Merge pull request #12767 from adrianeboyd/backport/v3.5.4-1

Backports for v3.5.4

requirements.txt

@@ -9,7 +9,7 @@ murmurhash>=0.28.0,<1.1.0
 wasabi>=0.9.1,<1.2.0
 srsly>=2.4.3,<3.0.0
 catalogue>=2.0.6,<2.1.0
-typer>=0.3.0,<0.8.0
+typer>=0.3.0,<0.10.0
 pathy>=0.10.0
 smart-open>=5.2.1,<7.0.0
 # Third party dependencies

setup.cfg

@@ -52,7 +52,7 @@ install_requires =
     srsly>=2.4.3,<3.0.0
     catalogue>=2.0.6,<2.1.0
     # Third-party dependencies
-    typer>=0.3.0,<0.8.0
+    typer>=0.3.0,<0.10.0
     pathy>=0.10.0
     smart-open>=5.2.1,<7.0.0
     tqdm>=4.38.0,<5.0.0

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.5.3"
+__version__ = "3.5.4"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

spacy/language.py

@@ -716,6 +716,11 @@ def create_pipe_from_source(
                 )
             )
         pipe = source.get_pipe(source_name)
+        # There is no actual solution here. Either the component has the right
+        # name for the source pipeline or the component has the right name for
+        # the current pipeline. This prioritizes the current pipeline.
+        if hasattr(pipe, "name"):
+            pipe.name = name
         # Make sure the source config is interpolated so we don't end up with
         # orphaned variables in our final config
         source_config = source.config.interpolate()
@@ -793,6 +798,7 @@ def add_pipe(
         pipe_index = self._get_pipe_index(before, after, first, last)
         self._pipe_meta[name] = self.get_factory_meta(factory_name)
         self._components.insert(pipe_index, (name, pipe_component))
+        self._link_components()
         return pipe_component
 
     def _get_pipe_index(
@@ -928,6 +934,7 @@ def rename_pipe(self, old_name: str, new_name: str) -> None:
         if old_name in self._config["initialize"]["components"]:
             init_cfg = self._config["initialize"]["components"].pop(old_name)
             self._config["initialize"]["components"][new_name] = init_cfg
+        self._link_components()
 
     def remove_pipe(self, name: str) -> Tuple[str, PipeCallable]:
         """Remove a component from the pipeline.
@@ -951,6 +958,7 @@ def remove_pipe(self, name: str) -> Tuple[str, PipeCallable]:
         # Make sure the name is also removed from the set of disabled components
         if name in self.disabled:
             self._disabled.remove(name)
+        self._link_components()
         return removed
 
     def disable_pipe(self, name: str) -> None:
@@ -1673,8 +1681,16 @@ def _link_components(self) -> None:
         # The problem is we need to do it during deserialization...And the
         # components don't receive the pipeline then. So this does have to be
         # here :(
+        # First, fix up all the internal component names in case they have
+        # gotten out of sync due to sourcing components from different
+        # pipelines, since find_listeners uses proc2.name for the listener
+        # map.
+        for name, proc in self.pipeline:
+            if hasattr(proc, "name"):
+                proc.name = name
         for i, (name1, proc1) in enumerate(self.pipeline):
             if isinstance(proc1, ty.ListenedToComponent):
+                proc1.listener_map = {}
                 for name2, proc2 in self.pipeline[i + 1 :]:
                     proc1.find_listeners(proc2)
 
