mirror of
https://github.com/unshackle-dl/unshackle.git
synced 2026-11-18 06:55:07 +00:00
feat(dl): exclude languages with a - prefix on -l, -vl, -al, -sl and -fsl
This commit is contained in:
@@ -7,7 +7,13 @@ import click
|
||||
import pytest
|
||||
|
||||
from unshackle.core.tracks.subtitle import Subtitle
|
||||
from unshackle.core.utils.click_types import QUALITY_LIST, SLOW_DELAY_RANGE, SeasonRange, SubtitleCodecChoice
|
||||
from unshackle.core.utils.click_types import (
|
||||
LANGUAGE_RANGE,
|
||||
QUALITY_LIST,
|
||||
SLOW_DELAY_RANGE,
|
||||
SeasonRange,
|
||||
SubtitleCodecChoice,
|
||||
)
|
||||
|
||||
choice = SubtitleCodecChoice(Subtitle.Codec)
|
||||
|
||||
@@ -60,6 +66,23 @@ def test_slow_delay_range_accepts_bool(value, expected):
|
||||
assert SLOW_DELAY_RANGE.convert(value, None, None) == expected
|
||||
|
||||
|
||||
# --- LanguageRange ----------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"value,expected",
|
||||
[
|
||||
("all,-es", ["all", "-es"]),
|
||||
("-es", ["-es"]),
|
||||
("all, -es ; -fr", ["all", "-es", "-fr"]),
|
||||
(["all", "-es"], ["all", "-es"]),
|
||||
],
|
||||
)
|
||||
def test_language_range_passes_exclusion_tokens_through(value, expected):
|
||||
"""The '-' prefix is resolved at filter time, so the type must keep the token intact."""
|
||||
assert LANGUAGE_RANGE.convert(value) == expected
|
||||
|
||||
|
||||
# --- SeasonRange ------------------------------------------------------------
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,80 @@
|
||||
"""Tests for the `-` exclusion prefix on the language flags (-l, -vl, -al, -sl, -fsl)."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import pytest
|
||||
from langcodes import Language
|
||||
|
||||
from unshackle.core.utilities import excluded_language_tags, partition_exclusions
|
||||
from unshackle.core.utils.click_types import LANGUAGE_RANGE
|
||||
|
||||
# --- partition_exclusions ---------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"tokens,expected",
|
||||
[
|
||||
(["all", "-es"], (["all"], ["es"])),
|
||||
(["-es"], ([], ["es"])),
|
||||
(["en", "ja"], (["en", "ja"], [])),
|
||||
(["-es", "-fr", "en"], (["en"], ["es", "fr"])),
|
||||
([], ([], [])),
|
||||
(None, ([], [])),
|
||||
],
|
||||
)
|
||||
def test_partition_splits_on_the_leading_dash(tokens, expected):
|
||||
assert partition_exclusions(tokens) == expected
|
||||
|
||||
|
||||
def test_partition_keeps_the_written_order_and_drops_repeats():
|
||||
assert partition_exclusions(["ja", "en", "ja", "-es", "-es"]) == (["ja", "en"], ["es"])
|
||||
|
||||
|
||||
@pytest.mark.parametrize("token", ["-", " - ", "", " "])
|
||||
def test_partition_skips_tokens_with_no_value(token):
|
||||
assert partition_exclusions(["en", token]) == (["en"], [])
|
||||
|
||||
|
||||
def test_partition_trims_whitespace_around_a_token():
|
||||
assert partition_exclusions([" en ", "- es "]) == (["en"], ["es"])
|
||||
|
||||
|
||||
def test_partition_reads_the_tokens_language_range_produces():
|
||||
assert partition_exclusions(LANGUAGE_RANGE.convert("all,-es;-fr")) == (["all"], ["es", "fr"])
|
||||
|
||||
|
||||
# --- excluded_language_tags ---------------------------------------------------
|
||||
|
||||
|
||||
def test_close_match_excludes_the_regional_variants():
|
||||
assert excluded_language_tags(["es"], ["es-419", "es-ES", "en-US"]) == {"es-419", "es-ES"}
|
||||
|
||||
|
||||
def test_exact_match_prefers_the_string_equal_tag():
|
||||
# same string preference as selection: an exact 'es' only takes 'es' when it exists
|
||||
assert excluded_language_tags(["es"], ["es", "es-ES", "es-419"], exact=True) == {"es"}
|
||||
|
||||
|
||||
def test_exact_match_falls_back_to_the_paradigm_variant():
|
||||
# no literal 'es' available, so 'es' resolves the way an exact '-sl es' selection would
|
||||
assert excluded_language_tags(["es"], ["es-ES", "es-419"], exact=True) == {"es-ES"}
|
||||
|
||||
|
||||
def test_exact_match_keeps_an_unnamed_regional_variant():
|
||||
assert excluded_language_tags(["es-ES"], ["es-ES", "es-419"], exact=True) == {"es-ES"}
|
||||
|
||||
|
||||
def test_language_objects_are_accepted():
|
||||
assert excluded_language_tags(["es"], [Language.get("es")]) == {"es"}
|
||||
|
||||
|
||||
def test_an_untagged_track_is_never_excluded():
|
||||
assert excluded_language_tags(["es"], [None, "en-US"]) == set()
|
||||
|
||||
|
||||
def test_no_exclusions_excludes_nothing():
|
||||
assert excluded_language_tags([], ["es-419", "en-US"]) == set()
|
||||
|
||||
|
||||
def test_an_unmatched_language_is_kept():
|
||||
assert excluded_language_tags(["es", "fr"], ["en-US", "ja-JP"]) == set()
|
||||
@@ -150,3 +150,24 @@ def test_language_range_yaml_shapes(value, expected):
|
||||
ctx = make_ctx()
|
||||
apply_service_dl_overrides(ctx, {"v_lang": value}, log)
|
||||
assert ctx.params["v_lang"] == expected
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"value,expected",
|
||||
[
|
||||
("all,-es", ["all", "-es"]),
|
||||
("-es", ["-es"]),
|
||||
(["all", "-es"], ["all", "-es"]),
|
||||
],
|
||||
)
|
||||
def test_language_exclusion_tokens_survive_the_override_convert(value, expected):
|
||||
"""A service dl override is re-converted, so its exclusion tokens must reach the filter stage intact."""
|
||||
ctx = make_ctx()
|
||||
apply_service_dl_overrides(ctx, {"v_lang": value}, log)
|
||||
assert ctx.params["v_lang"] == expected
|
||||
|
||||
|
||||
def test_cli_exclusion_beats_service_config():
|
||||
ctx = make_ctx(["-vl", "-es"])
|
||||
apply_service_dl_overrides(ctx, {"v_lang": ["en"]}, log)
|
||||
assert ctx.params["v_lang"] == ["-es"]
|
||||
|
||||
Reference in New Issue
Block a user