Make DocBin output stable data (set iteration)

2020-09-25 22:20:44 +02:00 · 2020-09-25 22:20:44 +02:00 · 092ce4648e
parent 26afd3bd90
commit 092ce4648e
1 changed files with 1 additions and 1 deletions
--- 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,
        }