Files
ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.Tests/AuditLogAppendOnlyGuardTests.cs
T

469 lines
24 KiB
C#

using System.Text.RegularExpressions;
namespace ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.Tests;
/// <summary>
/// Code-level guard for the AuditLog append-only invariant (task M2.10, #18).
///
/// The DB-role control (DENY UPDATE / DENY DELETE on dbo.AuditLog in migration
/// 20260602174346_CollapseAuditLogToCanonical) is the runtime enforcement layer.
/// This test is the compile-time / test-time backstop: it fails the test run if
/// any C# source file in the ConfigurationDatabase project contains an UPDATE or
/// DELETE statement that targets the AuditLog table.
///
/// <b>Matching rule (see <c>ContainsAuditLogMutation</c> for full detail)</b>
/// A line is flagged as a violation iff it matches the DML-syntax pattern:
/// • <c>UPDATE\s+(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b</c> — UPDATE targeting AuditLog
/// • <c>DELETE\s+(?:FROM\s+)?(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b</c> — DELETE targeting AuditLog
///
/// These tight DML-syntax patterns naturally exclude false positives:
/// - DENY UPDATE ON dbo.AuditLog … → "DENY" comes before UPDATE; the regex
/// requires UPDATE to be immediately followed by (optional schema.) AuditLog,
/// so "UPDATE ON" does NOT match "UPDATE AuditLog".
/// - ALTER TABLE dbo.AuditLog SWITCH … → ALTER TABLE precedes the table name;
/// no UPDATE/DELETE keyword present.
/// - Comments like "// AuditLog … UPDATE …" → UPDATE is not immediately followed
/// by AuditLog (there are intervening words).
/// - DELETE FROM Notifications … → AuditLog not present.
///
/// <b>Known limitations:</b> This guard scans only raw SQL strings — EF Core methods
/// such as <c>ExecuteDeleteAsync</c>, <c>ExecuteUpdateAsync</c>, and <c>RemoveRange</c>
/// targeting the AuditLog entity are NOT covered and must never be introduced.
/// Additionally, the scan is line-oriented: DML where the keyword and table name appear
/// on separate lines is an accepted, undetected edge case.
///
/// <b>Allow-list.</b> Two narrow maintenance-path exemptions carry the exact
/// <see cref="AuditPurgeAllowedMarker"/> trailing comment:
/// <list type="bullet">
/// <item><description>
/// M5.5 (T3) — <c>AuditLogRepository.PurgeChannelOlderThanAsync</c>: the
/// one sanctioned batched <c>DELETE TOP (@batch) FROM dbo.AuditLog</c>,
/// running on the purge/maintenance connection.
/// </description></item>
/// <item><description>
/// M5.6 (T5) — <c>AuditLogRepository.BackfillSourceNodeAsync</c>: the
/// one sanctioned batched <c>UPDATE TOP (@batch) dbo.AuditLog SET SourceNode</c>,
/// running on the maintenance connection. The sentinel backfill is a
/// one-time ops procedure; the append-only invariant still applies to all
/// other columns and all other UPDATE forms.
/// </description></item>
/// </list>
/// The allow-list is applied in the file-scan test only
/// (<see cref="ConfigurationDatabase_ShouldNotContainAuditLogMutations"/>) — the
/// raw mutation matcher (<see cref="ContainsAuditLogMutation"/>) is marker-blind,
/// so the matcher's self-tests remain honest and any OTHER UPDATE/DELETE against
/// AuditLog (or any DML lacking the marker) still fails the build.
/// </summary>
public class AuditLogAppendOnlyGuardTests
{
/// <summary>
/// The exact trailing-comment marker that exempts a single sanctioned
/// maintenance-path DML line from the append-only guard. Carried at the END of
/// the SQL constant string in both <c>AuditLogRepository.PurgeChannelOlderThanAsync</c>
/// (M5.5 T3 batched DELETE) and <c>AuditLogRepository.BackfillSourceNodeAsync</c>
/// (M5.6 T5 batched UPDATE). Kept deliberately specific so it cannot be pasted
/// onto an unrelated mutation without a reviewer noticing.
