ersatztv/ErsatzTV.Tests/Integration/LibraryRepositoryTests.cs

using ErsatzTV.Core;
using ErsatzTV.Core.Domain;
using ErsatzTV.Infrastructure.Data;
using ErsatzTV.Infrastructure.Data.Repositories;
using ErsatzTV.Tests.Support;
using LanguageExt;
using Microsoft.EntityFrameworkCore;
using NSubstitute;
using NUnit.Framework;
using Shouldly;
using IFileSystem = System.IO.Abstractions.IFileSystem;

namespace ErsatzTV.Tests.Integration;

[TestFixture]
public class LibraryRepositoryTests
{
    private InMemoryTvContext _db = null!;
    private LibraryRepository _repository = null!;

    [SetUp]
    public async Task SetUp()
    {
        _db = await InMemoryTvContext.CreateAsync();
        _repository = new LibraryRepository(Substitute.For<IFileSystem>(), _db.Factory);
    }

    [TearDown]
    public async Task TearDown() => await _db.DisposeAsync();

    // Regression for ersatztv#488: the Jellyfin (remote) sync path takes its LibraryPath straight off the
    // JellyfinLibrary entity, so LibraryPath.LibraryFolders is never eager-loaded (null). GetOrAddFolder
    // used to read that navigation collection directly and threw ArgumentNullException on the very first
    // item of every Jellyfin music-video scan. The repository must resolve the folder from the database
    // instead, so an unloaded collection is not a precondition.
    [Test]
    public async Task GetOrAddFolder_Should_Create_Folder_When_LibraryFolders_Not_Loaded()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");

        // mimic the Jellyfin path: Paths is populated, but LibraryFolders was never included
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        LibraryFolder result =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        result.ShouldNotBeNull();
        result.Id.ShouldBeGreaterThan(0);
        result.Path.ShouldBe("/data/music/artist1");
        result.LibraryPathId.ShouldBe(libraryPathId);

        await using TvContext context = _db.CreateContext();
        List<LibraryFolder> folders = await context.LibraryFolders
            .Where(f => f.LibraryPathId == libraryPathId)
            .ToListAsync();
        folders.Count.ShouldBe(1);
        folders[0].Path.ShouldBe("/data/music/artist1");
    }

    // Re-scanning must be idempotent: a second GetOrAddFolder for the same path returns the existing row
    // rather than inserting a duplicate LibraryFolder (there is no unique constraint behind it).
    [Test]
    public async Task GetOrAddFolder_Should_Be_Idempotent_On_Rescan()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        LibraryFolder first =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");
        LibraryFolder second =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        second.Id.ShouldBe(first.Id);

        await using TvContext context = _db.CreateContext();
        int count = await context.LibraryFolders.CountAsync(f => f.LibraryPathId == libraryPathId);
        count.ShouldBe(1);
    }

    // Covers the maybeParentFolder = Some(...) branch: on a folder already in the db, the parent id is
    // persisted through the raw Dapper UPDATE against the no-tracking entity (not change tracking), and the
    // returned object reflects it. Guards the AsNoTracking + raw-UPDATE interaction the DB-lookup fix relies on.
    [Test]
    public async Task GetOrAddFolder_Should_Persist_ParentId_On_Existing_Folder()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        LibraryFolder parent =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music");
        // first pass creates the child with no parent
        LibraryFolder child =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");
        child.ParentId.ShouldBeNull();

        // second pass supplies the parent — the existing row must be updated, not duplicated
        LibraryFolder updated =
            await _repository.GetOrAddFolder(libraryPath, Option<int>.Some(parent.Id), "/data/music/artist1");
        updated.Id.ShouldBe(child.Id);
        updated.ParentId.ShouldBe(parent.Id);

        await using TvContext context = _db.CreateContext();
        LibraryFolder persisted = await context.LibraryFolders.SingleAsync(f => f.Id == child.Id);
        persisted.ParentId.ShouldBe(parent.Id);
        int count = await context.LibraryFolders.CountAsync(f => f.Path == "/data/music/artist1");
        count.ShouldBe(1);
    }

    // ersatztv#491: the unique index is on (LibraryPathId, PathHash) because Path is unbounded, so every
    // new row must carry the hash or the constraint is unenforceable for it.
    [Test]
    public async Task GetOrAddFolder_Should_Populate_PathHash_On_New_Folder()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        LibraryFolder result = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        result.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/artist1"));

        await using TvContext context = _db.CreateContext();
        LibraryFolder persisted = await context.LibraryFolders.SingleAsync(f => f.Id == result.Id);
        persisted.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/artist1"));
    }

