fix(mtconnect): close Java-driver parity gaps found by the #804 review

- Lift an Agent's MTConnectError body under a non-2xx status (cppagent 2.x serves
  OUT_OF_RANGE as HTTP 400, NO_DEVICE as 404) into the refusal-marked
  InvalidDataException, reading at most 64 KiB. The 400 used to be a transport
  fault, so the OUT_OF_RANGE re-baseline never ran against a real 2.x Agent.
- Run the instanceId restart test on every re-baseline snapshot: on 2.x a restart
  is first seen there (the old cursor gets a 400), and was adopted silently.
- Report the stream Degraded after 3 consecutive re-baselines with no /sample
  chunk (it read Healthy for ever); LastSuccessfulRead keeps advancing.
- Prohibit DTDs on the /probe and write-answer parses; bound the streams walk to
  64 levels (unbounded recursion = uncatchable StackOverflowException).
- Skip structural elements under <Components>/<Devices> instead of failing the probe.
- Never serve a non-finite float as Good; serve integer-valued decimals on
  integral tags losslessly (a real fraction stays BadOutOfRange).
- Merge sibling browse containers that resolve to one folder name.

Unit 678 -> 714, integration 18 -> 20 (live fixture); every gap test failed first.
This commit is contained in:
Joseph Doherty
2026-11-10 23:08:42 -05:00
parent 308b1b3b56
commit d6392dae17
10 changed files with 1168 additions and 33 deletions
@@ -256,7 +256,8 @@ public interface IMTConnectAgentClient : IDisposable
/// <b>This check alone does NOT cover every ring-buffer overflow.</b> It can only judge
/// a chunk the Agent was willing to send — and cppagent answers a <c>from</c> that has
/// already fallen out of its buffer with an <c>MTConnectError</c> / <c>OUT_OF_RANGE</c>
/// document served under <b>HTTP 200</b>, which this client surfaces as an
/// document — served under <b>HTTP 200</b> by older Agents and under <b>HTTP 400</b> by a 2.x
/// one (both lifted since #804) — which this client surfaces as an
/// <see cref="InvalidDataException"/> out of <see cref="SampleAsync(long, CancellationToken)"/>, never as a chunk.
/// A pump that re-baselines only on <c>IsSequenceGap</c> will therefore fault instead of
/// recovering exactly when it has fallen furthest behind. Treat an <c>OUT_OF_RANGE</c>
@@ -175,7 +175,7 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
// ResponseContentRead (the default) buffers the whole body *under* this awaited, token-bound
// call, so the parse below reads from memory — no network read can outlive the deadline.
using var response = await SendAsync(_probeUri, ct).ConfigureAwait(false);
using var response = await SendAsync(_probeUri, "MTConnectDevices", "/probe response", ct).ConfigureAwait(false);
await using var body = await response.Content.ReadAsStreamAsync(ct).ConfigureAwait(false);
@@ -216,7 +216,7 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
{
ObjectDisposedException.ThrowIf(Volatile.Read(ref _disposed) != 0, this);
using var response = await SendAsync(_currentUri, ct).ConfigureAwait(false);
using var response = await SendAsync(_currentUri, "MTConnectStreams", "streams response", ct).ConfigureAwait(false);
await using var body = await response.Content.ReadAsStreamAsync(ct).ConfigureAwait(false);
@@ -432,7 +432,13 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
XElement? root;
try
{
root = XDocument.Parse(body).Root;
root = MTConnectXml.ParseHardened(body).Root;
}
catch (XmlException) when (body.Contains("<!DOCTYPE", StringComparison.OrdinalIgnoreCase))
{
// The hardened parse refuses a DOCTYPE outright (#804). Such an answer cannot be read, so it cannot be
// CONFIRMED either — reporting it as an accepted write would be the one wrong answer here.
return "The Agent answered with a document carrying a DOCTYPE, which this driver refuses to parse.";
}
catch (XmlException)
{
@@ -491,7 +497,8 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
$"{_sampleUriBase}?from={from}{_sampleQuerySuffix}&count={count ?? _sampleCount}&heartbeat={_heartbeatMs}"),
UriKind.Absolute);
private async Task<HttpResponseMessage> SendAsync(Uri uri, CancellationToken ct)
private async Task<HttpResponseMessage> SendAsync(
Uri uri, string expectedRootName, string subject, CancellationToken ct)
{
using var lifetime = CancellationTokenSource.CreateLinkedTokenSource(ct, _disposeCts.Token);
using var deadline = CancellationTokenSource.CreateLinkedTokenSource(lifetime.Token);
@@ -510,7 +517,7 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
throw TimedOut(uri);
}
response.EnsureSuccessStatusCode();
await EnsureAgentAnsweredAsync(response, expectedRootName, subject, deadline.Token).ConfigureAwait(false);
return response;
}
@@ -537,11 +544,79 @@ public sealed class MTConnectAgentClient : IMTConnectAgentClient, IDisposable
throw TimedOut(uri);
}
response.EnsureSuccessStatusCode();
await EnsureAgentAnsweredAsync(response, "MTConnectStreams", "streams response", deadline.Token)
.ConfigureAwait(false);
return response;
}
/// <summary>
/// How much of a <b>failure</b> body is read looking for the Agent's <c>MTConnectError</c> document. An Agent's
/// error document is a few hundred bytes; a proxy's HTML error page never needs to be held in full.
/// </summary>
internal const int MaxErrorBodyBytes = 64 * 1024;
/// <summary>
/// Passes a 2xx response through; otherwise throws — the Agent's own refusal (a refusal-marked
/// <see cref="InvalidDataException"/>, see <see cref="MTConnectXml.AgentRefusalFromErrorBody"/>) when the
/// failure body is an <c>MTConnectError</c> document, else the plain <see cref="HttpRequestException"/>
/// <see cref="HttpResponseMessage.EnsureSuccessStatusCode"/> raises. The response is disposed on every throw.
/// </summary>
/// <remarks>
/// At most <see cref="MaxErrorBodyBytes"/> of the body are read, under the caller's deadline. A body that
/// cannot be read in time is not worth a different failure: the status alone is reported, exactly as before.
/// </remarks>
private static async Task EnsureAgentAnsweredAsync(
HttpResponseMessage response, string expectedRootName, string subject, CancellationToken deadline)
{
if (response.IsSuccessStatusCode)
{
return;
}
try
{
string? head = null;
try
{
head = await ReadHeadAsync(response.Content, deadline).ConfigureAwait(false);
}
catch (Exception ex) when (ex is IOException or HttpRequestException or OperationCanceledException)
{
// Unreadable body: fall through to the status-only failure below — what was reported before.
}
var refusal = MTConnectXml.AgentRefusalFromErrorBody(head, (int)response.StatusCode, expectedRootName, subject);
if (refusal is not null)
{
throw refusal;
}
response.EnsureSuccessStatusCode();
}
catch
{
response.Dispose();
throw;
}
}
/// <summary>Reads at most <see cref="MaxErrorBodyBytes"/> of a failure body as UTF-8.</summary>
private static async Task<string> ReadHeadAsync(HttpContent content, CancellationToken ct)
{
await using var body = await content.ReadAsStreamAsync(ct).ConfigureAwait(false);
var buffer = new byte[MaxErrorBodyBytes];
var filled = 0;
int read;
while (filled < buffer.Length &&
(read = await body.ReadAsync(buffer.AsMemory(filled, buffer.Length - filled), ct).ConfigureAwait(false)) > 0)
{
filled += read;
}
return Encoding.UTF8.GetString(buffer, 0, filled);
}
/// <summary>Reads a non-multipart streaming body whole, under the unary deadline.</summary>
private async Task<string> ReadWholeBodyAsync(Stream body, Uri uri, CancellationTokenSource lifetime)
{
@@ -161,6 +161,17 @@ public sealed partial class MTConnectDriver
/// </remarks>
private static readonly TimeSpan TeardownWait = TimeSpan.FromSeconds(5);
/// <summary>
/// How many consecutive <c>/current</c> re-baselines with no <c>/sample</c> chunk delivered between them
/// report the stream Degraded (#804; the Java driver's <c>MAX_REBASELINES_WITHOUT_PROGRESS</c>). One
/// re-baseline is a genuine ring-buffer overrun resolving; three in a row is an Agent and a cursor/count
/// that cannot agree.
