lmxopcua/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Historian.Sql.Common.Tests/SdkAggregateParityTests.cs

using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Conformance;
using static ZB.MOM.WW.OtOpcUa.Driver.Historian.Sql.Common.Tests.Fixture;

namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Sql.Common.Tests;

/// <summary>
///     #677: our processed reads against the pinned SDK's own Part 13 aggregate calculators (<see cref="SdkAggregateOracle"/>),
///     forward AND reverse, bucket by bucket — timestamps, values and status. The per-sample aggregates are bucketed with
///     <see cref="BucketPlan.IndexOf"/> (the C# statement of the backends' SQL bucket math; the integration suites run the
///     same comparison through the real SQL) and evaluated by <see cref="AggregateEvaluator.EvaluateAll"/>; the
///     time-weighted ones by <see cref="TimeWeightedAggregator"/>.
/// </summary>
/// <remarks>
///     Deliberate, documented divergences the datasets avoid (they are not anchoring questions):
///     <list type="bullet">
///       <item>an <b>empty</b> interval inside the data range: the SDK's Count answers 0/Good, ours <c>BadNoData</c>;</item>
///       <item><b>Uncertain</b> samples in a per-sample aggregate: the SDK's Average/Count/Min/Max use Good samples only,
///         ours every usable (Good + Uncertain) sample (TreatUncertainAsBad = false applied consistently);</item>
///       <item>the per-sample <b>Calculated / MultipleValues</b> info bits (the SDK's MinMax sets Calculated only when the
///         extreme is not at the interval start, and flags ties) — those comparisons check code bits + Partial only;</item>
///       <item>a <b>truncated</b> interval: ours sets Partial on a non-Bad time-weighted result (Part 13 §5.3.3.2 Case 3
///         requires it; the SDK does not), so the non-multiple windows mask that one bucket's Partial bit;</item>
///       <item>a time-weighted <c>BadNoData</c> carries the Calculated bit in ours (every processed status does), not in the
///         SDK's — masked by <see cref="MaskDocumented"/>;</item>
///       <item><b>TimeAverage2 / Total2 over an interval wholly inside an outage:</b> ours generic <c>Bad</c> (data, but no
///         non-Bad time — Part 13's PercentData rule), the SDK <c>BadNoData</c> — masked by <see cref="MaskDocumented"/>;</item>
///       <item><b>the end-of-data interval</b> (the last sample inside it, nothing after) of TimeAverage2 / Total2 /
///         PercentGood / PercentBad: the SDK gives the region after the last sample a 1 ms duration (an artifact of its
///         <c>GetRegionsInValueSet</c>); Part 13 ends TimeAverage2/Total2 at the last sample and runs the PercentGood/Bad
///         region to the interval end, which ours does (#680; pinned by <c>TimeWeightedAggregatorTests</c>). That
///         interval's value is not compared; its status, Partial bit and timestamp are.</item>
///       <item><b>TimeAverage / Total, reverse, a sample exactly on an interval's later edge:</b> the SDK's backward
///         <c>UpdateSlice</c> files it as the early bound (below), so the interval takes the status of the segment beyond
///         it (Uncertain when that segment skips a Bad sample); ours keeps the interval's own segments — masked by
///         <see cref="MaskDocumented"/>;</item>
///       <item><b>Interpolative, reverse, a sample exactly at the point:</b> the SDK's backward <c>UpdateSlice</c> files
///         a sample AT the point as the early bound (<c>&gt;= 0</c>), so it interpolates from it to the next Good sample —
///         same value, but the Interpolated bit, and Uncertain when a Bad sample sits between. Ours returns the raw
///         sample with its own status in both directions (as the SDK itself does forward). Reverse Interpolative
///         therefore compares timestamps and values (the anchoring question) but not status. (The SDK's asymmetry —
///         forward it returns the raw sample — is its defect; ours is the same in both directions.)</item>
///     </list>
/// </remarks>
public sealed class SdkAggregateParityTests
{
    private static readonly DateTime Now = At(3600);

    /// <summary>Dense: every 2.5 s from −10 to +100, values cycling, one Bad sample at +22.5 — no empty interval.</summary>
    private static readonly StoredSample[] Dense = Enumerable.Range(0, 45)
        .Select(i => (t: -10 + i * 2.5, i))
        .Select(x => S(x.t, HistorianValue.FromDouble(10 + (x.i * 7 % 13)), x.t == 22.5 ? Bad : Good))
        .ToArray();

