From 693971dd8fda2ffcce5c28d9d14381cae5d85780 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Tue, 27 Mar 2018 22:25:40 +0200
Subject: [PATCH] Improve error message if token text is empty string (see
 #2101)

---
 spacy/tokens/doc.pyx | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx
index 07f1f3336..4bb1db46f 100644
--- a/spacy/tokens/doc.pyx
+++ b/spacy/tokens/doc.pyx
@@ -557,7 +557,8 @@ cdef class Doc:
             t.idx = (t-1).idx + (t-1).lex.length + (t-1).spacy
         t.l_edge = self.length
         t.r_edge = self.length
-        assert t.lex.orth != 0
+        if t.lex.orth == 0:
+            raise ValueError("Invalid token: empty string ('')")
         t.spacy = has_space
         self.length += 1
         return t.idx + t.lex.length + t.spacy