Add duplicate audio comparison controls

docs/design/audio-comparison.md

@@ -0,0 +1,32 @@
+# Audio comparison for duplicate review
+
+## Problem
+
+Filenames alone are weak evidence. DJs need to hear each candidate and locate it
+on disk before deciding which copy is authoritative.
+
+## Design
+
+Exact-duplicate and cloud-conflict groups expose a shared audio player with a
+preview action for each file. Switching files reuses the same player, making
+back-to-back comparison quick. A separate action reveals the selected file in
+macOS Finder.
+
+The browser never receives unrestricted filesystem access. Each analyzed audio
+path gets a short, process-local HMAC token. Preview and Finder endpoints reject
+altered, expired, missing, non-audio, or otherwise unsigned paths. Audio serving
+supports HTTP byte ranges so playback can seek without loading an entire track.
+
+## Edge cases
+
+- A file moved after analysis is rejected.
+- Forged or stale tokens cannot select another local file.
+- Preview controls remain useful if autoplay is blocked because native audio
+  controls stay visible.
+- Finder failures are reported beside the button without affecting analysis.
+
+## Tests
+
+- Valid signed audio resolves to the analyzed file.
+- A modified token is rejected.
+- Duplicate detail payloads include preview and Finder controls for every file.

serato_doctor/web.py

@@ -1,12 +1,18 @@
 import argparse
+import base64
+import binascii
+import hmac
 import json
+import mimetypes
+import secrets
+import subprocess
 from collections import Counter
 from dataclasses import asdict
 from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
 from importlib import resources
 from pathlib import Path
 from typing import Iterable, Optional
-from urllib.parse import urlsplit
+from urllib.parse import parse_qs, quote, urlsplit
 
 from serato_doctor.crate_parser import load_library_crates
 from serato_doctor.database_parser import parse_database
@@ -28,6 +34,7 @@ from serato_doctor.repair import (
 
 MAX_REQUEST_BYTES = 64 * 1024
 DETAIL_LIMIT = 50
+FILE_TOKEN_SECRET = secrets.token_bytes(32)
 STATIC_FILES = {
     "/": ("index.html", "text/html; charset=utf-8"),
     "/app.css": ("app.css", "text/css; charset=utf-8"),
@@ -41,6 +48,44 @@ def _display_path(path: Path) -> str:
     return str(path)
 
 
+def _file_token(path: Path) -> str:
+    encoded = base64.urlsafe_b64encode(str(path.resolve()).encode()).decode()
+    signature = hmac.digest(FILE_TOKEN_SECRET, encoded.encode(), "sha256").hex()
+    return f"{encoded}.{signature}"
+
+
+def _verified_audio(token: str) -> Path:
+    try:
+        encoded, signature = token.rsplit(".", 1)
+        expected = hmac.digest(
+            FILE_TOKEN_SECRET, encoded.encode(), "sha256"
+        ).hex()
+        if not hmac.compare_digest(signature, expected):
+            raise ValueError
+        path = Path(base64.urlsafe_b64decode(encoded.encode()).decode())
+    except (binascii.Error, ValueError, UnicodeDecodeError):
+        raise ValueError("Invalid or expired file preview")
+    if not path.is_file() or path.suffix.casefold() not in {
+        ".mp3",
+        ".m4a",
+        ".wav",
+        ".aif",
+        ".aiff",
+        ".flac",
+    }:
+        raise ValueError("Audio file is no longer available")
+    return path
+
+
+def _file_preview(path: Path) -> dict:
+    token = _file_token(path)
+    return {
+        "path": _display_path(path),
+        "audio_url": f"/api/audio?token={quote(token)}",
+        "reveal_token": token,
+    }
+
+
 def _first_reason(match) -> str:
     for item in match.evidence:
         if item.matched:
@@ -159,6 +204,9 @@ def diagnostic_details(library: Library, limit: int = DETAIL_LIMIT) -> dict:
                 {
                     "filename": group.display_name,
                     "files": [_display_path(track.path) for track in group.tracks],
+                    "file_previews": [
+                        _file_preview(track.path) for track in group.tracks
+                    ],
                 }
                 for group in exact_duplicates[:limit]
             ],
@@ -174,6 +222,9 @@ def diagnostic_details(library: Library, limit: int = DETAIL_LIMIT) -> dict:
                 {
                     "filename": group.display_name,
                     "files": [_display_path(track.path) for track in group.tracks],
+                    "file_previews": [
+                        _file_preview(track.path) for track in group.tracks
+                    ],
                 }
                 for group in cloud_conflicts[:limit]
             ],
@@ -298,7 +349,15 @@ def backup_history(serato: Path) -> dict:
 
