From c1f3fe99feeb926b2b8a502110cb9e83cc593ca8 Mon Sep 17 00:00:00 2001
From: Jim Geovedi <jim@geovedi.com>
Date: Mon, 24 Jul 2017 13:57:21 +0700
Subject: [PATCH] updated punctuation rules

---
 spacy/lang/id/punctuation.py | 40 +++++++++++++++++++++++++-----------
 1 file changed, 28 insertions(+), 12 deletions(-)

diff --git a/spacy/lang/id/punctuation.py b/spacy/lang/id/punctuation.py
index 68af3e126..85da34074 100644
--- a/spacy/lang/id/punctuation.py
+++ b/spacy/lang/id/punctuation.py
@@ -2,33 +2,49 @@
 from __future__ import unicode_literals
 
 from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
-from ..char_classes import merge_chars, split_chars, _currency
+from ..char_classes import merge_chars, split_chars, _currency, _units
 from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES
-from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
+from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER, HYPHENS
+
+_units = (_units + 's bit Gbps Mbps mbps Kbps kbps ƒ ppi px '
+          'Hz kHz MHz GHz mAh '
+          'ratus rb ribu ribuan '
+          'juta jt jutaan mill?iar million bil[l]?iun bilyun billion '
+          )
+_currency = (_currency + r'Rp IDR RMB SGD S\$ ')
+_months = ('Januari Februari Maret April Mei Juni Juli Agustus September Oktober November Desember '
+           'January February March May June July August October December '
+           'Jan Feb Mar Jun Jul Aug Sept Oct Okt Nov Des ')
 
-_units = ('s bit Gbps Mbps mbps Kbps kbps ƒ '
-          'kHz MHz GHz mAh ')
-_currency = r'Rp IDR RMB SGD S\$' + _currency
 
 UNITS = merge_chars(_units)
 CURRENCY = merge_chars(_currency)
 HTML_PREFIX = r'<(b|strong|i|em|p|span|div|br)\s?/>'
 HTML_SUFFIX = r'</(b|strong|i|em|p|span|div)>'
+MONTHS = merge_chars(_months)
+LIST_CURRENCY = split_chars(_currency)
 
-_prefixes = TOKENIZER_PREFIXES + split_chars(_currency) + [HTML_PREFIX] + ['ke-']
 
-_suffixes = TOKENIZER_SUFFIXES + [
-        r'(?<=[0-9])(?:{})'.format(CURRENCY),
-        r'(?<=[0-9])(?:{})'.format(UNITS),
+_prefixes = TOKENIZER_PREFIXES + LIST_CURRENCY + [HTML_PREFIX] + ['[Kk]e-', '/', '—']
+
+_suffixes = TOKENIZER_SUFFIXES + [r'\-[Nn]ya', '—'] + [
+        r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
+        r'(?<=[0-9])(?:{u})'.format(u=UNITS),
         r'(?<=[0-9])%',
         r'(?<=[0-9{a}]{h})(?:[\.,:-])'.format(a=ALPHA, h=HTML_SUFFIX),
         r'(?<=[0-9{a}])(?:{h})'.format(a=ALPHA, h=HTML_SUFFIX),
     ]
 
 _infixes = TOKENIZER_INFIXES + [
-    r'(?<=[0-9])([\\/])(?=[0-9%-])',
-    r'(?<=[0-9])(%)(?=[{a}0-9/])'.format(a=ALPHA),
-    r'(?<=[0-9]{u})\/(?=[0-9])'.format(u=UNITS),
+    r'(?<=[0-9])[\\/](?=[0-9%-])',
+    r'(?<=[0-9])%(?=[{a}0-9/])'.format(a=ALPHA),
+    r'(?<={u})[\/-](?=[0-9])'.format(u=UNITS),
+    r'(?<={m})[\/-](?=[0-9])'.format(m=MONTHS),
+    r'(?<=[0-9\)][\.,])"(?=[0-9])',
+    r'(?<=[{a}\)][\.,\'])["—](?=[{a}])'.format(a=ALPHA),
+    r'(?<=[{a}])-(?=[0-9])'.format(a=ALPHA),
+    r'(?<=[0-9])-(?=[{a}])'.format(a=ALPHA),
+    r'(?<=[{a}])[\/-](?={c}{a})'.format(a=ALPHA, c=CURRENCY),
 ]
 
 TOKENIZER_PREFIXES = _prefixes