Let Lexer.getObj return a dummy-Cmd for commands that start with a non-visible ASCII character (issue 13999)

This way we avoid breaking badly generated PDF documents where a non-visible ASCII character is "glued" to a valid command.

src/core/parser.js

@@ -1255,7 +1255,7 @@ class Lexer {
         return Cmd.get("}");
       case 0x29: // ')'
         // Consume the current character in order to avoid permanently hanging
-        // the worker thread if `Lexer.getObject` is called from within a loop
+        // the worker thread if `Lexer.getObj` is called from within a loop
         // containing try-catch statements, since we would otherwise attempt
         // to parse the *same* character over and over (fixes issue8061.pdf).
         this.nextChar();
@@ -1264,6 +1264,15 @@ class Lexer {
 
     // Start reading a command.
     let str = String.fromCharCode(ch);
+    // A valid command cannot start with a non-visible ASCII character,
+    // and the next character may be (the start of) a valid command.
+    if (ch < 0x20 || ch > 0x7f) {
+      const nextCh = this.peekChar();
+      if (nextCh >= 0x20 && nextCh <= 0x7f) {
+        this.nextChar();
+        return Cmd.get(str);
+      }
+    }
     const knownCommands = this.knownCommands;
     let knownCommandFound = knownCommands && knownCommands[str] !== undefined;
     while ((ch = this.nextChar()) >= 0 && !specialChars[ch]) {

test/pdfs/issue13999.pdf.link

@@ -0,0 +1 @@
+https://github.com/mozilla/pdf.js/files/7147166/default.pdf

test/test_manifest.json

@@ -5885,5 +5885,13 @@
        "rounds": 1,
        "enableXfa": true,
        "type": "eq"
+    },
+    {  "id": "issue13999",
+       "file": "pdfs/issue13999.pdf",
+       "md5": "8829c76887e7827390e9a5f73cab23f2",
+       "link": true,
+       "rounds": 1,
+       "lastPage": 1,
+       "type": "eq"
     }
 ]

test/unit/parser_spec.js

@@ -13,9 +13,9 @@
  * limitations under the License.
  */
 
+import { Cmd, EOF, Name } from "../../src/core/primitives.js";
 import { Lexer, Linearization, Parser } from "../../src/core/parser.js";
 import { FormatError } from "../../src/shared/util.js";
-import { Name } from "../../src/core/primitives.js";
 import { StringStream } from "../../src/core/stream.js";
 
 describe("parser", function () {
@@ -217,6 +217,32 @@ describe("parser", function () {
         }
       });
     });
+
+    describe("getObj", function () {
+      it(
+        "should stop immediately when the start of a command is " +
+          "a non-visible ASCII character (issue 13999)",
+        function () {
+          const input = new StringStream("\x14q\nQ");
+          const lexer = new Lexer(input);
+
+          let obj = lexer.getObj();
+          expect(obj instanceof Cmd).toEqual(true);
+          expect(obj.cmd).toEqual("\x14");
+
+          obj = lexer.getObj();
+          expect(obj instanceof Cmd).toEqual(true);
+          expect(obj.cmd).toEqual("q");
+
+          obj = lexer.getObj();
+          expect(obj instanceof Cmd).toEqual(true);
+          expect(obj.cmd).toEqual("Q");
+
+          obj = lexer.getObj();
+          expect(obj).toEqual(EOF);
+        }
+      );
+    });
   });
 
   describe("Linearization", function () {