    /// <summary>Tag A with Good bounds on both sides, plus an Uncertain sample and an outage marker further on.</summary>
    private static readonly StoredSample[] Bounded =
    [
        S(-10, HistorianValue.FromDouble(5), Good),
        .. A,
        S(55, HistorianValue.FromDouble(70), Uncertain),
        S(62, HistorianValue.Empty, BadNoCommunication),
        S(71, HistorianValue.FromDouble(30), Good),
        S(100, HistorianValue.FromDouble(60), Good),
    ];

    /// <summary>
    ///     #680: data that ENDS inside every window (nothing after +52.5): every 2.5 s from −10, values cycling, a Bad
    ///     sample at +22.5 and an Uncertain one at +40 — the end-of-data rules (TimeAverage2/Total2 stop at the last
    ///     sample, Partial, then BadNoData; TimeAverage/Total extrapolate, Uncertain).
    /// </summary>
    private static readonly StoredSample[] EndsInside = Enumerable.Range(0, 26)
        .Select(i => (t: -10 + i * 2.5, i))
        .Select(x => S(x.t, HistorianValue.FromDouble(10 + (x.i * 7 % 13)),
            x.t == 22.5 ? Bad : x.t == 40 ? Uncertain : Good))
        .ToArray();

    /// <summary>
    ///     #680: an outage +18 … +45 that wholly contains an interval of every window ([20,40), [20,35), [23,43), (20,40]):
    ///     TimeAverage/Total bridge it (Uncertain); TimeAverage2/Total2 have no non-Bad time there.
    /// </summary>
    private static readonly StoredSample[] OutageInside =
    [
        S(-10, HistorianValue.FromDouble(5), Good),
        S(0, HistorianValue.FromDouble(10), Good),
        S(15, HistorianValue.FromDouble(20), Good),
        S(18, HistorianValue.Empty, BadNoCommunication),
        S(45, HistorianValue.FromDouble(30), Good),
        S(60, HistorianValue.FromDouble(40), Good),
        S(100, HistorianValue.FromDouble(40), Good),
    ];

    /// <summary>Data that starts inside the window (no sample before +7) and runs past its end.</summary>
    private static readonly StoredSample[] LateStart = Enumerable.Range(0, 20)
        .Select(i => S(7 + i * 5, HistorianValue.FromDouble(i % 2 == 0 ? 20 : 40), Good))
        .ToArray();

    public static TheoryData<double, double, double> Windows => new()
    {
        { 0, 80, 20 }, { 80, 0, 20 },   // whole intervals (samples sit on the edges: the inclusivity question)
        { 0, 50, 20 }, { 50, 0, 20 },   // a truncated interval: latest forward, EARLIEST reverse
        { 5, 80, 15 }, { 80, 5, 15 },   // a misaligned window
        { 3, 77, 20 }, { 77, 3, 20 },   // misaligned and truncated
        { 0, 60, 0 }, { 60, 0, 0 },     // one interval
    };

    private static IReadOnlyList<DataValueSnapshot> Ours(HistoryAggregateType agg, double from, double to, double intervalS,
        StoredSample[] data)
    {
        var plan = BucketPlan.Create(At(from), At(to), TimeSpan.FromSeconds(intervalS));
        if (AggregateFamilies.FamilyOf(agg) == AggregateFamily.TimeWeighted)
            return TimeWeightedAggregator.Evaluate(agg, plan, data, Now);
        return AggregateEvaluator.EvaluateAll(agg, plan, InMemoryRows(plan, data, agg == HistoryAggregateType.MaximumActualTime),
            data.Min(s => s.TimeUtc), Now);
    }

    private static IReadOnlyList<SdkAggregateOracle.Result> Sdk(HistoryAggregateType agg, double from, double to,
        double intervalS, StoredSample[] data)
    {
        var interval = intervalS > 0 ? TimeSpan.FromSeconds(intervalS) : (At(to) - At(from)).Duration();
        return SdkAggregateOracle.Run(agg, At(from), At(to), interval, data.Select(s => (s.TimeUtc, s.Value, s.Status)));
    }