/// </summary>
internal const string AuditPurgeAllowedMarker = "AUDIT-PURGE-ALLOWED";
// ---------------------------------------------------------------------------
// Source root location — same walk-up pattern used by ArchitecturalConstraintTests
// in the Commons.Tests project.
// ---------------------------------------------------------------------------
private static string GetConfigurationDatabaseSourceDirectory()
{
// Walk up from the test binary output directory until we find the
// ConfigurationDatabase csproj (a known anchor in the repo tree).
var dir = new DirectoryInfo(AppContext.BaseDirectory);
while (dir != null)
{
var candidate = Path.Combine(
dir.FullName,
"src",
"ZB.MOM.WW.ScadaBridge.ConfigurationDatabase",
"ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.csproj");
if (File.Exists(candidate))
{
return Path.GetDirectoryName(candidate)!;
}
dir = dir.Parent;
}
throw new InvalidOperationException(
"Could not locate ZB.MOM.WW.ScadaBridge.ConfigurationDatabase.csproj " +
"by walking up from the test output directory. " +
"Ensure the test is run from inside the repo clone.");
}
// ---------------------------------------------------------------------------
// Detection helper — kept as a static method so it can be unit-tested in
// isolation below without requiring any file I/O.
// ---------------------------------------------------------------------------
/// <summary>
/// Returns <see langword="true"/> when the supplied text (typically a single
/// source line) contains a SQL UPDATE or DELETE DML statement that directly
/// targets the <c>AuditLog</c> table.
///
/// <b>Matching rule.</b> The regex requires the DML keyword to be
/// immediately followed (possibly via FROM) by the optional schema prefix
/// (<c>dbo.</c> or <c>[dbo].</c>) and then the table name <c>AuditLog</c>
/// or <c>[AuditLog]</c> as a whole word:
/// <code>
/// UPDATE\s+(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b
/// DELETE\s+(?:FROM\s+)?(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b
/// </code>
/// This tight DML-syntax pattern naturally excludes false positives without
/// any additional keyword checks:
/// <list type="bullet">
/// <item><description>
/// <c>DENY UPDATE ON dbo.AuditLog …</c> — "UPDATE ON" is never immediately
/// followed by AuditLog; the pattern requires UPDATE → optional schema → AuditLog.
/// </description></item>
/// <item><description>
/// <c>ALTER TABLE dbo.AuditLog SWITCH …</c> — no UPDATE/DELETE keyword present.
/// </description></item>
/// <item><description>
/// <c>// AuditLog is append-only; never issue an UPDATE against it.</c> —
/// UPDATE is not followed by AuditLog here.
/// </description></item>
/// <item><description>
/// <c>DELETE FROM dbo.Notifications …</c> — AuditLog not present.
/// </description></item>
/// </list>
/// </summary>
/// <param name="text">A single source line (or any string to probe).</param>
/// <returns><see langword="true"/> if a mutation against AuditLog is detected.</returns>
internal static bool ContainsAuditLogMutation(string text)
{
if (string.IsNullOrEmpty(text))
{
return false;
}
// DML-syntax pattern: the UPDATE or DELETE keyword must be directly followed
// (optionally via FROM) by the optional schema qualifier and then the table name.
//
// Schema sub-pattern : (?:\[?dbo\]?\.)?
// matches: nothing, "dbo.", "[dbo]."
//
// Table sub-pattern : \[?AuditLog\]?
// matches: "AuditLog", "[AuditLog]"
//
// UPDATE\s+(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b
// matches: "UPDATE AuditLog", "UPDATE dbo.AuditLog",
// "UPDATE [AuditLog]", "UPDATE [dbo].[AuditLog]"
// does NOT match: "DENY UPDATE ON dbo.AuditLog" (UPDATE is followed by ON)
//
// DELETE\s+(?:FROM\s+)?(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b
// matches: "DELETE FROM AuditLog", "DELETE FROM dbo.AuditLog",
// "DELETE FROM [AuditLog]", "DELETE FROM [dbo].[AuditLog]"
// does NOT match: "DENY DELETE ON dbo.AuditLog" (DELETE is followed by ON)
return AuditLogMutationPattern.IsMatch(text);
}
// The DELETE branch tolerates an optional TOP (...) batch-size clause between
// DELETE and the (optional) FROM — e.g. "DELETE TOP (@batch) FROM dbo.AuditLog"
// (the M5.5 T3 batched purge shape). Without this the guard would silently miss a
// batched row DELETE against AuditLog, which is exactly the kind of mutation it
// must catch. The TOP sub-pattern is (?:TOP\s*\(.*?\)\s+)? — optional, lazy inside
// the parens so it never swallows past the matching ')'.
