From 897d0841bed5e0637aca7dec7744bedc06b54fae Mon Sep 17 00:00:00 2001
From: Yiqing-Zhou <40547184+Yiqing-Zhou@users.noreply.github.com>
Date: Mon, 22 Jul 2019 20:49:09 +0800
Subject: [PATCH] read().splitlines() -> readlines()

splitlines() does not work as what we expect here for bert-base-chinese because there is a '\u2028' (unicode line seperator) token in vocab file. Value of '\u2028'.splitlines() is ['', ''].
Perhaps we should use readlines() instead.
---
 pytorch_transformers/tokenization_bert.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/pytorch_transformers/tokenization_bert.py b/pytorch_transformers/tokenization_bert.py
index f1e900caaf..1ca758eda5 100644
--- a/pytorch_transformers/tokenization_bert.py
+++ b/pytorch_transformers/tokenization_bert.py
@@ -67,10 +67,9 @@ def load_vocab(vocab_file):
     """Loads a vocabulary file into a dictionary."""
     vocab = collections.OrderedDict()
     with open(vocab_file, "r", encoding="utf-8") as reader:
-        tokens = reader.read().splitlines()
+        tokens = reader.readlines()
     for index, token in enumerate(tokens):
         vocab[token] = index
-        index += 1
     return vocab