    /// <summary>Masks the Partial bit of our one truncated interval (a documented divergence: ours flags it, the SDK does not).</summary>
    private static IReadOnlyList<DataValueSnapshot> MaskTruncation(IReadOnlyList<DataValueSnapshot> ours, double from,
        double to, double intervalS)
    {
        var plan = BucketPlan.Create(At(from), At(to), TimeSpan.FromSeconds(intervalS));
        var list = ours.ToList();
        for (long i = 0; i < plan.BucketCount; i++)
        {
            if (!plan.IsTruncated(i)) continue;
            var k = (int)(plan.Reversed ? plan.BucketCount - 1 - i : i);
            list[k] = list[k] with { StatusCode = list[k].StatusCode & ~HistorianInfoBits.HistorianPartial };
        }
        return list;
    }

    /// <summary>
    ///     Applies the documented divergences listed on the class (other than truncation): strips the Calculated bit from our
    ///     <c>BadNoData</c>; maps our generic-Bad TimeAverage2/Total2 outage interval to the SDK's <c>BadNoData</c>; takes the
    ///     SDK's value for the end-of-data interval of TimeAverage2/Total2/PercentGood/PercentBad (its 1 ms artifact).
    /// </summary>
    private static IReadOnlyList<DataValueSnapshot> MaskDocumented(HistoryAggregateType agg, IReadOnlyList<DataValueSnapshot> ours,
        IReadOnlyList<SdkAggregateOracle.Result> sdk, double from, double to, double intervalS, StoredSample[] data)
    {
        var plan = BucketPlan.Create(At(from), At(to), TimeSpan.FromSeconds(intervalS));
        var list = ours.ToList();
        var last = data.Max(x => x.TimeUtc).Ticks;
        var dataEnds = last < Math.Max(At(from).Ticks, At(to).Ticks) && data.Single(x => x.TimeUtc.Ticks == last).IsUsable;
        for (long i = 0; i < plan.BucketCount; i++)
        {
            var k = (int)(plan.Reversed ? plan.BucketCount - 1 - i : i);
            if (k >= sdk.Count) continue; // the count mismatch is reported by ShouldMatch
            var code = list[k].StatusCode & StatusBits.CodeBitsMask;
            if (code == HistorianStatusCodes.BadNoData)
                list[k] = list[k] with { StatusCode = list[k].StatusCode & ~StatusBits.HistorianBitsMask };
            var twoVariant = agg is HistoryAggregateType.TimeAverage2 or HistoryAggregateType.Total2;
            if (twoVariant && code == HistorianStatusCodes.Bad && (sdk[k].StatusCode & StatusBits.CodeBitsMask) == HistorianStatusCodes.BadNoData)
                list[k] = list[k] with { StatusCode = HistorianStatusCodes.BadNoData };
            // Reverse TimeAverage/Total: the SDK's backward UpdateSlice files a sample exactly on the interval's later edge
            // as the early bound, so the interval inherits the status of the segment beyond it (the root cause of the
            // reverse Interpolative divergence). Ours keeps the interval's own segments.
            if (plan.Reversed && agg is HistoryAggregateType.TimeAverage or HistoryAggregateType.Total
                && data.Any(x => x.TimeUtc.Ticks == plan.UpperTicks(i))
                && code == HistorianStatusCodes.Good
                && (sdk[k].StatusCode & StatusBits.CodeBitsMask) == HistorianStatusCodes.UncertainDataSubNormal)
                list[k] = list[k] with { StatusCode = (list[k].StatusCode & ~StatusBits.CodeBitsMask) | HistorianStatusCodes.UncertainDataSubNormal };
            if (dataEnds && (twoVariant || agg is HistoryAggregateType.PercentGood or HistoryAggregateType.PercentBad)
                && last >= plan.LowerTicks(i) && last < plan.UpperTicks(i) && sdk[k].Value is not null)
                list[k] = list[k] with { Value = sdk[k].Value };
        }
        return list;
    }

