feat: Phase 2 complete — 13 Phases of COBOL type classification and test benchmark

P0.6: gcov infrastructure P1: extract_structure output expansion (11 new feature fields) P2: Confusion group rule engine (8 pairs + contradiction + backtrack) P3: 4-factor confidence calculation + quality gate update P4: 33+2 COBOL program type test samples (22 files, 7 categories) P5: parametrized/ test data generation engine P6: japanese_data.py lookup tables P7-10: Type-specific test suites (~159 parametrized tests) P11: Full classification pipeline (classify_program) + orchestrator integration P12: Documentation (module-interfaces, test-plan v3.0, coverage-matrix) Architecture decisions: - classification_pipeline/ merged to hina/pipeline/ - parametrized/ as independent module - japanese_data.py as root-level file - hina/__all__ only exports classify_program() Co-Authored-By: Claude <noreply@anthropic.com>
2026-06-19 23:51:55 +08:00
parent 63b5284715
commit bc1d56d1a4
129 changed files with 19378 additions and 261 deletions
@@ -0,0 +1,49 @@
+"""Prepare test data for Playwright E2E tests."""
+from pathlib import Path
+
+FIXTURES = Path(__file__).parent / "fixtures"
+COBOL_GIT = Path(r"D:\cobol-java\jcl-cobol-git")
+
+
+def prepare():
+    results = []
+
+    # Check simple fixtures
+    for f in ["simple.cpy", "simple.cbl", "simple.yaml"]:
+        p = FIXTURES / f
+        results.append(("OK" if p.exists() else "MISSING", f"fixtures/{f}"))
+
+    # Create bad COBOL
+    bad = FIXTURES / "bad.cbl"
+    if not bad.exists():
+        src = (FIXTURES / "simple.cbl").read_text()
+        bad.write_text(src.replace("STOP RUN.", "THIS_IS_SYNTAX_ERROR"))
+        results.append(("CREATED", "fixtures/bad.cbl"))
+    else:
+        results.append(("OK", "fixtures/bad.cbl"))
+
+    # Check COBOL system data
+    for f in ["member.dat", "rate.dat", "transactions.dat"]:
+        p = COBOL_GIT / "data/input" / f
+        results.append(("OK" if p.exists() else "MISSING", f"jcl-cobol-git/data/input/{f}"))
+
+    for f in ["validated_tx.dat"]:
+        p = COBOL_GIT / "data/work" / f
+        results.append(("OK" if p.exists() else "MISSING", f"jcl-cobol-git/data/work/{f}"))
+
+    # Check COBOL programs
+    for f in ["CRDVAL.cbl", "CRDCALC.cbl"]:
+        p = COBOL_GIT / "cobol" / f
+        results.append(("OK" if p.exists() else "MISSING", f"jcl-cobol-git/cobol/{f}"))
+
+    # Check Java
+    for f in ["CrdVal.java", "CrdCalc.java"]:
+        p = COBOL_GIT / "java/src/main/java/coboljava" / f
+        results.append(("OK" if p.exists() else "MISSING", f"jcl-cobol-git/java/{f}"))
+
+    return results
+
+
+if __name__ == "__main__":
+    for status, name in prepare():
+        print(f"[{status:7s}] {name}")