    // ersatztv#491: rows that predate the PathHash column are left null by the migration (nulls are
    // distinct in a unique index, so the index applies cleanly); the first scan that touches one heals it.
    [Test]
    public async Task GetOrAddFolder_Should_Heal_A_Legacy_Null_PathHash()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        int legacyId;
        await using (TvContext seed = _db.CreateContext())
        {
            var legacy = new LibraryFolder
            {
                LibraryPathId = libraryPathId, Path = "/data/music/artist1", PathHash = null
            };
            await seed.LibraryFolders.AddAsync(legacy);
            await seed.SaveChangesAsync();
            legacyId = legacy.Id;
        }

        LibraryFolder result = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        result.Id.ShouldBe(legacyId);
        result.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/artist1"));

        await using TvContext context = _db.CreateContext();
        LibraryFolder persisted = await context.LibraryFolders.SingleAsync(f => f.Id == legacyId);
        persisted.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/artist1"));
        (await context.LibraryFolders.CountAsync(f => f.LibraryPathId == libraryPathId)).ShouldBe(1);
    }

    // ersatztv#491 / H1: when the lookup matches more than one row (legacy duplicates that predate the
    // unique index, which is exactly the state the migration cleans up), it must resolve deterministically
    // to the lowest Id. An unordered FirstOrDefault can return a different row as the plan changes — and
    // adding the composite index alone can flip it — which would make the PathHash heal non-idempotent:
    // each scan would heal a different row and the second would collide on (LibraryPathId, PathHash).
    [Test]
    public async Task GetOrAddFolder_Should_Resolve_Legacy_Duplicates_Deterministically()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        int firstId;
        await using (TvContext seed = _db.CreateContext())
        {
            var a = new LibraryFolder { LibraryPathId = libraryPathId, Path = "/data/music/artist1" };
            var b = new LibraryFolder { LibraryPathId = libraryPathId, Path = "/data/music/artist1" };
            await seed.LibraryFolders.AddRangeAsync(a, b);
            await seed.SaveChangesAsync();
            firstId = Math.Min(a.Id, b.Id);
        }

        // repeated calls must agree, and must agree with MIN(Id) — the same row the migration keeps
        LibraryFolder first = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");
        LibraryFolder second = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        first.Id.ShouldBe(firstId);
        second.Id.ShouldBe(firstId);

        await using TvContext context = _db.CreateContext();

        // exactly one of the two got the hash — the heal is idempotent, not alternating
        (await context.LibraryFolders.CountAsync(
            f => f.LibraryPathId == libraryPathId && f.PathHash != null)).ShouldBe(1);
        LibraryFolder healed = await context.LibraryFolders.SingleAsync(f => f.Id == firstId);
        healed.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/artist1"));
    }

    // ersatztv#491 / H1: on MySQL the lookup's SQL equality is case-INsensitive (longtext under the
    // default collation), so it hands back BOTH "/x/Foo" and "/x/foo" for a "/x/foo" scan — verified on a
    // real MySQL 8.4 server, where an unordered LIMIT 1 returns "/x/Foo". PathHash is a case-SENSITIVE
    // hash, so identity has to be settled ordinally or the heal stamps the wrong path's hash onto a row.
    //
    // This pins that decision with no database at all, because no SQLite-backed test can: SQLite's `=` on
    // TEXT is binary, so the case-differing candidate never reaches the in-memory step. Feeding the
    // candidate list directly is the only way to exercise it in CI.
    [Test]
    public void ResolveExact_Should_Pick_The_Ordinal_Match_Not_A_Case_Variant()
    {
        var candidates = new List<LibraryFolder>
        {
            new() { Id = 10, Path = "/x/Foo" },
            new() { Id = 11, Path = "/x/foo" }
        };

        LibraryRepository.ResolveExact(candidates, "/x/foo").Id.ShouldBe(11);
        LibraryRepository.ResolveExact(candidates, "/x/Foo").Id.ShouldBe(10);

        // a spelling that matches nothing ordinally is absent, not "close enough"
        LibraryRepository.ResolveExact(candidates, "/x/FOO").ShouldBeNull();
        LibraryRepository.ResolveExact([], "/x/foo").ShouldBeNull();
    }

    // MySQL's comparison is always case-insensitive and, on a PAD SPACE collation, also ignores trailing
    // spaces ('/x/foo' = '/x/foo ' is TRUE under utf8mb4_general_ci and utf8mb4_bin; 8.4's default
    // utf8mb4_0900_ai_ci is NO PAD, so this axis is server-dependent). Where it applies, the SQL narrowing
    // hands back trailing-space siblings too. Those are distinct directories on Linux and hash
    // differently, so the ordinal settle has to keep them apart — same defect class as the case variant,
    // second axis. Ordinal compares length first, so this holds; pin it.
    [Test]
    public void ResolveExact_Should_Distinguish_Paths_Differing_Only_In_Trailing_Space()
    {
        var candidates = new List<LibraryFolder>
        {
            new() { Id = 20, Path = "/x/foo" },
            new() { Id = 21, Path = "/x/foo " }
        };

