mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 05:37:03 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
62 lines
2.1 KiB
Python
62 lines
2.1 KiB
Python
from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from ..char_classes import ALPHA, merge_chars, split_chars, _currency, _units
|
|
|
|
|
|
_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" USD 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 = merge_chars(_units)
|
|
CURRENCY = merge_chars(_currency)
|
|
HTML_PREFIX = r"<(b|strong|i|em|p|span|div|br)\s?/>|<a([^>]+)>"
|
|
HTML_SUFFIX = r"</(b|strong|i|em|p|span|div|a)>"
|
|
MONTHS = merge_chars(_months)
|
|
LIST_CURRENCY = split_chars(_currency)
|
|
|
|
_prefixes = list(TOKENIZER_PREFIXES)
|
|
_prefixes.remove("#") # hashtag
|
|
_prefixes = _prefixes + LIST_CURRENCY + [HTML_PREFIX] + ["/", "—"]
|
|
|
|
_suffixes = (
|
|
TOKENIZER_SUFFIXES
|
|
+ [r"\-[Nn]ya", "-[KkMm]u", "[—-]"]
|
|
+ [
|
|
# disabled: variable width currency variable
|
|
# r"(?<={c})(?:[0-9]+)".format(c=CURRENCY),
|
|
r"(?<=[0-9])(?:{u})".format(u=UNITS),
|
|
r"(?<=[0-9])%",
|
|
# disabled: variable width HTML_SUFFIX variable
|
|
# 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),
|
|
# disabled: variable width units variable
|
|
# r"(?<={u})[\/-](?=[0-9])".format(u=UNITS),
|
|
# disabled: variable width months variable
|
|
# 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
|
|
TOKENIZER_SUFFIXES = _suffixes
|
|
TOKENIZER_INFIXES = _infixes
|