Reorganise French punctuation rules

spacy/lang/fr/punctuation.py

@@ -1,29 +1,29 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from ..char_classes import TOKENIZER_INFIXES, LIST_PUNCT LIST_ELLIPSES
-from ..char_classes import LIST_QUOTES, CURRENCY, QUOTES, UNITS
-from ..char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER
+from ..punctuation import TOKENIZER_INFIXES
+from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
+from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
 
 
 ELISION = " ' ’ ".strip().replace(' ', '').replace('\n', '')
-HYPHENS = r"""- – — ‐ ‑""".strip().replace(' ', '').replace('\n', '')
+HYPHENS = r"- – — ‐ ‑".strip().replace(' ', '').replace('\n', '')
 
 
-TOKENIZER_SUFFIXES = (
-    LIST_PUNCT +
-    LIST_ELLIPSES +
-    LIST_QUOTES +
-    [
-        r'(?<=[0-9])\+',
-        r'(?<=°[FfCcKk])\.',  # 4°C. -> ["4°C", "."]
-        r'(?<=[0-9])°[FfCcKk]',  # 4°C -> ["4", "°C"]
-        r'(?<=[0-9])%',  # 4% -> ["4", "%"]
-        r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
-        r'(?<=[0-9])(?:{u})'.format(u=UNITS),
-        r'(?<=[0-9{al}{p}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES),
-        r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER)])
+_suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
+             [r'(?<=[0-9])\+',
+              r'(?<=°[FfCcKk])\.',  # 4°C. -> ["4°C", "."]
+              r'(?<=[0-9])°[FfCcKk]',  # 4°C -> ["4", "°C"]
+              r'(?<=[0-9])%',  # 4% -> ["4", "%"]
+              r'(?<=[0-9])(?:{})'.format(CURRENCY),
+              r'(?<=[0-9])(?:{})'.format(UNITS),
+              r'(?<=[0-9{}{}(?:{})])\.'.format(ALPHA_LOWER, r'%²\-\)\]\+', QUOTES),
+              r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER)])
 
 
-TOKENIZER_INFIXES += [
-    r'(?<=[{a}][{el}])(?=[{a}])'.format(a=ALPHA, el=ELISION)]
+_infixes = (TOKENIZER_INFIXES +
+            [r'(?<=[{a}][{el}])(?=[{a}])'.format(a=ALPHA, el=ELISION)])
+
+
+TOKENIZER_SUFFIXES = _suffixes
+TOKENIZER_INFIXES = _infixes