Add duplicate audio hash detection

serato_doctor/web.py

@@ -18,6 +18,7 @@ from serato_doctor.crate_parser import load_library_crates
 from serato_doctor.database_parser import parse_database
 from serato_doctor.duplicates import find_duplicate_groups
 from serato_doctor.health import analyze_health
+from serato_doctor.hashing import compare_audio_files
 from serato_doctor.matching import MatchingEngine, normalize
 from serato_doctor.models.crate import CrateKind
 from serato_doctor.models.duplicate import DuplicateKind
@@ -357,6 +358,9 @@ def duplicate_repair_batch(
     if not plans:
         raise ValueError("Choose at least one duplicate group")
     replaced = [str(path) for plan in plans for path in plan.replaced]
+    comparisons = [
+        compare_audio_files((plan.keeper,) + plan.replaced) for plan in plans
+    ]
     result = {
         "choice_count": len(plans),
         "replaced": replaced,
@@ -364,8 +368,9 @@ def duplicate_repair_batch(
             {
                 "keeper": str(plan.keeper),
                 "replaced": [str(path) for path in plan.replaced],
+                "hash_status": comparison["status"],
             }
-            for plan in plans
+            for plan, comparison in zip(plans, comparisons)
         ],
         "metadata_backups": len(plans[0].metadata_files),
         "strategy": "shortcut",
@@ -438,6 +443,7 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
             "/api/duplicates/apply",
             "/api/duplicates/batch/preview",
             "/api/duplicates/batch/apply",
+            "/api/duplicates/hash",
             "/api/backups/restore",
             "/api/backups",
             "/api/reveal",
@@ -471,6 +477,24 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
                     raise ValueError("That backup does not belong to this library")
                 restored = restore_backup(backup)
                 result = {"restored": [str(path) for path in restored]}
+            elif self.path == "/api/duplicates/hash":
+                tokens = payload["tokens"]
+                if not isinstance(tokens, list) or not 2 <= len(tokens) <= 10:
+                    raise ValueError("Compare between 2 and 10 audio files")
+                comparison = compare_audio_files(
+                    _verified_audio(token) for token in tokens
+                )
+                result = {
+                    "status": comparison["status"],
+                    "files": [
+                        {
+                            "path": item["path"],
+                            "size": item["size"],
+                            "fingerprint": item["sha256"][:12],
+                        }
+                        for item in comparison["files"]
+                    ],
+                }
             elif self.path.startswith("/api/duplicates/batch/"):
                 raw_limit = payload.get("backup_limit", 10)
                 backup_limit = None if raw_limit is None else int(raw_limit)