Handle corrupt PDFs that lack /Kids array and just inline the /Page dictionary (issue 21436)

This basically extends PR 9549 to the fallback `getAllPageDicts` method, which didn't exist at the time, in order to support more cases of corrupt PDF documents.

src/core/catalog.js

@@ -1484,6 +1484,22 @@ class Catalog {
         }
       }
       if (!Array.isArray(kids)) {
+        // Prevent errors in corrupt PDF documents that violate the
+        // specification by *inlining* Page dicts (fixes issue21436.pdf).
+        let type = currentNode.getRaw("Type");
+        if (type instanceof Ref) {
+          try {
+            type = await xref.fetchAsync(type);
+          } catch (ex) {
+            addPageError(ex);
+            break;
+          }
+        }
+        if (isName(type, "Page") || !currentNode.has("Kids")) {
+          addPageDict(currentNode, null);
+          break;
+        }
+
         addPageError(
           new FormatError("Page dictionary kids object is not an array.")
         );

test/pdfs/.gitignore

@@ -929,6 +929,7 @@
 !issue_cff_unsigned_bbox.pdf
 !90ms_rksj_h_sample.pdf
 !issue21346.pdf
+!issue21436.pdf
 !cidfont_cmap_overflow.pdf
 !jbig2_file_header.pdf
 !text_field_own_canvas_calc.pdf

test/pdfs/issue21436.pdf

@@ -0,0 +1,28 @@
+%PDF-1.7
+1 0 obj
+<< /Type /Catalog /Pages 3 0 R >>
+endobj
+2 0 obj
+<< /Type /Pages /Kids [3 0 R] /Count 1 >>
+endobj
+3 0 obj
+<< /Type /Page /Parent 2 0 R /MediaBox [0 0 200 200] /Contents 4 0 R /Resources << >> >>
+endobj
+4 0 obj
+<< /Length 18 >>
+stream
+10 10 180 180 re S
+endstream
+endobj
+xref
+0 5
+0000000000 65535 f 
+0000000009 00000 n 
+0000000058 00000 n 
+0000000115 00000 n 
+0000000219 00000 n 
+trailer
+<< /Size 5 /Root 1 0 R >>
+startxref
+287
+%%EOF

test/test_manifest.json

@@ -2802,6 +2802,13 @@
     "link": true,
     "type": "eq"
   },
+  {
+    "id": "issue21436",
+    "file": "pdfs/issue21436.pdf",
+    "md5": "93c4292a52db8a37eefd651cb677d2a9",
+    "rounds": 1,
+    "type": "eq"
+  },
   {
     "id": "txt2pdf",
     "file": "pdfs/txt2pdf.pdf",

test/unit/api_spec.js

@@ -827,6 +827,42 @@ describe("api", function () {
       ]);
     });
 
+    it("creates pdf doc from PDF files, with /Pages tree without /Kids array", async function () {
+      const loadingTask1 = getDocument(buildGetDocumentParams("issue9540.pdf"));
+      const loadingTask2 = getDocument(
+        buildGetDocumentParams("issue21436.pdf")
+      );
+
+      expect(loadingTask1).toBeInstanceOf(PDFDocumentLoadingTask);
+      expect(loadingTask2).toBeInstanceOf(PDFDocumentLoadingTask);
+
+      const pdfDocument1 = await loadingTask1.promise;
+      const pdfDocument2 = await loadingTask2.promise;
+
+      expect(pdfDocument1.numPages).toEqual(1);
+      expect(pdfDocument2.numPages).toEqual(1);
+
+      const pageA = await pdfDocument1.getPage(1);
+      expect(pageA).toBeInstanceOf(PDFPageProxy);
+
+      const opListA = await pageA.getOperatorList();
+      expect(opListA.fnArray.length).toEqual(19);
+      expect(opListA.argsArray.length).toEqual(19);
+      expect(opListA.lastChunk).toEqual(true);
+      expect(opListA.separateAnnots).toEqual(null);
+
+      const pageB = await pdfDocument2.getPage(1);
+      expect(pageB).toBeInstanceOf(PDFPageProxy);
+
+      const opListB = await pageB.getOperatorList();
+      expect(opListB.fnArray.length).toEqual(1);
+      expect(opListB.argsArray.length).toEqual(1);
+      expect(opListB.lastChunk).toEqual(true);
+      expect(opListB.separateAnnots).toEqual(null);
+
+      await Promise.all([loadingTask1.destroy(), loadingTask2.destroy()]);
+    });
+
     it("creates pdf doc from PDF files, with circular references", async function () {
       const loadingTask1 = getDocument(
         buildGetDocumentParams("poppler-91414-0-53.pdf")