Add duplicate filename diagnostics

serato_doctor/models/__init__.py

@@ -1,4 +1,5 @@
 from serato_doctor.models.crate import Crate, CrateKind
+from serato_doctor.models.duplicate import DuplicateGroup, DuplicateKind
 from serato_doctor.models.health import HealthReport
 from serato_doctor.models.library import Library
 from serato_doctor.models.match import MatchEvidence, TrackMatch
@@ -9,6 +10,8 @@ __all__ = [
     "Crate",
     "CrateKind",
     "DiskTrack",
+    "DuplicateGroup",
+    "DuplicateKind",
     "HealthReport",
     "Library",
     "MatchEvidence",

serato_doctor/models/duplicate.py

@@ -0,0 +1,30 @@
+from dataclasses import dataclass
+from enum import Enum
+from typing import Tuple
+
+from serato_doctor.models.track import DiskTrack
+
+
+class DuplicateKind(str, Enum):
+    EXACT_NAME = "exact_name"
+    CLOUD_CONFLICT = "cloud_conflict"
+
+
+@dataclass(frozen=True)
+class DuplicateGroup:
+    """A deterministic group of files that warrants duplicate review."""
+
+    kind: DuplicateKind
+    comparison_key: str
+    tracks: Tuple[DiskTrack, ...]
+
+    @property
+    def extra_files(self) -> int:
+        return max(0, len(self.tracks) - 1)
+
+    @property
+    def display_name(self) -> str:
+        return min(
+            (track.filename for track in self.tracks),
+            key=lambda name: (len(name), name.casefold()),
+        )

serato_doctor/models/health.py

@@ -15,6 +15,8 @@ class HealthReport:
     disk_tracks: int
     duplicate_filename_groups: int
     duplicate_files: int
+    suspected_cloud_conflict_groups: int
+    suspected_cloud_conflict_files: int
     unused_tracks: int
     suggested_matches: int
     static_crates: int