spaCy/spacy/lang/sl/punctuation.py
Luka Dragar b64243ed55
Updates to Slovenian language (#11162)
* Added examples for Slovene

* Update spacy/lang/sl/examples.py

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Corrected a typo in one of the sentences

* Updated support for Slovenian

* Some minor changes to corrections

* Added forint currency

* Corrected HYPHENS_PERMITTED regex and some formatting

* Minor changes

* Un-xfail tokenizer test

* Format

Co-authored-by: Luka Dragar <D20124481@mytudublin.ie>
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
2022-08-05 10:10:18 +02:00

85 lines
3.2 KiB
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

from ..char_classes import (
LIST_ELLIPSES,
LIST_ICONS,
HYPHENS,
LIST_PUNCT,
LIST_QUOTES,
CURRENCY,
UNITS,
PUNCT,
LIST_CURRENCY,
CONCAT_QUOTES,
)
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA
from ..char_classes import merge_chars
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
INCLUDE_SPECIAL = ["\\+", "\\/", "\\", "\\¯", "\\=", "\\×"] + HYPHENS.split("|")
_prefixes = INCLUDE_SPECIAL + BASE_TOKENIZER_PREFIXES
_suffixes = (
INCLUDE_SPECIAL
+ LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_ICONS
+ [
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[{al}{e}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
# split initials like J.K. Rowling
r"(?<=[A-Z]\.)(?:[A-Z].)",
]
)
# a list of all suffixes following a hyphen that are shouldn't split (eg. BTC-jev)
# source: Obeliks tokenizer - https://github.com/clarinsi/obeliks/blob/master/obeliks/res/TokRulesPart1.txt
CONCAT_QUOTES = CONCAT_QUOTES.replace("'", "")
HYPHENS_PERMITTED = (
"((a)|(evemu)|(evskega)|(i)|(jevega)|(jevska)|(jevskimi)|(jinemu)|(oma)|(ovim)|"
"(ovski)|(e)|(evi)|(evskem)|(ih)|(jevem)|(jevske)|(jevsko)|(jini)|(ov)|(ovima)|"
"(ovskih)|(em)|(evih)|(evskemu)|(ja)|(jevemu)|(jevskega)|(ji)|(jinih)|(ova)|"
"(ovimi)|(ovskim)|(ema)|(evim)|(evski)|(je)|(jevi)|(jevskem)|(jih)|(jinim)|"
"(ove)|(ovo)|(ovskima)|(ev)|(evima)|(evskih)|(jem)|(jevih)|(jevskemu)|(jin)|"
"(jinima)|(ovega)|(ovska)|(ovskimi)|(eva)|(evimi)|(evskim)|(jema)|(jevim)|"
"(jevski)|(jina)|(jinimi)|(ovem)|(ovske)|(ovsko)|(eve)|(evo)|(evskima)|(jev)|"
"(jevima)|(jevskih)|(jine)|(jino)|(ovemu)|(ovskega)|(u)|(evega)|(evska)|"
"(evskimi)|(jeva)|(jevimi)|(jevskim)|(jinega)|(ju)|(ovi)|(ovskem)|(evem)|"
"(evske)|(evsko)|(jeve)|(jevo)|(jevskima)|(jinem)|(om)|(ovih)|(ovskemu)|"
"(ovec)|(ovca)|(ovcu)|(ovcem)|(ovcev)|(ovcema)|(ovcih)|(ovci)|(ovce)|(ovcimi)|"
"(evec)|(evca)|(evcu)|(evcem)|(evcev)|(evcema)|(evcih)|(evci)|(evce)|(evcimi)|"
"(jevec)|(jevca)|(jevcu)|(jevcem)|(jevcev)|(jevcema)|(jevcih)|(jevci)|(jevce)|"
"(jevcimi)|(ovka)|(ovke)|(ovki)|(ovko)|(ovk)|(ovkama)|(ovkah)|(ovkam)|(ovkami)|"
"(evka)|(evke)|(evki)|(evko)|(evk)|(evkama)|(evkah)|(evkam)|(evkami)|(jevka)|"
"(jevke)|(jevki)|(jevko)|(jevk)|(jevkama)|(jevkah)|(jevkam)|(jevkami)|(timi)|"
"(im)|(ima)|(a)|(imi)|(e)|(o)|(ega)|(ti)|(em)|(tih)|(emu)|(tim)|(i)|(tima)|"
"(ih)|(ta)|(te)|(to)|(tega)|(tem)|(temu))"
)
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}0-9])(?:{h})(?!{hp}$)(?=[{a}])".format(
a=ALPHA, h=HYPHENS, hp=HYPHENS_PERMITTED
),
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
]
)
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes