From 0e71bd973fa39e9b39f2ff4e023a42cde2064ff7 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 15 Apr 2022 15:34:58 +0200
Subject: [PATCH] Return doc offsets in Matcher on spans (#10576)

The returned match offsets were only adjusted for `as_spans`, not
generally. Because the `on_match` callbacks are always applied to the
doc, the `Matcher` matches on spans should consistently use the doc
offsets.
---
 spacy/matcher/matcher.pyx               |  7 ++++---
 spacy/tests/matcher/test_matcher_api.py | 13 ++++++++++---
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/spacy/matcher/matcher.pyx b/spacy/matcher/matcher.pyx
index 745d7cf43..863bd198c 100644
--- a/spacy/matcher/matcher.pyx
+++ b/spacy/matcher/matcher.pyx
@@ -252,6 +252,10 @@ cdef class Matcher:
         # non-overlapping ones this `match` can be either (start, end) or
         # (start, end, alignments) depending on `with_alignments=` option.
         for key, *match in matches:
+            # Adjust span matches to doc offsets
+            if isinstance(doclike, Span):
+                match[0] += doclike.start
+                match[1] += doclike.start
             span_filter = self._filter.get(key)
             if span_filter is not None:
                 pairs = pairs_by_id.get(key, [])
@@ -282,9 +286,6 @@ cdef class Matcher:
         if as_spans:
             final_results = []
             for key, start, end, *_ in final_matches:
-                if isinstance(doclike, Span):
-                    start += doclike.start
-                    end += doclike.start
                 final_results.append(Span(doc, start, end, label=key))
         elif with_alignments:
             # convert alignments List[Dict[str, int]] --> List[int]
diff --git a/spacy/tests/matcher/test_matcher_api.py b/spacy/tests/matcher/test_matcher_api.py
index c02d65cdf..9d401382f 100644
--- a/spacy/tests/matcher/test_matcher_api.py
+++ b/spacy/tests/matcher/test_matcher_api.py
@@ -591,9 +591,16 @@ def test_matcher_span(matcher):
     doc = Doc(matcher.vocab, words=text.split())
     span_js = doc[:3]
     span_java = doc[4:]
-    assert len(matcher(doc)) == 2
-    assert len(matcher(span_js)) == 1
-    assert len(matcher(span_java)) == 1
+    doc_matches = matcher(doc)
+    span_js_matches = matcher(span_js)
+    span_java_matches = matcher(span_java)
+    assert len(doc_matches) == 2
+    assert len(span_js_matches) == 1
+    assert len(span_java_matches) == 1
+
+    # match offsets always refer to the doc
+    assert doc_matches[0] == span_js_matches[0]
+    assert doc_matches[1] == span_java_matches[0]
 
 
 def test_matcher_as_spans(matcher):