From 393a13d1af2a0c22a04643e61e7c4b95b653250b Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal@gmail.com>
Date: Fri, 9 Oct 2015 19:24:33 +1100
Subject: [PATCH] * Add unicode em dash to specials.json, so that we can
 control what POS tag it gets. This way we can prevent sentence boundary
 detection errors, to address Issue #130.

---
 lang_data/en/generate_specials.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lang_data/en/generate_specials.py b/lang_data/en/generate_specials.py
index 6ad503aec..e50cd77d4 100644
--- a/lang_data/en/generate_specials.py
+++ b/lang_data/en/generate_specials.py
@@ -133,6 +133,9 @@ hardcoded_specials = {
                 "Mt.": [{"F": "Mt.", "L": "Mount"}],
 
                 "''": [{"F": "''"}],
+
+                "—": [{"F": "—", "L": "--", "P": ":"}],
+
                 "Corp.": [{"F": "Corp."}],
                 "Inc.": [{"F": "Inc."}],
                 "Co.": [{"F": "Co."}],