//
// The UPDATE branch similarly tolerates an optional TOP (...) clause between
// UPDATE and (optional schema.) AuditLog — e.g.
// "UPDATE TOP (@batch) dbo.AuditLog SET SourceNode = @sentinel …"
// (the M5.6 T5 batched backfill shape).
private static readonly Regex AuditLogMutationPattern = new(
@"\bUPDATE\s+(?:TOP\s*\(.*?\)\s+)?(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b" +
@"|\bDELETE\s+(?:TOP\s*\(.*?\)\s+)?(?:FROM\s+)?(?:\[?dbo\]?\.)?(?:\[?AuditLog\]?)\b",
RegexOptions.IgnoreCase | RegexOptions.Compiled);
/// <summary>
/// Returns <see langword="true"/> when <paramref name="line"/> carries the narrow
/// <see cref="AuditPurgeAllowedMarker"/> exemption. Sanctioned uses are:
/// <list type="bullet">
/// <item><description>M5.5 T3 — the per-channel maintenance-path batched DELETE.</description></item>
/// <item><description>M5.6 T5 — the SourceNode sentinel batched UPDATE.</description></item>
/// </list>
/// A flagged line that lacks the marker is NOT allow-listed. The mutation matcher
/// itself stays marker-blind; the allow-list is applied only by the file-scan test,
/// so the matcher's self-tests still observe the raw mutation.
/// </summary>
/// <param name="line">A single source line already known to contain a mutation.</param>
/// <returns><see langword="true"/> if the line is a sanctioned maintenance-path exemption.</returns>
internal static bool IsAllowListed(string line) =>
line.Contains(AuditPurgeAllowedMarker, StringComparison.Ordinal);
// ---------------------------------------------------------------------------
// Guard test: scan every *.cs file in ConfigurationDatabase (excluding
// Designer/Snapshot EF artefacts and the obj/ directory).
// ---------------------------------------------------------------------------
[Fact]
public void ConfigurationDatabase_ShouldNotContainAuditLogMutations()
{
var sourceDir = GetConfigurationDatabaseSourceDirectory();
// Enumerate all .cs files; exclude EF scaffolding and build output.
var csFiles = Directory.GetFiles(sourceDir, "*.cs", SearchOption.AllDirectories)
.Where(f => !f.Contains(Path.DirectorySeparatorChar + "obj" + Path.DirectorySeparatorChar))
.Where(f => !f.EndsWith(".Designer.cs", StringComparison.OrdinalIgnoreCase))
.Where(f => !f.EndsWith("ModelSnapshot.cs", StringComparison.OrdinalIgnoreCase))
.ToList();
Assert.True(csFiles.Count > 0,
$"Expected to find .cs files under {sourceDir} but found none — source directory location may be wrong.");
var violations = new List<string>();
foreach (var file in csFiles)
{
var content = File.ReadAllText(file);
// Scan line-by-line so violation messages cite the exact line number.
var lines = content.Split('\n');
for (var i = 0; i < lines.Length; i++)
{
if (ContainsAuditLogMutation(lines[i]) && !IsAllowListed(lines[i]))
{
var relativePath = Path.GetRelativePath(sourceDir, file);
violations.Add($"{relativePath}:{i + 1}: {lines[i].Trim()}");
}
}
}
Assert.True(violations.Count == 0,
"AuditLog append-only guard: found UPDATE/DELETE targeting dbo.AuditLog " +
"in ConfigurationDatabase source. AuditLog is APPEND-ONLY (retention uses " +
"partition-switch DDL, not row DELETE/UPDATE). Violation(s):\n" +
string.Join("\n", violations));
}
// ---------------------------------------------------------------------------
// Self-verifying matcher unit tests — prove the helper does what it claims.
