diff --git a/spacy/errors.py b/spacy/errors.py index 608305a06..5ee1476c2 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -230,8 +230,9 @@ class Errors(metaclass=ErrorsWithCodes): "initialized component.") E004 = ("Can't set up pipeline component: a factory for '{name}' already " "exists. Existing factory: {func}. New factory: {new_func}") - E005 = ("Pipeline component '{name}' returned None. If you're using a " - "custom component, maybe you forgot to return the processed Doc?") + E005 = ("Pipeline component '{name}' returned {returned_type} instead of a " + "Doc. If you're using a custom component, maybe you forgot to " + "return the processed Doc?") E006 = ("Invalid constraints for adding pipeline component. You can only " "set one of the following: before (component name or index), " "after (component name or index), first (True) or last (True). " diff --git a/spacy/language.py b/spacy/language.py index ec330753c..34a06e576 100644 --- a/spacy/language.py +++ b/spacy/language.py @@ -1028,8 +1028,8 @@ class Language: raise ValueError(Errors.E109.format(name=name)) from e except Exception as e: error_handler(name, proc, [doc], e) - if doc is None: - raise ValueError(Errors.E005.format(name=name)) + if not isinstance(doc, Doc): + raise ValueError(Errors.E005.format(name=name, returned_type=type(doc))) return doc def disable_pipes(self, *names) -> "DisabledPipes": diff --git a/spacy/tests/test_language.py b/spacy/tests/test_language.py index 6f3ba8acc..03a98d32f 100644 --- a/spacy/tests/test_language.py +++ b/spacy/tests/test_language.py @@ -670,3 +670,25 @@ def test_dot_in_factory_names(nlp): with pytest.raises(ValueError, match="not permitted"): Language.factory("my.evil.component.v1", func=evil_component) + + +def test_component_return(): + """Test that an error is raised if components return a type other than a + doc.""" + nlp = English() + + @Language.component("test_component_good_pipe") + def good_pipe(doc): + return doc + + nlp.add_pipe("test_component_good_pipe") + nlp("text") + nlp.remove_pipe("test_component_good_pipe") + + @Language.component("test_component_bad_pipe") + def bad_pipe(doc): + return doc.text + + nlp.add_pipe("test_component_bad_pipe") + with pytest.raises(ValueError, match="instead of a Doc"): + nlp("text")