add failing tests for dumppdf crash

Author: 0xabu

tests/test_tools_dumppdf.py

@@ -1,5 +1,5 @@
 import warnings
-
+from nose.tools import raises
 from helpers import absolute_sample_path
 from tempfilepath import TemporaryFilePath
 from pdfminer.pdfdocument import PDFNoValidXRefWarning
@@ -51,3 +51,13 @@ def test_5(self):
 
     def test_6(self):
         run('nonfree/naacl06-shinyama.pdf', '-t -a')
+
+    @raises(TypeError)
+    def test_simple1_raw(self):
+        """Known issue: crash in dumpxml writing binary to text stream."""
+        run('simple1.pdf', '-r -a')
+
+    @raises(TypeError)
+    def test_simple1_binary(self):
+        """Known issue: crash in dumpxml writing binary to text stream."""
+        run('simple1.pdf', '-b -a')

tools/dumppdf.py

@@ -61,10 +61,10 @@ def dumpxml(out: TextIO, obj: object, codec: Optional[str] = None) -> None:
 
     if isinstance(obj, PDFStream):
         if codec == 'raw':
-            # Likely bug: writing bytes to text I/O.
+            # Bug: writing bytes to text I/O. This will raise TypeError.
             out.write(obj.get_rawdata())  # type: ignore [arg-type]
         elif codec == 'binary':
-            # Likely bug: writing bytes to text I/O.
+            # Bug: writing bytes to text I/O. This will raise TypeError.
             out.write(obj.get_data())  # type: ignore [arg-type]
         else:
             out.write('<stream>\n<props>\n')