) {
+        pending("Linked test-cases are not supported in Node.js.");
+      }
+      const loadingTask = getDocument(buildGetDocumentParams("issue10272.pdf"));
+      const pdfDoc = await loadingTask.promise;
+      const destination = await pdfDoc.getDestination("link_1");
+      expect(destination).toEqual([
+        { num: 17, gen: 0 },
+        { name: "XYZ" },
+        69,
+        125,
+        0,
+      ]);
+
+      await loadingTask.destroy();
+    });
+
     it("gets non-string destination", async function () {
       let numberPromise = pdfDocument.getDestination(4.3);
       let booleanPromise = pdfDocument.getDestination(true);