 class SeratoDoctorHandler(BaseHTTPRequestHandler):
     def do_GET(self) -> None:
-        asset = STATIC_FILES.get(urlsplit(self.path).path)
+        request = urlsplit(self.path)
+        if request.path == "/api/audio":
+            try:
+                token = parse_qs(request.query)["token"][0]
+                self._audio_response(_verified_audio(token))
+            except (KeyError, IndexError, OSError, ValueError) as error:
+                self._json_response(404, {"error": str(error)})
+            return
+        asset = STATIC_FILES.get(request.path)
         if asset is None:
             self._json_response(404, {"error": "Not found"})
             return
@@ -322,6 +381,7 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
             "/api/duplicates/apply",
             "/api/backups/restore",
             "/api/backups",
+            "/api/reveal",
         }
         if self.path not in allowed:
             self._json_response(404, {"error": "Not found"})
@@ -338,6 +398,10 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
                 result = analyze_paths(
                     Path(payload["serato"]), Path(payload["music"]), roots
                 )
+            elif self.path == "/api/reveal":
+                path = _verified_audio(payload["token"])
+                subprocess.run(["open", "-R", str(path)], check=True)
+                result = {"revealed": str(path)}
             elif self.path == "/api/backups":
                 result = backup_history(Path(payload["serato"]))
             elif self.path == "/api/backups/restore":
@@ -370,6 +434,38 @@ class SeratoDoctorHandler(BaseHTTPRequestHandler):
             return
         self._json_response(200, result)
 
+    def _audio_response(self, path: Path) -> None:
+        size = path.stat().st_size
+        start, end = 0, size - 1
+        status = 200
+        range_header = self.headers.get("Range")
+        if range_header and range_header.startswith("bytes="):
+            raw_start, _, raw_end = range_header[6:].partition("-")
+            start = int(raw_start or 0)
+            end = min(int(raw_end) if raw_end else end, end)
+            if start < 0 or start > end:
+                raise ValueError("Invalid audio range")
+            status = 206
+        length = end - start + 1
+        self.send_response(status)
+        self.send_header(
+            "Content-Type", mimetypes.guess_type(path.name)[0] or "audio/mpeg"
+        )
+        self.send_header("Accept-Ranges", "bytes")
+        self.send_header("Content-Length", str(length))
+        if status == 206:
+            self.send_header("Content-Range", f"bytes {start}-{end}/{size}")
+        self.end_headers()
+        with path.open("rb") as audio:
+            audio.seek(start)
+            remaining = length
+            while remaining:
+                chunk = audio.read(min(64 * 1024, remaining))
+                if not chunk:
+                    break
+                self.wfile.write(chunk)
+                remaining -= len(chunk)
+
     def _json_response(self, status: int, payload: dict) -> None:
         content = json.dumps(payload).encode("utf-8")
         self.send_response(status)

serato_doctor/webui/app.js

@@ -18,6 +18,10 @@ const restoreRepairButton = document.querySelector('#restore-repair');
 const loadBackupsButton = document.querySelector('#load-backups');
 const backupSummary = document.querySelector('#backup-summary');
 const backupList = document.querySelector('#backup-list');
+const audioPreview = document.querySelector('#audio-preview');
+const audioPreviewName = document.querySelector('#audio-preview-name');
+const audioPlayer = document.querySelector('#audio-player');
+const closeAudioPreview = document.querySelector('#close-audio-preview');
 let latestAnalysis = null;
 let selectedDuplicateGroup = null;
 let previewedRepair = null;
@@ -84,8 +88,8 @@ backupList.addEventListener('click', async (event) => {
 });
 
