From d67b0f196a2fc09479099a52d64462527c83a647 Mon Sep 17 00:00:00 2001
From: adrianeboyd <adrianeboyd@gmail.com>
Date: Wed, 13 Nov 2019 21:22:18 +0100
Subject: [PATCH] Fix initialization of token mappings in new align (#4640)

Initialize all values in `a2b` and `b2a` since `numpy.empty()` otherwise
result unspecified integers.
---
 spacy/gold.pyx | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/spacy/gold.pyx b/spacy/gold.pyx
index ea3589ea5..d79bc8205 100644
--- a/spacy/gold.pyx
+++ b/spacy/gold.pyx
@@ -129,6 +129,8 @@ def align(tokens_a, tokens_b):
     cost = 0
     a2b = numpy.empty(len(tokens_a), dtype="i")
     b2a = numpy.empty(len(tokens_b), dtype="i")
+    a2b.fill(-1)
+    b2a.fill(-1)
     a2b_multi = {}
     b2a_multi = {}
     i = 0
@@ -138,7 +140,6 @@ def align(tokens_a, tokens_b):
     while i < len(tokens_a) and j < len(tokens_b):
         a = tokens_a[i][offset_a:]
         b = tokens_b[j][offset_b:]
-        a2b[i] =  b2a[j] = -1
         if a == b:
             if offset_a == offset_b == 0:
                 a2b[i] = j