Fix assertionerror when dumping pdf with reference to objid 0 (#318)

Fixes #94 
Added: test to get check if `PDFObjectNotFound` error is raised if objid 0 is requested.

CHANGELOG.md

@@ -8,6 +8,9 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 ### Added
 - Support for extracting JBIG2 encoded images ([#311](https://github.com/pdfminer/pdfminer.six/pull/311) and [#46](https://github.com/pdfminer/pdfminer.six/pull/46))
 
+### Fixed
+- Unhandled AssertionError when dumping pdf containing reference to object id 0 ([#318](https://github.com/pdfminer/pdfminer.six/pull/318))
+
 ## [20191020] - 2019-10-20
 
 ### Deprecated

pdfminer/pdfdocument.py

@@ -671,7 +671,11 @@ class PDFDocument(object):
 
     # can raise PDFObjectNotFound
     def getobj(self, objid):
-        assert objid != 0
+        """Get object from PDF
+
+        :raises PDFException if PDFDocument is not initialized
+        :raises PDFObjectNotFound if objid does not exist in PDF
+        """
         if not self.xrefs:
             raise PDFException('PDFDocument is not initialized')
         log.debug('getobj: objid=%r', objid)

tests/test_pdfdocument.py

@@ -0,0 +1,15 @@
+from nose.tools import raises
+from pdfminer.pdftypes import PDFObjectNotFound
+
+from pdfminer.pdfdocument import PDFDocument
+from pdfminer.pdfparser import PDFParser
+
+
+class TestPdfDocument(object):
+
+    @raises(PDFObjectNotFound)
+    def test_get_zero_objid_raises_pdfobjectnotfound(self):
+        with open('../samples/simple1.pdf', 'rb') as in_file:
+            parser = PDFParser(in_file)
+            doc = PDFDocument(parser)
+            doc.getobj(0)