Joseph Doherty
7349260231
F1: the SDK applies its m_startOfData Partial rule to forward reads only; ours now does too (AggregateEvaluator.EvaluateAll + TimeWeightedAggregator). New reverse late-start parity tests through the SDK oracle (unit) and real SQL (conformance, both backends). F2: AggregateEvaluator.NeedsEarliestSample — the earliest-sample query runs only for forward reads of aggregates other than Average, and is bounded by the window end (SqlServer < @end, QuestDB ts < $2). F3: per-sample SDK parity extended to Range, Start, End, Delta, Min/Max ActualTime and PercentGood/Bad (oracle maps StatusAggregateCalculator); pre-existing definitional differences masked and marked #680. Docs: Historian.md Partial/SDK-parity sections, CLAUDE.md bullet.
260 lines
15 KiB
C#
260 lines
15 KiB
C#
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 (the SDK does not), so the
|
||
/// non-multiple windows mask that one bucket's Partial bit;</item>
|
||
/// <item>the SDK's <b>end-of-data</b> Partial rule (forward, the interval holding the last sample when nothing follows
|
||
/// and nothing was extrapolated) is not implemented: every dataset carries data past the window end.</item>
|
||
/// </list>
|
||
/// Pre-existing forward divergences this parity test surfaced (#671 behaviour, unchanged here — forward results were
|
||
/// to stay as they are; recorded for a follow-up rather than fixed in place):
|
||
/// <list type="bullet">
|
||
/// <item><b>TimeAverage / Total status:</b> the SDK (interpolated bounds) reports <c>UncertainDataSubNormal</c> when
|
||
/// <i>any</i> region of the interval is non-Good (e.g. a segment bridged across a Bad sample); ours applies the
|
||
/// time-based rule (Uncertain time counts as Good) to these two as well, so a bridged-but-fully-covered interval
|
||
/// is Good. Values and timestamps agree; the status code bits are not compared for these two.</item>
|
||
/// <item><b>Total over an interval the data starts inside:</b> the SDK integrates only the defined part
|
||
/// (value·s over the covered seconds); ours is <c>TimeAverage × interval seconds</c>. The Partial bit and timestamp
|
||
/// agree; that value is not compared.</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>>= 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.</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>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;
|
||
}
|
||
|
||
[Theory]
|
||
[MemberData(nameof(Windows))]
|
||
public void Time_weighted_aggregates_match_the_SDK(double from, double to, double intervalS)
|
||
{
|
||
foreach (var agg in new[]
|
||
{
|
||
HistoryAggregateType.TimeAverage, HistoryAggregateType.TimeAverage2, HistoryAggregateType.Total,
|
||
HistoryAggregateType.Total2, HistoryAggregateType.Interpolative,
|
||
})
|
||
foreach (var (name, data) in new[] { ("Bounded", Bounded), ("Dense", Dense) })
|
||
SdkAggregateOracle.ShouldMatch(MaskTruncation(Ours(agg, from, to, intervalS, data), from, to, intervalS),
|
||
Sdk(agg, from, to, intervalS, data), $"{agg} {name} {from}→{to}/{intervalS}s",
|
||
compareCalculatedInterpolatedBits: !(agg == HistoryAggregateType.Interpolative && from > to),
|
||
compareCodeBits: agg is not (HistoryAggregateType.TimeAverage or HistoryAggregateType.Total)
|
||
&& !(agg == HistoryAggregateType.Interpolative && from > to));
|
||
}
|
||
|
||
[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,
|
||
compareValues: !PercentAggregate(agg),
|
||
// 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,
|
||
HistoryAggregateType.PercentGood, HistoryAggregateType.PercentBad,
|
||
];
|
||
|
||
/// <summary>
|
||
/// pre-existing, #680: ours is the per-SAMPLE percentage (100 × Good samples / all samples); the SDK's
|
||
/// <c>StatusAggregateCalculator</c> is the per-DURATION one (Good time / interval time). Different definitions, so the
|
||
/// values are not compared; timestamp, status and Partial still are.
|
||
/// </summary>
|
||
private static bool StartOrEnd(HistoryAggregateType agg) =>
|
||
agg is HistoryAggregateType.Start or HistoryAggregateType.End;
|
||
|
||
private static bool PercentAggregate(HistoryAggregateType agg) =>
|
||
agg is HistoryAggregateType.PercentGood or HistoryAggregateType.PercentBad;
|
||
|
||
[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: Total over the interval the data starts inside (TimeAverage × interval vs the SDK's
|
||
// integral of the covered part); Start's raw-sample timestamp/status (see Per_sample_aggregates_match_the_SDK).
|
||
compareValues: agg != HistoryAggregateType.Total,
|
||
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, compareValues: agg != HistoryAggregateType.Total);
|
||
(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,
|
||
};
|
||
}
|
||
}
|
||
}
|