From 913992aa3de6f1aa22cb5f31f6a856f791a3b87a Mon Sep 17 00:00:00 2001
From: thomashacker <EdwardSchmuhl@web.de>
Date: Fri, 4 Nov 2022 17:21:14 +0100
Subject: [PATCH] add underscore changes and test to span.to_doc

---
 spacy/tests/doc/test_underscore.py | 50 +++++++++++++++++++++++++++++-
 spacy/tokens/span.pyx              | 12 +++++--
 2 files changed, 59 insertions(+), 3 deletions(-)

diff --git a/spacy/tests/doc/test_underscore.py b/spacy/tests/doc/test_underscore.py
index 96ddb730a..82b53220e 100644
--- a/spacy/tests/doc/test_underscore.py
+++ b/spacy/tests/doc/test_underscore.py
@@ -350,7 +350,7 @@ def test_underscore_for_unique_span(en_tokenizer):
     assert doc.user_data[("._.", "token_extension", 0, None)] == "token extension"
 
 def test_underscore_for_unique_span_from_docs(en_tokenizer):
-    """Test that spans in the user_data keep the same data structure"""
+    """Test that spans in the user_data keep the same data structure when using Doc.from_docs"""
     Span.set_extension(name="span_extension", default=None)
     Token.set_extension(name="token_extension", default=None)
 
@@ -462,4 +462,52 @@ def test_underscore_for_unique_span_from_docs(en_tokenizer):
             )
         ]
         == "span_2a extension"
+    )
+
+def test_underscore_for_unique_span_as_span(en_tokenizer):
+    """Test that spans in the user_data keep the same data structure when using Span.as_doc"""
+    Span.set_extension(name="span_extension", default=None)
+
+    # Initialize doc
+    text = "Hello, world!"
+    doc = en_tokenizer(text)
+    span_1 = Span(doc, 0, 2, "SPAN_1")
+    span_2 = Span(doc, 0, 2, "SPAN_2")
+
+    # Set custom extensions
+    span_1._.span_extension = "span_1 extension"
+    span_2._.span_extension = "span_2 extension"
+
+    span_doc = span_1.as_doc(copy_user_data=True)
+
+    # Assert extensions
+    assert (
+        span_doc.user_data[
+            (
+                "._.",
+                "span_extension",
+                span_1.start_char,
+                span_1.end_char,
+                span_1.label,
+                span_1.kb_id,
+                span_1.id,
+            )
+        ]
+        == "span_1 extension"
+    )
+
+        # Assert extensions
+    assert (
+        span_doc.user_data[
+            (
+                "._.",
+                "span_extension",
+                span_2.start_char,
+                span_2.end_char,
+                span_2.label,
+                span_2.kb_id,
+                span_2.id,
+            )
+        ]
+        == "span_2 extension"
     )
\ No newline at end of file
diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx
index d853f6fef..0435f9260 100644
--- a/spacy/tokens/span.pyx
+++ b/spacy/tokens/span.pyx
@@ -274,12 +274,20 @@ cdef class Span:
             char_offset = self.start_char
             for key, value in self.doc.user_data.items():
                 if isinstance(key, tuple) and len(key) == 4 and key[0] == "._.":
-                    data_type, name, start, end = key
+                    data_type = key[0]
+                    name = key[1]
+                    start = key[2]
+                    end = key[3]
                     if start is not None or end is not None:
                         start -= char_offset
                         if end is not None:
                             end -= char_offset
-                        user_data[(data_type, name, start, end)] = copy.copy(value)
+                            _label = key[4]
+                            _kb_id = key[5]
+                            _span_id = key[6]
+                            user_data[(data_type, name, start, end, _label, _kb_id, _span_id)] = copy.copy(value)
+                        else:
+                            user_data[(data_type, name, start, end)] = copy.copy(value)
                 else:
                     user_data[key] = copy.copy(value)
             doc.user_data = user_data