Allow Matcher to match on ENT_ID and ENT_KB_ID (explosion#9688)

nrodnova · adrianeboyd · web-flow · commit a4c43e5c577d · 2021-11-24T10:37:10.000+01:00
* Added ENT_ID and ENT_KB_ID into the list of the attributes that Matcher matches on

* Added ENT_ID and ENT_KB_ID to TEST_PATTERNS in test_pattern_validation.py. Disabled tests that I added before

* Update website/docs/api/matcher.md

* Format

* Remove skipped tests

Co-authored-by: Adriane Boyd &lt;adrianeboyd@gmail.com&gt;
diff --git a/spacy/schemas.py b/spacy/schemas.py
@@ -222,6 +222,8 @@ class TokenPattern(BaseModel):
     lemma: Optional[StringValue] = None
     shape: Optional[StringValue] = None
     ent_type: Optional[StringValue] = None
+    ent_id: Optional[StringValue] = None
+    ent_kb_id: Optional[StringValue] = None
     norm: Optional[StringValue] = None
     length: Optional[NumberValue] = None
     spacy: Optional[StrictBool] = None
diff --git a/spacy/tests/matcher/test_pattern_validation.py b/spacy/tests/matcher/test_pattern_validation.py
@@ -22,6 +22,8 @@
     ([{"TEXT": {"VALUE": "foo"}}], 2, 0),  # prev: (1, 0)
     ([{"IS_DIGIT": -1}], 1, 0),
     ([{"ORTH": -1}], 1, 0),
+    ([{"ENT_ID": -1}], 1, 0),
+    ([{"ENT_KB_ID": -1}], 1, 0),
     # Good patterns
     ([{"TEXT": "foo"}, {"LOWER": "bar"}], 0, 0),
     ([{"LEMMA": {"IN": ["love", "like"]}}, {"POS": "DET", "OP": "?"}], 0, 0),
@@ -33,6 +35,8 @@
     ([{"orth": "foo"}], 0, 0),  # prev: xfail
     ([{"IS_SENT_START": True}], 0, 0),
     ([{"SENT_START": True}], 0, 0),
+    ([{"ENT_ID": "STRING"}], 0, 0),
+    ([{"ENT_KB_ID": "STRING"}], 0, 0),
 ]
 
 
diff --git a/website/docs/api/matcher.md b/website/docs/api/matcher.md
@@ -44,6 +44,8 @@ rule-based matching are:
 | `SPACY`                                         | Token has a trailing space. ~~bool~~                                                                                      |
 |  `POS`, `TAG`, `MORPH`, `DEP`, `LEMMA`, `SHAPE` | The token's simple and extended part-of-speech tag, morphological analysis, dependency label, lemma, shape. ~~str~~       |
 | `ENT_TYPE`                                      | The token's entity label. ~~str~~                                                                                         |
+| `ENT_ID`                                        | The token's entity ID (`ent_id`). ~~str~~                                                                                 |
+| `ENT_KB_ID`                                     | The token's entity knowledge base ID (`ent_kb_id`). ~~str~~                                                               |
 | `_` <Tag variant="new">2.1</Tag>                | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). ~~Dict[str, Any]~~ |
 | `OP`                                            | Operator or quantifier to determine how often to match a token pattern. ~~str~~                                           |
 
