Engine-agnostic morphological-parser conformance suite (v2: typologically-selected languages)

.github/workflows/conformance.yml

@@ -0,0 +1,63 @@
+name: Conformance
+
+on:
+  push:
+    branches:
+      - "**"
+    paths:
+      - "conformance/**"
+      - "src/SIL.Machine.Morphology.HermitCrab*/**"
+  pull_request:
+    paths:
+      - "conformance/**"
+      - "src/SIL.Machine.Morphology.HermitCrab*/**"
+
+jobs:
+  conformance:
+    name: Conformance suite
+    runs-on: ubuntu-22.04
+
+    steps:
+      - uses: actions/checkout@v6
+
+      - name: Setup .NET
+        uses: actions/setup-dotnet@v5
+        with:
+          dotnet-version: |
+            10.0.x
+
+      - name: Restore dependencies
+        run: dotnet restore src/SIL.Machine.Morphology.HermitCrab.Conformance/SIL.Machine.Morphology.HermitCrab.Conformance.csproj
+
+      # Gate (a): every fixture's declared parses/rejections must match what the C# oracle
+      # actually produces (self-check mode runs the reference engine in-process against every
+      # words.yaml, including budget_ms pathological fixtures).
+      - name: Run conformance self-check
+        run: >-
+          dotnet run --no-restore --project src/SIL.Machine.Morphology.HermitCrab.Conformance --
+          --fixtures conformance --include-pathological
+
+      # Gate (b): zero dead rules. --coverage-report also (re)writes fixtures.csv/coverage.csv/
+      # rules.csv, which the next step checks for staleness. This step's own exit code is the
+      # dead-rule gate (Program.cs returns 1 when CoverageReport.WriteCsvs finds any rule no word
+      # exercises) -- deliberately not grepped from stdout, which would be brittle. `if: always()`
+      # so this still runs (and reports its own true status) even if the self-check step above
+      # failed, keeping the two gates distinguishable in the log rather than one skipping the other.
+      - name: Run coverage report (dead-rule gate)
+        if: always()
+        run: >-
+          dotnet run --no-restore --project src/SIL.Machine.Morphology.HermitCrab.Conformance --
+          --fixtures conformance --coverage-report
+
+      # Gate (c): the checked-in fixtures.csv/coverage.csv/rules.csv must already reflect the
+      # fixtures as they stand -- generated so nobody needs to remember to refresh them, but that
+      # only holds if forgetting to refresh them is a CI failure. Runs after the coverage-report
+      # step (which just regenerated all three) and `if: always()` for the same reason as above:
+      # a dead rule and a stale index are two different failures and must not collapse into one.
+      - name: Verify generated coverage files are fresh
+        if: always()
+        run: |
+          if ! git diff --exit-code -- conformance/fixtures.csv conformance/coverage.csv conformance/rules.csv; then
+            echo "::error::conformance/fixtures.csv, coverage.csv, or rules.csv is stale relative to the fixtures (diff above). Run 'dotnet run --project src/SIL.Machine.Morphology.HermitCrab.Conformance -- --fixtures conformance --coverage-report' locally and commit the result."
+            exit 1
+          fi

Machine.sln

@@ -45,6 +45,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "SIL.Machine.Tokenization.Se
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "SIL.Machine.Tokenization.SentencePiece.Tests", "tests\SIL.Machine.Tokenization.SentencePiece.Tests\SIL.Machine.Tokenization.SentencePiece.Tests.csproj", "{AB5F75C1-64B7-4E0F-A4B5-B14EB16E6DDC}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "SIL.Machine.Morphology.HermitCrab.Conformance", "src\SIL.Machine.Morphology.HermitCrab.Conformance\SIL.Machine.Morphology.HermitCrab.Conformance.csproj", "{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -99,6 +101,10 @@ Global
 		{AB5F75C1-64B7-4E0F-A4B5-B14EB16E6DDC}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{AB5F75C1-64B7-4E0F-A4B5-B14EB16E6DDC}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{AB5F75C1-64B7-4E0F-A4B5-B14EB16E6DDC}.Release|Any CPU.Build.0 = Release|Any CPU
+		{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
@@ -116,6 +122,7 @@ Global
 		{0BBEED18-3CC1-4BA6-8E11-603A5D2DEDC9} = {31B4F5EB-E148-4A51-84B5-B90BB8F38AD3}
 		{09135223-6285-4268-BFA3-147BDB5B663B} = {31B4F5EB-E148-4A51-84B5-B90BB8F38AD3}
 		{AB5F75C1-64B7-4E0F-A4B5-B14EB16E6DDC} = {66246A1C-8D45-40FB-A660-C58577122CA7}
+		{8E40C2C5-F4C5-4A41-B78A-10A43FCF0CE3} = {31B4F5EB-E148-4A51-84B5-B90BB8F38AD3}
 	EndGlobalSection
 	GlobalSection(ExtensibilityGlobals) = postSolution
 		SolutionGuid = {9F18C25E-E140-43C3-B177-D562E1628370}