"""Tests for scanner parsers (CSV, MD, YAML, OpenAPI).""" from pathlib import Path import pytest from app.modules.scanner.infrastructure.parsers.csv_parser import CsvParser DESIGN_DIR = Path("/workspace/arch-design-agent-skill-dashboard/design") @pytest.fixture def csv_parser(): return CsvParser() # ── CSV Parser Tests ── class TestCsvParserCapabilities: def test_parse_capability_map(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "business-architecture" / "02-capability-map.csv") assert "capabilities" in result caps = result["capabilities"] assert len(caps) > 0 cap = caps[0] assert cap.capability_id.startswith("CAP-") assert cap.name # should have a name assert isinstance(cap.related_value_flows, list) def test_capability_related_value_flows_split(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "business-architecture" / "02-capability-map.csv") caps = result["capabilities"] # CAP-PROGRESS-DESIGN has "VF-02 VF-03" which should be split progress_cap = [c for c in caps if c.capability_id == "CAP-PROGRESS-DESIGN"] assert len(progress_cap) == 1 assert progress_cap[0].related_value_flows == ["VF-02", "VF-03"] class TestCsvParserModules: def test_parse_modules(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "application-architecture" / "02-modules.csv") assert "modules" in result mods = result["modules"] assert len(mods) > 0 mod = mods[0] assert mod.module_id.startswith("MOD-") assert isinstance(mod.depends_on, list) assert isinstance(mod.capabilities, list) def test_module_list_fields(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "application-architecture" / "02-modules.csv") mods = result["modules"] scanner = [m for m in mods if m.module_id == "MOD-SCANNER"] assert len(scanner) == 1 assert "MOD-DESIGN" in scanner[0].depends_on assert len(scanner[0].capabilities) > 0 class TestCsvParserTraceability: def test_parse_traceability(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "traceability.csv") assert "traceability_links" in result links = result["traceability_links"] assert len(links) > 0 link = links[0] assert link.trace_id.startswith("TR-") assert isinstance(link.entity_ids, list) assert isinstance(link.value_flow_ids, list) def test_traceability_space_split(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "traceability.csv") links = result["traceability_links"] # TR-04 has many entity_ids space-separated tr04 = [l for l in links if l.trace_id == "TR-04"] assert len(tr04) == 1 assert len(tr04[0].entity_ids) > 5 class TestCsvParserOtherTypes: def test_parse_value_flows(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "business-architecture" / "03-value-flows.csv") assert "value_flows" in result assert len(result["value_flows"]) > 0 def test_parse_user_journeys(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "business-architecture" / "04-user-journeys.csv") assert "user_journeys" in result assert len(result["user_journeys"]) > 0 def test_parse_integrations(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "application-architecture" / "03-integrations.csv") assert "integrations" in result assert len(result["integrations"]) > 0 def test_parse_external_systems(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "application-architecture" / "01-external-systems.csv") assert "external_systems" in result assert len(result["external_systems"]) > 0 def test_parse_entities(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "data-architecture" / "01-entities.csv") assert "entities" in result assert len(result["entities"]) > 0 def test_parse_data_flows(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "data-architecture" / "02-data-flows.csv") assert "data_flows" in result assert len(result["data_flows"]) > 0 def test_parse_data_security(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "data-architecture" / "03-data-security.csv") assert "data_securities" in result assert len(result["data_securities"]) > 0 def test_parse_tech_selections(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "technology-architecture" / "00-technology-selection.csv") assert "tech_selections" in result assert len(result["tech_selections"]) > 0 def test_parse_runtime_components(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "technology-architecture" / "01-runtime-components.csv") assert "runtime_components" in result assert len(result["runtime_components"]) > 0 def test_parse_environments(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "technology-architecture" / "02-environments.csv") assert "environments" in result assert len(result["environments"]) > 0 def test_parse_change_log(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "change-log.csv") assert "change_log_entries" in result assert len(result["change_log_entries"]) > 0 def test_parse_shared_terminology(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "_shared" / "01-shared-terminology.csv") assert "shared_terms" in result terms = result["shared_terms"] assert len(terms) > 0 # Check used_by_domains is a list (space-split) assert isinstance(terms[0].used_by_domains, list) assert len(terms[0].used_by_domains) > 0 def test_parse_ubiquitous_language(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "design" / "02-ubiquitous-language.csv") assert "ubiquitous_terms" in result assert len(result["ubiquitous_terms"]) > 0 def test_parse_scenarios(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "design" / "03-scenarios-and-flows.csv") assert "scenarios" in result assert len(result["scenarios"]) > 0 def test_parse_domain_modules(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "design" / "04-domain-modules.csv") assert "domain_modules" in result assert len(result["domain_modules"]) > 0 def test_parse_domain_entities(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "design" / "05-domain-entities.csv") assert "domain_entities" in result assert len(result["domain_entities"]) > 0 def test_parse_codebase_alignment(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "application-architecture" / "06-codebase-alignment.csv") assert "codebase_alignments" in result assert len(result["codebase_alignments"]) > 0 def test_parse_codebase_mapping(self, csv_parser): result = csv_parser.parse(DESIGN_DIR / "domains" / "design" / "07-codebase-mapping.csv") assert "codebase_alignments" in result assert len(result["codebase_alignments"]) > 0 class TestCsvParserUnknown: def test_unknown_csv_returns_empty(self, csv_parser, tmp_path): unknown = tmp_path / "unknown-file.csv" unknown.write_text("col1,col2\nval1,val2\n") result = csv_parser.parse(unknown) assert result == {} def test_nonexistent_file_returns_empty(self, csv_parser): result = csv_parser.parse(Path("/nonexistent/file.csv")) assert result == {} # ── MD Parser Tests ── from app.modules.scanner.infrastructure.parsers.md_parser import MdParser @pytest.fixture def md_parser(): return MdParser() class TestMdParserScopeAndGoals: def test_parse_scope_and_goals(self, md_parser): result = md_parser.parse(DESIGN_DIR / "business-architecture" / "01-scope-and-goals.md") assert "design_documents" in result docs = result["design_documents"] assert len(docs) == 1 assert docs[0].doc_id == "DOC-BA-001" assert docs[0].title == "范围与目标" assert isinstance(docs[0].owners, list) assert isinstance(docs[0].downstream, list) assert "scope_and_goals" in result sag = result["scope_and_goals"] assert len(sag) == 1 assert sag[0].doc_id == "DOC-BA-001" class TestMdParserDomainOverview: def test_parse_domain_overview(self, md_parser): result = md_parser.parse(DESIGN_DIR / "domains" / "design" / "01-domain-overview.md") # domain-overview.md has no frontmatter in this repo, so it produces no DesignDocument # If it has no frontmatter, it returns empty # Check: this file does not have frontmatter content = (DESIGN_DIR / "domains" / "design" / "01-domain-overview.md").read_text() if content.startswith("---"): assert "design_documents" in result assert "domains" in result assert result["domains"][0].domain_name == "design" else: # No frontmatter, so empty result and Domain produced from filename assert result == {} or "domains" in result class TestMdParserSystemContext: def test_parse_system_context(self, md_parser): result = md_parser.parse(DESIGN_DIR / "application-architecture" / "01-system-context.md") assert "design_documents" in result assert "system_context" in result sc = result["system_context"] assert len(sc) == 1 assert sc[0].doc_id == "DOC-AA-001" assert sc[0].title == "系统上下文" assert len(sc[0].content) > 0 class TestMdParserAdrTemplate: def test_adr_template_no_adr_entity(self, md_parser): result = md_parser.parse(DESIGN_DIR / "adr" / "ADR-000-template.md") # ADR-000-template has no frontmatter, so empty content = (DESIGN_DIR / "adr" / "ADR-000-template.md").read_text() if not content.startswith("---"): assert result == {} else: # If it has frontmatter, should NOT produce ADR (it's a template) assert "adrs" not in result class TestMdParserNoFrontmatter: def test_no_frontmatter_returns_empty(self, md_parser, tmp_path): md = tmp_path / "test.md" md.write_text("# Just a heading\n\nSome content.