From e6fc4afb04a0e6f442793b6b420d4a0e381cd758 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 18 Dec 2016 15:48:00 +0100
Subject: [PATCH 1/2] Whitespace

---
 spacy/morphology.pyx | 1 +
 1 file changed, 1 insertion(+)

diff --git a/spacy/morphology.pyx b/spacy/morphology.pyx
index fbcbc2e66..fb6273753 100644
--- a/spacy/morphology.pyx
+++ b/spacy/morphology.pyx
@@ -140,6 +140,7 @@ cdef class Morphology:
         lemma = self.strings[lemma_string]
         return lemma
 
+
 IDS = {
     "Animacy_anim": Animacy_anim,
     "Animacy_inam": Animacy_inam,

From 44f4f008bd7df82647b215466c6b268847f53f44 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 18 Dec 2016 15:50:09 +0100
Subject: [PATCH 2/2] Wire up lemmatizer rules for English

---
 spacy/en/__init__.py | 3 +++
 spacy/language.py    | 4 +++-
 spacy/lemmatizer.py  | 9 ++++++---
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/spacy/en/__init__.py b/spacy/en/__init__.py
index 623585f7d..6e706db52 100644
--- a/spacy/en/__init__.py
+++ b/spacy/en/__init__.py
@@ -19,6 +19,8 @@ from ..language_data import EMOTICONS
 from .language_data import ORTH_ONLY
 from .language_data import get_time_exc
 
+from .lemma_rules import LEMMA_RULES
+
 
 TOKENIZER_EXCEPTIONS = dict(language_data.TOKENIZER_EXCEPTIONS)
 TOKENIZER_PREFIXES = tuple(language_data.TOKENIZER_PREFIXES)
@@ -47,3 +49,4 @@ class English(Language):
         infixes = TOKENIZER_INFIXES
         tag_map = TAG_MAP
         stop_words = STOP_WORDS
+        lemma_rules = LEMMA_RULES
diff --git a/spacy/language.py b/spacy/language.py
index 78dbac953..7d3d91846 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -38,7 +38,7 @@ class BaseDefaults(object):
         if nlp is None or nlp.path is None:
             return Lemmatizer({}, {}, {})
         else:
-            return Lemmatizer.load(nlp.path)
+            return Lemmatizer.load(nlp.path, rules=self.lemma_rules)
 
     @classmethod
     def create_vocab(cls, nlp=None):
@@ -159,6 +159,8 @@ class BaseDefaults(object):
 
     stop_words = set()
 
+    lemma_rules = {}
+
     lex_attr_getters = {
         attrs.LOWER: lambda string: string.lower(),
         attrs.NORM: lambda string: string,
diff --git a/spacy/lemmatizer.py b/spacy/lemmatizer.py
index a79ecb009..960467a0b 100644
--- a/spacy/lemmatizer.py
+++ b/spacy/lemmatizer.py
@@ -9,7 +9,7 @@ from .symbols import POS, NOUN, VERB, ADJ, PUNCT
 
 class Lemmatizer(object):
     @classmethod
-    def load(cls, path):
+    def load(cls, path, rules=None):
         index = {}
         exc = {}
         for pos in ['adj', 'noun', 'verb']:
@@ -25,8 +25,11 @@ class Lemmatizer(object):
                     exc[pos] = read_exc(file_)
             else:
                 exc[pos] = {}
-        with (path / 'vocab' / 'lemma_rules.json').open('r', encoding='utf8') as file_:
-            rules = json.load(file_)
+        if rules is None and (path / 'vocab' / 'lemma_rules.json').exists():
+            with (path / 'vocab' / 'lemma_rules.json').open('r', encoding='utf8') as file_:
+                rules = json.load(file_)
+        elif rules is None:
+            rules = {}
         return cls(index, exc, rules)
 
     def __init__(self, index, exceptions, rules):