/// </summary>
internal const int MaxRebaselinesWithoutProgress = 3;
/// <summary>The type-only <c>LastError</c> a stalled stream (<see cref="MaxRebaselinesWithoutProgress"/>) reports.</summary>
internal const string StalledStreamReason = "repeated /sample re-baselines with no observations in between";
/// <summary>
/// Config-JSON reader options, mirroring the sibling driver factories. Note there is
/// deliberately <b>no</b> <c>JsonStringEnumConverter</c>: enum-carrying DTO fields stay
@@ -1433,6 +1444,9 @@ public sealed partial class MTConnectDriver
var devices = 0;
var variables = 0;
// Siblings that resolve to one folder name share ONE folder (#804) — see SiblingFolders.
var deviceFolders = new SiblingFolders(builder);
foreach (var device in model.Devices)
{
if (device is null || !InDeviceScope(device, deviceScope))
@@ -1454,7 +1468,7 @@ public sealed partial class MTConnectDriver
}
devices++;
variables += StreamContainer(device, builder.Folder(name, name), writeEnabled);
variables += StreamContainer(device, deviceFolders.Get(name), writeEnabled);
}
// A configured scope that matches NO device is an authoring error — almost always a typo or
@@ -1555,6 +1569,8 @@ public sealed partial class MTConnectDriver
streamed++;
}
var componentFolders = new SiblingFolders(scope);
foreach (var component in container.Components)
{
if (component is null)
@@ -1574,12 +1590,42 @@ public sealed partial class MTConnectDriver
continue;
}
streamed += StreamContainer(component, scope.Folder(name, name), writeEnabled);
streamed += StreamContainer(component, componentFolders.Get(name), writeEnabled);
}
return streamed;
}
/// <summary>
/// One builder folder per distinct name under one parent scope: two sibling containers that resolve to the
/// same folder name (two components named alike, or one's <c>name</c> equal to another's <c>id</c>) are
/// streamed into a SINGLE shared folder, deterministically, rather than as two same-named folders.
/// </summary>
/// <remarks>
/// <b>Why (#804, Java-driver parity).</b> A browse picker keys a folder by its path, so two same-named sibling
/// folders share one key: the universal browser's capture (<c>CapturingAddressSpaceBuilder</c>) indexes the
/// FIRST and every expand of that path returns the first one's children — the second container's data items
/// were listed in the tree but unreachable. Merging is what the Java driver does for the same collision, and
/// it loses nothing: every data item is still streamed, keyed by its own DataItem id. A data item whose name
/// equals a sibling folder's is NOT a collision here — a leaf is keyed by its DataItem id, never its path.
/// </remarks>
private sealed class SiblingFolders(IAddressSpaceBuilder parent)
{
private readonly Dictionary<string, IAddressSpaceBuilder> _folders = new(StringComparer.Ordinal);
/// <summary>The folder named <paramref name="name"/> under the parent, created on first use.</summary>
public IAddressSpaceBuilder Get(string name)
{
if (!_folders.TryGetValue(name, out var folder))
{
folder = parent.Folder(name, name);
_folders[name] = folder;
}
return folder;
}
}
/// <summary>
/// Whether <see cref="WriteAsync"/> would accept a write to <paramref name="dataItem"/> — the
/// browse-time answer, asked of the same two facts the runtime asks of.
@@ -2186,6 +2232,9 @@ public sealed partial class MTConnectDriver
var counts = new SampleCountState(options.SampleCount);
Volatile.Write(ref _effectiveSampleCount, counts.Count);
// #804 (Java-driver parity) — consecutive re-baselines with no /sample chunk delivered in between.
var rebaselinesWithoutProgress = 0;
try
{
if (republishOnStart)
@@ -2215,7 +2264,15 @@ public sealed partial class MTConnectDriver
}
}
var outcome = await ConsumeStreamAsync(client, options, cursor, instanceId, generation, counts, ct).ConfigureAwait(false);
var outcome = await ConsumeStreamAsync(
client, options, cursor, instanceId, generation, counts,
holdStalled: rebaselinesWithoutProgress >= MaxRebaselinesWithoutProgress, ct)
.ConfigureAwait(false);
if (outcome.DeliveredAny)
{
rebaselinesWithoutProgress = 0;
}
cursor = outcome.Cursor;
instanceId = outcome.InstanceId;
@@ -2291,6 +2348,25 @@ public sealed partial class MTConnectDriver
attempt = outcome.DeliveredAny ? 0 : attempt + 1;
_reconnectAttempts = attempt;
// #804 — the backoff above PACES a stream that only ever re-baselines, but each /current
// also marked the stream delivered, so it read Healthy for ever while no /sample chunk
// arrived (a SampleCount at or above the Agent's bufferSize is refused OUT_OF_RANGE on
// EVERY open). After MaxRebaselinesWithoutProgress in a row it is reported Degraded, and
// stays so (holdStalled) until a chunk is delivered.
if (!outcome.DeliveredAny &&
++rebaselinesWithoutProgress == MaxRebaselinesWithoutProgress)
{
if (!TryHoldStreamStalled(generation, StalledStreamReason))
{
return;
}
_logger.LogWarning(
outcome.Error,
"MTConnect driver {DriverInstanceId}: {Count} consecutive /current re-baselines of {AgentUri} without a single /sample chunk in between; reporting the stream Degraded until one is delivered. Values are re-baselined, not streamed. An Agent answering every /sample with OUT_OF_RANGE usually means SampleCount is at or above its bufferSize.",
_driverInstanceId, rebaselinesWithoutProgress, AgentDisplay(options));
}
break;
default:
@@ -2354,6 +2430,7 @@ public sealed partial class MTConnectDriver
long instanceId,
long generation,
SampleCountState counts,
bool holdStalled,
CancellationToken ct)
{
// The RUNNING cursor the gap check is made against: the previous chunk's nextSequence, equal
@@ -2402,23 +2479,13 @@ public sealed partial class MTConnectDriver
// Dropped BEFORE the re-baseline, and the subscribers are told: if the /current
// then fails, holding stale values from a dead device model would be worse than
// holding none.
if (!TryCaptureSessionState(generation, out var restartIndex, out var restartTracker))
if (!TryDropForAgentRestart(generation, chunk.InstanceId, options))
{
return new StreamOutcome(StreamVerdict.Cancelled, expected, instanceId, delivered, null);
}
// Not live while the index is empty (review m2): reads go to /current until the re-baseline lands.
_pumpLive = false;
restartIndex.Clear();
restartTracker.Clear();
FanOut(SubscribedReferences(), restartIndex);
// The driver's own state is consistent by this point, so it is safe to hand the
// restart to arbitrary caller code — which may call straight back into
// DiscoverAsync.
AnnounceAgentRestart(chunk.InstanceId, options);
return await RebaselineAsync(client, options, expected, instanceId, delivered, generation, ct)
return await RebaselineAsync(
client, options, expected, chunk.InstanceId, delivered, generation, holdStalled, ct)
.ConfigureAwait(false);
}
@@ -2428,7 +2495,7 @@ public sealed partial class MTConnectDriver
"MTConnect driver {DriverInstanceId} fell out of {AgentUri}'s buffer (expected sequence {Expected}, oldest retained {FirstSequence}); re-baselining from /current.",
_driverInstanceId, AgentDisplay(options), expected, chunk.FirstSequence);
return await RebaselineAsync(client, options, expected, instanceId, delivered, generation, ct)
return await RebaselineAsync(client, options, expected, instanceId, delivered, generation, holdStalled, ct)
.ConfigureAwait(false);
}
@@ -2501,7 +2568,7 @@ public sealed partial class MTConnectDriver
"MTConnect driver {DriverInstanceId} could not resume {AgentUri}'s /sample stream at sequence {Cursor} (the Agent rejected it as out of range); re-baselining from /current.",
_driverInstanceId, AgentDisplay(options), cursor);
return await RebaselineAsync(client, options, expected, instanceId, delivered, generation, ct)
return await RebaselineAsync(client, options, expected, instanceId, delivered, generation, holdStalled, ct)
.ConfigureAwait(false);
}
catch (Exception ex)
@@ -2532,6 +2599,7 @@ public sealed partial class MTConnectDriver
long fallbackInstanceId,
bool deliveredAny,
long generation,
bool holdStalled,
CancellationToken ct)
{
try
@@ -2545,8 +2613,31 @@ public sealed partial class MTConnectDriver
StreamVerdict.Cancelled, fallbackCursor, fallbackInstanceId, deliveredAny, null);
}
// #804 — the restart test runs on the SNAPSHOT too (the Java driver's rule). On a real 2.x Agent this
// is how a restart is usually first seen: the restarted process refuses the dead one's cursor with
// HTTP 400 OUT_OF_RANGE, so no chunk ever reaches the in-stream instanceId check above, and the
// re-baseline used to adopt the new instanceId silently — no rediscovery prompt, and the dead model's
// held values (data items the new Agent may not declare) kept being served.
