Merge branch 'develop' of https://github.com/explosion/spaCy into develop

spacy/lang/ja/__init__.py

@@ -33,8 +33,7 @@ class Japanese(Language):
     Defaults = JapaneseDefaults
 
     def make_doc(self, text):
-        words = self.tokenizer(text)
-        return Doc(self.vocab, words=words, spaces=[False]*len(words))
+        return self.tokenizer(text)
 
 
 __all__ = ['Japanese']

spacy/lang/ja/examples.py

@@ -0,0 +1,18 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.ja.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+sentences = [
+    'アップルがイギリスの新興企業を１０億ドルで購入を検討',
+    '自動運転車の損害賠償責任、自動車メーカーに一定の負担を求める',
+    '歩道を走る自動配達ロボ、サンフランシスコ市が走行禁止を検討',
+    'ロンドンはイギリスの大都市です。'
+]

spacy/lang/zh/examples.py

@@ -0,0 +1,18 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.zh.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+
+sentences = [
+    "蘋果公司正考量用一億元買下英國的新創公司",
+    "自駕車將保險責任歸屬轉移至製造商",
+    "舊金山考慮禁止送貨機器人在人行道上行駛",
+    "倫敦是英國的大城市"
+]