mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 10:56:31 +03:00
3e8bc1272f
* add punctuation to grc Add support for special editorial punctuation that is common in ancient Greek texts. Ancient Greek texts, as found in digital and print form, have been largely edited by scholars. Restorations and improvements are normally marked with special characters that need to be handled properly by the tokenizer. * add unit tests * simplify regex * move generic quotes to char classes * rename unit test * fix regex Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com> Co-authored-by: svlandeg <svlandeg@github.com> Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com> Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
19 lines
1.3 KiB
Python
19 lines
1.3 KiB
Python
import pytest
|
|
|
|
|
|
# fmt: off
|
|
GRC_TOKEN_EXCEPTION_TESTS = [
|
|
("τὸ 〈τῆς〉 φιλοσοφίας ἔργον ἔνιοί φασιν ἀπὸ ⟦βαρβάρων⟧ ἄρξαι.", ["τὸ", "〈", "τῆς", "〉", "φιλοσοφίας", "ἔργον", "ἔνιοί", "φασιν", "ἀπὸ", "⟦", "βαρβάρων", "⟧", "ἄρξαι", "."]),
|
|
("τὴν δὲ τῶν Αἰγυπτίων φιλοσοφίαν εἶναι τοιαύτην περί τε †θεῶν† καὶ ὑπὲρ δικαιοσύνης.", ["τὴν", "δὲ", "τῶν", "Αἰγυπτίων", "φιλοσοφίαν", "εἶναι", "τοιαύτην", "περί", "τε", "†", "θεῶν", "†", "καὶ", "ὑπὲρ", "δικαιοσύνης", "."]),
|
|
("⸏πόσις δ' Ἐρεχθεύς ἐστί μοι σεσωσμένος⸏", ["⸏", "πόσις", "δ'", "Ἐρεχθεύς", "ἐστί", "μοι", "σεσωσμένος", "⸏"]),
|
|
("⸏ὔπνον ἴδωμεν⸎", ["⸏", "ὔπνον", "ἴδωμεν", "⸎"]),
|
|
]
|
|
# fmt: on
|
|
|
|
|
|
@pytest.mark.parametrize("text,expected_tokens", GRC_TOKEN_EXCEPTION_TESTS)
|
|
def test_grc_tokenizer(grc_tokenizer, text, expected_tokens):
|
|
tokens = grc_tokenizer(text)
|
|
token_list = [token.text for token in tokens if not token.is_space]
|
|
assert expected_tokens == token_list
|