if (current.InstanceId != fallbackInstanceId)
{
_logger.LogWarning(
"MTConnect driver {DriverInstanceId} saw {AgentUri} restart while re-baselining (instanceId {Previous} -> {Current}); dropping every held observation.",
_driverInstanceId, AgentDisplay(options), fallbackInstanceId, current.InstanceId);
if (!TryDropForAgentRestart(generation, current.InstanceId, options))
{
return new StreamOutcome(
StreamVerdict.Cancelled, fallbackCursor, fallbackInstanceId, deliveredAny, null);
}
}
PublishAgentCursor(generation, current.InstanceId, current.NextSequence);
if (!ApplyAndFanOut(current, generation, baseline: true) || !TryMarkStreamDelivered(generation))
// A stalled stream (#804) keeps its Degraded verdict across the re-baseline: the /current answered, but
// it is not the /sample progress the verdict is about. Only a delivered chunk clears it.
if (!ApplyAndFanOut(current, generation, baseline: true) ||
!(holdStalled && !deliveredAny
? TryHoldStreamStalled(generation, StalledStreamReason)
: TryMarkStreamDelivered(generation)))
{
return new StreamOutcome(
StreamVerdict.Cancelled, fallbackCursor, fallbackInstanceId, deliveredAny, null);
@@ -2732,6 +2823,63 @@ public sealed partial class MTConnectDriver
}
}
/// <summary>
/// An Agent restart (a changed <c>instanceId</c>) seen by the pump started under <paramref name="generation"/>:
/// drop every held observation and condition state — the device model they describe may no longer exist —
/// tell the subscribers, and raise rediscovery (once per distinct id).
/// </summary>
/// <returns><see langword="false"/> when the pump's session has been replaced (nothing dropped).</returns>
private bool TryDropForAgentRestart(long generation, long newInstanceId, MTConnectDriverOptions options)
{
if (!TryCaptureSessionState(generation, out var restartIndex, out var restartTracker))
{
return false;
}
// Not live while the index is empty (review m2): reads go to /current until the re-baseline lands.
_pumpLive = false;
restartIndex.Clear();
restartTracker.Clear();
FanOut(SubscribedReferences(), restartIndex);
// The driver's own state is consistent by this point, so it is safe to hand the restart to arbitrary
// caller code — which may call straight back into DiscoverAsync.
AnnounceAgentRestart(newInstanceId, options);
return true;
}
/// <summary>
/// #804: the pump started under <paramref name="generation"/> has re-baselined
/// <see cref="MaxRebaselinesWithoutProgress"/> times in a row without one <c>/sample</c> chunk: degrade the
/// stream — generation-checked, like <see cref="TryDegradeStream"/> — but stamp
/// <c>LastSuccessfulRead</c> now, because each <c>/current</c> it re-baselined from IS the Agent answering.
/// That is deliberate: the comms-loss watchdog reconnects on non-Healthy AND a frozen stamp, and a reconnect
/// cannot fix an Agent that refuses the count or cursor — it would only reconnect-loop the driver (the
/// "an Agent refusal is a reply" health contract).
/// </summary>
/// <param name="generation">The pump's session generation.</param>
/// <param name="message">The type-only reason.</param>
/// <returns><see langword="false"/> when the pump's session has been replaced (nothing written).</returns>
private bool TryHoldStreamStalled(long generation, string message)
{
lock (_subscriptionLock)
{
if (_sessionGeneration != generation)
{
return false;
}
_streamDegraded = true;
if (ReadHealth().State != DriverState.Faulted)
{
WriteHealth(new DriverHealth(DriverState.Degraded, DateTime.UtcNow, message));
}
return true;
}
}
/// <summary>
/// Review I-1: the stream of the pump started under <paramref name="generation"/> delivered — clear its
/// degradation, mark it live and publish Healthy, all under the generation check and in one critical section,
@@ -558,6 +558,13 @@ internal sealed class MTConnectObservationIndex
case DriverDataType.Float32:
if (float.TryParse(text, NumberStyles.Float, CultureInfo.InvariantCulture, out var single))
{
// .NET parses an overflowing literal ("1e39") to ±Infinity and accepts the NaN/Infinity
// spellings outright; publishing either as a Good reading is a fabricated value (#804).
if (!float.IsFinite(single))
{
return NonFiniteStatus(text);
}
value = single;
return Good;
}
@@ -567,6 +574,11 @@ internal sealed class MTConnectObservationIndex
case DriverDataType.Float64:
if (double.TryParse(text, NumberStyles.Float, CultureInfo.InvariantCulture, out var real))
{
if (!double.IsFinite(real))
{
return NonFiniteStatus(text);
}
value = real;
return Good;
}
@@ -636,8 +648,65 @@ internal sealed class MTConnectObservationIndex
// Integer parse failed. Distinguishing the two causes is worth one extra parse: it tells an
// operator whether to retype the tag or widen it.
return double.TryParse(text, NumberStyles.Float, CultureInfo.InvariantCulture, out _)
? BadOutOfRange // a number the authored type cannot represent (overflow, or a fraction)
: BadTypeMismatch; // not a number at all
if (!decimal.TryParse(text, NumberStyles.Float, CultureInfo.InvariantCulture, out var exact))
{
return double.TryParse(text, NumberStyles.Float, CultureInfo.InvariantCulture, out _)
? BadOutOfRange // a number the authored type cannot represent (beyond even decimal's range)
: BadTypeMismatch; // not a number at all
}
// #804 (Java-driver parity): Agents do format integer-valued items as "42.000000". A decimal whose value
// IS an integer converts losslessly, so it is served. A real fraction ("3.5") is still refused rather than
// truncated (stricter than the Java driver, which truncates toward zero): truncating is a fabricated value.
return decimal.Truncate(exact) == exact && TryIntegral(exact, type, out value)
? Good
: BadOutOfRange;
}
/// <summary>
/// The status for a float text that parsed to a non-finite value: an overflowing numeric literal is a
/// number the type cannot represent (<c>BadOutOfRange</c>); a NaN/Infinity spelling is not a measurement
/// at all (<c>BadTypeMismatch</c>).
/// </summary>
private static uint NonFiniteStatus(string text)
{
foreach (var c in text)
{
if (c is not ((>= '0' and <= '9') or '+' or '-' or '.' or 'e' or 'E'))
{
return BadTypeMismatch;
}
}
return BadOutOfRange;
}
/// <summary>Range-checked conversion of an integer-valued decimal onto an integral driver type.</summary>
private static bool TryIntegral(decimal exact, DriverDataType type, out object? value)
{
value = null;
switch (type)
{
case DriverDataType.Int16 when exact is >= short.MinValue and <= short.MaxValue:
value = (short)exact;
return true;
case DriverDataType.Int32 when exact is >= int.MinValue and <= int.MaxValue:
value = (int)exact;
return true;
case DriverDataType.Int64 when exact is >= long.MinValue and <= long.MaxValue:
value = (long)exact;
return true;
case DriverDataType.UInt16 when exact is >= ushort.MinValue and <= ushort.MaxValue:
value = (ushort)exact;
return true;
case DriverDataType.UInt32 when exact is >= uint.MinValue and <= uint.MaxValue:
value = (uint)exact;
return true;
case DriverDataType.UInt64 when exact is >= ulong.MinValue and <= ulong.MaxValue:
value = (ulong)exact;
return true;
default:
return false;
}
}
}
@@ -80,7 +80,7 @@ internal static class MTConnectProbeParser
XDocument document;
try
{
document = XDocument.Parse(xml);
document = MTConnectXml.ParseHardened(xml);
}
catch (XmlException ex)
{
@@ -101,7 +101,7 @@ internal static class MTConnectProbeParser
XDocument document;
try
{
document = XDocument.Load(stream);
document = MTConnectXml.LoadHardened(stream);
}
catch (XmlException ex)
{
@@ -125,7 +125,7 @@ internal static class MTConnectProbeParser
?? throw new InvalidDataException(
"MTConnect /probe response has no <Devices> element; it does not describe a device model.");
var devices = devicesContainer.Elements().Select(ReadDevice).ToList();
var devices = ComponentLikeChildren(devicesContainer).Select(ReadDevice).ToList();
if (devices.Count == 0)
{
throw new InvalidDataException(
@@ -162,11 +162,25 @@ internal static class MTConnectProbeParser
}
return MTConnectXml.ChildrenNamed(container, "Components")
.SelectMany(components => components.Elements())
.SelectMany(ComponentLikeChildren)
.Select(element => ReadComponent(element, depth))
.ToList();
}
/// <summary>
/// Element names that can sit beside components but are MTConnect's own structural children, never a
/// component or device. Defence in depth (#804, Java-driver parity): a schema-valid document never puts one
/// directly under <c>&lt;Components&gt;</c> or <c>&lt;Devices&gt;</c>, but the "every element child is a
/// component" rule is deliberately permissive, and without this list a stray <c>&lt;Description&gt;</c> there
/// would fail the WHOLE probe on its missing <c>id</c> — every data item lost over one misplaced element.