// ---------------------------------------------------------------------------
[Fact]
public void ContainsAuditLogMutation_ReturnsFalse_ForCleanSource()
{
// The guard scan over real source PASSES (no violations) — this fact is
// already asserted by ConfigurationDatabase_ShouldNotContainAuditLogMutations.
// Here we verify the helper directly on a representative set of CLEAN lines
// that appear in the production source tree.
// INSERT is not a mutation (append-only operations are fine).
Assert.False(ContainsAuditLogMutation(
"INSERT INTO dbo.AuditLog (EventId, OccurredAtUtc) VALUES (@id, @ts);"));
// SELECT is not a mutation.
Assert.False(ContainsAuditLogMutation(
"SELECT COUNT(*) FROM dbo.AuditLog WHERE OccurredAtUtc >= @threshold;"));
// ALTER TABLE SWITCH is the retention purge — not a row-level mutation.
Assert.False(ContainsAuditLogMutation(
"ALTER TABLE dbo.AuditLog SWITCH PARTITION 3 TO dbo.AuditLog_Staging;"));
// DENY DDL from the role-grant migration — must not be flagged.
Assert.False(ContainsAuditLogMutation(
"DENY UPDATE ON dbo.AuditLog TO scadabridge_audit_writer;"));
Assert.False(ContainsAuditLogMutation(
"DENY DELETE ON dbo.AuditLog TO scadabridge_audit_writer;"));
// GRANT DDL — also must not be flagged.
Assert.False(ContainsAuditLogMutation(
"GRANT INSERT ON dbo.AuditLog TO scadabridge_audit_writer;"));
Assert.False(ContainsAuditLogMutation(
"GRANT SELECT ON dbo.AuditLog TO scadabridge_audit_writer;"));
// DELETE on a different table — AuditLog not on the same line.
Assert.False(ContainsAuditLogMutation(
"DELETE FROM dbo.Notifications WHERE Status = 'Delivered';"));
// DELETE on a different table even though AuditLog appears nearby in the
// same line but beyond the proximity window (padded to >120 chars between).
var longSeparator = new string(' ', 130);
Assert.False(ContainsAuditLogMutation(
$"DELETE FROM dbo.Notifications WHERE Id = @id;{longSeparator}-- see also AuditLog"));
// Comment-only mention of AuditLog with UPDATE elsewhere in a comment.
Assert.False(ContainsAuditLogMutation(
"// AuditLog is append-only; never issue an UPDATE against it."));
// TRUNCATE on the staging table (not AuditLog directly); staging name only.
Assert.False(ContainsAuditLogMutation(
"TRUNCATE TABLE dbo.AuditLog_Staging_abc123;"));
}
[Fact]
public void ContainsAuditLogMutation_ReturnsTrue_ForPlantedViolations()
{
// Planted positive cases — the guard MUST catch these.
// Classic UPDATE targeting AuditLog.
Assert.True(ContainsAuditLogMutation(
"UPDATE AuditLog SET Status = 'Corrected' WHERE EventId = @id;"));
// UPDATE with schema prefix.
Assert.True(ContainsAuditLogMutation(
"UPDATE dbo.AuditLog SET DetailsJson = @json WHERE EventId = @id;"));
// DELETE FROM AuditLog.
Assert.True(ContainsAuditLogMutation(
"DELETE FROM AuditLog WHERE OccurredAtUtc < @threshold;"));
// DELETE with schema prefix.
Assert.True(ContainsAuditLogMutation(
"DELETE FROM dbo.AuditLog WHERE Status = 'Parked';"));
// Mixed case (SQL is case-insensitive in practice).
Assert.True(ContainsAuditLogMutation(
"update dbo.AuditLog set Actor = 'system' where Actor is null;"));
// AuditLog mentioned earlier in the line (e.g. in a comment prefix), with a real
// UPDATE dbo.AuditLog DML following — the DML occurrence must still be caught.
