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

README.rst

@@ -4,12 +4,10 @@ spaCy: Industrial-strength NLP
 spaCy is a library for advanced natural language processing in Python and
 Cython. spaCy is built on  the very latest research, but it isn't researchware.
 It was designed from day one to be used in real products. spaCy currently supports
-English, German and French, as well as tokenization for Spanish, Italian,
-Portuguese, Dutch, Swedish, Finnish, Norwegian, Hungarian, Bengali, Hebrew,
-Chinese and Japanese. It's commercial open-source software, released under the
-MIT license.
-
-📊 **Help us improve the library!** `Take the spaCy user survey <https://survey.spacy.io>`_.
+English, German, French and Spanish, as well as tokenization for Italian,
+Portuguese, Dutch, Swedish, Finnish, Norwegian, Danish, Hungarian, Polish,
+Bengali, Hebrew, Chinese and Japanese. It's commercial open-source software,
+released under the MIT license.
 
 💫 **Version 1.8 out now!** `Read the release notes here. <https://github.com/explosion/spaCy/releases/>`_
 
@@ -85,7 +83,7 @@ Features
 * GIL-free **multi-threading**
 * Efficient binary serialization
 * Easy **deep learning** integration
-* Statistical models for **English** and **German**
+* Statistical models for **English**, **German**, **French** and **Spanish**
 * State-of-the-art speed
 * Robust, rigorously evaluated accuracy
 
@@ -197,7 +195,7 @@ To load a model, use ``spacy.load()`` with the model's shortcut link:
 .. code:: python
 
     import spacy
-    nlp = spacy.load('en_default')
+    nlp = spacy.load('en')
     doc = nlp(u'This is a sentence.')
 
 If you've installed a model via pip, you can also ``import`` it directly and
@@ -313,7 +311,7 @@ and ``--model`` are optional and enable additional tests:
     # make sure you are using recent pytest version
     python -m pip install -U pytest
 
-    python -m pytest <spacy-directory> --vectors --models --slow
+    python -m pytest <spacy-directory>
 
 🛠 Changelog
 ============

spacy/tests/lang/en/test_noun_chunks.py

@@ -1,15 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-from ...attrs import HEAD, DEP
-from ...symbols import nsubj, dobj, amod, nmod, conj, cc, root
-from ...syntax.iterators import english_noun_chunks
-from ..util import get_doc
+from ....attrs import HEAD, DEP
+from ....symbols import nsubj, dobj, amod, nmod, conj, cc, root
+from ....lang.en.syntax_iterators import SYNTAX_ITERATORS
+from ...util import get_doc
 
 import numpy
 
 
-def test_doc_noun_chunks_not_nested(en_tokenizer):
+def test_en_noun_chunks_not_nested(en_tokenizer):
     text = "Peter has chronic command and control issues"
     heads = [1, 0, 4, 3, -1, -2, -5]
     deps = ['nsubj', 'ROOT', 'amod', 'nmod', 'cc', 'conj', 'dobj']
@@ -21,7 +21,7 @@ def test_doc_noun_chunks_not_nested(en_tokenizer):
         [HEAD, DEP],
         numpy.asarray([[1, nsubj], [0, root], [4, amod], [3, nmod], [-1, cc],
                        [-2, conj], [-5, dobj]], dtype='uint64'))
-    tokens.noun_chunks_iterator = english_noun_chunks
+    tokens.noun_chunks_iterator = SYNTAX_ITERATORS['noun_chunks']
     word_occurred = {}
     for chunk in tokens.noun_chunks:
         for word in chunk:

website/docs/usage/v2.jade

@@ -251,7 +251,7 @@ p
         +cell #[code lang.xx.lex_attrs]
 
     +row
-        +cell #[code syntax.syntax_iterators]
+        +cell #[code syntax.iterators]
         +cell #[code lang.xx.syntax_iterators]
 
     +row