Reorganise Bengali punctuation rules

spacy/lang/bn/punctuation.py

@@ -1,45 +1,33 @@
 # coding: utf8
 from __future__ import unicode_literals
 
+from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, UNITS
+from ..char_classes import ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS, QUOTES
 
 
-CURRENCY_SYMBOLS = r"\$ ¢ £ € ¥ ฿ ৳"
+_currency = r"\$|¢|£|€|¥|฿|৳"
+_quotes = QUOTES.replace("'", '')
+_list_punct = LIST_PUNCT + '। ॥'.strip().split()
 
-_PUNCT = '। ॥'
 
-LIST_PUNCT.extend(_PUNCT.strip().split())
+_prefixes = ([r'\+'] + _list_punct + LIST_ELLIPSES + LIST_QUOTES)
 
-TOKENIZER_PREFIXES = (
-    [r'\+'] +
-    LIST_PUNCT +
-    LIST_ELLIPSES +
-    LIST_QUOTES
-)
-
-TOKENIZER_SUFFIXES = (
-    LIST_PUNCT +
-    LIST_ELLIPSES +
-    LIST_QUOTES +
-    [
-        r'(?<=[0-9])\+',
+_suffixes = (_list_punct + LIST_ELLIPSES + LIST_QUOTES +
+             [r'(?<=[0-9])\+',
               r'(?<=°[FfCcKk])\.',
-        r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
-        r'(?<=[0-9])(?:{u})'.format(u=UNITS),
-        r'(?<=[{al}{p}{c}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES, c=CURRENCY_SYMBOLS),
-        r'(?<=[{al})])-e'.format(al=ALPHA_LOWER)
-    ]
-)
+              r'(?<=[0-9])(?:{})'.format(_currency),
+              r'(?<=[0-9])(?:{})'.format(UNITS),
+              r'(?<=[{}(?:{})])\.'.format('|'.join([ALPHA_LOWER, r'%²\-\)\]\+', QUOTES]), _currency)])
 
-TOKENIZER_INFIXES = (
-    LIST_ELLIPSES +
-    [
-        r'(?<=[{al}])\.(?=[{au}])'.format(al=ALPHA_LOWER, au=ALPHA_UPPER),
+_infixes = (LIST_ELLIPSES +
+            [r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
              r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
              r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
              r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA),
              r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
-        r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_QUOTES.replace("'", "").strip().replace(" ", "")),
-    ]
-)
-from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, UNITS
-from ..char_classes import ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS, QUOTES
+             r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_quotes)])
+
+
+TOKENIZER_PREFIXES = _prefixes
+TOKENIZER_SUFFIXES = _suffixes
+TOKENIZER_INFIXES = _infixes