From 092ce4648e959453cbc25843f7d9afcb234b540e Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Fri, 25 Sep 2020 22:20:44 +0200
Subject: [PATCH] Make DocBin output stable data (set iteration)

---
 spacy/tokens/_serialize.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/spacy/tokens/_serialize.py b/spacy/tokens/_serialize.py
index c9a20f6c0..2d4e9af9d 100644
--- a/spacy/tokens/_serialize.py
+++ b/spacy/tokens/_serialize.py
@@ -171,7 +171,7 @@ class DocBin:
             "tokens": tokens.tobytes("C"),
             "spaces": spaces.tobytes("C"),
             "lengths": numpy.asarray(lengths, dtype="int32").tobytes("C"),
-            "strings": list(self.strings),
+            "strings": list(sorted(self.strings)),
             "cats": self.cats,
             "flags": self.flags,
         }