Better error handling

This commit is contained in:
Gyorgy Orosz 2017-01-14 22:24:58 +01:00
parent b03a46792c
commit b4df202bfa
3 changed files with 5 additions and 8 deletions

View File

@ -2,7 +2,7 @@
from __future__ import unicode_literals
from ..language_data.punctuation import ALPHA_LOWER, LIST_ELLIPSES, QUOTES, ALPHA_UPPER, LIST_QUOTES, UNITS, \
CURRENCY, LIST_PUNCT, ALPHA
CURRENCY, LIST_PUNCT, ALPHA, _QUOTES
CURRENCY_SYMBOLS = r"\$ ¢ £ € ¥ ฿"
@ -35,7 +35,7 @@ TOKENIZER_INFIXES = (
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),
r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_QUOTES.replace("'", "").strip().replace(" ", "")),
]
)
__all__ = ["TOKENIZER_PREFIXES", "TOKENIZER_SUFFIXES", "TOKENIZER_INFIXES"]

View File

@ -63,7 +63,6 @@ EU.
F.
Fla.
Folyt.
Ford.
Fpk.
Főszerk.
G.
@ -184,7 +183,6 @@ Ty.
Tyr.
U.
Ui.
User.
Ut.
V.
VB.
@ -261,7 +259,6 @@ ea.
ed.
eff.
egyh.
el.
ell.
elv.
elvt.
@ -349,7 +346,7 @@ io.
ip.
ir.
irod.
is.
irod.
isk.
ism.
izr.
@ -604,7 +601,6 @@ zs.
ált.
ápr.
ásv.
át.
é.
ék.
ény.

View File

@ -36,6 +36,7 @@ HYPHEN_TESTS = [
('Lakik-e... van.', ['Lakik', '-e', '...', 'van', '.']),
('Lakik-e van?', ['Lakik', '-e', 'van', '?']),
('Lakik-elem van?', ['Lakik-elem', 'van', '?']),
('Az életbiztosításáról- egy.', ['Az', 'életbiztosításáról-', 'egy', '.']),
('Van lakik-elem.', ['Van', 'lakik-elem', '.']),
('A 7-es busz?', ['A', '7-es', 'busz', '?']),
('A 7-es?', ['A', '7-es', '?']),
@ -218,7 +219,7 @@ QUOTE_TESTS = [
('"Ime, hat"-ban irja.', ['"', 'Ime', ',', 'hat', '"', '-ban', 'irja', '.']),
('Az "Ime, hat".', ['Az', '"', 'Ime', ',', 'hat', '"', '.']),
('Egy 24"-os monitor.', ['Egy', '24"-os', 'monitor', '.']),
# ("A don't van.", ['A', "don't", 'van', '.'])
("A McDonald's van.", ['A', "McDonald's", 'van', '.'])
]
DOT_TESTS = [