ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests/Scripts/SiteScriptCompileCacheTests.cs

using Microsoft.CodeAnalysis.CSharp.Scripting;
using Microsoft.CodeAnalysis.Scripting;
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Scripts;

namespace ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.Scripts;

/// <summary>
/// Tests for the process-wide <see cref="SiteScriptCompileCache"/>. The cache is
/// static/process-wide state, so this class shares the "SiteScriptCompileCache" xunit
/// collection with <c>ScriptCompilationServiceTests</c> and <c>DeploymentWarmThenGateTests</c>
/// (no cross-class parallelism between those three, so no concurrent
/// <see cref="SiteScriptCompileCache.Clear"/>).
/// </summary>
/// <remarks>
/// <para>
/// <b>Deferred-work register row 91.</b> That collection does NOT stop the rest of the
/// assembly: any test class that compiles a script — Instance/Script actor tests, deployment
/// tests — goes through <see cref="SiteScriptCompileCache.GetOrAdd"/> too, in parallel, and
/// bumps the same process-global <see cref="SiteScriptCompileCache.Hits"/> /
/// <see cref="SiteScriptCompileCache.Count"/>. Absolute assertions such as
/// <c>Assert.Equal(1, Hits)</c> after a <c>Clear()</c> therefore only held while nothing else
/// happened to be compiling; they failed roughly 1 run in 4 of a full parallel solution run and
/// were always green in isolation.
/// </para>
/// <para>
/// The fix follows the register's row-74 pattern: assert the DELTA attributable to this test's
/// OWN keys across its own scoped action, never an absolute global value. Two habits carry it:
/// every test keys its cache entries on a per-test-instance unique token (<see cref="_uniq"/>),
/// so no other class can collide with or serve them; and the global counters are only ever
/// asserted as one-sided bounds (<c>&gt;= baseline + n</c>), since foreign traffic can only add.
/// A collection fixture spanning every script-compiling class in the assembly would fix it too,
/// but would serialise most of the suite for the benefit of five facts.
/// </para>
/// </remarks>
[Collection("SiteScriptCompileCache")]
public class SiteScriptCompileCacheTests
{
    /// <summary>
    /// Slack allowed on <see cref="SiteScriptCompileCache.Count"/> bounds for entries inserted
    /// by test classes outside this collection while a bound test runs (register row 91). The
    /// exactness of the eviction claims comes from the per-key probes, not from this bound.
    /// </summary>
    private const int ForeignEntrySlack = 512;

    /// <summary>Per-test-instance token making every cache key in this test uniquely ours.</summary>
    private readonly string _uniq = Guid.NewGuid().ToString("N");

    /// <summary>Builds a cache key body that no other test class in the assembly can produce.</summary>
    private string Code(string body) => $"/*{_uniq}*/ {body}";

    private static ScriptCompilationResult Ok() =>
        ScriptCompilationResult.Succeeded(CSharpScript.Create<object?>("1", ScriptOptions.Default, typeof(ScriptGlobals)));

    [Fact]
    public void GetOrAdd_SameCodeAndGlobals_ComputesOnce()
    {
        var code = Code("return 1;");
        var hitsBefore = SiteScriptCompileCache.Hits;
        var factoryCalls = 0;
        ScriptCompilationResult Factory() { factoryCalls++; return Ok(); }

        var r1 = SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals), Factory);
        var r2 = SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals), Factory);

        // Scoped to our own key, so these two are exact and are the real claim: one compile,
        // and the second lookup returned that very instance rather than a re-computation.
        Assert.Equal(1, factoryCalls);
        Assert.Same(r1, r2);

        // Hits is process-global; a parallel class's compile can only push the delta up, so the
        // claim "the second lookup was counted as a hit" is a lower bound, not an equality.
        Assert.True(SiteScriptCompileCache.Hits >= hitsBefore + 1,
            $"expected the second GetOrAdd to register a hit; hits went {hitsBefore} -> {SiteScriptCompileCache.Hits}");
    }

    [Fact]
    public void GetOrAdd_SameCode_DifferentGlobals_AreSeparateEntries()
    {
        var code = Code("1 > 0");
        var scriptCompiles = 0;
        var triggerCompiles = 0;

        var script = SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals),
            () => { scriptCompiles++; return Ok(); });
        var trigger = SiteScriptCompileCache.GetOrAdd(code, typeof(TriggerExpressionGlobals),
            () => { triggerCompiles++; return Ok(); });

        // "No cross-globals hit" asserted where it is actually observable and ours: the second
        // lookup had to compute, and the two globals surfaces hold distinct entries. (The old
        // form — Count == 2 and Hits == 0 on the process-global counters — was only true while
        // no other class was compiling.)
        Assert.Equal(1, scriptCompiles);
        Assert.Equal(1, triggerCompiles);
        Assert.NotSame(script, trigger);

        // Each entry is independently addressable afterwards: re-getting either must serve the
        // matching cached result, never the other globals surface's.
        Assert.Same(script, SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals),
            () => throw new InvalidOperationException("script entry was not cached")));
        Assert.Same(trigger, SiteScriptCompileCache.GetOrAdd(code, typeof(TriggerExpressionGlobals),
            () => throw new InvalidOperationException("trigger entry was not cached")));
    }

    [Fact]
    public void Overflow_StaysWithinTheBound()
    {
        SiteScriptCompileCache.Clear();
        for (var i = 0; i <= SiteScriptCompileCache.MaxEntries; i++)
            SiteScriptCompileCache.GetOrAdd(Code($"return {i};"), typeof(ScriptGlobals), Ok);