@@ -1808,6 +1824,7 @@ def from_config(
                         raw_config=raw_config,
                     )
                 else:
+                    assert "source" in pipe_cfg
                     # We need the sourced components to reference the same
                     # vocab without modifying the current vocab state **AND**
                     # we still want to load the source model vectors to perform
@@ -1827,6 +1844,10 @@ def from_config(
                     source_name = pipe_cfg.get("component", pipe_name)
                     listeners_replaced = False
                     if "replace_listeners" in pipe_cfg:
+                        # Make sure that the listened-to component has the
+                        # state of the source pipeline listener map so that the
+                        # replace_listeners method below works as intended.
+                        source_nlps[model]._link_components()
                         for name, proc in source_nlps[model].pipeline:
                             if source_name in getattr(proc, "listening_components", []):
                                 source_nlps[model].replace_listeners(
@@ -1838,6 +1859,8 @@ def from_config(
                         nlp.add_pipe(
                             source_name, source=source_nlps[model], name=pipe_name
                         )
+                        # At this point after nlp.add_pipe, the listener map
+                        # corresponds to the new pipeline.
                     if model not in source_nlp_vectors_hashes:
                         source_nlp_vectors_hashes[model] = hash(
                             source_nlps[model].vocab.vectors.to_bytes(
@@ -1892,27 +1915,6 @@ def from_config(
                 raise ValueError(
                     Errors.E942.format(name="pipeline_creation", value=type(nlp))
                 )
-        # Detect components with listeners that are not frozen consistently
-        for name, proc in nlp.pipeline:
-            if isinstance(proc, ty.ListenedToComponent):
-                # Remove listeners not in the pipeline
-                listener_names = proc.listening_components
-                unused_listener_names = [
-                    ll for ll in listener_names if ll not in nlp.pipe_names
-                ]
-                for listener_name in unused_listener_names:
-                    for listener in proc.listener_map.get(listener_name, []):
-                        proc.remove_listener(listener, listener_name)
-
-                for listener_name in proc.listening_components:
-                    # e.g. tok2vec/transformer
-                    # If it's a component sourced from another pipeline, we check if
-                    # the tok2vec listeners should be replaced with standalone tok2vec
-                    # models (e.g. so component can be frozen without its performance
-                    # degrading when other components/tok2vec are updated)
-                    paths = sourced.get(listener_name, {}).get("replace_listeners", [])
-                    if paths:
-                        nlp.replace_listeners(name, listener_name, paths)
         return nlp
 
     def replace_listeners(

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
-    assert tok2vec.listeners == []
+    # Check that the Tok2Vec component finds its listeners
     optimizer = nlp.initialize(lambda: train_examples)
     assert tok2vec.listeners == [tagger_tok2vec]
 
@@ -217,7 +216,6 @@ def test_tok2vec_listener_callback():
     assert nlp.pipe_names == ["tok2vec", "tagger"]
     tagger = nlp.get_pipe("tagger")
     tok2vec = nlp.get_pipe("tok2vec")
-    nlp._link_components()
     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 +424,46 @@ 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")
-    ner = new_nlp.get_pipe("ner")
-    assert tok2vec.listening_components == ["ner"]
+    tagger = new_nlp.get_pipe("tagger2")
+    ner = new_nlp.get_pipe("ner3")
+    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 +555,57 @@ 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)
+    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"
+
+    # 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)
+    assert nlp1.get_pipe("tok2vec").listening_components == ["tagger", "ner"]
+    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"]

spacy/tests/serialize/test_resource_warning.py

@@ -72,7 +72,7 @@ def entity_linker():
 
     def create_kb(vocab):
         kb = InMemoryLookupKB(vocab, entity_vector_length=1)
-        kb.add_entity("test", 0.0, zeros((1, 1), dtype="f"))
+        kb.add_entity("test", 0.0, zeros((1,), dtype="f"))
         return kb
 
     entity_linker = nlp.add_pipe("entity_linker")

spacy/tests/serialize/test_serialize_config.py

@@ -10,6 +10,7 @@
 from spacy.ml.models import MaxoutWindowEncoder, MultiHashEmbed
 from spacy.ml.models import build_tb_parser_model, build_Tok2Vec_model
 from spacy.schemas import ConfigSchema, ConfigSchemaPretrain
+from spacy.training import Example
 from spacy.util import load_config, load_config_from_str
 from spacy.util import load_model_from_config, registry
 
@@ -415,6 +416,55 @@ def test_config_overrides():
     assert nlp.pipe_names == ["tok2vec", "tagger"]
 