/// </summary>
private static readonly HashSet<string> NotAComponent =
new(StringComparer.Ordinal) { "DataItems", "Description", "Configuration", "References", "Compositions" };
/// <summary>A container's element children minus <see cref="NotAComponent"/>.</summary>
private static IEnumerable<XElement> ComponentLikeChildren(XElement container) =>
container.Elements().Where(child => !NotAComponent.Contains(child.Name.LocalName));
private static IReadOnlyList<MTConnectDataItem> ReadDataItems(XElement container) =>
MTConnectXml.ChildrenNamed(container, "DataItems")
.SelectMany(dataItems => MTConnectXml.ChildrenNamed(dataItems, "DataItem"))
@@ -109,6 +109,17 @@ internal static class MTConnectStreamsParser
/// <summary>How those messages name the header element.</summary>
private const string HeaderOwner = "the <Header>";
/// <summary>
/// Bound on element nesting (#804, Java-driver parity). <see cref="ReadElement"/> and
/// <see cref="ReadChildren"/> recurse once per nesting level, and the document comes from an
/// unauthenticated peer: a part nested a few hundred thousand levels deep (well inside the
/// multipart reader's 32 MiB part cap) would otherwise recurse into a
/// <see cref="StackOverflowException"/>, which .NET cannot catch — it would take the whole server
/// process down, not just this driver. A real streams document nests about eight levels
/// (<c>MTConnectStreams/Streams/DeviceStream/ComponentStream/Samples/observation/Entry/Cell</c>).
/// </summary>
internal const int MaxElementDepth = 64;
/// <summary>
/// How the whole document is read. Two settings are load-bearing rather than incidental.
/// </summary>
@@ -381,6 +392,12 @@ internal static class MTConnectStreamsParser
ValueSink? textSink,
List<MTConnectDataSetEntry>? entryCollector = null)
{
if (reader.Depth >= MaxElementDepth)
{
throw new InvalidDataException(
$"MTConnect {Subject} nests elements more than {MaxElementDepth} levels deep; refusing to recurse further.");
}
var isObservation = parent != ContainerKind.None;
var isCondition = parent == ContainerKind.Condition;
var kind = ContainerKindOf(reader);
@@ -28,6 +28,96 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.MTConnect;
/// </remarks>
internal static class MTConnectXml
{
/// <summary>
/// The reader settings every <b>tree-building</b> parse of an Agent document uses (the
/// <c>/probe</c> model, an error body, a write answer). The Agent is an unauthenticated peer on
/// the plant network, so a DOCTYPE is refused outright and nothing external is ever resolved —
/// no legitimate MTConnect document carries one. <see cref="XDocument.Parse(string)"/> on its own
/// <i>parses</i> DTDs (it expands internal entities up to ten million characters); the streams
/// parser already prohibited them, and this is what brings the other parses into line (#804).
/// <see cref="XmlReaderSettings.IgnoreWhitespace"/> reproduces <c>XDocument.Parse</c>'s default.
/// </summary>
private static readonly XmlReaderSettings HardenedTreeSettings = new()
{
DtdProcessing = DtdProcessing.Prohibit,
XmlResolver = null,
IgnoreWhitespace = true,
CloseInput = false,
};
/// <summary>Parses <paramref name="xml"/> into a tree with DTDs prohibited (see <see cref="HardenedTreeSettings"/>).</summary>
/// <param name="xml">The document text.</param>
/// <returns>The parsed document.</returns>
/// <exception cref="XmlException">The text is not well-formed, or carries a DOCTYPE.</exception>
public static XDocument ParseHardened(string xml)
{
using var text = new StringReader(xml);
using var reader = XmlReader.Create(text, HardenedTreeSettings);
return XDocument.Load(reader);
}
/// <summary>Loads <paramref name="stream"/> into a tree with DTDs prohibited (see <see cref="HardenedTreeSettings"/>).</summary>
/// <param name="stream">The document bytes; not closed.</param>
/// <returns>The parsed document.</returns>
/// <exception cref="XmlException">The bytes are not well-formed, or carry a DOCTYPE.</exception>
public static XDocument LoadHardened(Stream stream)
{
using var reader = XmlReader.Create(stream, HardenedTreeSettings);
return XDocument.Load(reader);
}
/// <summary>
/// The Agent's <c>MTConnectError</c> document in <paramref name="body"/>, rendered as the
/// refusal-marked <see cref="InvalidDataException"/> every caller already routes (see
/// <see cref="IsAgentRefusal"/>), or <see langword="null"/> when the body is not one.
/// </summary>
/// <remarks>
/// <b>Why this exists (#804).</b> A modern Agent (cppagent 2.x, the fixture's
/// <c>mtconnect/agent:2.7</c>) does not serve its error documents under HTTP 200 the way older
/// ones did: it answers an out-of-range <c>/sample?from=</c> — and a <c>count</c> at or above its
/// buffer — with <b>HTTP 400</b>, and an unknown device with <b>404</b>, each carrying a
/// well-formed <c>MTConnectError</c> body. A status check alone turns those into an
/// <see cref="HttpRequestException"/>, which the pump treats as a transient transport loss and
/// reconnects at the SAME evicted cursor, so the <c>OUT_OF_RANGE</c> re-baseline never ran
/// against a real 2.x Agent. Lifting the document is what routes it.
/// </remarks>
/// <param name="body">The (already size-bounded) response body.</param>
/// <param name="status">The HTTP status the body arrived under, for the message.</param>
/// <param name="expectedRootName">The root the request expected.</param>
/// <param name="subject">How to describe the document.</param>
/// <returns>The refusal to throw, or <see langword="null"/>.</returns>
public static InvalidDataException? AgentRefusalFromErrorBody(
string? body, int status, string expectedRootName, string subject)
{
if (string.IsNullOrWhiteSpace(body))
{
return null;
}
XElement? root;
try
{
root = ParseHardened(body.Trim('', ' ', '\t', '\r', '\n')).Root;
}
catch (XmlException)
{
return null;
}
if (root is null || !IsNamed(root, "MTConnectError"))
{
return null;
}
var ex = new InvalidDataException(
$"{DescribeUnexpectedRoot(root, expectedRootName, subject)} (served under HTTP {status})");
ex.Data[AgentRefusalDataKey] = true;
return ex;
}
/// <summary>Does <paramref name="element"/> have the given local name, whatever its namespace?</summary>
/// <param name="element">The element to test.</param>
/// <param name="localName">The unqualified name to match.</param>
@@ -837,6 +837,116 @@ public sealed class MTConnectAgentIntegrationTests(MTConnectAgentFixture agent)
}
}
// ---- #804: the 2.x Agent's error documents under a non-2xx status ----
/// <summary>
/// #804 — a 2.x Agent answers a <c>from</c> outside its buffer with <b>HTTP 400</b> + <c>MTConnectError</c>
/// <c>OUT_OF_RANGE</c> (live-verified against this fixture). The client must surface it as the
/// <see cref="InvalidDataException"/> the pump re-baselines on; before #804 it was a bare
/// <see cref="HttpRequestException"/>, which the pump read as transport loss and reconnected at the same
/// evicted cursor — the documented OUT_OF_RANGE re-baseline never ran against a real 2.x Agent.
/// </summary>
[Fact(Timeout = TestTimeoutMs)]
public async Task A_sample_cursor_outside_the_buffer_is_the_agents_out_of_range_refusal()
{
SkipIfDown();
// A cursor the Agent cannot hold: far past its nextSequence. (An OLD cursor is not reliable here — a
// freshly restarted Agent may still hold sequence 1, and then the stream simply opens.)
var next = (long?)(await CurrentAsync()).Root?.Elements().FirstOrDefault(e => e.Name.LocalName == "Header")
?.Attribute("nextSequence") ?? 0L;
using var client = new MTConnectAgentClient(LiveOptions());
var ex = await Should.ThrowAsync<InvalidDataException>(async () =>
{
await foreach (var _ in client.SampleAsync(next + 1_000_000, Ct))
{
}
});
ex.Message.ShouldContain("OUT_OF_RANGE");
}
/// <summary>
/// #804 — a <c>SampleCount</c> at or above the Agent's <c>bufferSize</c> is refused <c>OUT_OF_RANGE</c> on
/// EVERY <c>/sample</c> open (live: <c>'count' must be less than N</c>). The driver keeps serving values off
/// <c>/current</c> re-baselines, and — after three in a row with no <c>/sample</c> chunk — reports the stream
/// Degraded with <c>LastSuccessfulRead</c> still advancing, rather than Healthy for ever (before #804 the
/// 400 was a transport fault: Degraded, but every value stuck at the priming <c>/current</c>).
