Merge feature/analyze-command into develop

2026-06-30 18:17:20 -07:00
parent 22424d0b5c e6f313d98a
commit c92d929f37
5 changed files with 151 additions and 13 deletions
@@ -0,0 +1,37 @@
+# Serato Doctor
+
+Serato Doctor is a read-only-first toolkit for inspecting and eventually repairing
+DJ libraries. Serato is the first supported engine.
+
+## Analyze a Library
+
+```shell
+serato-doctor analyze \
+  --serato ~/Music/_Serato_ \
+  --music ~/Music/Jukebox
+```
+
+Analysis prints a transparent reference-integrity score plus broken references,
+duplicate filenames, unused tracks, and suggested filename matches. It does not
+modify the library or create report files.
+
+If crates contain an older library root, supply it explicitly:
+
+```shell
+serato-doctor analyze --reference-root /Users/old-user/OneDrive/Jukebox
+```
+
+## Generate Detailed Reports
+
+Running without a command preserves the original scanner behavior and writes CSV
+and text reports:
+
+```shell
+serato-doctor --serato ~/Music/_Serato_ --music ~/Music/Jukebox
+```
+
+Use `--verbose` for progress on standard error or `--log-file PATH` for an
+aggregate diagnostic log.
+
+Serato Doctor never repairs files without an explicit future repair workflow,
+preview, backup, and rollback path.
@@ -17,6 +17,7 @@

 ## v0.2 — Diagnostics

+- [x] `serato-doctor analyze` command
 - [ ] Duplicate filename detection
 - [ ] Duplicate audio hash detection
 - [ ] Broken symlink detection
@@ -0,0 +1,27 @@
+# Analyze Command
+
+## Problem
+
+The health and matching engines are only Python APIs. Users need one safe command
+that summarizes library integrity without first interpreting CSV files.
+
+## Architecture
+
+`serato-doctor analyze` reuses the existing configured crate parser and filesystem
+scanner, then prints the immutable health report. The original no-command mode is
+retained as the report-producing scan workflow.
+
+Analyze mode does not create CSV or text reports. Both modes remain read-only with
+respect to Serato crates, databases, and music files.
+
+## Edge Cases
+
+- A library with no references displays `Not assessed` rather than a false score.
+- Historical roots continue to work through repeatable `--reference-root` flags.
+- Normal output remains separate from optional diagnostic logging.
+- Existing scripts that invoke the CLI without a subcommand remain compatible.
+
+## Verification
+
+Tests prove the legacy five-line output and reports remain unchanged, while analyze
+prints health metrics and does not create output files.
@@ -3,6 +3,7 @@ import argparse

 from serato_doctor.config import ScanConfig
 from serato_doctor.crate_parser import parse_crates
+from serato_doctor.health import analyze_health
 from serato_doctor.logging import configure_logging
 from serato_doctor.models.library import Library
 from serato_doctor.scanner import scan_audio
@@ -11,10 +12,23 @@ from serato_doctor.report import write_csv, write_missing_report

 def main():
    parser = argparse.ArgumentParser(prog="serato-doctor")
+    parser.add_argument(
+        "command", nargs="?", choices=("scan", "analyze"), default="scan"
+    )
    parser.add_argument("--serato", default=str(Path.home() / "Music/_Serato_"))
-    parser.add_argument("--music", default=str(Path.home() / "Library/CloudStorage/OneDrive-Personal/Jukebox"))
-    parser.add_argument("--out", default=str(Path.home() / "Desktop/serato_doctor_scan.csv"))
-    parser.add_argument("--report", default=str(Path.home() / "Desktop/serato_doctor_missing_report.txt"))
+    parser.add_argument(
+        "--music",
+        default=str(
+            Path.home() / "Library/CloudStorage/OneDrive-Personal/Jukebox"
+        ),
+    )
+    parser.add_argument(
+        "--out", default=str(Path.home() / "Desktop/serato_doctor_scan.csv")
+    )
+    parser.add_argument(
+        "--report",
+        default=str(Path.home() / "Desktop/serato_doctor_missing_report.txt"),
+    )
    parser.add_argument(
        "--reference-root",
        action="append",
@@ -37,7 +51,7 @@ def main():
        log_file=Path(args.log_file) if args.log_file else None,
    )
    logger = configure_logging(config.verbose, config.log_file)
-    logger.info("Starting read-only library scan")
+    logger.info("Starting read-only library inspection")
    logger.debug("Serato directory: %s", config.serato)
    logger.debug("Music directory: %s", config.music)

