explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

removed -el from suffix rules

Browse Source
This commit is contained in:
Jim Geovedi 2017-07-26 19:28:38 +07:00
parent 6eee7a7411
commit f288964441
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
spacy/lang/id/punctuation.py
View File

@ -12,9 +12,10 @@ _units = (_units + 's bit Gbps Mbps mbps Kbps kbps ƒ ppi px '
'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 ')
_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 = merge_chars(_units)
@ -27,7 +28,7 @@ LIST_CURRENCY = split_chars(_currency)
_prefixes = TOKENIZER_PREFIXES + LIST_CURRENCY + [HTML_PREFIX] + ['/', '—']
_suffixes = TOKENIZER_SUFFIXES + [r'\-[Nn]ya', '-[KkMm]u' '-el', '[—-]'] + [
_suffixes = TOKENIZER_SUFFIXES + [r'\-[Nn]ya', '-[KkMm]u', '[—-]'] + [
r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
r'(?<=[0-9])(?:{u})'.format(u=UNITS),
r'(?<=[0-9])%',