Lyra/worker/tests/test_slskd_search_fallback.py

"""Soulseek search fallback: the Soulseek server drops searches containing blocklisted terms
(major-label artists / album titles) → 0 responses. search_album retries with album-only then
artist-only, keeping only path-matching results so it never grabs a same-titled foreign album."""
import json

import lyra_worker.adapters._slskd as slskd_mod
from lyra_worker.adapters._slskd import (
    SlskdClient,
    _keep_matching,
    _norm,
    _path_matches,
)


# --- pure helpers -----------------------------------------------------------------------------

def test_norm_strips_diacritics_and_punctuation():
    assert _norm("Beyoncé") == "beyonce"
    assert _norm("I Am… Sasha Fierce") == "i am sasha fierce"
    assert _norm("AC/DC") == "ac dc"


def test_path_matches_is_accent_and_punctuation_tolerant():
    p = r"@@bckfj\All\Beyonce\I Am... Sasha Fierce CD1\03 Halo.flac"
    assert _path_matches("Beyoncé", p)              # accent folded
    assert _path_matches("I Am… Sasha Fierce", p)   # ellipsis / punctuation ignored
    assert not _path_matches("Rihanna", p)


def test_path_matches_short_needle_requires_whole_string():
    assert _path_matches("U2", r"x\U2 - Achtung Baby\01.flac")
    assert not _path_matches("U2", r"x\Blur - 13\01.flac")


def test_keep_matching_drops_foreign_and_empty_responses():
    responses = [
        {"username": "a", "files": [{"filename": r"x\Rihanna - Unapologetic\01.flac"}]},
        {"username": "b", "files": [{"filename": r"x\Someone Else - Unapologetic\01.flac"}]},
    ]
    kept = _keep_matching(responses, "Rihanna")
    assert [r["username"] for r in kept] == ["a"]


# --- fallback orchestration (HTTP faked) ------------------------------------------------------

class _Resp:
    def __init__(self, payload):
        self._p = payload

    def raise_for_status(self):
        pass

    def json(self):
        return self._p


class _FakeSearch:
    """Routes slskd search HTTP by URL: POST returns an id, GET on the search returns a completed
    state, GET on /responses returns the canned responses for that query. Records queries sent."""
    def __init__(self, by_query):
        self.by_query = by_query          # {searchText: [responses]}
        self.queries = []                 # searchText values POSTed, in order
        self._id_query = {}
        self._n = 0

    def post(self, url, **kw):
        text = kw["json"]["searchText"]
        self.queries.append(text)
        self._n += 1
        sid = f"s{self._n}"
        self._id_query[sid] = text
        return _Resp({"id": sid})

    def get(self, url, **kw):
        if url.endswith("/responses"):
            sid = url.rsplit("/", 2)[-2]
            return _Resp(self.by_query.get(self._id_query[sid], []))
        return _Resp({"state": "Completed, TimedOut"})


def _client():
    return SlskdClient({"slskd.url": "http://x", "slskd.api_key": "k", "slskd.downloadsDir": "/x"})


def _install(monkeypatch, fake):
    monkeypatch.setattr(slskd_mod, "requests", fake)
    monkeypatch.setattr(slskd_mod.time, "sleep", lambda _s: None)


def test_primary_hit_does_not_trigger_fallback(monkeypatch):
    fake = _FakeSearch({
        "Rihanna Unapologetic": [
            {"username": "a", "hasFreeUploadSlot": True, "uploadSpeed": 1, "queueLength": 0,
             "files": [{"filename": r"x\Rihanna - Unapologetic\01.flac", "size": 5}]},
        ],
    })
    _install(monkeypatch, fake)
    out = _client().search_album("Rihanna", "Unapologetic")
    assert len(out) == 1
    assert fake.queries == ["Rihanna Unapologetic"]  # no fallback searches


def test_album_only_fallback_recovers_blocklisted_artist(monkeypatch):
    # Primary (artist blocked) → 0; album-only returns the artist's folder → recovered.
    fake = _FakeSearch({
        "Beyoncé I Am… Sasha Fierce": [],  # blocked
        "i am sasha fierce": [
            {"username": "a", "hasFreeUploadSlot": True, "uploadSpeed": 1, "queueLength": 0,
             "files": [{"filename": r"x\Beyonce - I Am... Sasha Fierce\01.flac", "size": 5}]},
            {"username": "b", "hasFreeUploadSlot": True, "uploadSpeed": 1, "queueLength": 0,
             "files": [{"filename": r"x\Other Artist - I Am Sasha Fierce\01.flac", "size": 5}]},
        ],
    })
    _install(monkeypatch, fake)
    out = _client().search_album("Beyoncé", "I Am… Sasha Fierce")
    assert fake.queries == ["Beyoncé I Am… Sasha Fierce", "i am sasha fierce"]
    peers = [json.loads(c["source_ref"])["username"] for c in out]
    assert peers == ["a"]  # foreign same-titled album dropped


def test_artist_only_fallback_when_album_title_blocked(monkeypatch):
    # Album-only also blocked/empty → fall through to artist-only, filtered by album in path.
    fake = _FakeSearch({
        "Foo Lemonade": [],
        "lemonade": [],  # album title itself blocked
        "foo": [
            {"username": "a", "hasFreeUploadSlot": True, "uploadSpeed": 1, "queueLength": 0,
             "files": [{"filename": r"x\Foo - Lemonade\01.flac", "size": 5}]},
        ],
    })
    _install(monkeypatch, fake)
    out = _client().search_album("Foo", "Lemonade")
    assert fake.queries == ["Foo Lemonade", "lemonade", "foo"]
    assert len(out) == 1


def test_fallback_yields_nothing_when_title_too_generic(monkeypatch):
    # 'Adele 21': artist blocked, album title '21' returns lots of non-Adele content → filtered
    # to nothing rather than grabbing a wrong album.
    fake = _FakeSearch({
        "Adele 21": [],
        "21": [
            {"username": "z", "hasFreeUploadSlot": True, "uploadSpeed": 1, "queueLength": 0,
             "files": [{"filename": r"x\21 Savage - Savage Mode\01.flac", "size": 5}]},
        ],
        "adele": [],  # artist blocked
    })
    _install(monkeypatch, fake)
    out = _client().search_album("Adele", "21")
    assert out == []