1 files changed, 96 insertions, 2 deletions
diff --git a/packages/meshbay-node/tests/test_musicbrainz.py b/packages/meshbay-node/tests/test_musicbrainz.py
index 482395d..4d075d3 100644
--- a/packages/meshbay-node/tests/test_musicbrainz.py
+++ b/packages/meshbay-node/tests/test_musicbrainz.py
@@ -4,8 +4,7 @@ import time
 
 import httpx
 import pytest
-
-from meshbay_node.musicbrainz import MusicBrainzClient, _MIN_INTERVAL_SECS
+from meshbay_node.musicbrainz import _MIN_INTERVAL_SECS, MusicBrainzClient, _escape_lucene
 
 
 class FakeRoster:
@@ -55,6 +54,101 @@ async def test_no_results_returns_none_and_zero_confidence():
     await client.close()
 
 
+def test_escape_lucene_escapes_query_syntax_characters():
+    # Verified live against musicbrainz.org before writing the fallback
+    # below: a literal "(" inside a quoted phrase is read as query syntax,
+    # not a character to match, and silently drops the phrase to zero
+    # results rather than raising.
+    assert _escape_lucene("Hebron Gate (2003)") == r"Hebron Gate \(2003\)"
+    assert _escape_lucene('Say "It" Loud') == r"Say \"It\" Loud"
+    assert _escape_lucene("Rock & Roll: Live") == r"Rock \& Roll\: Live"
+    assert _escape_lucene("no specials here") == "no specials here"
+
+
+@pytest.mark.asyncio
+async def test_strict_match_does_not_pay_for_a_second_request():
+    """A tag that already matches MusicBrainz's own spelling should cost
+    exactly one request — the fallback below exists for the case that
+    doesn't, not for every call."""
+    calls = []
+
+    def handle(request: httpx.Request) -> httpx.Response:
+        calls.append(str(request.url))
+        return httpx.Response(200, json={
+            "releases": [{"id": "abc-123", "title": "The Great Album",
+                          "artist-credit": [{"name": "Some Artist"}]}],
+        })
+
+    client = MusicBrainzClient(
+        roster=FakeRoster(),
+        transport=httpx.MockTransport(handle),
+    )
+    await client.search_release("Some Artist", "The Great Album")
+
+    assert len(calls) == 1
+    await client.close()
+
+
+@pytest.mark.asyncio
+async def test_falls_back_to_a_loose_query_when_the_strict_one_finds_nothing():
+    """
+    Regression for the real failure mode found against the live service:
+    `artist:"Groundation" AND release:"Hebron Gate"` finds the release
+    (score 100), but a local album tag/folder carrying a trailing year —
+    "Hebron Gate (2003)", a common rip-folder shape — drops the strict
+    exact-phrase query to zero hits, not a low-scored one. The loose,
+    unscoped query must be tried next instead of stopping at "no match".
+    """
+    calls = []
+
+    def handle(request: httpx.Request) -> httpx.Response:
+        query = request.url.params.get("query", "")
+        calls.append(query)
+        if query.startswith("artist:"):
+            return httpx.Response(200, json={"releases": []})
+        return httpx.Response(200, json={
+            "releases": [{"id": "xyz-789", "title": "Hebron Gate",
+                          "artist-credit": [{"name": "Groundation"}]}],
+        })
+
+    client = MusicBrainzClient(
+        roster=FakeRoster(),
+        transport=httpx.MockTransport(handle),
+    )
+    result, ratio = await client.search_release("Groundation", "Hebron Gate (2003)")
+
+    assert result is not None
+    assert result["id"] == "xyz-789"
+    assert ratio > 0.5
+    assert len(calls) == 2, "must retry with a loose query after the strict one finds nothing"
+    await client.close()
+
+
+@pytest.mark.asyncio
+async def test_confidence_reflects_a_wrong_artist_on_a_same_titled_release():
+    """
+    The loose fallback query has no field scoping at all, so a same-
+    titled release by an unrelated artist must not read as confidently as
+    one that also matches on artist — otherwise the fallback trades
+    "never finds a mismatch" for "sometimes confirms a wrong one".
+    """
+    def handle(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(200, json={
+            "releases": [{"id": "wrong-1", "title": "Live",
+                          "artist-credit": [{"name": "An Entirely Different Band"}]}],
+        })
+
+    client = MusicBrainzClient(
+        roster=FakeRoster(),
+        transport=httpx.MockTransport(handle),
+    )
+    result, ratio = await client.search_release("Groundation", "Live")
+
+    assert result is not None
+    assert ratio < 0.6, "a title-only match against the wrong artist must not read as confident"
+    await client.close()
+
+
 @pytest.mark.asyncio
 async def test_no_contact_configured_makes_no_request(monkeypatch):
     monkeypatch.delenv("MESHBAY_MUSICBRAINZ_CONTACT_DEFAULT", raising=False)