Merge branch 'master' into spacy.io

spacy/matcher/phrasematcher.pxd

@@ -9,7 +9,7 @@ from ..vocab cimport Vocab
 
 
 cdef class PhraseMatcher:
-    cdef Vocab vocab
+    cdef readonly Vocab vocab
     cdef attr_id_t attr
     cdef object _callbacks
     cdef object _docs

spacy/tests/regression/test_issue4373.py

@@ -0,0 +1,13 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from spacy.matcher import Matcher, PhraseMatcher
+from spacy.vocab import Vocab
+
+
+def test_issue4373():
+    """Test that PhraseMatcher.vocab can be accessed (like Matcher.vocab)."""
+    matcher = Matcher(Vocab())
+    assert isinstance(matcher.vocab, Vocab)
+    matcher = PhraseMatcher(Vocab())
+    assert isinstance(matcher.vocab, Vocab)

website/docs/api/docbin.md

@@ -46,7 +46,7 @@ Create a `DocBin` object to hold serialized annotations.
 | Argument          | Type     | Description                                                                                                                                                                                |
 | ----------------- | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
 | `attrs`           | list     | List of attributes to serialize. `orth` (hash of token text) and `spacy` (whether the token is followed by whitespace) are always serialized, so they're not required. Defaults to `None`. |
-| `store_user_data` | bool     | Whether to include the `Doc.user_data`. Defaults to `False`.                                                                                                                               |
+| `store_user_data` | bool     | Whether to include the `Doc.user_data` and the values of custom extension attributes. Defaults to `False`.                                                                                 |
 | **RETURNS**       | `DocBin` | The newly constructed object.                                                                                                                                                              |
 
 ## DocBin.\_\len\_\_ {#len tag="method"}

website/docs/usage/saving-loading.md

@@ -92,6 +92,25 @@ doc_bin = DocBin().from_bytes(bytes_data)
 docs = list(doc_bin.get_docs(nlp.vocab))
 ```
 
+If `store_user_data` is set to `True`, the `Doc.user_data` will be serialized as
+well, which includes the values of
+[extension attributes](/processing-pipelines#custom-components-attributes) (if
+they're serializable with msgpack).
+
+<Infobox title="Important note on serializing extension attributes" variant="warning">
+
+Including the `Doc.user_data` and extension attributes will only serialize the
+**values** of the attributes. To restore the values and access them via the
+`doc._.` property, you need to register the global attribute on the `Doc` again.
+
+```python
+docs = list(doc_bin.get_docs(nlp.vocab))
+Doc.set_extension("my_custom_attr", default=None)
+print([doc._.my_custom_attr for doc in docs])
+```
+
+</Infobox>
+
 ### Using Pickle {#pickle}
 
 > #### Example