 function detailLines(item) {
-  if (item.files) {
+  if (item.file_previews) {
-    return item.files.map((file) => `<li>${escapeHtml(file)}</li>`).join('');
+    return item.file_previews.map((file) => `<li class="file-compare-row"><span>${escapeHtml(file.path)}</span><div><button type="button" data-audio-url="${escapeHtml(file.audio_url)}" data-audio-name="${escapeHtml(file.path)}">▶ Play preview</button><button type="button" data-reveal-token="${escapeHtml(file.reveal_token)}">Show in Finder</button></div></li>`).join('');
   }
   const lines = [];
   if (item.artist || item.title) lines.push(`${item.artist || 'Unknown artist'} — ${item.title || item.filename}`);
@@ -138,7 +142,7 @@ function chooseDuplicate(detailKey, index) {
   repairPreview.hidden = true;
   repairMessage.textContent = '';
   repairChoice.innerHTML = group.files.map((file, fileIndex) => `
-    <label class="keeper-option"><input type="radio" name="keeper" value="${escapeHtml(file)}" ${fileIndex === 0 ? 'checked' : ''}><span><strong>${fileIndex === 0 ? 'Keep this file' : 'Keep instead'}</strong><small>${escapeHtml(file)}</small></span></label>
+    <div class="keeper-option"><label><input type="radio" name="keeper" value="${escapeHtml(file)}" ${fileIndex === 0 ? 'checked' : ''}><span><strong>${fileIndex === 0 ? 'Keep this file' : 'Keep instead'}</strong><small>${escapeHtml(file)}</small></span></label><div class="file-actions"><button type="button" data-audio-url="${escapeHtml(group.file_previews[fileIndex].audio_url)}" data-audio-name="${escapeHtml(file)}">▶ Play preview</button><button type="button" data-reveal-token="${escapeHtml(group.file_previews[fileIndex].reveal_token)}">Show in Finder</button></div></div>
   `).join('');
   repairPanel.hidden = false;
   repairPanel.scrollIntoView({behavior: 'smooth', block: 'start'});
@@ -194,7 +198,33 @@ restoreRepairButton.addEventListener('click', async () => {
 });
 
 repairChoice.addEventListener('change', () => { previewedRepair = null; applyRepairButton.disabled = true; repairPreview.hidden = true; repairMessage.textContent = 'Keeper changed. Preview the plan again.'; });
-drilldownList.addEventListener('click', (event) => { const item = event.target.closest('[data-duplicate-index]'); if (item) chooseDuplicate(document.querySelector('.drill-trigger.selected')?.dataset.detail, Number(item.dataset.duplicateIndex)); });
+async function handleFileAction(event) {
+  const previewButton = event.target.closest('[data-audio-url]');
+  const revealButton = event.target.closest('[data-reveal-token]');
+  if (!previewButton && !revealButton) return false;
+  event.preventDefault(); event.stopPropagation();
+  if (previewButton) {
+    audioPlayer.src = previewButton.dataset.audioUrl;
+    audioPreviewName.textContent = previewButton.dataset.audioName.split('/').pop();
+    audioPreview.hidden = false;
+    try { await audioPlayer.play(); } catch (_) { /* Native controls remain available. */ }
+  } else {
+    const original = revealButton.textContent;
+    revealButton.disabled = true; revealButton.textContent = 'Opening…';
+    try {
+      const response = await fetch('/api/reveal', {method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({token: revealButton.dataset.revealToken})});
+      const result = await response.json();
+      if (!response.ok) throw new Error(result.error || 'Could not open Finder');
+      revealButton.textContent = 'Shown in Finder';
+    } catch (error) { revealButton.textContent = error.message; }
+    setTimeout(() => { revealButton.disabled = false; revealButton.textContent = original; }, 1800);
+  }
+  return true;
+}
+
+closeAudioPreview.addEventListener('click', () => { audioPlayer.pause(); audioPlayer.removeAttribute('src'); audioPlayer.load(); audioPreview.hidden = true; });
+repairChoice.addEventListener('click', handleFileAction);
+drilldownList.addEventListener('click', async (event) => { if (await handleFileAction(event)) return; const item = event.target.closest('[data-duplicate-index]'); if (item) chooseDuplicate(document.querySelector('.drill-trigger.selected')?.dataset.detail, Number(item.dataset.duplicateIndex)); });
 drilldownList.addEventListener('keydown', (event) => { if (event.key !== 'Enter' && event.key !== ' ') return; const item = event.target.closest('[data-duplicate-index]'); if (item) { event.preventDefault(); chooseDuplicate(document.querySelector('.drill-trigger.selected')?.dataset.detail, Number(item.dataset.duplicateIndex)); } });
 
 function render(data) {

serato_doctor/webui/index.html

@@ -116,8 +116,13 @@
         <div id="backup-summary" class="backup-summary">Analyze your library, then choose a duplicate to preview its automatic backup.</div>
         <div id="backup-list" class="backup-list"></div>
       </section>
+      <div id="audio-preview" class="audio-preview" hidden>
+        <div><span>Now previewing</span><strong id="audio-preview-name"></strong></div>
+        <audio id="audio-player" controls preload="metadata"></audio>
+        <button id="close-audio-preview" type="button" aria-label="Close audio preview">×</button>
+      </div>
     </main>
   </div>
-  <script src="/app.js?v=3" defer></script>
+  <script src="/app.js?v=4" defer></script>
 </body>
 </html>

