From 92ae36f84e677393cd303f58035e8ad8e0d965b7 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 4 Jun 2017 21:53:39 +0200
Subject: [PATCH] Improve way noun chunks iterator is looked up

---
 spacy/language.py    | 4 +++-
 spacy/tokens/doc.pyx | 6 ++++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/spacy/language.py b/spacy/language.py
index 16acbe63b..e559e7c58 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -107,7 +107,8 @@ class BaseDefaults(object):
         'tags': lambda nlp, **cfg: [NeuralTagger(nlp.vocab, **cfg)],
         'dependencies': lambda nlp, **cfg: [
             NeuralDependencyParser(nlp.vocab, **cfg),
-            nonproj.deprojectivize],
+            nonproj.deprojectivize,
+        ],
         'entities': lambda nlp, **cfg: [NeuralEntityRecognizer(nlp.vocab, **cfg)],
     }
 
@@ -126,6 +127,7 @@ class BaseDefaults(object):
     lemma_index = {}
     morph_rules = {}
     lex_attr_getters = LEX_ATTRS
+    syntax_iterators = {}
 
 
 class Language(object):
diff --git a/spacy/tokens/doc.pyx b/spacy/tokens/doc.pyx
index daf36bb85..30b5f2f0b 100644
--- a/spacy/tokens/doc.pyx
+++ b/spacy/tokens/doc.pyx
@@ -26,7 +26,6 @@ from ..attrs cimport ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX, LENGTH, CLUST
 from ..attrs cimport LENGTH, POS, LEMMA, TAG, DEP, HEAD, SPACY, ENT_IOB, ENT_TYPE
 from ..attrs cimport SENT_START
 from ..parts_of_speech cimport CCONJ, PUNCT, NOUN, univ_pos_t
-from ..syntax.iterators import CHUNKERS
 from ..util import normalize_slice
 from ..compat import is_config
 from .. import about
@@ -65,6 +64,9 @@ cdef attr_t get_token_attr(const TokenC* token, attr_id_t feat_name) nogil:
     else:
         return Lexeme.get_struct_attr(token.lex, feat_name)
 
+def _get_chunker(lang):
+    cls = util.get_lang_class(lang)
+    return cls.Defaults.syntax_iterators.get('noun_chunks')
 
 cdef class Doc:
     """A sequence of Token objects. Access sentences and named entities, export
@@ -117,7 +119,7 @@ cdef class Doc:
         self.user_data = {}
         self._py_tokens = []
         self._vector = None
-        self.noun_chunks_iterator = CHUNKERS.get(self.vocab.lang)
+        self.noun_chunks_iterator = _get_chunker(self.vocab.lang)
         cdef unicode orth
         cdef bint has_space
         if orths_and_spaces is None and words is not None: