From 27f988b1671854e2c08b6c6a5653eeb2f38bc3d6 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Tue, 15 Sep 2015 14:41:48 +1000
Subject: [PATCH] * Remove the vectors option to Vocab, preferring to either
 load vectors from disk, or set them on the Lexeme objects.

---
 spacy/language.py | 13 +++----------
 spacy/vocab.pyx   |  7 +++----
 2 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/spacy/language.py b/spacy/language.py
index c3a938458..ecce54e7a 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -137,21 +137,14 @@ class Language(object):
         return path.join(path.dirname(__file__), 'data')
 
     @classmethod
-    def default_vectors(cls, data_dir):
-        return None
-
-    @classmethod
-    def default_vocab(cls, data_dir=None, get_lex_attr=None, vectors=None):
+    def default_vocab(cls, data_dir=None, get_lex_attr=None):
         if data_dir is None:
             data_dir = cls.default_data_dir()
-        if vectors is None:
-            vectors = cls.default_vectors(data_dir)
         if get_lex_attr is None:
             get_lex_attr = cls.default_lex_attrs(data_dir)
         return Vocab.from_dir(
                 path.join(data_dir, 'vocab'),
-                get_lex_attr=get_lex_attr,
-                vectors=vectors)
+                get_lex_attr=get_lex_attr)
 
     @classmethod
     def default_tokenizer(cls, vocab, data_dir):
@@ -214,7 +207,7 @@ class Language(object):
         self.entity = entity
         self.matcher = matcher
 
-    def __call__(self, text, tag=True, parse=True, entity=True, merge_mwes=False):
+    def __call__(self, text, tag=True, parse=True, entity=True):
         """Apply the pipeline to some text.  The text can span multiple sentences,
         and can contain arbtrary whitespace.  Alignment into the original string
         is preserved.
diff --git a/spacy/vocab.pyx b/spacy/vocab.pyx
index 7a07bde7a..210fa8426 100644
--- a/spacy/vocab.pyx
+++ b/spacy/vocab.pyx
@@ -56,11 +56,10 @@ cdef class Vocab:
 
         self.load_lexemes(path.join(data_dir, 'strings.txt'), path.join(data_dir, 'lexemes.bin'))
         if vectors is None and path.exists(path.join(data_dir, 'vec.bin')):
-            self.repvec_length = self.load_rep_vectors(path.join(data_dir, 'vec.bin'))
+            self.vectors_length = self.load_vectors(path.join(data_dir, 'vec.bin'))
         return self
 
-    def __init__(self, get_lex_attr=None, tag_map=None, vectors=None, lemmatizer=None,
-                 serializer_freqs=None):
+    def __init__(self, get_lex_attr=None, tag_map=None, lemmatizer=None, serializer_freqs=None):
         if tag_map is None:
             tag_map = {}
         if lemmatizer is None:
@@ -262,7 +261,7 @@ cdef class Vocab:
             i += 1
         fp.close()
 
-    def load_rep_vectors(self, loc):
+    def load_vectors(self, loc):
         cdef CFile file_ = CFile(loc, b'rb')
         cdef int32_t word_len
         cdef int32_t vec_len