serato_doctor/webui/layout-fixes.css

@@ -7,3 +7,112 @@
     margin-top: 28px;
   }
 }
+
+.file-compare-row {
+  display: grid;
+  gap: 8px;
+  padding: 9px 0;
+  border-top: 1px solid rgba(255, 255, 255, .05);
+}
+
+.file-compare-row:first-child {
+  border-top: 0;
+}
+
+.file-compare-row div,
+.file-actions {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 7px;
+}
+
+.file-compare-row button,
+.file-actions button {
+  border: 1px solid rgba(155, 135, 245, .25);
+  border-radius: 8px;
+  padding: 7px 9px;
+  background: rgba(155, 135, 245, .08);
+  color: #d8d2f6;
+  font: 700 10px/1 inherit;
+  cursor: pointer;
+}
+
+.keeper-option {
+  justify-content: space-between;
+}
+
+.keeper-option > label {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  min-width: 0;
+  cursor: pointer;
+}
+
+.audio-preview {
+  position: fixed;
+  right: 24px;
+  bottom: 20px;
+  display: grid;
+  grid-template-columns: minmax(150px, .7fr) minmax(240px, 1.3fr) auto;
+  align-items: center;
+  gap: 16px;
+  width: min(720px, calc(100vw - 48px));
+  padding: 13px 14px;
+  border: 1px solid rgba(102, 217, 232, .3);
+  border-radius: 14px;
+  background: rgba(16, 21, 29, .96);
+  box-shadow: 0 16px 48px rgba(0, 0, 0, .45);
+  z-index: 5;
+}
+
+.audio-preview[hidden] {
+  display: none;
+}
+
+.audio-preview span,
+.audio-preview strong {
+  display: block;
+}
+
+.audio-preview span {
+  color: var(--cyan);
+  font-size: 9px;
+  text-transform: uppercase;
+  letter-spacing: .1em;
+}
+
+.audio-preview strong {
+  max-width: 360px;
+  margin-top: 4px;
+  overflow: hidden;
+  color: var(--text);
+  font-size: 11px;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
+.audio-preview audio {
+  width: 100%;
+  height: 34px;
+}
+
+.audio-preview > button {
+  border: 0;
+  background: transparent;
+  color: var(--muted);
+  font-size: 22px;
+  cursor: pointer;
+}
+
+@media (max-width: 680px) {
+  .keeper-option,
+  .audio-preview {
+    align-items: stretch;
+    grid-template-columns: 1fr;
+  }
+
+  .keeper-option {
+    flex-direction: column;
+  }
+}

tests/test_web.py

@@ -3,7 +3,13 @@ from pathlib import Path
 
 import pytest
 
-from serato_doctor.web import STATIC_FILES, analyze_paths, duplicate_repair
+from serato_doctor.web import (
+    STATIC_FILES,
+    _file_token,
+    _verified_audio,
+    analyze_paths,
+    duplicate_repair,
+)
 
 
 def test_web_analysis_uses_production_health_pipeline(tmp_path):
@@ -77,3 +83,33 @@ def test_duplicate_repair_preview_does_not_change_files(tmp_path):
     assert result["database_v2_modified"] is False
     assert second.read_bytes() == b"second"
     assert not second.is_symlink()
+
+
+def test_audio_preview_tokens_only_open_signed_audio(tmp_path):
+    track = tmp_path / "Track.mp3"
+    track.write_bytes(b"audio")
+
+    token = _file_token(track)
+
+    assert _verified_audio(token) == track
+    with pytest.raises(ValueError, match="Invalid or expired"):
+        _verified_audio(token + "changed")
+
+
+def test_duplicate_details_include_preview_and_finder_controls(tmp_path):
+    serato = tmp_path / "_Serato_"
+    serato.mkdir()
+    music = tmp_path / "Music"
+    first = music / "A" / "Track.mp3"
+    second = music / "B" / "Track.mp3"
+    first.parent.mkdir(parents=True)
+    second.parent.mkdir(parents=True)
+    first.write_bytes(b"first")
+    second.write_bytes(b"second")
+
+    result = analyze_paths(serato, music)
+    group = result["details"]["duplicate_filenames"]["items"][0]
+
+    assert len(group["file_previews"]) == 2
+    assert group["file_previews"][0]["audio_url"].startswith("/api/audio?")
+    assert group["file_previews"][0]["reveal_token"]