Reintroduce the old sanitizer testsuite from html5lib-tests

This is imported into this repo as its expectations are very much
implementation dependent

Author: gsnedders

html5lib/tests/conftest.py

@@ -2,11 +2,13 @@
 
 from .tree_construction import TreeConstructionFile
 from .tokenizer import TokenizerFile
+from .sanitizer import SanitizerFile
 
 _dir = os.path.abspath(os.path.dirname(__file__))
 _testdata = os.path.join(_dir, "testdata")
 _tree_construction = os.path.join(_testdata, "tree-construction")
 _tokenizer = os.path.join(_testdata, "tokenizer")
+_sanitizer_testdata = os.path.join(_dir, "sanitizer-testdata")
 
 
 def pytest_collectstart():
@@ -24,3 +26,6 @@ def pytest_collect_file(path, parent):
     elif dir == _tokenizer:
         if path.ext == ".test":
             return TokenizerFile(path, parent)
+    elif dir == _sanitizer_testdata:
+        if path.ext == ".dat":
+            return SanitizerFile(path, parent)