@@ -53,15 +67,30 @@ def main():
    logger.info("Scanned %d disk tracks", len(library.tracks))
    logger.info("Found %d references missing by filename", missing_count)

-    write_csv(results, config.out)
-    write_missing_report(results, config.report)
-    logger.info("Wrote CSV and missing-reference reports")
-
-    print(f"Crate references: {len(library.references)}")
-    print(f"Disk tracks: {len(library.tracks)}")
-    print(f"Missing by filename: {missing_count}")
-    print(f"CSV: {config.out}")
-    print(f"Report: {config.report}")
+    if args.command == "analyze":
+        health = analyze_health(library)
+        score = f"{health.score:.1f}%" if health.score is not None else "Not assessed"
+        logger.info("Calculated library health: %s", score)
+        print(f"Overall Health: {score}")
+        print(f"Score Basis: {health.score_basis}")
+        print(f"Tracks: {health.disk_tracks}")
+        print(f"Crate References: {health.total_references}")
+        print(f"Healthy References: {health.healthy_references}")
+        print(f"Broken References: {health.missing_references}")
+        print(f"Unique Missing Filenames: {health.unique_missing_filenames}")
+        print(f"Duplicate Filename Groups: {health.duplicate_filename_groups}")
+        print(f"Duplicate Files: {health.duplicate_files}")
+        print(f"Unused Tracks: {health.unused_tracks}")
+        print(f"Suggested Matches: {health.suggested_matches}")
+    else:
+        write_csv(results, config.out)
+        write_missing_report(results, config.report)
+        logger.info("Wrote CSV and missing-reference reports")
+        print(f"Crate references: {len(library.references)}")
+        print(f"Disk tracks: {len(library.tracks)}")
+        print(f"Missing by filename: {missing_count}")
+        print(f"CSV: {config.out}")
+        print(f"Report: {config.report}")


 if __name__ == "__main__":
@@ -84,3 +84,47 @@ def test_cli_accepts_old_reference_root(tmp_path, monkeypatch, capsys):
    output = capsys.readouterr().out
    assert "Crate references: 1" in output
    assert "Missing by filename: 0" in output
+
+
+def test_analyze_prints_health_without_writing_reports(tmp_path, monkeypatch, capsys):
+    serato = tmp_path / "serato"
+    subcrates = serato / "Subcrates"
+    music = tmp_path / "music"
+    subcrates.mkdir(parents=True)
+    music.mkdir()
+    crate_text = (
+        "Users/sample-user/Jukebox/Found.mp3otrk"
+        "Users/sample-user/Jukebox/Missing.mp3otrk"
+    )
+    (subcrates / "Test.crate").write_bytes(crate_text.encode("utf-16-le"))
+    (music / "Found.mp3").write_bytes(b"synthetic audio")
+    csv_path = tmp_path / "scan.csv"
+    report_path = tmp_path / "report.txt"
+    monkeypatch.setattr(
+        sys,
+        "argv",
+        [
+            "serato-doctor",
+            "analyze",
+            "--serato",
+            str(serato),
+            "--music",
+            str(music),
+            "--out",
+            str(csv_path),
+            "--report",
+            str(report_path),
+        ],
+    )
+
+    main()
+
+    output = capsys.readouterr().out
+    assert "Overall Health: 50.0%" in output
+    assert "Tracks: 1" in output
+    assert "Crate References: 2" in output
+    assert "Healthy References: 1" in output
+    assert "Broken References: 1" in output
+    assert "Unused Tracks: 0" in output
+    assert not csv_path.exists()
+    assert not report_path.exists()