/// </summary>
[Fact(Timeout = TestTimeoutMs)]
public async Task A_sample_count_the_agent_refuses_is_reported_degraded_while_values_keep_flowing()
{
SkipIfDown();
var bufferSize = (int?)agent.ProbeDocument?.Root?.Elements().FirstOrDefault(e => e.Name.LocalName == "Header")
?.Attribute("bufferSize");
if (bufferSize is not > 0)
{
Assert.Skip($"The Agent at {agent.AgentUri} declares no bufferSize in its /probe header.");
}
var ids = await NumericSampleIdsAsync();
if (ids.Count == 0)
{
Assert.Skip($"The Agent at {agent.AgentUri} is currently reporting no numeric SAMPLE value.");
}
var options = new MTConnectDriverOptions
{
AgentUri = agent.AgentUri,
RequestTimeoutMs = 15_000,
SampleIntervalMs = 200,
SampleCount = bufferSize.Value + 1,
HeartbeatMs = 5_000,
Probe = new MTConnectProbeOptions { Enabled = false },
Reconnect = new MTConnectReconnectOptions { MinBackoffMs = 0, MaxBackoffMs = 200 },
};
var driver = new MTConnectDriver(options, "mtconnect-live-oor");
await using var live = new LiveDriver(driver);
await driver.InitializeAsync(
JsonSerializer.Serialize(new
{
agentUri = options.AgentUri,
requestTimeoutMs = options.RequestTimeoutMs,
sampleIntervalMs = options.SampleIntervalMs,
sampleCount = options.SampleCount,
heartbeatMs = options.HeartbeatMs,
probe = new { enabled = false },
reconnect = new { minBackoffMs = 0, maxBackoffMs = 200, backoffMultiplier = 2.0 },
tags = ids.Select(id => new { fullName = id, driverDataType = "Float64" }),
}),
Ct);
var seen = new ConcurrentQueue<DataChangeEventArgs>();
driver.OnDataChange += (_, e) => seen.Enqueue(e);
await driver.SubscribeAsync([.. ids], TimeSpan.FromMilliseconds(200), Ct);
var deadline = DateTime.UtcNow + StreamWait;
while (driver.GetHealth().LastError != "repeated /sample re-baselines with no observations in between" &&
DateTime.UtcNow < deadline)
{
await Task.Delay(100, Ct);
}
var health = driver.GetHealth();
health.State.ShouldBe(DriverState.Degraded);
health.LastError.ShouldBe("repeated /sample re-baselines with no observations in between");
var stamp = health.LastSuccessfulRead.ShouldNotBeNull();
// Values keep flowing off the re-baselines: the stamp advances and Good values keep arriving.
var before = seen.Count;
deadline = DateTime.UtcNow + StreamWait;
while ((driver.GetHealth().LastSuccessfulRead <= stamp || seen.Count <= before) && DateTime.UtcNow < deadline)
{
await Task.Delay(100, Ct);
}
driver.GetHealth().State.ShouldBe(DriverState.Degraded);
driver.GetHealth().LastSuccessfulRead!.Value.ShouldBeGreaterThan(stamp);
seen.Skip(before).ShouldContain(e => e.Snapshot.StatusCode == Good);
}
private static bool Is(string? value, string expected) =>
string.Equals(value?.Trim(), expected, StringComparison.OrdinalIgnoreCase);
@@ -0,0 +1,482 @@
using System.Net;
using System.Text;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
namespace ZB.MOM.WW.OtOpcUa.Driver.MTConnect.Tests;
/// <summary>
/// Gitea #804 — the gaps a parity review against the ignitionoee Java MTConnect driver verified in this
/// driver, one region per gap. Each test failed against the pre-#804 driver; the capability matrix that
/// says which Java behaviours were already covered (and by which existing tests) is
/// <c>docs/drivers/MTConnect.md</c> §"Java reference parity (#804)".
/// </summary>
public sealed class MTConnectJavaParityTests
{
private static CancellationToken Ct => TestContext.Current.CancellationToken;
private const string OutOfRangeError =
"""
<?xml version="1.0" encoding="UTF-8"?>
<MTConnectError xmlns="urn:mtconnect.org:MTConnectError:2.0">
<Header creationTime="2026-11-10T12:00:00Z" sender="agent" instanceId="1" version="2.7.0.12" bufferSize="16384"/>
<Errors>
<Error errorCode="OUT_OF_RANGE">'from' must be greater than 59962705</Error>
</Errors>
</MTConnectError>
""";
private const string NoDeviceError =
"""
<MTConnectError xmlns="urn:mtconnect.org:MTConnectError:2.0">
<Errors><Error errorCode="NO_DEVICE">Could not find the device 'nosuch'</Error></Errors>
</MTConnectError>
""";
private static MTConnectAgentClient NewClient(HttpMessageHandler handler) =>
new(new MTConnectDriverOptions { AgentUri = "http://agent:5000", RequestTimeoutMs = 5000 }, handler);
private static async Task DrainAsync(IAsyncEnumerable<MTConnectStreamsResult> stream)
{
await foreach (var _ in stream)
{
}
}
// ───────────── gap 1: an Agent error document under a non-2xx status is the Agent's refusal ─────────────
// cppagent 2.x (the fixture's mtconnect/agent:2.7, verified live) answers an evicted `from` and a count at or
// above its buffer with HTTP 400 + MTConnectError OUT_OF_RANGE. Pre-#804 the client threw a bare
// HttpRequestException, which the pump treats as a transient transport loss: it reconnected at the SAME
// evicted cursor for ever and the OUT_OF_RANGE re-baseline never ran against a real 2.x Agent.
[Fact]
public async Task Sample_answered_400_with_an_out_of_range_document_surfaces_as_the_agents_refusal()
{
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.BadRequest, OutOfRangeError)));
var ex = await Should.ThrowAsync<InvalidDataException>(async () => await DrainAsync(client.SampleAsync(1, Ct)));
ex.Message.ShouldContain("OUT_OF_RANGE: 'from' must be greater than 59962705");
ex.Message.ShouldContain("HTTP 400");
MTConnectXml.IsAgentRefusal(ex).ShouldBeTrue();
}
[Fact]
public async Task Current_answered_404_with_a_no_device_document_is_an_agent_refusal_not_a_comms_fault()
{
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.NotFound, NoDeviceError)));
var ex = await Should.ThrowAsync<InvalidDataException>(() => client.CurrentAsync(Ct));
ex.Message.ShouldContain("NO_DEVICE");
MTConnectXml.IsAgentRefusal(ex).ShouldBeTrue();
}
[Fact]
public async Task Probe_answered_404_with_an_error_document_carries_the_agents_own_words()
{
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.NotFound, NoDeviceError)));
var ex = await Should.ThrowAsync<InvalidDataException>(() => client.ProbeAsync(Ct));
ex.Message.ShouldContain("Could not find the device 'nosuch'");
ex.Message.ShouldContain("expected <MTConnectDevices>");
}
/// <summary>Positive control: a non-2xx body that is NOT an MTConnect error document keeps the status-only failure.</summary>
[Fact]
public async Task A_non_2xx_proxy_page_is_still_a_plain_http_failure()
{
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.BadGateway, "<html><body>502</body></html>")));
await Should.ThrowAsync<HttpRequestException>(() => client.CurrentAsync(Ct));
}
/// <summary>The failure body is read only up to the cap: a huge error page never becomes a huge string.</summary>
[Fact]
public async Task An_error_document_beyond_the_body_cap_is_not_read_in_full()
{
var padding = new string(' ', 70 * 1024); // past the 64 KiB failure-body cap
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.BadRequest, padding + OutOfRangeError)));
// The document starts past the cap, so it is never seen: status-only failure, not a refusal.
await Should.ThrowAsync<HttpRequestException>(async () => await DrainAsync(client.SampleAsync(1, Ct)));
}
// ───────────── gap 2 (driver-level, MTConnectSubscribeTests): repeated re-baselines without progress ─────────────
// ───────────── gap 3: streams parser nesting bound ─────────────
// ReadElement/ReadChildren recurse per nesting level; an unbounded depth from an unauthenticated peer is a
// StackOverflowException, which .NET cannot catch — the whole server process dies.
