Add ent_id_ to strings serialized with Doc (#6353)

spacy/tests/doc/test_doc_api.py

@@ -109,6 +109,7 @@ def test_doc_api_serialize(en_tokenizer, text):
     tokens[0].lemma_ = "lemma"
     tokens[0].norm_ = "norm"
     tokens[0].ent_kb_id_ = "ent_kb_id"
+    tokens[0].ent_id_ = "ent_id"
     new_tokens = Doc(tokens.vocab).from_bytes(tokens.to_bytes())
     assert tokens.text == new_tokens.text
     assert [t.text for t in tokens] == [t.text for t in new_tokens]
@@ -116,6 +117,7 @@ def test_doc_api_serialize(en_tokenizer, text):
     assert new_tokens[0].lemma_ == "lemma"
     assert new_tokens[0].norm_ == "norm"
     assert new_tokens[0].ent_kb_id_ == "ent_kb_id"
+    assert new_tokens[0].ent_id_ == "ent_id"
 
     new_tokens = Doc(tokens.vocab).from_bytes(
         tokens.to_bytes(exclude=["tensor"]), exclude=["tensor"]

spacy/tests/pipeline/test_entity_ruler.py

@@ -166,3 +166,22 @@ def test_entity_ruler_overlapping_spans(nlp):
     doc = ruler(nlp.make_doc("foo bar baz"))
     assert len(doc.ents) == 1
     assert doc.ents[0].label_ == "FOOBAR"
+
+
+@pytest.mark.parametrize("n_process", [1, 2])
+def test_entity_ruler_multiprocessing(nlp, n_process):
+    ruler = EntityRuler(nlp)
+    texts = [
+        "I enjoy eating Pizza Hut pizza."
+    ]
+
+    patterns = [
+        {"label": "FASTFOOD", "pattern": "Pizza Hut", "id": "1234"}
+    ]
+
+    ruler.add_patterns(patterns)
+    nlp.add_pipe(ruler)
+
+    for doc in nlp.pipe(texts, n_process=2):
+        for ent in doc.ents:
+            assert ent.ent_id_ == "1234"

spacy/tokens/doc.pyx

@@ -933,6 +933,7 @@ cdef class Doc:
             strings.add(token.dep_)
             strings.add(token.ent_type_)
             strings.add(token.ent_kb_id_)
+            strings.add(token.ent_id_)
             strings.add(token.norm_)
         # Msgpack doesn't distinguish between lists and tuples, which is
         # vexing for user data. As a best guess, we *know* that within