Assert.True(ContainsAuditLogMutation(
"-- AuditLog: UPDATE dbo.AuditLog SET x = 1"));
// ---- Bracketed identifier forms (SSMS-generated SQL) ----
// UPDATE [dbo].[AuditLog] — bracketed schema and bracketed table.
Assert.True(ContainsAuditLogMutation(
"UPDATE [dbo].[AuditLog] SET DetailsJson = @json WHERE EventId = @id;"));
// UPDATE [AuditLog] — bracketed table, no schema prefix.
Assert.True(ContainsAuditLogMutation(
"UPDATE [AuditLog] SET Status = 'Corrected' WHERE EventId = @id;"));
// DELETE FROM [dbo].[AuditLog] — bracketed schema and bracketed table.
Assert.True(ContainsAuditLogMutation(
"DELETE FROM [dbo].[AuditLog] WHERE OccurredAtUtc < @threshold;"));
// DELETE FROM [AuditLog] — bracketed table, no schema prefix.
Assert.True(ContainsAuditLogMutation(
"DELETE FROM [AuditLog] WHERE OccurredAtUtc < @threshold;"));
// ---- Batched DELETE TOP (...) forms (M5.5 T3 purge shape) ----
// The matcher must catch a batched DELETE against AuditLog regardless of the
// marker — the allow-list (IsAllowListed) is what forgives the ONE sanctioned
// line, not the matcher.
Assert.True(ContainsAuditLogMutation(
"DELETE TOP (@batch) FROM dbo.AuditLog WHERE Category = @channel AND OccurredAtUtc < @threshold;"));
Assert.True(ContainsAuditLogMutation(
"DELETE TOP (5000) FROM dbo.AuditLog WHERE OccurredAtUtc < @threshold;"));
Assert.True(ContainsAuditLogMutation(
"DELETE TOP(100) FROM [dbo].[AuditLog] WHERE Status = 'Parked';"));
// ---- Batched UPDATE TOP (...) forms (M5.6 T5 backfill shape) ----
// The matcher must also catch a batched UPDATE against AuditLog, regardless of
// the marker — the allow-list is what forgives the ONE sanctioned backfill line.
Assert.True(ContainsAuditLogMutation(
"UPDATE TOP (@batch) dbo.AuditLog SET SourceNode = @sentinel WHERE SourceNode IS NULL AND OccurredAtUtc < @before;"));
Assert.True(ContainsAuditLogMutation(
"UPDATE TOP (500) dbo.AuditLog SET SourceNode = 'unknown' WHERE SourceNode IS NULL;"));
Assert.True(ContainsAuditLogMutation(
"UPDATE TOP(100) [dbo].[AuditLog] SET SourceNode = @s WHERE SourceNode IS NULL;"));
}
[Fact]
public void ContainsAuditLogMutation_ReturnsFalse_ForDenyGrantAndPartitionSwitchSamples()
{
// Extra explicit coverage for the four concrete exclusion patterns
// that appear in the real migration files.
// From 20260602174346_CollapseAuditLogToCanonical.cs and 20260520142214_AddAuditLogTable.cs:
Assert.False(ContainsAuditLogMutation(
"DENY UPDATE ON dbo.AuditLog TO scadabridge_audit_writer;"));
Assert.False(ContainsAuditLogMutation(
"DENY DELETE ON dbo.AuditLog TO scadabridge_audit_writer;"));
// From AuditLogRepository.cs SwitchOutPartitionAsync:
Assert.False(ContainsAuditLogMutation(
"ALTER TABLE dbo.AuditLog SWITCH PARTITION ' + CAST(@partitionNumber AS nvarchar(10)) + ' TO dbo.[' + @stagingName + '];"));
// Notifications DELETE (legitimate; AuditLog not present on the line):
Assert.False(ContainsAuditLogMutation(
"DELETE FROM dbo.Notifications WHERE CompletedAtUtc < @cutoff;"));
// Notifications DELETE using bracketed identifiers — AuditLog not present:
Assert.False(ContainsAuditLogMutation(
"DELETE FROM [dbo].[Notifications] WHERE CompletedAtUtc < @cutoff;"));
// SiteCalls DELETE (legitimate; AuditLog not present on the line):
Assert.False(ContainsAuditLogMutation(
"DELETE FROM dbo.SiteCalls WHERE TerminalAtUtc < @cutoff;"));
}
// ---------------------------------------------------------------------------
// Allow-list self-tests (M5.5 T3 / M5.6 T5) — prove the narrow exemption only
// forgives the marked maintenance-path DML and still blocks everything else.
