Add support for elision in French

spacy/fr/__init__.py

@@ -7,6 +7,7 @@ from ..language import Language
 from ..attrs import LANG
 
 from .language_data import *
+from .punctuation import TOKENIZER_INFIXES
 
 
 class French(Language):
@@ -18,3 +19,4 @@ class French(Language):
 
         tokenizer_exceptions = TOKENIZER_EXCEPTIONS
         stop_words = STOP_WORDS
+        infixes = tuple(TOKENIZER_INFIXES)

spacy/fr/punctuation.py

@@ -0,0 +1,16 @@
+# encoding: utf8
+
+from __future__ import unicode_literals
+
+from ..language_data.punctuation import ALPHA, TOKENIZER_INFIXES
+
+
+_ELISION = " ' ’ "
+ELISION = _ELISION.strip().replace(' ', '').replace('\n', '')
+
+TOKENIZER_INFIXES += [
+    r'(?<=[{a}][{el}])(?=[{a}])'.format(a=ALPHA, el=ELISION),
+]
+
+
+__all__ = ["TOKENIZER_SUFFIXES", "TOKENIZER_INFIXES"]