Add German norm exceptions

spacy/lang/de/__init__.py

@@ -2,21 +2,25 @@
 from __future__ import unicode_literals
 
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .norm_exceptions import NORM_EXCEPTIONS
 from .tag_map import TAG_MAP
 from .stop_words import STOP_WORDS
 from .lemmatizer import LOOKUP
 from .syntax_iterators import SYNTAX_ITERATORS
 
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
+from ..norm_exceptions import BASE_NORMS
 from ...language import Language
 from ...lemmatizerlookup import Lemmatizer
-from ...attrs import LANG
-from ...util import update_exc
+from ...attrs import LANG, NORM
+from ...util import update_exc, add_lookups
 
 
 class GermanDefaults(Language.Defaults):
     lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
     lex_attr_getters[LANG] = lambda text: 'de'
+    lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
+                                         BASE_NORMS, NORM_EXCEPTIONS)
 
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
     tag_map = dict(TAG_MAP)

spacy/lang/de/norm_exceptions.py

@@ -0,0 +1,17 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+# Here we only want to include the absolute most common words. Otherwise,
+# this list would get impossibly long for German – especially considering the
+# old vs. new spelling rules, and all possible cases.
+
+
+_exc = {
+    "daß": "dass"
+}
+
+
+NORM_EXCEPTIONS = {}
+
+for string, norm in _exc.items():
+    NORM_EXCEPTIONS[string.title()] = norm