PYTHON-2820 Test serialization of BSON with embedded null bytes in strings (#723)

Author: ShaneHarvey

test/bson_corpus/document.json

@@ -51,6 +51,10 @@
         {
             "description": "Invalid subdocument: bad string length in field",
             "bson": "1C00000003666F6F001200000002626172000500000062617A000000"
+        },
+        {
+            "description": "Null byte in sub-document key",
+            "bson": "150000000378000D00000010610000010000000000"
         }
     ]
 }

test/bson_corpus/regex.json

@@ -54,11 +54,11 @@
     ],
     "decodeErrors": [
         {
-            "description": "embedded null in pattern",
+            "description": "Null byte in pattern string",
             "bson": "0F0000000B610061006300696D0000"
         },
         {
-            "description": "embedded null in flags",
+            "description": "Null byte in flags string",
             "bson": "100000000B61006162630069006D0000"
         }
     ]

test/bson_corpus/top.json

@@ -79,6 +79,10 @@
         {
             "description": "Document truncated mid-key",
             "bson": "1200000002666F"
+        },
+        {
+            "description": "Null byte in document key",
+            "bson": "0D000000107800000100000000"
         }
     ],
     "parseErrors": [
@@ -241,7 +245,22 @@
         {
             "description": "Bad DBpointer (extra field)",
             "string": "{\"a\": {\"$dbPointer\": {\"a\": {\"$numberInt\": \"1\"}, \"$id\": {\"$oid\": \"56e1fc72e0c917e9c4714161\"}, \"c\": {\"$numberInt\": \"2\"}, \"$ref\": \"b\"}}}"
+        },
+        {
+            "description" : "Null byte in document key",
+            "string" : "{\"a\\u0000\": 1 }"
+        },
+        {
+            "description" : "Null byte in sub-document key",
+            "string" : "{\"a\" : {\"b\\u0000\": 1 }}"
+        },
+        {
+            "description": "Null byte in $regularExpression pattern",
+            "string": "{\"a\" : {\"$regularExpression\" : { \"pattern\": \"b\\u0000\", \"options\" : \"i\"}}}"
+        },
+        {
+            "description": "Null byte in $regularExpression options",
+            "string": "{\"a\" : {\"$regularExpression\" : { \"pattern\": \"b\", \"options\" : \"i\\u0000\"}}}"
         }
-
     ]
 }

test/test_bson_corpus.py

@@ -31,7 +31,7 @@
 from bson.codec_options import CodecOptions
 from bson.decimal128 import Decimal128
 from bson.dbref import DBRef
-from bson.errors import InvalidBSON, InvalidId
+from bson.errors import InvalidBSON, InvalidDocument, InvalidId
 from bson.json_util import JSONMode
 from bson.son import SON
 
@@ -51,6 +51,8 @@
     # This variant of $numberLong may have been generated by an old version
     # of mongoexport.
     'Bad $numberLong (number, not string)',
+    # We parse Regex flags with extra characters, including nulls.
+    'Null byte in $regularExpression options',
 ])
 
 _DEPRECATED_BSON_TYPES = {
@@ -198,10 +200,14 @@ def run_test(self):
                     decode_extjson(parse_error_case['string'])
                 else:
                     try:
-                        decode_extjson(parse_error_case['string'])
+                        doc = decode_extjson(parse_error_case['string'])
+                        # Null bytes are validated when encoding to BSON.
+                        if 'Null' in description:
+                            to_bson(doc)
                         raise AssertionError('exception not raised for test '
                                              'case: ' + description)
-                    except (ValueError, KeyError, TypeError, InvalidId):
+                    except (ValueError, KeyError, TypeError, InvalidId,
+                            InvalidDocument):
                         pass
             elif bson_type == '0x05':
                 try: