e07c9ec77b
Several weeks of work accumulated without being committed. Grouped here for clarity; see CHANGELOG.md [Unreleased] for the user-facing summary. Highlights ---------- P1 #2 — ISO 639-2/B canonical migration - New Language VO + LanguageRegistry (alfred/domain/shared/knowledge/). - iso_languages.yaml as single source of truth for language codes. - SubtitleKnowledgeBase now delegates lookup to LanguageRegistry; subtitles.yaml only declares subtitle-specific tokens (vostfr, vf, vff, …). - SubtitlePreferences default → ["fre", "eng"]; subtitle filenames written as {iso639_2b}.srt (legacy fr.srt still read via alias). - Scanner: dropped _LANG_KEYWORDS / _SDH_TOKENS / _FORCED_TOKENS / SUBTITLE_EXTENSIONS hardcoded dicts. - Fixed: 'hi' token no longer marks SDH (conflicted with Hindi alias). - Added settings.min_movie_size_bytes (was a module constant). P1 #3 — Release parser unification + data-driven tokenizer - parse_release() is now the single source of truth for release-name parsing. - alfred/knowledge/release/separators.yaml declares the token separators used by the tokenizer (., space, [, ], (, ), _). New conventions can be added without code changes. - Tokenizer now splits on any configured separator instead of name.split('.'). Releases like 'The Father (2020) [1080p] [WEBRip] [5.1] [YTS.MX]' parse via the direct path without sanitization fallback. - Site-tag extraction always runs first; well-formedness only rejects truly forbidden chars. - _parse_season_episode() extended with NxNN / NxNNxNN alt forms. - Removed dead helpers: _sanitize, _normalize. Domain cleanup - Deleted fossil services with zero production callers: alfred/domain/movies/services.py alfred/domain/tv_shows/services.py alfred/domain/subtitles/services.py (replaced by subtitles/services/ package) alfred/domain/subtitles/repositories.py - Split monolithic subtitle services into a package (identifier, matcher, placer, pattern_detector, utils) + dedicated knowledge/ package. - MediaInfo split into dedicated package (alfred/domain/shared/media/: audio, video, subtitle, info, matching). Persistence cleanup - Removed dead JSON repositories (movie/subtitle/tvshow_repository.py). Tests - Major expansion of the test suite organized to mirror the source tree. - Removed obsolete *_edge_cases test files superseded by structured tests. - Suite: 990 passed, 8 skipped. Misc - .gitignore: exclude env_backup/ and *.bak. - Adjustments across agent/llm, app.py, application/filesystem, and infrastructure/filesystem to align with the new domain layout.
217 lines
8.0 KiB
Python
217 lines
8.0 KiB
Python
"""Tests for ``alfred.agent.workflows.loader.WorkflowLoader``.
|
|
|
|
Two layers of coverage:
|
|
|
|
1. **TestRealWorkflows** — Asserts on the YAML files that ship in the repo
|
|
(``alfred/agent/workflows/``). These tests act as a structural contract:
|
|
if a step id, tool name, or naming convention is renamed, the test
|
|
surfaces the change immediately. They use the real loader with no
|
|
monkeypatching.
|
|
|
|
2. **TestLoaderMechanics** — Loader behavior in isolation, using a
|
|
monkeypatched workflows directory. Covers ``get`` / ``names`` / ``all``,
|
|
YAML ``name`` precedence over filename, malformed-file resilience,
|
|
deterministic ordering on name collision, and the empty-directory case.
|
|
|
|
Current workflow naming convention is ``<domain>.<workflow_name>``
|
|
(e.g. ``media.organize_media``), not the legacy bare ``organize_media``.
|
|
"""
|
|
|
|
import pytest
|
|
import yaml
|
|
|
|
from alfred.agent.workflows.loader import WorkflowLoader
|
|
|
|
ORGANIZE_MEDIA = "media.organize_media"
|
|
MANAGE_SUBTITLES = "media.manage_subtitles"
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Fixtures
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.fixture
|
|
def workflows_dir(tmp_path):
|
|
"""A temp directory pre-populated with one valid workflow YAML."""
|
|
wf = {
|
|
"name": "test_workflow",
|
|
"description": "A test workflow",
|
|
"tools": ["list_folder", "move_media"],
|
|
"steps": [
|
|
{"id": "step1", "tool": "list_folder"},
|
|
],
|
|
}
|
|
(tmp_path / "test_workflow.yaml").write_text(yaml.dump(wf))
|
|
return tmp_path
|
|
|
|
|
|
@pytest.fixture
|
|
def loader_from_dir(workflows_dir, monkeypatch):
|
|
"""WorkflowLoader pointed at our temp dir."""
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", workflows_dir)
|
|
return WorkflowLoader()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Real loader (loads actual YAML files from the repo)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestRealWorkflows:
|
|
"""Contract tests against the workflows shipped in ``alfred/agent/workflows``."""
|
|
|
|
def test_organize_media_loaded(self):
|
|
loader = WorkflowLoader()
|
|
assert ORGANIZE_MEDIA in loader.names()
|
|
|
|
def test_manage_subtitles_loaded(self):
|
|
loader = WorkflowLoader()
|
|
assert MANAGE_SUBTITLES in loader.names()
|
|
|
|
def test_organize_media_has_required_keys(self):
|
|
loader = WorkflowLoader()
|
|
wf = loader.get(ORGANIZE_MEDIA)
|
|
assert wf is not None
|
|
assert wf["name"] == ORGANIZE_MEDIA
|
|
assert "steps" in wf
|
|
assert "tools" in wf
|
|
|
|
def test_organize_media_tools_list(self):
|
|
loader = WorkflowLoader()
|
|
wf = loader.get(ORGANIZE_MEDIA)
|
|
tools = wf["tools"]
|
|
# The four required tools that compose the move pipeline.
|
|
for required in (
|
|
"list_folder",
|
|
"move_to_destination",
|
|
"manage_subtitles",
|
|
"create_seed_links",
|
|
):
|
|
assert required in tools, f"missing tool: {required}"
|
|
# There is no single ``resolve_destination`` tool anymore — the
|
|
# workflow declares the four media-type-specific resolvers.
|
|
for resolver in (
|
|
"resolve_season_destination",
|
|
"resolve_episode_destination",
|
|
"resolve_movie_destination",
|
|
"resolve_series_destination",
|
|
):
|
|
assert resolver in tools, f"missing resolver: {resolver}"
|
|
|
|
def test_organize_media_steps_order(self):
|
|
loader = WorkflowLoader()
|
|
wf = loader.get(ORGANIZE_MEDIA)
|
|
step_ids = [s["id"] for s in wf["steps"]]
|
|
# resolve_destination is the *step id* (not tool name) that fans
|
|
# out to the four resolvers.
|
|
assert step_ids.index("resolve_destination") < step_ids.index("move_file")
|
|
assert step_ids.index("move_file") < step_ids.index("handle_subtitles")
|
|
assert step_ids.index("ask_seeding") < step_ids.index("create_seed_links")
|
|
|
|
def test_ask_seeding_has_yes_no_answers(self):
|
|
loader = WorkflowLoader()
|
|
wf = loader.get(ORGANIZE_MEDIA)
|
|
ask_step = next(s for s in wf["steps"] if s["id"] == "ask_seeding")
|
|
answers = ask_step["ask_user"]["answers"]
|
|
# PyYAML parses bare yes/no as booleans, quoted as strings — normalize.
|
|
answer_keys = {str(k).lower() for k in answers.keys()}
|
|
assert "yes" in answer_keys
|
|
assert "no" in answer_keys
|
|
|
|
def test_naming_convention_present(self):
|
|
loader = WorkflowLoader()
|
|
wf = loader.get(ORGANIZE_MEDIA)
|
|
assert "naming_convention" in wf
|
|
assert "tv_show" in wf["naming_convention"]
|
|
assert "movie" in wf["naming_convention"]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# WorkflowLoader mechanics (via monkeypatched dir)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
class TestLoaderMechanics:
|
|
"""Loader behavior driven by YAML files in a temp directory."""
|
|
|
|
def test_get_returns_workflow(self, loader_from_dir):
|
|
wf = loader_from_dir.get("test_workflow")
|
|
assert wf is not None
|
|
assert wf["name"] == "test_workflow"
|
|
|
|
def test_get_returns_none_for_unknown(self, loader_from_dir):
|
|
assert loader_from_dir.get("nonexistent") is None
|
|
|
|
def test_names_returns_list(self, loader_from_dir):
|
|
names = loader_from_dir.names()
|
|
assert isinstance(names, list)
|
|
assert "test_workflow" in names
|
|
|
|
def test_all_returns_dict(self, loader_from_dir):
|
|
all_wf = loader_from_dir.all()
|
|
assert isinstance(all_wf, dict)
|
|
assert "test_workflow" in all_wf
|
|
|
|
def test_uses_yaml_name_field(self, tmp_path, monkeypatch):
|
|
"""Name from YAML content takes priority over filename stem."""
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", tmp_path)
|
|
|
|
wf = {"name": "my_custom_name", "steps": []}
|
|
(tmp_path / "completely_different_filename.yaml").write_text(yaml.dump(wf))
|
|
|
|
loader = WorkflowLoader()
|
|
assert "my_custom_name" in loader.names()
|
|
assert "completely_different_filename" not in loader.names()
|
|
|
|
def test_falls_back_to_stem_when_no_name(self, tmp_path, monkeypatch):
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", tmp_path)
|
|
|
|
(tmp_path / "my_workflow.yaml").write_text(yaml.dump({"steps": []}))
|
|
loader = WorkflowLoader()
|
|
assert "my_workflow" in loader.names()
|
|
|
|
def test_skips_malformed_yaml(self, tmp_path, monkeypatch):
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", tmp_path)
|
|
|
|
(tmp_path / "valid.yaml").write_text(yaml.dump({"name": "valid", "steps": []}))
|
|
(tmp_path / "broken.yaml").write_text("key: [unclosed bracket")
|
|
|
|
loader = WorkflowLoader()
|
|
assert "valid" in loader.names()
|
|
assert "broken" not in loader.names()
|
|
|
|
def test_deterministic_load_order(self, tmp_path, monkeypatch):
|
|
"""Files loaded in sorted order — later file wins on name collision."""
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", tmp_path)
|
|
|
|
(tmp_path / "a_workflow.yaml").write_text(
|
|
yaml.dump({"name": "duplicate", "version": 1})
|
|
)
|
|
(tmp_path / "b_workflow.yaml").write_text(
|
|
yaml.dump({"name": "duplicate", "version": 2})
|
|
)
|
|
|
|
loader = WorkflowLoader()
|
|
# b_workflow loaded last → version 2 wins
|
|
assert loader.get("duplicate")["version"] == 2
|
|
|
|
def test_empty_directory(self, tmp_path, monkeypatch):
|
|
import alfred.agent.workflows.loader as loader_module
|
|
|
|
monkeypatch.setattr(loader_module, "_WORKFLOWS_DIR", tmp_path)
|
|
|
|
loader = WorkflowLoader()
|
|
assert loader.names() == []
|
|
assert loader.all() == {}
|