private static string Streams(string body) =>
$"""
<MTConnectStreams xmlns="urn:mtconnect.org:MTConnectStreams:2.0">
<Header creationTime="2026-11-10T12:00:00Z" instanceId="1" bufferSize="16" firstSequence="1" lastSequence="5" nextSequence="6"/>
<Streams>{body}</Streams>
</MTConnectStreams>
""";
[Fact]
public void Streams_parse_refuses_absurd_nesting_instead_of_recursing_without_bound()
{
const int depth = 80; // beyond the 64-level bound
var xml = Streams(string.Concat(Enumerable.Repeat("<x>", depth)) + string.Concat(Enumerable.Repeat("</x>", depth)));
var ex = Should.Throw<InvalidDataException>(() => MTConnectStreamsParser.Parse(xml));
ex.Message.ShouldContain("levels deep");
}
/// <summary>Positive control: a real document's nesting (with a TABLE's Entry/Cell) parses under the bound.</summary>
[Fact]
public void Streams_parse_accepts_ordinary_device_nesting()
{
var xml = Streams(
"""
<DeviceStream name="d" uuid="u"><ComponentStream component="Path" componentId="p">
<Events>
<WorkOffsetTable dataItemId="wo" timestamp="2026-11-10T12:00:00Z" sequence="5" count="1">
<Entry key="G54"><Cell key="X">1.0</Cell></Entry>
</WorkOffsetTable>
<Execution dataItemId="exec" timestamp="2026-11-10T12:00:00Z" sequence="4">ACTIVE</Execution>
</Events>
</ComponentStream></DeviceStream>
""");
var result = MTConnectStreamsParser.Parse(xml);
result.Observations.Select(o => o.DataItemId).ShouldBe(["wo", "exec"]);
}
// ───────────── gap 4: DOCTYPE refused on every tree-building parse ─────────────
// The streams parser already prohibited DTDs; the /probe parse (and the write-answer parse) went through
// XDocument.Parse, which PARSES a DTD and expands its internal entities.
private const string ProbeWithDoctype =
"""
<?xml version="1.0"?>
<!DOCTYPE MTConnectDevices [ <!ENTITY injected "Injected"> ]>
<MTConnectDevices xmlns="urn:mtconnect.org:MTConnectDevices:2.0">
<Header instanceId="1"/>
<Devices><Device id="d1" name="&injected;"><DataItems><DataItem id="a" category="EVENT" type="AVAILABILITY"/></DataItems></Device></Devices>
</MTConnectDevices>
""";
[Fact]
public void Probe_parse_refuses_a_doctype_from_a_string()
{
var ex = Should.Throw<InvalidDataException>(() => MTConnectProbeParser.Parse(ProbeWithDoctype));
ex.Message.ShouldContain("not well-formed XML");
}
[Fact]
public void Probe_parse_refuses_a_doctype_from_a_stream()
{
using var stream = new MemoryStream(Encoding.UTF8.GetBytes(ProbeWithDoctype));
Should.Throw<InvalidDataException>(() => MTConnectProbeParser.Parse(stream));
}
/// <summary>A write answered with a DOCTYPE'd document cannot be read, so it is NOT reported as accepted.</summary>
[Fact]
public async Task A_write_answered_with_a_doctype_document_is_not_confirmed()
{
const string body =
"""
<!DOCTYPE MTConnectError [ <!ENTITY e "x"> ]>
<MTConnectError><Errors><Error errorCode="UNSUPPORTED">&e;</Error></Errors></MTConnectError>
""";
using var client = NewClient(new StubHandler(_ => Respond(HttpStatusCode.OK, body)));
var outcome = await client.WriteObservationAsync("d", "item", "v", Ct);
outcome.Accepted.ShouldBeFalse();
outcome.AgentError.ShouldNotBeNull().ShouldContain("DOCTYPE");
}
// ───────────── gap 5: no fabricated non-finite floats ─────────────
// .NET parses an overflowing literal to ±Infinity and accepts NaN/Infinity spellings; all were Good.
[Theory]
[InlineData(DriverDataType.Float64, "1e400", 0x803C0000u)] // BadOutOfRange — a number the type cannot hold
[InlineData(DriverDataType.Float64, "-1e400", 0x803C0000u)]
[InlineData(DriverDataType.Float32, "1e39", 0x803C0000u)] // fits a double, overflows a float
[InlineData(DriverDataType.Float64, "NaN", 0x80740000u)] // BadTypeMismatch — not a measurement
[InlineData(DriverDataType.Float64, "Infinity", 0x80740000u)]
[InlineData(DriverDataType.Float32, "-Infinity", 0x80740000u)]
public void A_non_finite_float_is_never_served_as_good(DriverDataType type, string text, uint expected)
{
var snap = Coerce(type, text);
snap.StatusCode.ShouldBe(expected);
snap.Value.ShouldBeNull();
}
// ───────────── gap 6: an integer-valued decimal on an integral tag ─────────────
// Agents format integer-valued items as "42.000000"; that was BadOutOfRange on every integral tag.
[Theory]
[InlineData(DriverDataType.Int32, "42.000000", 42)]
[InlineData(DriverDataType.Int64, "1.5e3", 1500L)]
[InlineData(DriverDataType.Int16, "-7.0", (short)-7)]
[InlineData(DriverDataType.UInt32, "4000000000.0", 4000000000u)]
public void An_integer_valued_decimal_converts_losslessly(DriverDataType type, string text, object expected)
{
var snap = Coerce(type, text);
snap.StatusCode.ShouldBe(0u);
snap.Value.ShouldBe(expected);
}
/// <summary>…but a REAL fraction is still refused, never truncated (deliberately stricter than the Java driver).</summary>
[Theory]
[InlineData(DriverDataType.Int32, "42.5")]
[InlineData(DriverDataType.Int16, "40000.0")]
[InlineData(DriverDataType.UInt16, "-1.0")]
[InlineData(DriverDataType.Int64, "1e30")]
public void A_fraction_or_an_out_of_range_decimal_stays_out_of_range(DriverDataType type, string text)
{
var snap = Coerce(type, text);
snap.StatusCode.ShouldBe(0x803C0000u);
snap.Value.ShouldBeNull();
}
private static DataValueSnapshot Coerce(DriverDataType type, string text)
{
var index = new MTConnectObservationIndex([new MTConnectTagDefinition("x", type)]);
index.Apply(new MTConnectStreamsResult(
1L, 2L, 1L, [new MTConnectObservation("x", text, new DateTime(2026, 11, 10, 12, 0, 0, DateTimeKind.Utc))]));
return index.Get("x");
}
// ───────────── gap 7: sibling containers resolving to one folder name ─────────────
// Two same-named sibling folders share one path key in the browse picker; the second one's data items were
// listed but unreachable on expand. Merged into ONE folder (what the Java driver does).
