Inboxintel/tests/InboxIntel.IntegrationTests/LiveDbSearchTests.cs

using FluentAssertions;
using InboxIntel.Application.Abstractions;
using InboxIntel.Application.Search;
using InboxIntel.Domain.Entities;
using InboxIntel.Infrastructure.Persistence;
using InboxIntel.Infrastructure.Search;
using Microsoft.EntityFrameworkCore;
using Pgvector;
using Pgvector.EntityFrameworkCore;
using Xunit;

namespace InboxIntel.IntegrationTests;

/// <summary>
/// AUDIT M-7: live-PostgreSQL regression tests for the search paths the InMemory provider
/// cannot translate (websearch_to_tsquery, ts_rank_cd, ts_headline, pg_trgm word_similarity,
/// pgvector cosine). These previously existed only as throwaway manual verifications.
///
/// They run when LIVEDB_CONNECTION points at a pgvector-enabled Postgres (the CI `db-tests`
/// job provides one as a service container) and no-op otherwise, so the default local /
/// InMemory test run is unaffected.
/// </summary>
[Trait("Category", "LiveDb")]
[Collection("LiveDb")] // serialise LiveDb classes: concurrent MigrateAsync on a fresh DB races
public class LiveDbSearchTests
{
    private static string? Conn => Environment.GetEnvironmentVariable("LIVEDB_CONNECTION");

    private sealed class FakeCurrentUser : ICurrentUser
    {
        public Guid UserId { get; set; }
        public bool IsAuthenticated => UserId != Guid.Empty;
    }

    private static DbContextOptions<AppDbContext> Options() =>
        new DbContextOptionsBuilder<AppDbContext>().UseNpgsql(Conn!, o => o.UseVector()).Options;

    private static Vector Vec(float x, float y)
    {
        var arr = new float[768];
        arr[0] = x; arr[1] = y;
        return new Vector(arr);
    }

    private static async Task<Guid> SeedAsync(DbContextOptions<AppDbContext> opts)
    {
        var uid = Guid.NewGuid();
        using var db = new AppDbContext(opts, new FakeCurrentUser());
        await db.Database.MigrateAsync();
        db.Users.Add(new User { Id = uid, GoogleSubjectId = "g" + uid, Email = uid + "@t.t" });
        var dom = new MailDomain { UserId = uid, Name = "t.t" };
        var snd = new Sender { UserId = uid, Address = "a@t.t", DisplayName = "A", Domain = dom };
        var thr = new MailThread { UserId = uid, GmailThreadId = "th" + uid };
        db.Domains.Add(dom); db.Senders.Add(snd); db.Threads.Add(thr);
        db.Emails.AddRange(
            new Email { UserId = uid, GmailMessageId = "subj" + uid, Subject = "Invoice March", BodyText = "hello there", Sender = snd, Thread = thr, Embedding = Vec(1, 0), SentAtUtc = DateTimeOffset.UtcNow.AddDays(-2) },
            new Email { UserId = uid, GmailMessageId = "body" + uid, Subject = "Weekly notes", BodyText = "we received your invoice today", Sender = snd, Thread = thr, Embedding = Vec(0, 1), SentAtUtc = DateTimeOffset.UtcNow.AddDays(-1) });
        await db.SaveChangesAsync();
        return uid;
    }

    private static async Task CleanupAsync(DbContextOptions<AppDbContext> opts, Guid uid)
    {
        using var db = new AppDbContext(opts, new FakeCurrentUser());
        await db.Emails.Where(e => e.UserId == uid).ExecuteDeleteAsync();
        await db.Threads.Where(t => t.UserId == uid).ExecuteDeleteAsync();
        await db.Senders.Where(s => s.UserId == uid).ExecuteDeleteAsync();
        await db.Domains.Where(d => d.UserId == uid).ExecuteDeleteAsync();
        await db.Users.Where(u => u.Id == uid).ExecuteDeleteAsync();
    }

    [Fact]
    public async Task Ranked_search_weights_subject_hits_first_and_explains_body_hits()
    {
        if (Conn is null) return; // soft-skip outside the live-db CI job
        var opts = Options();
        var uid = await SeedAsync(opts);
        try
        {
            using var ctx = new AppDbContext(opts, new FakeCurrentUser { UserId = uid });
            var res = await new SearchService(ctx).SearchAsync(uid, GmailQueryParser.Parse("invoice", 1, 10));

            res.TotalCount.Should().Be(2);
            res.Items[0].Subject.Should().Be("Invoice March");                 // subject weight A wins
            var bodyHit = res.Items.First(i => i.Subject == "Weekly notes");
            bodyHit.MatchHighlight.Should().Contain("invoice");                // ts_headline present
            bodyHit.MatchHighlight.Should().Contain(((char)0xE000).ToString()); // sentinel wrapping
        }
        finally { await CleanupAsync(opts, uid); }
    }

    [Fact]
    public async Task Typo_falls_back_to_trigram_word_similarity()
    {
        if (Conn is null) return;
        var opts = Options();
        var uid = await SeedAsync(opts);
        try
        {
            using var ctx = new AppDbContext(opts, new FakeCurrentUser { UserId = uid });
            var res = await new SearchService(ctx).SearchAsync(uid, GmailQueryParser.Parse("invoce", 1, 10));
            res.TotalCount.Should().BeGreaterThan(0, "the typo should fuzzy-match via pg_trgm");
        }
        finally { await CleanupAsync(opts, uid); }
    }

    [Fact]
    public async Task Pgvector_cosine_orders_nearest_embedding_first()
    {
        if (Conn is null) return;
        var opts = Options();
        var uid = await SeedAsync(opts);
        try
        {
            using var ctx = new AppDbContext(opts, new FakeCurrentUser { UserId = uid });
            var query = Vec(1, 0);
            var ordered = await ctx.Emails
                .Where(e => e.Embedding != null)
                .OrderBy(e => e.Embedding!.CosineDistance(query))
                .Select(e => e.Subject)
                .ToListAsync();
            ordered.Should().Equal("Invoice March", "Weekly notes");
        }
        finally { await CleanupAsync(opts, uid); }
    }
}