 
+@pytest.mark.filterwarnings("ignore:\\[W036")
+def test_config_overrides_registered_functions():
+    nlp = spacy.blank("en")
+    nlp.add_pipe("attribute_ruler")
+    with make_tempdir() as d:
+        nlp.to_disk(d)
+        nlp_re1 = spacy.load(
+            d,
+            config={
+                "components": {
+                    "attribute_ruler": {
+                        "scorer": {"@scorers": "spacy.tagger_scorer.v1"}
+                    }
+                }
+            },
+        )
+        assert (
+            nlp_re1.config["components"]["attribute_ruler"]["scorer"]["@scorers"]
+            == "spacy.tagger_scorer.v1"
+        )
+
+        @registry.misc("test_some_other_key")
+        def misc_some_other_key():
+            return "some_other_key"
+
+        nlp_re2 = spacy.load(
+            d,
+            config={
+                "components": {
+                    "attribute_ruler": {
+                        "scorer": {
+                            "@scorers": "spacy.overlapping_labeled_spans_scorer.v1",
+                            "spans_key": {"@misc": "test_some_other_key"},
+                        }
+                    }
+                }
+            },
+        )
+        assert nlp_re2.config["components"]["attribute_ruler"]["scorer"][
+            "spans_key"
+        ] == {"@misc": "test_some_other_key"}
+        # run dummy evaluation (will return None scores) in order to test that
+        # the spans_key value in the nested override is working as intended in
+        # the config
+        example = Example.from_dict(nlp_re2.make_doc("a b c"), {})
+        scores = nlp_re2.evaluate([example])
+        assert "spans_some_other_key_f" in scores
+
+
 def test_config_interpolation():
     config = Config().from_str(nlp_config_string, interpolate=False)
     assert config["corpora"]["train"]["path"] == "${paths.train}"

spacy/tests/test_misc.py

@@ -237,6 +237,10 @@ def test_minor_version(a1, a2, b1, b2, is_match):
             {"training.batch_size": 128, "training.optimizer.learn_rate": 0.01},
             {"training": {"batch_size": 128, "optimizer": {"learn_rate": 0.01}}},
         ),
+        (
+            {"attribute_ruler.scorer.@scorers": "spacy.tagger_scorer.v1"},
+            {"attribute_ruler": {"scorer": {"@scorers": "spacy.tagger_scorer.v1"}}},
+        ),
     ],
 )
 def test_dot_to_dict(dot_notation, expected):
@@ -245,6 +249,29 @@ def test_dot_to_dict(dot_notation, expected):
     assert util.dict_to_dot(result) == dot_notation
 
 
+@pytest.mark.parametrize(
+    "dot_notation,expected",
+    [
+        (
+            {"token.pos": True, "token._.xyz": True},
+            {"token": {"pos": True, "_": {"xyz": True}}},
+        ),
+        (
+            {"training.batch_size": 128, "training.optimizer.learn_rate": 0.01},
+            {"training": {"batch_size": 128, "optimizer": {"learn_rate": 0.01}}},
+        ),
+        (
+            {"attribute_ruler.scorer": {"@scorers": "spacy.tagger_scorer.v1"}},
+            {"attribute_ruler": {"scorer": {"@scorers": "spacy.tagger_scorer.v1"}}},
+        ),
+    ],
+)
+def test_dot_to_dict_overrides(dot_notation, expected):
+    result = util.dot_to_dict(dot_notation)
+    assert result == expected
+    assert util.dict_to_dot(result, for_overrides=True) == dot_notation
+
+
 def test_set_dot_to_object():
     config = {"foo": {"bar": 1, "baz": {"x": "y"}}, "test": {"a": {"b": "c"}}}
     with pytest.raises(KeyError):

spacy/training/initialize.py

@@ -67,7 +67,8 @@ def init_nlp(config: Config, *, use_gpu: int = -1) -> "Language":
         with nlp.select_pipes(enable=resume_components):
             logger.info("Resuming training for: %s", resume_components)
             nlp.resume_training(sgd=optimizer)
-    # Make sure that listeners are defined before initializing further
+    # Make sure that internal component names are synced and listeners are
+    # defined before initializing further
     nlp._link_components()
     with nlp.select_pipes(disable=[*frozen_components, *resume_components]):
         if T["max_epochs"] == -1: