Add tests to demonstrate source/name/listener_map issues

spacy/tests/pipeline/test_tok2vec.py

@@ -188,8 +188,7 @@ def test_tok2vec_listener(with_vectors):
         for tag in t[1]["tags"]:
             tagger.add_label(tag)
 
-    # Check that the Tok2Vec component finds it listeners
+    # Check that the Tok2Vec component finds its listeners
-    assert tok2vec.listeners == []
     optimizer = nlp.initialize(lambda: train_examples)
     assert tok2vec.listeners == [tagger_tok2vec]
 
@@ -217,7 +216,7 @@ def test_tok2vec_listener_callback():
     assert nlp.pipe_names == ["tok2vec", "tagger"]
     tagger = nlp.get_pipe("tagger")
     tok2vec = nlp.get_pipe("tok2vec")
-    nlp._link_components()
+    nlp._link_components()  # TODO: remove
     docs = [nlp.make_doc("A random sentence")]
     tok2vec.model.initialize(X=docs)
     gold_array = [[1.0 for tag in ["V", "Z"]] for word in docs]
@@ -426,29 +425,46 @@ def test_replace_listeners_from_config():
         nlp.to_disk(dir_path)
         base_model = str(dir_path)
         new_config = {
-            "nlp": {"lang": "en", "pipeline": ["tok2vec", "tagger", "ner"]},
+            "nlp": {
+                "lang": "en",
+                "pipeline": ["tok2vec", "tagger2", "ner3", "tagger4"],
+            },
             "components": {
                 "tok2vec": {"source": base_model},
-                "tagger": {
+                "tagger2": {
                     "source": base_model,
+                    "component": "tagger",
                     "replace_listeners": ["model.tok2vec"],
                 },
-                "ner": {"source": base_model},
+                "ner3": {
+                    "source": base_model,
+                    "component": "ner",
+                },
+                "tagger4": {
+                    "source": base_model,
+                    "component": "tagger",
+                },
             },
         }
         new_nlp = util.load_model_from_config(new_config, auto_fill=True)
     new_nlp.initialize(lambda: examples)
     tok2vec = new_nlp.get_pipe("tok2vec")
-    tagger = new_nlp.get_pipe("tagger")
+    tagger = new_nlp.get_pipe("tagger2")
-    ner = new_nlp.get_pipe("ner")
+    ner = new_nlp.get_pipe("ner3")
-    assert tok2vec.listening_components == ["ner"]
+    assert "ner" not in new_nlp.pipe_names
+    assert "tagger" not in new_nlp.pipe_names
+    assert tok2vec.listening_components == ["ner3", "tagger4"]
     assert any(isinstance(node, Tok2VecListener) for node in ner.model.walk())
     assert not any(isinstance(node, Tok2VecListener) for node in tagger.model.walk())
     t2v_cfg = new_nlp.config["components"]["tok2vec"]["model"]
     assert t2v_cfg["@architectures"] == "spacy.Tok2Vec.v2"
-    assert new_nlp.config["components"]["tagger"]["model"]["tok2vec"] == t2v_cfg
+    assert new_nlp.config["components"]["tagger2"]["model"]["tok2vec"] == t2v_cfg
     assert (
-        new_nlp.config["components"]["ner"]["model"]["tok2vec"]["@architectures"]
+        new_nlp.config["components"]["ner3"]["model"]["tok2vec"]["@architectures"]
+        == "spacy.Tok2VecListener.v1"
+    )
+    assert (
+        new_nlp.config["components"]["tagger4"]["model"]["tok2vec"]["@architectures"]
         == "spacy.Tok2VecListener.v1"
     )
 
@@ -540,3 +556,60 @@ def test_tok2vec_listeners_textcat():
     assert cats1["imperative"] < 0.9
     assert [t.tag_ for t in docs[0]] == ["V", "J", "N"]
     assert [t.tag_ for t in docs[1]] == ["N", "V", "J", "N"]
+
+
+def test_tok2vec_listener_source_link_name():
+    """The component's internal name and the tok2vec listener map correspond
+    to the most recently modified pipeline.
+    """
+    orig_config = Config().from_str(cfg_string_multi)
+    nlp1 = util.load_model_from_config(orig_config, auto_fill=True, validate=True)
+    nlp1._link_components()  # TODO: remove
+    assert nlp1.get_pipe("tok2vec").listening_components == ["tagger", "ner"]
+
+    nlp2 = English()
+    nlp2.add_pipe("tok2vec", source=nlp1)
+    nlp2.add_pipe("tagger", name="tagger2", source=nlp1)
+
+    # there is no way to have the component have the right name for both
+    # pipelines, right now the most recently modified pipeline is prioritized
+    #assert nlp1.get_pipe("tagger").name == nlp2.get_pipe("tagger2").name == "tagger2"  # TODO: uncomment
+
+    # there is no way to have the tok2vec have the right listener map for both
+    # pipelines, right now the most recently modified pipeline is prioritized
+    assert nlp2.get_pipe("tok2vec").listening_components == ["tagger2"]
+    nlp2.add_pipe("ner", name="ner3", source=nlp1)
+    assert nlp2.get_pipe("tok2vec").listening_components == ["tagger2", "ner3"]
+    nlp2.remove_pipe("ner3")
+    assert nlp2.get_pipe("tok2vec").listening_components == ["tagger2"]
+    nlp2.remove_pipe("tagger2")
+    assert nlp2.get_pipe("tok2vec").listening_components == []
+
+    # at this point the tok2vec component corresponds to nlp2
+    assert nlp1.get_pipe("tok2vec").listening_components == []
+
+    # modifying the nlp1 pipeline syncs the tok2vec listener map back to nlp1
+    nlp1.add_pipe("sentencizer")
+    assert nlp1.get_pipe("tok2vec").listening_components == ["tagger", "ner"]
+
+    # modifying nlp2 syncs it back to nlp2
+    nlp2.add_pipe("sentencizer")
+    assert nlp1.get_pipe("tok2vec").listening_components == []
+
+
+def test_tok2vec_listener_source_replace_listeners():
+    orig_config = Config().from_str(cfg_string_multi)
+    nlp1 = util.load_model_from_config(orig_config, auto_fill=True, validate=True)
+    nlp1._link_components()  # TODO: remove
+    assert nlp1.get_pipe("tok2vec").listening_components == ["tagger", "ner"]
+    nlp1._link_components()  # TODO: remove
+    nlp1.replace_listeners("tok2vec", "tagger", ["model.tok2vec"])
+    assert nlp1.get_pipe("tok2vec").listening_components == ["ner"]
+
+    nlp2 = English()
+    nlp2.add_pipe("tok2vec", source=nlp1)
+    assert nlp2.get_pipe("tok2vec").listening_components == []
+    nlp2.add_pipe("tagger", source=nlp1)
+    assert nlp2.get_pipe("tok2vec").listening_components == []
+    nlp2.add_pipe("ner", name="ner2", source=nlp1)
+    assert nlp2.get_pipe("tok2vec").listening_components == ["ner2"]