From a053b1218e577b2471e0c20db8f0e7df3643229e Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 4 Jun 2017 20:18:20 -0500
Subject: [PATCH] Fix item counting during training

---
 spacy/gold.pyx | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/spacy/gold.pyx b/spacy/gold.pyx
index 6b07592cc..0e5db8329 100644
--- a/spacy/gold.pyx
+++ b/spacy/gold.pyx
@@ -177,7 +177,7 @@ class GoldCorpus(object):
             gold_tuples = read_json_file(loc)
             for item in gold_tuples:
                 yield item
-                i += 1
+                i += len(item[1])
                 if self.limit and i >= self.limit:
                     break
 
@@ -194,8 +194,12 @@ class GoldCorpus(object):
 
     def count_train(self):
         n = 0
+        i = 0
         for raw_text, paragraph_tuples in self.train_tuples:
-            n += len(paragraph_tuples)
+            n += sum([len(s[0][1]) for s in paragraph_tuples])
+            if self.limit and i >= self.limit:
+                break
+            i += len(paragraph_tuples)
         return n
 
     def train_docs(self, nlp, gold_preproc=False,