\n") result = md_parser.parse(md) assert result == {} def test_nonexistent_md_returns_empty(self, md_parser): result = md_parser.parse(Path("/nonexistent/file.md")) assert result == {} class TestMdParserSolutionLayering: def test_parse_solution_layering(self, md_parser): result = md_parser.parse(DESIGN_DIR / "application-architecture" / "02b-solution-layering.md") assert "design_documents" in result assert "solution_layer" in result sl = result["solution_layer"] assert len(sl) == 1 assert sl[0].doc_id == "DOC-AA-003" class TestMdParserModuleBoundary: def test_parse_module_boundary(self, md_parser): result = md_parser.parse(DESIGN_DIR / "application-architecture" / "07-module-boundary-rules.md") assert "design_documents" in result assert "module_boundary_rule" in result class TestMdParserRuntimeTopology: def test_parse_runtime_topology(self, md_parser): result = md_parser.parse(DESIGN_DIR / "technology-architecture" / "01-runtime-topology.md") assert "design_documents" in result assert "runtime_topology" in result class TestMdParserOperationalBaseline: def test_parse_operational_baseline(self, md_parser): result = md_parser.parse(DESIGN_DIR / "technology-architecture" / "03-operational-baseline.md") assert "design_documents" in result assert "operational_baseline" in result class TestMdParserReleasePlan: def test_parse_release_plan(self, md_parser): result = md_parser.parse(DESIGN_DIR / "technology-architecture" / "04-release-and-rollback.md") assert "design_documents" in result assert "release_plan" in result # ── YAML Parser Tests ── from app.modules.scanner.infrastructure.parsers.yaml_parser import YamlParser @pytest.fixture def yaml_parser(): return YamlParser() class TestYamlParser: def test_load_openapi_yaml(self, yaml_parser): data = yaml_parser.load( DESIGN_DIR / "application-architecture" / "04-api-contracts.openapi.yaml" ) assert data is not None assert "openapi" in data assert "paths" in data def test_load_nonexistent_returns_none(self, yaml_parser): result = yaml_parser.load(Path("/nonexistent/file.yaml")) assert result is None def test_load_plain_yaml(self, yaml_parser, tmp_path): f = tmp_path / "test.yaml" f.write_text("key: value\nlist:\n - one\n - two\n") data = yaml_parser.load(f) assert data == {"key": "value", "list": ["one", "two"]} # ── OpenAPI Parser Tests ── from app.modules.scanner.infrastructure.parsers.openapi_parser import OpenapiParser @pytest.fixture def openapi_parser(): return OpenapiParser() class TestOpenapiParser: def test_parse_api_contracts(self, openapi_parser): result = openapi_parser.parse( DESIGN_DIR / "application-architecture" / "04-api-contracts.openapi.yaml" ) assert "api_contracts" in result contracts = result["api_contracts"] assert len(contracts) > 0 # Check that contracts have correct fields contract = contracts[0] assert contract.path.startswith("/") assert contract.method in ("GET", "POST", "PUT", "DELETE", "PATCH", "OPTIONS", "HEAD") assert contract.doc_id.startswith("API-") def test_parse_health_endpoint(self, openapi_parser): result = openapi_parser.parse( DESIGN_DIR / "application-architecture" / "04-api-contracts.openapi.yaml" ) contracts = result["api_contracts"] health = [c for c in contracts if c.path == "/api/health"] assert len(health) == 1 assert health[0].method == "GET" assert health[0].operation_id == "healthCheck" def test_parse_nonexistent_returns_empty(self, openapi_parser): result = openapi_parser.parse(Path("/nonexistent/file.yaml")) assert result == {} def test_parse_non_openapi_yaml_returns_empty(self, openapi_parser, tmp_path): f = tmp_path / "not-openapi.yaml" f.write_text("key: value\n") result = openapi_parser.parse(f) assert result == {}