Allow copying of user_data in as_doc (#4282)

* Allow copying the user_data with as_doc + unit test

* add option to docs

* add typing

* import fix

* workaround to avoid bool clashing ...

* bint instead of bool

spacy/tests/doc/test_span.py

@@ -173,6 +173,21 @@ def test_span_as_doc(doc):
     assert span_doc[0].idx == 0
 
 
+def test_span_as_doc_user_data(doc):
+    """Test that the user_data can be preserved (but not by default). """
+    my_key = "my_info"
+    my_value = 342
+    doc.user_data[my_key] = my_value
+
+    span = doc[4:10]
+    span_doc_with = span.as_doc(copy_user_data=True)
+    span_doc_without = span.as_doc()
+
+    assert doc.user_data.get(my_key, None) is my_value
+    assert span_doc_with.user_data.get(my_key, None) is my_value
+    assert span_doc_without.user_data.get(my_key, None) is None
+
+
 def test_span_string_label_kb_id(doc):
     span = Span(doc, 0, 1, label="hello", kb_id="Q342")
     assert span.label_ == "hello"

spacy/tokens/span.pyx

@@ -200,13 +200,15 @@ cdef class Span:
         return Underscore(Underscore.span_extensions, self,
                           start=self.start_char, end=self.end_char)
 
-    def as_doc(self):
+    def as_doc(self, bint copy_user_data=False):
         """Create a `Doc` object with a copy of the `Span`'s data.
 
+        copy_user_data (bool): Whether or not to copy the original doc's user data.
         RETURNS (Doc): The `Doc` copy of the span.
 
         DOCS: https://spacy.io/api/span#as_doc
         """
+        # TODO: make copy_user_data a keyword-only argument (Python 3 only)
         words = [t.text for t in self]
         spaces = [bool(t.whitespace_) for t in self]
         cdef Doc doc = Doc(self.doc.vocab, words=words, spaces=spaces)
@@ -235,6 +237,8 @@ cdef class Span:
                 cat_start, cat_end, cat_label = key
                 if cat_start == self.start_char and cat_end == self.end_char:
                     doc.cats[cat_label] = value
+        if copy_user_data:
+            doc.user_data = self.doc.user_data
         return doc
 
     def _fix_dep_copy(self, attrs, array):

website/docs/api/span.md

@@ -292,9 +292,10 @@ Create a new `Doc` object corresponding to the `Span`, with a copy of the data.
 > assert doc2.text == u"New York"
 > ```
 
-| Name        | Type  | Description                             |
-| ----------- | ----- | --------------------------------------- |
-| **RETURNS** | `Doc` | A `Doc` object of the `Span`'s content. |
+| Name              | Type  | Description                                          |
+| ----------------- | ----- | ---------------------------------------------------- |
+| `copy_user_data`  | bool  | Whether or not to copy the original doc's user data. |
+| **RETURNS**       | `Doc` | A `Doc` object of the `Span`'s content.              |
 
 ## Span.root {#root tag="property" model="parser"}