From 41a90a7fbb7927f4d0c5a5d22f9669cb91e87347 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Thu, 3 Nov 2016 00:03:34 +0100
Subject: [PATCH] Add tokenizer exception for 'Ph.D.', to fix 592.

---
 spacy/en/language_data.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/spacy/en/language_data.py b/spacy/en/language_data.py
index a3e63d0c4..504103566 100644
--- a/spacy/en/language_data.py
+++ b/spacy/en/language_data.py
@@ -112,6 +112,10 @@ TOKENIZER_INFIXES = (r'''\.\.\.+ (?<=[a-z])\.(?=[A-Z]) (?<=[a-zA-Z])-(?=[a-zA-z]
 
 
 TOKENIZER_EXCEPTIONS = {
+  "Ph.D.": [
+    {
+        "F": "Ph.D."
+    }],
   "d.": [
     {
       "F": "d."