read entity_ruler patterns with srsly.read_jsonl.v1

spacy/language.py

@@ -1410,7 +1410,9 @@ class Language:
             kwargs = component_cfg.get(name, {})
             # Allow component_cfg to overwrite the top-level kwargs.
             kwargs.setdefault("batch_size", batch_size)
-            if hasattr(proc, "pipe"):
+            # non-trainable components may have a pipe() implementation that refers to dummy
+            # predict and set_annotations methods
+            if hasattr(proc, "pipe") and hasattr(proc, "is_trainable") and proc.is_trainable():
                 f = functools.partial(proc.pipe, **kwargs)
             else:
                 # Apply the function, but yield the doc

spacy/pipeline/entityruler.py

@@ -1,4 +1,4 @@
-from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable
+from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable, Sequence
 from collections import defaultdict
 from pathlib import Path
 import srsly
@@ -190,19 +190,18 @@ class EntityRuler(Pipe):
         get_examples: Callable[[], Iterable[Example]],
         *,
         nlp: Optional[Language] = None,
-        patterns_path: Optional[Path] = None
+        patterns: Optional[Sequence[PatternType]] = None,
     ):
         """Initialize the pipe for training.
 
         get_examples (Callable[[], Iterable[Example]]): Function that
             returns a representative sample of gold-standard Example objects.
         nlp (Language): The current nlp object the component is part of.
-        patterns_path: Path to serialized patterns.
+        patterns Optional[Iterable[PatternType]]: The list of patterns.
 
         DOCS: https://nightly.spacy.io/api/entityruler#initialize
         """
-        if patterns_path:
-            patterns = srsly.read_jsonl(patterns_path)
+        if patterns:
             self.add_patterns(patterns)
 
 

spacy/pipeline/transition_parser.pyx

@@ -437,7 +437,9 @@ cdef class Parser(Pipe):
             for name, component in nlp.pipeline:
                 if component is self:
                     break
-                if hasattr(component, "pipe"):
+                # non-trainable components may have a pipe() implementation that refers to dummy
+                # predict and set_annotations methods
+                if hasattr(component, "pipe") and hasattr(component, "is_trainable") and component.is_trainable():
                     doc_sample = list(component.pipe(doc_sample, batch_size=8))
                 else:
                     doc_sample = [component(doc) for doc in doc_sample]

spacy/schemas.py

@@ -119,7 +119,7 @@ def validate_init_settings(
     if types don't match or required values are missing.
 
     func (Callable): The initialize method of a given component etc.
-    settings (Dict[str, Any]): The settings from the repsective [initialize] block.
+    settings (Dict[str, Any]): The settings from the respective [initialize] block.
     section (str): Initialize section, for error message.
     name (str): Name of the block in the section.
     exclude (Iterable[str]): Parameter names to exclude from schema.

spacy/tests/pipeline/test_attributeruler.py

@@ -121,7 +121,7 @@ def test_attributeruler_init_patterns(nlp, pattern_dicts):
     assert doc.has_annotation("LEMMA")
     assert doc.has_annotation("MORPH")
     nlp.remove_pipe("attribute_ruler")
-    # initialize with patterns from asset
+    # initialize with patterns from misc registry
     nlp.config["initialize"]["components"]["attribute_ruler"] = {
         "patterns": {"@misc": "attribute_ruler_patterns"}
     }

spacy/tests/pipeline/test_entity_ruler.py

@@ -1,4 +1,6 @@
 import pytest
+
+from spacy import registry
 from spacy.tokens import Span
 from spacy.language import Language
 from spacy.pipeline import EntityRuler
@@ -11,6 +13,7 @@ def nlp():
 
 
 @pytest.fixture
+@registry.misc("entity_ruler_patterns")
 def patterns():
     return [
         {"label": "HELLO", "pattern": "hello world"},
@@ -42,6 +45,29 @@ def test_entity_ruler_init(nlp, patterns):
     assert doc.ents[1].label_ == "BYE"
 
 
+def test_entity_ruler_init_patterns(nlp, patterns):
+    # initialize with patterns
+    ruler = nlp.add_pipe("entity_ruler")
+    assert len(ruler.labels) == 0
+    ruler.initialize(lambda: [], patterns=patterns)
+    assert len(ruler.labels) == 4
+    doc = nlp("hello world bye bye")
+    assert doc.ents[0].label_ == "HELLO"
+    assert doc.ents[1].label_ == "BYE"
+    nlp.remove_pipe("entity_ruler")
+    # initialize with patterns from misc registry
+    nlp.config["initialize"]["components"]["entity_ruler"] = {
+        "patterns": {"@misc": "entity_ruler_patterns"}
+    }
+    ruler = nlp.add_pipe("entity_ruler")
+    assert len(ruler.labels) == 0
+    nlp.initialize()
+    assert len(ruler.labels) == 4
+    doc = nlp("hello world bye bye")
+    assert doc.ents[0].label_ == "HELLO"
+    assert doc.ents[1].label_ == "BYE"
+
+
 def test_entity_ruler_existing(nlp, patterns):
     ruler = nlp.add_pipe("entity_ruler")
     ruler.add_patterns(patterns)

website/docs/api/entityruler.md

@@ -82,13 +82,16 @@ Initialize the component with patterns from a file.
 >
 > ```python
 > entity_ruler = nlp.add_pipe("entity_ruler")
-> entity_ruler.initialize(lambda: [], nlp=nlp, patterns_path=patterns_path)
+> entity_ruler.initialize(lambda: [], nlp=nlp, patterns=patterns)
 > ```
 >
 > ```ini
 > ### config.cfg
 > [initialize.components.entity_ruler]
-> patterns_path = "data/patterns/patterns.jsonl"
+>
+> [initialize.components.entity_ruler.patterns]
+> @readers = "srsly.read_jsonl.v1"
+> path = "corpus/entity_ruler_patterns.jsonl
 > ```
 
 | Name           | Description                                                                                                                                                          |
@@ -96,7 +99,7 @@ Initialize the component with patterns from a file.
 | `get_examples` | Function that returns gold-standard annotations in the form of [`Example`](/api/example) objects. Not used by the `EntityRuler`. ~~Callable[[], Iterable[Example]]~~ |
 | _keyword-only_ |                                                                                                                                                                      |
 | `nlp`          | The current `nlp` object. Defaults to `None`. ~~Optional[Language]~~                                                                                                 |
-| `labels`       | Path to the .json file holding the serialized patterns. ~~Path~~                                                                                                     |
+| `patterns`     | The list of patterns. Defaults to `None`. ~~Optional[Sequence[Dict[str, Union[str, List[Dict[str, Any]]]]]]~~                                                        |
 
 ## EntityRuler.\_\len\_\_ {#len tag="method"}