diff --git a/src/ZB.MOM.WW.ScadaBridge.Transport/Import/LineDiffer.cs b/src/ZB.MOM.WW.ScadaBridge.Transport/Import/LineDiffer.cs index 88a830ee..beb4f98a 100644 --- a/src/ZB.MOM.WW.ScadaBridge.Transport/Import/LineDiffer.cs +++ b/src/ZB.MOM.WW.ScadaBridge.Transport/Import/LineDiffer.cs @@ -51,6 +51,16 @@ public sealed record LineDiffResult( /// public static class LineDiffer { + /// + /// Hard ceiling on the combined old+new line count fed to the Myers algorithm. Myers + /// records a V frontier snapshot per edit distance d (up to n + m rounds), + /// each snapshot sized O(n + m), so a fully-divergent diff is O((n + m)^2) + /// transient memory. To keep a bloated or crafted bundle from OOM-ing the active central + /// node during an import preview, oversized inputs short-circuit to a summary-only result + /// (the same shape the output cap emits) instead of running the trace. + /// + private const int MaxInputLines = 4000; + /// /// Computes a minimal per-line diff between and /// (either may be , treated as empty). @@ -68,6 +78,13 @@ public static class LineDiffer string[] oldLines = SplitLines(oldText); string[] newLines = SplitLines(newText); + // Input-size guard: bound the ALGORITHM INPUT (distinct from the output cap below) so an + // oversized diff degrades to a summary instead of allocating O((n + m)^2) Myers snapshots. + if (oldLines.Length + newLines.Length > MaxInputLines) + { + return SummaryOnlyResult(oldLines.Length, newLines.Length); + } + IReadOnlyList full = BuildDiff(oldLines, newLines, out int added, out int removed); bool truncated = full.Count > maxLines; @@ -91,6 +108,15 @@ public static class LineDiffer return new LineDiffResult(lines, truncated, added, removed); } + /// + /// Builds the truncated summary-only shape returned when the diff cannot be materialized in + /// full — no hunks, set, and the add/remove totals + /// approximated as a full replacement (every new line added, every old line removed). Used + /// by the input-size guard so a diff too large to run cheaply still reports its magnitude. + /// + private static LineDiffResult SummaryOnlyResult(int oldCount, int newCount) + => new([], Truncated: true, AddedCount: newCount, RemovedCount: oldCount); + /// /// Normalizes line endings (\r\n and lone \r to \n) and splits on \n. /// A or empty input yields an empty array (no lines), so the diff of two diff --git a/tests/ZB.MOM.WW.ScadaBridge.Transport.Tests/Import/LineDifferTests.cs b/tests/ZB.MOM.WW.ScadaBridge.Transport.Tests/Import/LineDifferTests.cs index fb84625e..cd655b05 100644 --- a/tests/ZB.MOM.WW.ScadaBridge.Transport.Tests/Import/LineDifferTests.cs +++ b/tests/ZB.MOM.WW.ScadaBridge.Transport.Tests/Import/LineDifferTests.cs @@ -1,3 +1,5 @@ +using System.Diagnostics; + using ZB.MOM.WW.ScadaBridge.Transport.Import; namespace ZB.MOM.WW.ScadaBridge.Transport.Tests.Import; @@ -189,4 +191,29 @@ public sealed class LineDifferTests Assert.Equal(0, result.AddedCount); Assert.Equal(0, result.RemovedCount); } + + [Fact] + public void OversizedInputs_ZeroCommonLines_DegradesToSummary_WithoutRunningMyers() + { + // Two 10,000-line inputs with zero common lines. Running the Myers trace here would + // record ~20,000 V-snapshots of ~160 KB each (multi-GB transient allocation), so the + // input-size guard must short-circuit to a summary-only result long before that. + var oldText = string.Join("\n", Enumerable.Range(1, 10_000).Select(i => $"old-line-{i}")); + var newText = string.Join("\n", Enumerable.Range(1, 10_000).Select(i => $"new-line-{i}")); + + var sw = Stopwatch.StartNew(); + var result = LineDiffer.Diff(oldText, newText); + sw.Stop(); + + // Summary-only shape: same as the output cap — Truncated, full totals, no hunks. + Assert.True(result.Truncated); + Assert.Empty(result.Lines); + Assert.Equal(10_000, result.AddedCount); + Assert.Equal(10_000, result.RemovedCount); + + // Must return within a small time budget; pathological slowness is a failure. + Assert.True( + sw.Elapsed < TimeSpan.FromSeconds(2), + $"Diff of oversized inputs took {sw.Elapsed.TotalSeconds:F1}s — the input-size guard did not short-circuit."); + } }