From 12292b36f97d9a0a510eb982cda104cd0d63499f Mon Sep 17 00:00:00 2001
From: d0ngw <agile.java@gmail.com>
Date: Fri, 9 May 2025 18:42:08 +0800
Subject: [PATCH] fix: match hyphenated words to lemmas in index_table (e.g.
 "co-authored" -> "co-author")

---
 spacy/pipeline/lemmatizer.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/spacy/pipeline/lemmatizer.py b/spacy/pipeline/lemmatizer.py
index 09e501595..0580b7b61 100644
--- a/spacy/pipeline/lemmatizer.py
+++ b/spacy/pipeline/lemmatizer.py
@@ -241,7 +241,10 @@ class Lemmatizer(Pipe):
                 if not form:
                     pass
                 elif form in index or not form.isalpha():
-                    forms.append(form)
+                    if form in index:
+                        forms.insert(0, form)
+                    else:
+                        forms.append(form)
                 else:
                     oov_forms.append(form)
         # Remove duplicates but preserve the ordering of applied "rules"