spaCy/spacy/lang/tl/tokenizer_exceptions.py
Ines Montani db55577c45
Drop Python 2.7 and 3.5 (#4828)
* 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]
2019-12-22 01:53:56 +01:00

18 lines
689 B
Python

from ...symbols import ORTH, LEMMA
_exc = {
"tayo'y": [{ORTH: "tayo", LEMMA: "tayo"}, {ORTH: "'y", LEMMA: "ay"}],
"isa'y": [{ORTH: "isa", LEMMA: "isa"}, {ORTH: "'y", LEMMA: "ay"}],
"baya'y": [{ORTH: "baya", LEMMA: "bayan"}, {ORTH: "'y", LEMMA: "ay"}],
"sa'yo": [{ORTH: "sa", LEMMA: "sa"}, {ORTH: "'yo", LEMMA: "iyo"}],
"ano'ng": [{ORTH: "ano", LEMMA: "ano"}, {ORTH: "'ng", LEMMA: "ang"}],
"siya'y": [{ORTH: "siya", LEMMA: "siya"}, {ORTH: "'y", LEMMA: "ay"}],
"nawa'y": [{ORTH: "nawa", LEMMA: "nawa"}, {ORTH: "'y", LEMMA: "ay"}],
"papa'no": [{ORTH: "papa'no", LEMMA: "papaano"}],
"'di": [{ORTH: "'di", LEMMA: "hindi"}],
}
TOKENIZER_EXCEPTIONS = _exc