* 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.

2015-10-09 19:24:33 +11:00 · 2015-10-09 19:24:33 +11:00 · 393a13d1af
parent 1490feda29
commit 393a13d1af
1 changed files with 3 additions and 0 deletions
--- 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."}],