    [Theory]
    [MemberData(nameof(Windows))]
    public void Time_weighted_aggregates_match_the_SDK(double from, double to, double intervalS)
    {
        var failures = new List<string>();
        foreach (var agg in new[]
                 {
                     HistoryAggregateType.TimeAverage, HistoryAggregateType.TimeAverage2, HistoryAggregateType.Total,
                     HistoryAggregateType.Total2, HistoryAggregateType.Interpolative, HistoryAggregateType.PercentGood,
                     HistoryAggregateType.PercentBad,
                 })
        foreach (var (name, data) in new[]
                 {
                     ("Bounded", Bounded), ("Dense", Dense), ("EndsInside", EndsInside), ("OutageInside", OutageInside),
                 })
        {
            try
            {
                var sdk = Sdk(agg, from, to, intervalS, data);
                var ours = MaskDocumented(agg, MaskTruncation(Ours(agg, from, to, intervalS, data), from, to, intervalS),
                    sdk, from, to, intervalS, data);
                SdkAggregateOracle.ShouldMatch(ours, sdk, $"{agg} {name} {from}→{to}/{intervalS}s",
                    compareCalculatedInterpolatedBits: !(agg == HistoryAggregateType.Interpolative && from > to),
                    compareCodeBits: !(agg == HistoryAggregateType.Interpolative && from > to));
            }
            catch (Exception ex)
            {
                failures.Add(ex.Message);
            }
        }
        failures.ShouldBeEmpty(string.Join("\n", failures));
    }

    [Theory]
    [MemberData(nameof(Windows))]
    public void Per_sample_aggregates_match_the_SDK(double from, double to, double intervalS)
    {
        var failures = new List<string>();
        foreach (var agg in PerSample)
        {
            try
            {
                SdkAggregateOracle.ShouldMatch(Ours(agg, from, to, intervalS, Dense), Sdk(agg, from, to, intervalS, Dense),
                    $"{agg} Dense {from}→{to}/{intervalS}s", compareCalculatedInterpolatedBits: false,
                    // pre-existing, #680: the SDK's Start/End return the raw first/last sample (any quality) with its own
                    // timestamp and stored status; ours return the first/last USABLE value stamped with the interval, under the
                    // per-sample status rule. The SDK's Delta is Good even when a Bad sample sits in the interval; ours is
                    // Uncertain. Values are compared wherever the SDK's answer is not Bad.
                    compareTimestamps: !StartOrEnd(agg),
                    compareCodeBits: !StartOrEnd(agg) && agg != HistoryAggregateType.Delta);
            }
            catch (Exception ex)
            {
                failures.Add(ex.Message);
            }
        }
        failures.ShouldBeEmpty(string.Join("\n", failures));
    }

    private static readonly HistoryAggregateType[] PerSample =
    [
        HistoryAggregateType.Average, HistoryAggregateType.Minimum, HistoryAggregateType.Maximum,
        HistoryAggregateType.Count, HistoryAggregateType.Range, HistoryAggregateType.Start, HistoryAggregateType.End,
        HistoryAggregateType.Delta, HistoryAggregateType.MinimumActualTime, HistoryAggregateType.MaximumActualTime,
    ];

    private static bool StartOrEnd(HistoryAggregateType agg) =>
        agg is HistoryAggregateType.Start or HistoryAggregateType.End;

    [Theory]
    [InlineData(HistoryAggregateType.TimeAverage)]
    [InlineData(HistoryAggregateType.TimeAverage2)]
    [InlineData(HistoryAggregateType.Total)]
    [InlineData(HistoryAggregateType.Total2)]
    [InlineData(HistoryAggregateType.Minimum)]
    [InlineData(HistoryAggregateType.Maximum)]
    [InlineData(HistoryAggregateType.Count)]
    [InlineData(HistoryAggregateType.Range)]
    [InlineData(HistoryAggregateType.Delta)]
    [InlineData(HistoryAggregateType.Start)]
    [InlineData(HistoryAggregateType.Average)]
    public void A_reverse_read_over_data_starting_inside_the_window_sets_no_start_of_data_Partial(HistoryAggregateType agg)
    {
        // Review F1: the SDK applies its start-of-data rule only on a FORWARD read (a reverse read keys m_startOfData on the
        // first value it is fed — the latest — which is past the window here). Reverse 40 → 0 at 10 s, first sample +7:
        // (0,10] holds the start of the data but is NOT Partial.
        var tw = AggregateFamilies.FamilyOf(agg) == AggregateFamily.TimeWeighted;
        var ours = Ours(agg, 40, 0, 10, LateStart);
        SdkAggregateOracle.ShouldMatch(ours, Sdk(agg, 40, 0, 10, LateStart), $"{agg} reverse LateStart",
            compareCalculatedInterpolatedBits: tw,
            // pre-existing, #680: Start's raw-sample timestamp/status (see Per_sample_aggregates_match_the_SDK).
            compareTimestamps: !StartOrEnd(agg),
            compareCodeBits: !StartOrEnd(agg) && agg != HistoryAggregateType.Delta);
        ours.ShouldAllBe(x => (x.StatusCode & HistorianInfoBits.HistorianPartial) == 0);
    }