        LibraryRepository.ResolveExact(candidates, "/x/foo").Id.ShouldBe(20);
        LibraryRepository.ResolveExact(candidates, "/x/foo ").Id.ShouldBe(21);
        LibraryRepository.ResolveExact(candidates, "/x/foo  ").ShouldBeNull();

        // the two spellings must also hash differently, or the unique index would reject one of them and
        // the migration's decision to keep both would be wrong
        PathUtils.GetPathHash("/x/foo").ShouldNotBe(PathUtils.GetPathHash("/x/foo "));
    }

    // Candidates arrive ordered by Id, and the first ordinal match wins — so true duplicates resolve to
    // MIN(Id), the same row the #491 migration keeps.
    [Test]
    public void ResolveExact_Should_Prefer_The_First_Candidate_On_A_True_Duplicate()
    {
        var candidates = new List<LibraryFolder>
        {
            new() { Id = 3, Path = "/x/Foo" },
            new() { Id = 7, Path = "/x/foo" },
            new() { Id = 9, Path = "/x/foo" }
        };

        LibraryRepository.ResolveExact(candidates, "/x/foo").Id.ShouldBe(7);
    }

    // End-to-end companion to the ResolveExact tests above. On SQLite this passes on pre-fix code too (the
    // SQL equality already excludes the case variant); its value is guarding the in-memory step against
    // later being relaxed to OrdinalIgnoreCase, and covering the heal/no-duplicate behaviour around it.
    [Test]
    public async Task GetOrAddFolder_Should_Not_Resolve_A_Folder_Differing_Only_In_Case()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };

        int upperId;
        await using (TvContext seed = _db.CreateContext())
        {
            var upper = new LibraryFolder { LibraryPathId = libraryPathId, Path = "/data/music/Foo" };
            var lower = new LibraryFolder { LibraryPathId = libraryPathId, Path = "/data/music/foo" };
            await seed.LibraryFolders.AddRangeAsync(upper, lower);
            await seed.SaveChangesAsync();
            upperId = upper.Id;
        }

        LibraryFolder result = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/foo");

        result.Path.ShouldBe("/data/music/foo");
        result.Id.ShouldNotBe(upperId);
        result.PathHash.ShouldBe(PathUtils.GetPathHash("/data/music/foo"));

        await using TvContext context = _db.CreateContext();

        // the case-differing sibling must be untouched — no foreign hash stamped onto it
        LibraryFolder upperPersisted = await context.LibraryFolders.SingleAsync(f => f.Id == upperId);
        upperPersisted.Path.ShouldBe("/data/music/Foo");
        upperPersisted.PathHash.ShouldBeNull();

        // and no duplicate was inserted for either spelling
        (await context.LibraryFolders.CountAsync(f => f.LibraryPathId == libraryPathId)).ShouldBe(2);
    }

    // The heal is opportunistic maintenance on a hot scan path: if some other row already owns
    // (LibraryPathId, hash) — a legacy duplicate the migration's grouping could not see — it must leave
    // the row unhealed rather than abort the scan.
    [Test]
    public async Task GetOrAddFolder_Should_Not_Fail_The_Scan_When_The_PathHash_Heal_Collides()
    {
        int libraryPathId = await SeedLibraryPath("/data/music");
        var libraryPath = new LibraryPath { Id = libraryPathId, Path = "/data/music", LibraryFolders = null };
        string hash = PathUtils.GetPathHash("/data/music/artist1");

        int legacyId;
        await using (TvContext seed = _db.CreateContext())
        {
            // a legacy row with a null hash, plus a squatter that already owns the hash it would heal to
            var legacy = new LibraryFolder { LibraryPathId = libraryPathId, Path = "/data/music/artist1" };
            var squatter = new LibraryFolder
            {
                LibraryPathId = libraryPathId, Path = "/data/music/squatter", PathHash = hash
            };
            await seed.LibraryFolders.AddRangeAsync(legacy, squatter);
            await seed.SaveChangesAsync();
            legacyId = legacy.Id;
        }

        // must not throw — the scan continues and simply returns the folder
        LibraryFolder result = await _repository.GetOrAddFolder(libraryPath, Option<int>.None, "/data/music/artist1");

        result.Id.ShouldBe(legacyId);

        await using TvContext context = _db.CreateContext();
        LibraryFolder persisted = await context.LibraryFolders.SingleAsync(f => f.Id == legacyId);
        persisted.PathHash.ShouldBeNull(); // heal declined, not half-applied
    }

    private async Task<int> SeedLibraryPath(string path)
    {
        await using TvContext context = _db.CreateContext();
        var libraryPath = new LibraryPath { Path = path };
        await context.LibraryPaths.AddAsync(libraryPath);
        await context.SaveChangesAsync();
        return libraryPath.Id;
    }
}