Retry parsing a module that has invalid type comments

It is possible for a module to use comments that might be interpreted
as type comments by the `ast` library. We do not want to completely crash on those
invalid type comments.

Close #708

4 files changed, 60 insertions, 6 deletions

diff --git a/ChangeLog b/ChangeLog
index 99457ef8..a38dab51 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -12,6 +12,14 @@ Release Date: TBA
 
 * Allow inferring positional only arguments.
 
+* Retry parsing a module that has invalid type comments
+
+  It is possible for a module to use comments that might be interpreted
+  as type comments by the `ast` library. We do not want to completely crash on those
+  invalid type comments.
+
+  Close #708
+
 * Scope the inference to the current bound node when inferring instances of classes
 
   When inferring instances of classes from arguments, such as ``self``
diff --git a/astroid/_ast.py b/astroid/_ast.py
index 2e44c1f1..66c5cf25 100644
--- a/astroid/_ast.py
+++ b/astroid/_ast.py
@@ -21,7 +21,10 @@ if PY38:
 FunctionType = namedtuple("FunctionType", ["argtypes", "returns"])
 
 
-def _get_parser_module(parse_python_two: bool = False):
+def _get_parser_module(parse_python_two=False, type_comments_support=True):
+    if not type_comments_support:
+        return ast
+
     if parse_python_two:
         parser_module = _ast_py2
     else:
@@ -29,12 +32,14 @@ def _get_parser_module(parse_python_two: bool = False):
     return parser_module or ast
 
 
-def _parse(string: str, parse_python_two: bool = False):
-    parse_module = _get_parser_module(parse_python_two=parse_python_two)
+def _parse(string: str, parse_python_two=False, type_comments=True):
+    parse_module = _get_parser_module(
+        parse_python_two=parse_python_two, type_comments_support=type_comments
+    )
     parse_func = parse_module.parse
-    if _ast_py3:
+    if parse_module is _ast_py3:
         if PY38:
-            parse_func = partial(parse_func, type_comments=True)
+            parse_func = partial(parse_func, type_comments=type_comments)
         if not parse_python_two:
             parse_func = partial(parse_func, feature_version=sys.version_info.minor)
     return parse_func(string)
diff --git a/astroid/builder.py b/astroid/builder.py
index 34bde0a1..7f30aaeb 100644
--- a/astroid/builder.py
+++ b/astroid/builder.py
@@ -165,7 +165,7 @@ class AstroidBuilder(raw_building.InspectBuilder):
     def _data_build(self, data, modname, path):
         """Build tree node from data and add some informations"""
         try:
-            node = _parse(data + "\n")
+            node = _parse_string(data)
         except (TypeError, ValueError, SyntaxError) as exc:
             raise exceptions.AstroidSyntaxError(
                 "Parsing Python code failed:\n{error}",
@@ -436,3 +436,19 @@ def extract_node(code, module_name=""):
     if len(extracted) == 1:
         return extracted[0]
     return extracted
+
+
+MISPLACED_TYPE_ANNOTATION_ERROR = "misplaced type annotation"
+
+
+def _parse_string(data, type_comments=True):
+    try:
+        node = _parse(data + "\n", type_comments=type_comments)
+    except SyntaxError as exc:
+        # If the type annotations are misplaced for some reason, we do not want
+        # to fail the entire parsing of the file, so we need to retry the parsing without
+        # type comment support.
+        if exc.args[0] != MISPLACED_TYPE_ANNOTATION_ERROR or not type_comments:
+            raise
+        node = _parse(data + "\n", type_comments=False)
+    return node
diff --git a/tests/unittest_builder.py b/tests/unittest_builder.py
index 0f1a470f..75557761 100644
--- a/tests/unittest_builder.py
+++ b/tests/unittest_builder.py
@@ -692,5 +692,30 @@ def test_module_build_dunder_file():
     assert module.path[0] == collections.__file__
 
 
+def test_parse_module_with_invalid_type_comments_does_not_crash():
+    node = builder.parse(
+        """
+    # op {
+    #   name: "AssignAddVariableOp"
+    #   input_arg {
+    #     name: "resource"
+    #     type: DT_RESOURCE
+    #   }
+    #   input_arg {
+    #     name: "value"
+    #     type_attr: "dtype"
+    #   }
+    #   attr {
+    #     name: "dtype"
+    #     type: "type"
+    #   }
+    #   is_stateful: true
+    # }
+    a, b = 2
+    """
+    )
+    assert isinstance(node, nodes.Module)
+
+
 if __name__ == "__main__":
     unittest.main()