Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

added hashtag rule and fixed currency rules

This commit is contained in:
Jim Geovedi 2017-07-30 21:23:28 +07:00
parent e9af79a803
commit bb08d696f9
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lang/id/punctuation.py
View File

@ -11,7 +11,7 @@ _units = (_units + 's bit Gbps Mbps mbps Kbps kbps ƒ ppi px '
'ratus rb ribu ribuan '
'juta jt jutaan mill?iar million bil[l]?iun bilyun billion '
)
_currency = (_currency + r'Rp IDR RMB SGD S\$ ')
_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 '
@ -25,7 +25,7 @@ HTML_SUFFIX = r'</(b|strong|i|em|p|span|div|a)>'
MONTHS = merge_chars(_months)
LIST_CURRENCY = split_chars(_currency)
TOKENIZER_PREFIXES.remove('#') # hashtag
_prefixes = TOKENIZER_PREFIXES + LIST_CURRENCY + [HTML_PREFIX] + ['/', '—']
_suffixes = TOKENIZER_SUFFIXES + [r'\-[Nn]ya', '-[KkMm]u', '[—-]'] + [