private const string CollidingProbe =
"""
<MTConnectDevices xmlns="urn:mtconnect.org:MTConnectDevices:2.0">
<Header instanceId="1"/>
<Devices>
<Device id="d1" name="Mill">
<Components>
<Axes id="ax" name="Axes">
<Components>
<Rotary id="c_rot" name="C"><DataItems><DataItem id="c_angle" category="SAMPLE" type="ANGLE"/></DataItems></Rotary>
<Linear id="c_lin" name="C"><DataItems><DataItem id="c_pos" category="SAMPLE" type="POSITION"/></DataItems></Linear>
<Linear id="X"><DataItems><DataItem id="x_pos" category="SAMPLE" type="POSITION"/></DataItems></Linear>
<Linear id="x2" name="X"><DataItems><DataItem id="x2_pos" category="SAMPLE" type="POSITION"/></DataItems></Linear>
</Components>
</Axes>
</Components>
</Device>
</Devices>
</MTConnectDevices>
""";
[Fact]
public async Task Sibling_components_resolving_to_one_name_share_one_folder_and_keep_every_data_item()
{
var client = CannedAgentClient.FromFixtures();
client.Probe = MTConnectProbeParser.Parse(CollidingProbe);
var driver = new MTConnectDriver(new MTConnectDriverOptions { AgentUri = "http://agent:5000" }, "mt1", _ => client);
await driver.InitializeAsync("{}", Ct);
var cap = new CapturingBuilder();
await driver.DiscoverAsync(cap, Ct);
cap.Folders.Select(f => f.Path).ShouldBe(["Mill", "Mill/Axes", "Mill/Axes/C", "Mill/Axes/X"]);
cap.Variables.Single(v => v.Attr.FullName == "c_angle").ParentPath.ShouldBe("Mill/Axes/C");
cap.Variables.Single(v => v.Attr.FullName == "c_pos").ParentPath.ShouldBe("Mill/Axes/C");
cap.Variables.Single(v => v.Attr.FullName == "x_pos").ParentPath.ShouldBe("Mill/Axes/X"); // id fallback
cap.Variables.Single(v => v.Attr.FullName == "x2_pos").ParentPath.ShouldBe("Mill/Axes/X"); // name
}
// ───────────── gap 8: structural elements are not components ─────────────
[Fact]
public void A_structural_element_under_components_or_devices_is_skipped_not_fatal()
{
const string xml =
"""
<MTConnectDevices xmlns="urn:mtconnect.org:MTConnectDevices:2.0">
<Header instanceId="1"/>
<Devices>
<Description>agent-wide note</Description>
<Device id="d1" name="Mill">
<Components>
<Description>stray, schema-invalid</Description>
<Controller id="ctl"><DataItems><DataItem id="mode" category="EVENT" type="CONTROLLER_MODE"/></DataItems></Controller>
</Components>
</Device>
</Devices>
</MTConnectDevices>
""";
var model = MTConnectProbeParser.Parse(xml);
model.Devices.ShouldHaveSingleItem().Components.ShouldHaveSingleItem().Id.ShouldBe("ctl");
}
// ───────────── plumbing ─────────────
private static HttpResponseMessage Respond(HttpStatusCode status, string body) =>
new(status) { Content = new StringContent(body, Encoding.UTF8, "application/xml") };
private sealed class StubHandler(Func<HttpRequestMessage, HttpResponseMessage> respond) : HttpMessageHandler
{
protected override Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken ct) =>
Task.FromResult(respond(request));
}
// ───────────── Java regression scenarios this driver already met (coverage, not gaps) ─────────────
// Ported from the Java MTConnectMultipartReaderTest / MTConnectStreamsParserTest cases that had no
// .NET counterpart. Each passed before #804; they pin behaviour the matrix records as "covered".
private static string Doc(long first, long next, string observations = "") => Streams(
$"""<DeviceStream name="d"><ComponentStream component="Path" componentId="p"><Events>{observations}</Events></ComponentStream></DeviceStream>""")
.Replace("firstSequence=\"1\"", $"firstSequence=\"{first}\"").Replace("nextSequence=\"6\"", $"nextSequence=\"{next}\"");
private static HttpResponseMessage MultipartResponse(byte[] body) => MultipartResponse(new ByteArrayContent(body));
private static HttpResponseMessage MultipartResponse(HttpContent content)
{
content.Headers.ContentType =
System.Net.Http.Headers.MediaTypeHeaderValue.Parse("multipart/x-mixed-replace; boundary=b0");
return new HttpResponseMessage(HttpStatusCode.OK) { Content = content };
}
private static async Task<List<MTConnectStreamsResult>> CollectAsync(MTConnectAgentClient client, int count)
{
var results = new List<MTConnectStreamsResult>();
await foreach (var chunk in client.SampleAsync(1, Ct))
{
results.Add(chunk);
if (results.Count == count)
{
break;
}
}
return results;
}
/// <summary>Java <c>contentLengthIsHonoredOverBoundaryScanning</c>: a document whose text contains the boundary token is returned whole.</summary>
[Fact]
public async Task A_declared_content_length_is_authoritative_over_a_boundary_token_inside_the_document()
{
var doc = Doc(1, 2, "<Message dataItemId=\"m\" timestamp=\"2026-11-10T12:00:00Z\">see\r\n--b0 inside the text</Message>");
var payload = Encoding.UTF8.GetBytes(doc);
var body = Encoding.ASCII.GetBytes($"--b0\r\nContent-type: text/xml\r\nContent-length: {payload.Length}\r\n\r\n")
.Concat(payload).Concat("\r\n--b0--\r\n"u8.ToArray()).ToArray();
using var client = NewClient(new StubHandler(_ => MultipartResponse(body)));
var chunk = (await CollectAsync(client, 1)).ShouldHaveSingleItem();
chunk.Observations.ShouldHaveSingleItem().Value.ShouldContain("--b0 inside the text");
}
/// <summary>Java <c>preambleBeforeTheFirstBoundaryIsSkipped</c> + <c>lineFeedOnlyFramingIsAccepted</c>.</summary>
[Fact]
public async Task A_preamble_is_skipped_and_line_feed_only_framing_is_accepted()
{
var first = Encoding.UTF8.GetBytes(Doc(1, 2));
var second = Encoding.UTF8.GetBytes(Doc(2, 3));
var body = Encoding.ASCII.GetBytes("this is preamble text\n--b0\nContent-length: " + first.Length + "\n\n")
.Concat(first)
.Concat(Encoding.ASCII.GetBytes("\n--b0\nContent-length: " + second.Length + "\n\n"))
.Concat(second)
.Concat("\n--b0--\n"u8.ToArray()).ToArray();
using var client = NewClient(new StubHandler(_ => MultipartResponse(body)));
var chunks = await CollectAsync(client, 2);
chunks.Select(c => c.NextSequence).ShouldBe([2L, 3L]);
}
/// <summary>Java <c>aBodyShorterThanItsDeclaredContentLengthThrows</c>: truncation is a lost stream, never an orderly end.</summary>
[Fact]
public async Task A_part_shorter_than_its_declared_content_length_is_a_lost_stream()
{
var payload = Encoding.UTF8.GetBytes(Doc(1, 2));
var body = Encoding.ASCII.GetBytes($"--b0\r\nContent-length: {payload.Length + 500}\r\n\r\n").Concat(payload).ToArray();
using var client = NewClient(new StubHandler(_ => MultipartResponse(body)));
await Should.ThrowAsync<MTConnectStreamEndedException>(async () => await DrainAsync(client.SampleAsync(1, Ct)));
}
/// <summary>Java <c>aPartLargerThanTheBufferCapIsRefused</c>: a peer that never frames a part cannot grow the buffer unbounded.</summary>
[Fact]
public async Task A_part_larger_than_the_buffer_cap_is_refused()
{
var head = "--b0\r\nContent-type: text/xml\r\n\r\n"u8.ToArray();
using var client = NewClient(new StubHandler(_ => MultipartResponse(new StreamContent(new EndlessPart(head)))));
var ex = await Should.ThrowAsync<InvalidDataException>(async () => await DrainAsync(client.SampleAsync(1, Ct)));
ex.Message.ShouldContain("refusing to buffer further");
}
/// <summary>Java <c>timestampWithANonZuluOffsetIsNormalizedToTheSameInstant</c>: the SourceTimestamp is the Agent's instant, in UTC.</summary>
[Fact]
public void A_timestamp_with_a_non_zulu_offset_is_normalized_to_the_same_utc_instant()
{
var result = MTConnectStreamsParser.Parse(
Doc(1, 2, """<Execution dataItemId="e" timestamp="2026-11-10T14:00:00.5+02:00">ACTIVE</Execution>"""));
var at = result.Observations.ShouldHaveSingleItem().TimestampUtc;
at.ShouldBe(new DateTime(2026, 11, 10, 12, 0, 0, 500, DateTimeKind.Utc));
at.Kind.ShouldBe(DateTimeKind.Utc);
}
/// <summary>
/// Java <c>anAbsurdlyDeepErrorDocumentStillYieldsTheAgentsWords</c>: the new nesting bound applies to the
/// observation walk only, so a deeply nested error document still reports the Agent's own text.
