Add test for factory registrations

spacy/tests/factory_registrations.json

@@ -0,0 +1,132 @@
+{
+  "attribute_ruler": {
+    "name": "attribute_ruler",
+    "module": "spacy.pipeline.attributeruler",
+    "function": "make_attribute_ruler"
+  },
+  "beam_ner": {
+    "name": "beam_ner",
+    "module": "spacy.pipeline.ner",
+    "function": "make_beam_ner"
+  },
+  "beam_parser": {
+    "name": "beam_parser",
+    "module": "spacy.pipeline.dep_parser",
+    "function": "make_beam_parser"
+  },
+  "doc_cleaner": {
+    "name": "doc_cleaner",
+    "module": "spacy.pipeline.functions",
+    "function": "make_doc_cleaner"
+  },
+  "entity_linker": {
+    "name": "entity_linker",
+    "module": "spacy.pipeline.entity_linker",
+    "function": "make_entity_linker"
+  },
+  "entity_ruler": {
+    "name": "entity_ruler",
+    "module": "spacy.pipeline.entityruler",
+    "function": "make_entity_ruler"
+  },
+  "future_entity_ruler": {
+    "name": "future_entity_ruler",
+    "module": "spacy.pipeline.span_ruler",
+    "function": "make_entity_ruler"
+  },
+  "lemmatizer": {
+    "name": "lemmatizer",
+    "module": "spacy.pipeline.lemmatizer",
+    "function": "make_lemmatizer"
+  },
+  "merge_entities": {
+    "name": "merge_entities",
+    "module": "spacy.language",
+    "function": "Language.component.<locals>.add_component.<locals>.factory_func"
+  },
+  "merge_noun_chunks": {
+    "name": "merge_noun_chunks",
+    "module": "spacy.language",
+    "function": "Language.component.<locals>.add_component.<locals>.factory_func"
+  },
+  "merge_subtokens": {
+    "name": "merge_subtokens",
+    "module": "spacy.language",
+    "function": "Language.component.<locals>.add_component.<locals>.factory_func"
+  },
+  "morphologizer": {
+    "name": "morphologizer",
+    "module": "spacy.pipeline.morphologizer",
+    "function": "make_morphologizer"
+  },
+  "ner": {
+    "name": "ner",
+    "module": "spacy.pipeline.ner",
+    "function": "make_ner"
+  },
+  "parser": {
+    "name": "parser",
+    "module": "spacy.pipeline.dep_parser",
+    "function": "make_parser"
+  },
+  "sentencizer": {
+    "name": "sentencizer",
+    "module": "spacy.pipeline.sentencizer",
+    "function": "make_sentencizer"
+  },
+  "senter": {
+    "name": "senter",
+    "module": "spacy.pipeline.senter",
+    "function": "make_senter"
+  },
+  "span_finder": {
+    "name": "span_finder",
+    "module": "spacy.pipeline.span_finder",
+    "function": "make_span_finder"
+  },
+  "span_ruler": {
+    "name": "span_ruler",
+    "module": "spacy.pipeline.span_ruler",
+    "function": "make_span_ruler"
+  },
+  "spancat": {
+    "name": "spancat",
+    "module": "spacy.pipeline.spancat",
+    "function": "make_spancat"
+  },
+  "spancat_singlelabel": {
+    "name": "spancat_singlelabel",
+    "module": "spacy.pipeline.spancat",
+    "function": "make_spancat_singlelabel"
+  },
+  "tagger": {
+    "name": "tagger",
+    "module": "spacy.pipeline.tagger",
+    "function": "make_tagger"
+  },
+  "textcat": {
+    "name": "textcat",
+    "module": "spacy.pipeline.textcat",
+    "function": "make_textcat"
+  },
+  "textcat_multilabel": {
+    "name": "textcat_multilabel",
+    "module": "spacy.pipeline.textcat_multilabel",
+    "function": "make_multilabel_textcat"
+  },
+  "tok2vec": {
+    "name": "tok2vec",
+    "module": "spacy.pipeline.tok2vec",
+    "function": "make_tok2vec"
+  },
+  "token_splitter": {
+    "name": "token_splitter",
+    "module": "spacy.pipeline.functions",
+    "function": "make_token_splitter"
+  },
+  "trainable_lemmatizer": {
+    "name": "trainable_lemmatizer",
+    "module": "spacy.pipeline.edit_tree_lemmatizer",
+    "function": "make_edit_tree_lemmatizer"
+  }
+}

spacy/tests/test_factory_registrations.py

@@ -0,0 +1,76 @@
+import json
+import inspect
+import pytest
+from pathlib import Path
+from spacy.language import Language
+from spacy.util import registry
+
+# Path to the reference factory registrations, relative to this file
+REFERENCE_FILE = Path(__file__).parent / "factory_registrations.json"
+
+# Monkey patch the util.is_same_func to handle Cython functions
+import inspect
+from spacy import util
+
+original_is_same_func = util.is_same_func
+
+def patched_is_same_func(func1, func2):
+    # Handle Cython functions
+    try:
+        return original_is_same_func(func1, func2)
+    except TypeError:
+        # For Cython functions, just compare the string representation
+        return str(func1) == str(func2)
+
+util.is_same_func = patched_is_same_func
+
+@pytest.fixture
+def reference_factory_registrations():
+    """Load reference factory registrations from JSON file"""
+    if not REFERENCE_FILE.exists():
+        pytest.fail(f"Reference file {REFERENCE_FILE} not found. Run export_factory_registrations.py first.")
+    
+    with REFERENCE_FILE.open("r") as f:
+        return json.load(f)
+
+def test_factory_registrations_preserved(reference_factory_registrations):
+    """Test that all factory registrations from the reference file are still present."""
+    # Ensure the registry is populated
+    registry.ensure_populated()
+    
+    # Get all factory registrations
+    all_factories = registry.factories.get_all()
+    
+    # Initialize our data structure to store current factory registrations
+    current_registrations = {}
+    
+    # Process factory registrations
+    for name, func in all_factories.items():
+        # Store information about each factory
+        try:
+            module_name = func.__module__
+        except (AttributeError, TypeError):
+            # For Cython functions, just use a placeholder
+            module_name = str(func).split()[1].split('.')[0]
+        
+        try:
+            func_name = func.__qualname__
+        except (AttributeError, TypeError):
+            # For Cython functions, use the function's name
+            func_name = func.__name__ if hasattr(func, "__name__") else str(func).split()[1].split('.')[-1]
+        
+        current_registrations[name] = {
+            "name": name,
+            "module": module_name,
+            "function": func_name,
+        }
+    
+    # Check for missing registrations
+    missing_registrations = set(reference_factory_registrations.keys()) - set(current_registrations.keys())
+    assert not missing_registrations, f"Missing factory registrations: {', '.join(sorted(missing_registrations))}"
+    
+    # Check for new registrations (not an error, but informative)
+    new_registrations = set(current_registrations.keys()) - set(reference_factory_registrations.keys())
+    if new_registrations:
+        # This is not an error, just informative
+        print(f"New factory registrations found: {', '.join(sorted(new_registrations))}")