From 02f2af3ad8f7d24ce11d3dfc05b817ba41c93013 Mon Sep 17 00:00:00 2001
From: Simon Gurcke <simon@gurcke.de>
Date: Mon, 23 Jan 2023 11:25:51 +1000
Subject: [PATCH] Add alignment_mode argument to Span.char_span()

---
 spacy/tokens/span.pyi |  1 +
 spacy/tokens/span.pyx | 11 ++++++++---
 2 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/spacy/tokens/span.pyi b/spacy/tokens/span.pyi
index 9986a90e6..00226098a 100644
--- a/spacy/tokens/span.pyi
+++ b/spacy/tokens/span.pyi
@@ -98,6 +98,7 @@ class Span:
         label: Union[int, str] = ...,
         kb_id: Union[int, str] = ...,
         vector: Optional[Floats1d] = ...,
+        alignment_mode: str = ...,
     ) -> Span: ...
     @property
     def conjuncts(self) -> Tuple[Token]: ...
diff --git a/spacy/tokens/span.pyx b/spacy/tokens/span.pyx
index 99a5f43bd..6e78b9b13 100644
--- a/spacy/tokens/span.pyx
+++ b/spacy/tokens/span.pyx
@@ -362,7 +362,7 @@ cdef class Span:
         result = xp.dot(vector, other.vector) / (self.vector_norm * other.vector_norm)
         # ensure we get a scalar back (numpy does this automatically but cupy doesn't)
         return result.item()
-    
+
     cpdef np.ndarray to_array(self, object py_attr_ids):
         """Given a list of M attribute IDs, export the tokens to a numpy
         `ndarray` of shape `(N, M)`, where `N` is the length of the document.
@@ -639,7 +639,7 @@ cdef class Span:
         else:
             return self.doc[root]
 
-    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, id=0):
+    def char_span(self, int start_idx, int end_idx, label=0, kb_id=0, vector=None, alignment_mode="strict", id=0):
         """Create a `Span` object from the slice `span.text[start : end]`.
 
         start (int): The index of the first character of the span.
@@ -649,11 +649,16 @@ cdef class Span:
         kb_id (uint64 or string):  An ID from a KB to capture the meaning of a named entity.
         vector (ndarray[ndim=1, dtype='float32']): A meaning representation of
             the span.
+        alignment_mode (str): How character indices are aligned to token
+            boundaries. Options: "strict" (character indices must be aligned
+            with token boundaries), "contract" (span of all tokens completely
+            within the character span), "expand" (span of all tokens at least
+            partially covered by the character span). Defaults to "strict".
         RETURNS (Span): The newly constructed object.
         """
         start_idx += self.c.start_char
         end_idx += self.c.start_char
-        return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector)
+        return self.doc.char_span(start_idx, end_idx, label=label, kb_id=kb_id, vector=vector, alignment_mode=alignment_mode)
 
     @property
     def conjuncts(self):