// ---------------------------------------------------------------------------
[Fact]
public void AllowList_ForgivesMarkedPurgeDelete_ButMatcherStillTrips()
{
// The sanctioned per-channel purge DELETE — verbatim shape from
// AuditLogRepository.PurgeChannelOlderThanAsync, carrying the trailing marker.
const string sanctioned =
"\"DELETE TOP (@batch) FROM dbo.AuditLog WHERE Category = @channel AND OccurredAtUtc < @threshold;\"; " +
"// AUDIT-PURGE-ALLOWED: per-channel retention override (M5.5 T3), maintenance path";
// The raw matcher STILL sees the mutation (the matcher is marker-blind) ...
Assert.True(ContainsAuditLogMutation(sanctioned));
// ... but the allow-list forgives it because of the trailing marker.
Assert.True(IsAllowListed(sanctioned));
}
[Fact]
public void AllowList_ForgivesMarkedBackfillUpdate_ButMatcherStillTrips()
{
// The sanctioned SourceNode sentinel backfill UPDATE — verbatim shape from
// AuditLogRepository.BackfillSourceNodeAsync, carrying the trailing marker.
const string sanctioned =
"\"UPDATE TOP (@batch) dbo.AuditLog SET SourceNode = @sentinel WHERE SourceNode IS NULL AND OccurredAtUtc < @before;\"; " +
"// AUDIT-PURGE-ALLOWED: SourceNode sentinel backfill (M5.6 T5), maintenance path";
// The raw matcher STILL sees the mutation (the matcher is marker-blind) ...
Assert.True(ContainsAuditLogMutation(sanctioned));
// ... but the allow-list forgives it because of the trailing marker.
Assert.True(IsAllowListed(sanctioned));
}
[Fact]
public void AllowList_DoesNotForgive_UnmarkedStrayDelete()
{
// A stray DELETE against AuditLog WITHOUT the marker — exactly the kind of
// regression the guard exists to catch. It must be flagged (matcher) AND not
// forgiven (allow-list), so the file-scan test would record it as a violation.
const string stray = "DELETE FROM dbo.AuditLog WHERE Status = 'Parked';";
Assert.True(ContainsAuditLogMutation(stray));
Assert.False(IsAllowListed(stray),
"A DELETE against AuditLog without the AUDIT-PURGE-ALLOWED marker must NOT be allow-listed.");
}
[Fact]
public void AllowList_DoesNotForgive_UnmarkedStrayUpdate()
{
// A stray UPDATE against AuditLog WITHOUT the marker — must still trip the guard.
const string stray = "UPDATE dbo.AuditLog SET Status = 'Corrected' WHERE EventId = @id;";
Assert.True(ContainsAuditLogMutation(stray));
Assert.False(IsAllowListed(stray),
"An UPDATE against AuditLog without the AUDIT-PURGE-ALLOWED marker must NOT be allow-listed.");
}
[Fact]
public void AllowList_DoesNotForgive_BatchedUpdateWithoutMarker()
{
// A batched UPDATE TOP ... AuditLog without the marker — the TOP clause variant
// must also be caught and not forgiven without the explicit marker.
const string stray = "UPDATE TOP (500) dbo.AuditLog SET SourceNode = 'unknown' WHERE SourceNode IS NULL;";
Assert.True(ContainsAuditLogMutation(stray));
Assert.False(IsAllowListed(stray),
"A batched UPDATE against AuditLog without the AUDIT-PURGE-ALLOWED marker must NOT be allow-listed.");
}
}