Miscellaneous Minor SpanGroups/DocBin Improvements (#10250)

* MultiHashEmbed vector docs correction

* doc copy span test

* ignore empty lists in DocBin.span_groups

* serialized empty list const + SpanGroups.is_empty

* add conditional deserial on from_bytes

* clean up + reorganize

* rm test

* add constant as class attribute

* rename to _EMPTY_BYTES

* Update spacy/tests/doc/test_span.py

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

spacy/tests/doc/test_span.py

@@ -655,3 +655,16 @@ def test_span_sents(doc, start, end, expected_sentences, expected_sentences_with
 def test_span_sents_not_parsed(doc_not_parsed):
     with pytest.raises(ValueError):
         list(Span(doc_not_parsed, 0, 3).sents)
+
+
+def test_span_group_copy(doc):
+    doc.spans["test"] = [doc[0:1], doc[2:4]]
+    assert len(doc.spans["test"]) == 2
+    doc_copy = doc.copy()
+    # check that the spans were indeed copied
+    assert len(doc_copy.spans["test"]) == 2
+    # add a new span to the original doc
+    doc.spans["test"].append(doc[3:4])
+    assert len(doc.spans["test"]) == 3
+    # check that the copy spans were not modified and this is an isolated doc
+    assert len(doc_copy.spans["test"]) == 2

spacy/tokens/_dict_proxies.py

@@ -6,6 +6,7 @@ import srsly
 from .span_group import SpanGroup
 from ..errors import Errors
 
+
 if TYPE_CHECKING:
     # This lets us add type hints for mypy etc. without causing circular imports
     from .doc import Doc  # noqa: F401
@@ -19,6 +20,8 @@ if TYPE_CHECKING:
 class SpanGroups(UserDict):
     """A dict-like proxy held by the Doc, to control access to span groups."""
 
+    _EMPTY_BYTES = srsly.msgpack_dumps([])
+
     def __init__(
         self, doc: "Doc", items: Iterable[Tuple[str, SpanGroup]] = tuple()
     ) -> None:
@@ -43,11 +46,13 @@ class SpanGroups(UserDict):
     def to_bytes(self) -> bytes:
         # We don't need to serialize this as a dict, because the groups
         # know their names.
+        if len(self) == 0:
+            return self._EMPTY_BYTES
         msg = [value.to_bytes() for value in self.values()]
         return srsly.msgpack_dumps(msg)
 
     def from_bytes(self, bytes_data: bytes) -> "SpanGroups":
-        msg = srsly.msgpack_loads(bytes_data)
+        msg = [] if bytes_data == self._EMPTY_BYTES else srsly.msgpack_loads(bytes_data)
         self.clear()
         doc = self._ensure_doc()
         for value_bytes in msg:

spacy/tokens/_serialize.py

@@ -12,6 +12,7 @@ from ..compat import copy_reg
 from ..attrs import SPACY, ORTH, intify_attr, IDS
 from ..errors import Errors
 from ..util import ensure_path, SimpleFrozenList
+from ._dict_proxies import SpanGroups
 
 # fmt: off
 ALL_ATTRS = ("ORTH", "NORM", "TAG", "HEAD", "DEP", "ENT_IOB", "ENT_TYPE", "ENT_KB_ID", "ENT_ID", "LEMMA", "MORPH", "POS", "SENT_START")
@@ -146,7 +147,7 @@ class DocBin:
             doc = Doc(vocab, words=tokens[:, orth_col], spaces=spaces)  # type: ignore
             doc = doc.from_array(self.attrs, tokens)  # type: ignore
             doc.cats = self.cats[i]
-            if self.span_groups[i]:
+            if self.span_groups[i] != SpanGroups._EMPTY_BYTES:
                 doc.spans.from_bytes(self.span_groups[i])
             else:
                 doc.spans.clear()