        // MaxEntries + 1 distinct inserts must not all be resident — the sweep ran. The bound
        // carries slack for foreign inserts (register row 91); the sharp claim is the eviction
        // probe below, which is scoped to keys only this test can produce.
        Assert.True(SiteScriptCompileCache.Count <= SiteScriptCompileCache.MaxEntries + ForeignEntrySlack,
            $"cache grew past its bound: {SiteScriptCompileCache.Count} vs max {SiteScriptCompileCache.MaxEntries}");

        var recomputed = 0;
        for (var i = 0; i < 16; i++)
        {
            var code = Code($"return {i};");
            SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals), () => { recomputed++; return Ok(); });
        }

        Assert.True(recomputed > 0, "no oldest-batch entry was evicted — the overflow sweep did not run");
    }

    // ── WP3.1: approximate LRU replaced the wholesale-Clear overflow cliff ──────────

    /// <summary>
    /// WP3.1 (test group 8): overflow must evict only the OLDEST batch, keeping hot entries.
    /// The old behaviour cleared all 1024 entries, so the very next deploy or Instance-Actor
    /// start paid a full recompile storm on actor threads.
    /// </summary>
    [Fact]
    public void Overflow_EvictsOldestBatch_AndKeepsRecentlyTouchedEntries()
    {
        // Note: the cache is process-wide static and other test classes compile into it
        // concurrently, so the assertions below are phrased as properties of the eviction
        // policy (what survives, what does not, nothing is wiped) rather than as exact
        // counts, which no test can own here.
        SiteScriptCompileCache.Clear();

        // Fill to the bound. Entries 1..N are inserted oldest-first.
        for (var i = 0; i < SiteScriptCompileCache.MaxEntries; i++)
            SiteScriptCompileCache.GetOrAdd(Code($"return {i};"), typeof(ScriptGlobals), Ok);

        // Touch entry 0 so it carries the NEWEST access stamp despite being inserted first.
        var hot = SiteScriptCompileCache.GetOrAdd(Code("return 0;"), typeof(ScriptGlobals), Ok);
        var hitsAfterTouch = SiteScriptCompileCache.Hits;

        // Push well past the bound so at least one eviction sweep definitely runs.
        for (var i = 0; i < 200; i++)
            SiteScriptCompileCache.GetOrAdd(Code($"return overflow{i};"), typeof(ScriptGlobals), Ok);

        // Nothing was cleared wholesale: the cache is still most of the way full and the hit
        // counter survived (Clear() would have reset it to 0).
        Assert.True(SiteScriptCompileCache.Count > SiteScriptCompileCache.MaxEntries / 2,
            $"cache collapsed to {SiteScriptCompileCache.Count} entries — this looks like a wholesale clear");
        Assert.True(SiteScriptCompileCache.Hits >= hitsAfterTouch);

        // The touched entry survived the sweep — a hit, not a recompile. This is the LRU
        // property: recency, not insertion order, decides what stays.
        var hitsBefore = SiteScriptCompileCache.Hits;
        var again = SiteScriptCompileCache.GetOrAdd(Code("return 0;"), typeof(ScriptGlobals),
            () => throw new InvalidOperationException("hot entry was evicted — LRU is not keeping recently-used entries"));
        // Assert.Same is the sharp claim (our own key, our own instance). The counter check is a
        // lower bound: Hits is process-global and a parallel class's hit lands in the same window
        // (register row 91 — this was `Assert.Equal(hitsBefore + 1, …)`).
        Assert.Same(hot, again);
        Assert.True(SiteScriptCompileCache.Hits >= hitsBefore + 1,
            $"expected the surviving hot entry to register a hit; hits went {hitsBefore} -> {SiteScriptCompileCache.Hits}");

        // …and untouched old entries genuinely were evicted, so the sweep really ran.
        var recomputed = 0;
        for (var i = 1; i <= 16; i++)
        {
            var code = Code($"return {i};");
            SiteScriptCompileCache.GetOrAdd(code, typeof(ScriptGlobals),
                () => { recomputed++; return Ok(); });
        }
        Assert.True(recomputed > 0, "no old entry was evicted — the overflow sweep did not run");
    }

    /// <summary>
    /// WP3.1: concurrent inserts crossing the bound together must not blow past it — the
    /// eviction sweep is double-checked under its own lock precisely so a stampede performs
    /// one sweep rather than one per racing thread.
    /// </summary>
    [Fact]
    public async Task ConcurrentGetOrAddStorm_KeepsTheBound()
    {
        SiteScriptCompileCache.Clear();

        const int perTask = 400;
        var tasks = Enumerable.Range(0, 8).Select(t => Task.Run(() =>
        {
            for (var i = 0; i < perTask; i++)
                SiteScriptCompileCache.GetOrAdd(Code($"return {t}_{i};"), typeof(ScriptGlobals), Ok);
        }));

        await Task.WhenAll(tasks);

        // A small transient overshoot is by design: threads that lose the double-checked
        // eviction race still insert their own entry afterwards, so the ceiling is "bounded",
        // not "never exceeded by one". The property under test is that 3200 distinct inserts
        // do not accumulate — before WP3.1 this was a wholesale Clear(), and a per-entry
        // eviction bug would show up here as unbounded growth, not as a handful of extra rows.
        // (Other test classes compile into this process-wide cache concurrently, which is the
        // other reason the bound is asserted with slack rather than exactly.)
        Assert.True(SiteScriptCompileCache.Count <= SiteScriptCompileCache.MaxEntries + ForeignEntrySlack,
            $"cache grew past its bound: {SiteScriptCompileCache.Count} vs max {SiteScriptCompileCache.MaxEntries} " +
            $"after {8 * perTask} distinct inserts");
    }
}