Add basic validation of the 'trailer' dictionary candidates in XRef.indexObjects (issue 9418)

This patch avoids choosing a (possible) 'trailer' dictionary that `XRef.parse` and/or the `Catalog` constructor/methods will reject anyway.
Since `XRef.indexObjects` is already parsing the entire PDF file, the extra dictionary look-ups added here shouldn't matter much. Besides, this is a fallback code-path that only applies to corrupt PDF files anyway.

src/core/obj.js

@@ -1260,7 +1260,7 @@ var XRef = (function XRefClosure() {
         this.readXRef(/* recoveryMode */ true);
       }
       // finding main trailer
-      var dict;
+      let trailerDict;
       for (i = 0, ii = trailers.length; i < ii; ++i) {
         stream.pos = trailers[i];
         var parser = new Parser(new Lexer(stream), /* allowStreams = */ true,
@@ -1270,18 +1270,33 @@ var XRef = (function XRefClosure() {
           continue;
         }
         // read the trailer dictionary
-        dict = parser.getObj();
+        let dict = parser.getObj();
         if (!isDict(dict)) {
           continue;
         }
+        // Do some basic validation of the trailer/root dictionary candidate.
+        let rootDict;
+        try {
+          rootDict = dict.get('Root');
+        } catch (ex) {
+          if (ex instanceof MissingDataException) {
+            throw ex;
+          }
+          continue;
+        }
+        if (!isDict(rootDict) || !rootDict.has('Pages')) {
+          continue;
+        }
         // taking the first one with 'ID'
         if (dict.has('ID')) {
           return dict;
         }
+        // The current dictionary is a candidate, but continue searching.
+        trailerDict = dict;
       }
-      // no tailer with 'ID', taking last one (if exists)
-      if (dict) {
-        return dict;
+      // No trailer with 'ID', taking last one (if exists).
+      if (trailerDict) {
+        return trailerDict;
       }
       // nothing helps
       throw new InvalidPDFException('Invalid PDF structure');

test/pdfs/.gitignore

@@ -68,6 +68,7 @@
 !issue9252.pdf
 !issue9262_reduced.pdf
 !issue9291.pdf
+!issue9418.pdf
 !issue9458.pdf
 !bad-PageLabels.pdf
 !decodeACSuccessive.pdf

test/test_manifest.json

@@ -748,6 +748,13 @@
        "link": false,
        "type": "eq"
     },
+    {  "id": "issue9418",
+       "file": "pdfs/issue9418.pdf",
+       "md5": "32ecad8098acb1938539d47944ecb54b",
+       "rounds": 1,
+       "link": false,
+       "type": "eq"
+    },
     {  "id": "issue9262",
        "file": "pdfs/issue9262_reduced.pdf",
        "md5": "5347ce2d7b3866625c22e115fd90e0de",