/// </summary>
[Fact]
public void An_absurdly_deep_error_document_still_yields_the_agents_words()
{
var nest = string.Concat(Enumerable.Repeat("<x>", 100));
var unnest = string.Concat(Enumerable.Repeat("</x>", 100));
var xml = $"""<MTConnectError><Errors>{nest}<Error errorCode="OUT_OF_RANGE">deep</Error>{unnest}</Errors></MTConnectError>""";
var ex = Should.Throw<InvalidDataException>(() => MTConnectStreamsParser.Parse(xml));
ex.Message.ShouldContain("OUT_OF_RANGE: deep");
}
/// <summary>A read-only stream that serves <c>head</c> then an endless run of document bytes with no boundary.</summary>
private sealed class EndlessPart(byte[] head) : Stream
{
private long _position;
public override int Read(byte[] buffer, int offset, int count)
{
var written = 0;
while (written < count)
{
buffer[offset + written] = _position < head.Length ? head[_position] : (byte)'a';
_position++;
written++;
}
return written;
}
public override bool CanRead => true;
public override bool CanSeek => false;
public override bool CanWrite => false;
public override long Length => throw new NotSupportedException();
public override long Position { get => _position; set => throw new NotSupportedException(); }
public override void Flush() { }
public override long Seek(long offset, SeekOrigin origin) => throw new NotSupportedException();
public override void SetLength(long value) => throw new NotSupportedException();
public override void Write(byte[] buffer, int offset, int count) => throw new NotSupportedException();
}
}
@@ -452,6 +452,56 @@ public sealed class MTConnectSubscribeTests
For(seen, "dev1_pos").Last().Snapshot.Value.ShouldBe(9.5d);
}
/// <summary>
/// #804 (Java-driver parity: the restart test runs on the re-baseline snapshot too). On a real 2.x Agent a
/// restart is usually seen FIRST by the re-baseline, not by a chunk: the restarted process refuses the dead
/// one's cursor with HTTP 400 <c>OUT_OF_RANGE</c> (live-observed on the fixture), so no chunk ever reaches the
/// in-stream <c>instanceId</c> check. The re-baseline used to adopt the new id silently — no rediscovery
/// prompt, and the dead model's held values kept being served.
/// </summary>
[Fact]
public async Task An_agent_restart_seen_only_by_the_rebaseline_drops_held_values_and_raises_rediscovery()
{
var (driver, client) = await InitializedDriverAsync();
var raised = new ConcurrentQueue<RediscoveryEventArgs>();
driver.OnRediscoveryNeeded += (_, e) => raised.Enqueue(e);
var seen = Record(driver);
// The restarted Agent refuses the old cursor, and its /current knows nothing about dev1_execution.
client.SampleFailures.Enqueue(new InvalidDataException("OUT_OF_RANGE: 'from' must be less than 42 (served under HTTP 400)"));
client.CurrentAnswers.Enqueue(ChunkFrom(RestartedInstanceId, 40, 42, ("dev1_pos", "9.5")));
await driver.SubscribeAsync(["dev1_pos", "dev1_execution"], TimeSpan.FromMilliseconds(50), Ct);
await client.WaitForSampleCallsAsync(2).WaitAsync(Watchdog, Ct);
driver.AgentInstanceId.ShouldBe(RestartedInstanceId);
raised.ShouldHaveSingleItem().Reason.ShouldContain("instanceId");
client.LastSampleFrom.ShouldBe(42);
driver.ObservationIndex.Get("dev1_execution").StatusCode.ShouldBe(BadWaitingForInitialData);
driver.ObservationIndex.Get("dev1_pos").Value.ShouldBe(9.5d);
For(seen, "dev1_execution").Last().Snapshot.StatusCode.ShouldBe(BadWaitingForInitialData);
}
/// <summary>…control: an OUT_OF_RANGE re-baseline against the SAME Agent raises nothing and keeps its values.</summary>
[Fact]
public async Task An_out_of_range_rebaseline_against_the_same_agent_raises_no_rediscovery()
{
var (driver, client) = await InitializedDriverAsync();
var raised = new ConcurrentQueue<RediscoveryEventArgs>();
driver.OnRediscoveryNeeded += (_, e) => raised.Enqueue(e);
client.SampleFailures.Enqueue(new InvalidDataException("OUT_OF_RANGE (served under HTTP 400)"));
client.CurrentAnswers.Enqueue(Chunk(5000, 5005, ("dev1_pos", "2.5")));
await driver.SubscribeAsync(["dev1_pos", "dev1_execution"], TimeSpan.FromMilliseconds(50), Ct);
await client.WaitForSampleCallsAsync(2).WaitAsync(Watchdog, Ct);
raised.ShouldBeEmpty();
driver.AgentInstanceId.ShouldBe(FixtureInstanceId);
driver.ObservationIndex.Get("dev1_execution").StatusCode.ShouldBe(Good);
}
// ---- stream ends ----
/// <summary>
@@ -1116,6 +1166,85 @@ public sealed class MTConnectSubscribeTests
driver.ReconnectAttempts.ShouldBe(0);
}
/// <summary>
/// <b>#804 (Java-driver parity: <c>MAX_REBASELINES_WITHOUT_PROGRESS</c>).</b> An Agent that answers EVERY
/// <c>/sample</c> open with <c>OUT_OF_RANGE</c> (live: a <c>count</c> at or above its <c>bufferSize</c>) is
/// re-baselined from <c>/current</c> each time, and the backoff paces that — but every re-baseline also marked
/// the stream delivered, so the driver read <b>Healthy</b> for ever while not one <c>/sample</c> chunk arrived.
/// After <see cref="MTConnectDriver.MaxRebaselinesWithoutProgress"/> in a row it is Degraded and stays so
/// across further re-baselines, with <c>LastSuccessfulRead</c> still advancing (each <c>/current</c> is the
/// Agent answering — the comms-loss watchdog must not reconnect-loop a configuration problem).
/// </summary>
[Fact]
public async Task Repeated_rebaselines_without_a_delivered_chunk_report_the_stream_degraded()
{
var options = Opts(new MTConnectReconnectOptions { MinBackoffMs = 0, MaxBackoffMs = 1 });
var (driver, client) = await InitializedDriverAsync(options: options);
client.SampleFailure = new InvalidDataException("MTConnectError OUT_OF_RANGE: 'count' must be less than 65 (served under HTTP 400)");
var handle = await driver.SubscribeAsync(["dev1_pos"], TimeSpan.FromMilliseconds(50), Ct);
try
{
// Well past the cap, so the hold across LATER re-baselines is what is asserted, not a lucky instant.
await client.WaitForSampleCallsAsync(MTConnectDriver.MaxRebaselinesWithoutProgress + 3).WaitAsync(Watchdog, Ct);
var stalledAt = driver.GetHealth();
stalledAt.State.ShouldBe(DriverState.Degraded);
stalledAt.LastError.ShouldBe(MTConnectDriver.StalledStreamReason);
stalledAt.LastSuccessfulRead.ShouldNotBeNull();
// LastSuccessfulRead keeps advancing while it is stalled: the /current answers are real.
await client.WaitForSampleCallsAsync(client.SampleCallCount + 2).WaitAsync(Watchdog, Ct);
driver.GetHealth().State.ShouldBe(DriverState.Degraded);
driver.GetHealth().LastSuccessfulRead!.Value.ShouldBeGreaterThanOrEqualTo(stalledAt.LastSuccessfulRead!.Value);
// Positive control: the Agent starts streaming again — one delivered chunk clears the verdict.
client.SampleFailure = null;
await client.PumpAsync(Chunk(PrimedNextSequence, PrimedNextSequence + 1, ("dev1_pos", "9.5")))
.WaitAsync(Watchdog, Ct);
await WaitForHealthAsync(driver, DriverState.Healthy, Ct);
}
finally
{
await driver.UnsubscribeAsync(handle, Ct).WaitAsync(Watchdog, Ct);
}
}
/// <summary>
/// …the falsification control: FEWER than the cap is an ordinary recovery and must stay Healthy (a genuine
/// ring-buffer overrun is resolved by one re-baseline).
/// </summary>
[Fact]
public async Task A_rebaseline_short_of_the_cap_stays_healthy()
{
var (driver, client) = await InitializedDriverAsync();
client.SampleFailures.Enqueue(new InvalidDataException("OUT_OF_RANGE (served under HTTP 400)"));
var handle = await driver.SubscribeAsync(["dev1_pos"], TimeSpan.FromMilliseconds(50), Ct);
try
{
await client.WaitForSampleCallsAsync(2).WaitAsync(Watchdog, Ct);
await client.PumpAsync(Chunk(PrimedNextSequence, PrimedNextSequence + 1, ("dev1_pos", "1.5")))
.WaitAsync(Watchdog, Ct);
driver.GetHealth().State.ShouldBe(DriverState.Healthy);
}
finally
{
await driver.UnsubscribeAsync(handle, Ct).WaitAsync(Watchdog, Ct);
}
}
private static async Task WaitForHealthAsync(MTConnectDriver driver, DriverState state, CancellationToken ct)
{
using var watchdog = CancellationTokenSource.CreateLinkedTokenSource(ct);
watchdog.CancelAfter(Watchdog);
while (driver.GetHealth().State != state)
{
await Task.Delay(5, watchdog.Token).ConfigureAwait(false);
}
}
/// <summary>
/// <b>I3 — a non-positive cap is an operator-authorable hot loop.</b> Clamping to it (the
/// obvious <c>Math.Max(0, …)</c>) makes EVERY delay zero, so the pump reconnect-spins as fast