Fix 594 use null id when encrypted but no id given (#595)

Co-authored-by: Pieter Marsman <pietermarsman@gmail.com>

CHANGELOG.md

@@ -9,6 +9,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 - Support for Paeth PNG filter compression (predictor value = 4) ([#537](https://github.com/pdfminer/pdfminer.six/pull/537))
 
 ### Fixed
+- `KeyError` when `'Encrypt'` but not `'ID'` present in `trailer` ([#594](https://github.com/pdfminer/pdfminer.six/pull/594))
 - Fix issue of ValueError and KeyError rasied in PDFdocument and PDFparser ([#573](https://github.com/pdfminer/pdfminer.six/pull/574))
 - Fix issue of TypeError: cannot unpack non-iterable PDFObjRef object, when unpacking the value of 'DW2' ([#529](https://github.com/pdfminer/pdfminer.six/pull/529))
 - `PermissionError` when creating temporary filepaths on windows when running tests ([#469](https://github.com/pdfminer/pdfminer.six/issues/469))

pdfminer/pdfdocument.py

@@ -583,7 +583,14 @@ class PDFDocument:
                 continue
             # If there's an encryption info, remember it.
             if 'Encrypt' in trailer:
-                self.encryption = (list_value(trailer['ID']),
+                if 'ID' in trailer:
+                    id_value = list_value(trailer['ID'])
+                else:
+                    # Some documents may not have a /ID, use two empty
+                    # byte strings instead. Solves
+                    # https://github.com/pdfminer/pdfminer.six/issues/594
+                    id_value = (b'', b'')
+                self.encryption = (id_value,
                                    dict_value(trailer['Encrypt']))
                 self._initialize_password(password)
             if 'Info' in trailer:

tests/test_pdfdocument.py

@@ -1,4 +1,4 @@
-from nose.tools import raises
+from nose.tools import assert_equal, raises
 
 from helpers import absolute_sample_path
 from pdfminer.pdfdocument import PDFDocument
@@ -14,3 +14,14 @@ class TestPdfDocument(object):
             parser = PDFParser(in_file)
             doc = PDFDocument(parser)
             doc.getobj(0)
+
+    def test_encrypted_no_id(self):
+        # Some documents may be encrypted but not have an /ID key in
+        # their trailer. Tests
+        # https://github.com/pdfminer/pdfminer.six/issues/594
+        path = absolute_sample_path('encryption/encrypted_doc_no_id.pdf')
+        with open(path, 'rb') as fp:
+            parser = PDFParser(fp)
+            doc = PDFDocument(parser)
+            assert_equal(doc.info,
+                         [{'Producer': b'European Patent Office'}])