    [Theory]
    [InlineData(HistoryAggregateType.TimeAverage)]
    [InlineData(HistoryAggregateType.TimeAverage2)]
    [InlineData(HistoryAggregateType.Total)]
    [InlineData(HistoryAggregateType.Total2)]
    [InlineData(HistoryAggregateType.Minimum)]
    [InlineData(HistoryAggregateType.Maximum)]
    [InlineData(HistoryAggregateType.Count)]
    [InlineData(HistoryAggregateType.Average)]
    public void The_interval_the_data_starts_inside_matches_the_SDK_Partial_bit(HistoryAggregateType agg)
    {
        // Forward [0,40) at 10 s: the data starts at +7, inside [0,10) — the SDK sets Partial there (m_startOfData) for
        // every calculator but plain Average; [10,20) … are fully covered.
        var tw = AggregateFamilies.FamilyOf(agg) == AggregateFamily.TimeWeighted;
        var ours = Ours(agg, 0, 40, 10, LateStart);
        SdkAggregateOracle.ShouldMatch(ours, Sdk(agg, 0, 40, 10, LateStart), $"{agg} LateStart",
            compareCalculatedInterpolatedBits: tw);
        (ours[0].StatusCode & HistorianInfoBits.HistorianPartial).ShouldBe(
            agg == HistoryAggregateType.Average ? 0u : HistorianInfoBits.HistorianPartial);
        ours.Skip(1).ShouldAllBe(x => (x.StatusCode & HistorianInfoBits.HistorianPartial) == 0);
    }

    /// <summary>The per-bucket statistics the backends' SQL computes, built in memory with <see cref="BucketPlan.IndexOf"/>.</summary>
    internal static IEnumerable<BucketRow> InMemoryRows(BucketPlan plan, IEnumerable<StoredSample> samples, bool maximum = false)
    {
        foreach (var g in samples.Select(s => (s, b: plan.IndexOf(s.TimeUtc))).Where(x => x.b is not null)
                     .GroupBy(x => x.b!.Value).OrderBy(g => g.Key))
        {
            var all = g.Select(x => x.s).OrderBy(s => s.TimeUtc).ToList();
            var usable = all.Where(s => s.IsUsable).ToList();
            var numeric = usable.Where(s => s.Value.Kind is HistorianValueKind.Double or HistorianValueKind.Int64
                or HistorianValueKind.Boolean).ToList();
            // ActualTime: the extreme usable value, ties ⇒ earliest (the SQL's ROW_NUMBER order).
            var extreme = numeric.OrderBy(s => maximum ? -s.Value.Number : s.Value.Number).ThenBy(s => s.TimeUtc)
                .Cast<StoredSample?>().FirstOrDefault();
            yield return new BucketRow
            {
                Bucket = g.Key,
                Total = all.Count,
                Usable = usable.Count,
                Good = all.Count(s => s.IsGood),
                Bad = all.Count - usable.Count,
                NonNumeric = usable.Count - numeric.Count,
                Avg = numeric.Count == 0 ? null : numeric.Average(s => s.Value.Number),
                Min = numeric.Count == 0 ? null : numeric.Min(s => s.Value.Number),
                Max = numeric.Count == 0 ? null : numeric.Max(s => s.Value.Number),
                Sum = numeric.Count == 0 ? null : numeric.Sum(s => s.Value.Number),
                First = usable.Count == 0 ? HistorianValue.Empty : usable[0].Value,
                Last = usable.Count == 0 ? HistorianValue.Empty : usable[^1].Value,
                Extreme = extreme?.Value.Number,
                ExtremeTime = extreme?.TimeUtc,
            };
        }
    }
}