andreferraro
6a45368cb0
- Added scripts/extract_article_contents.py for batch scraping with stealth Foxcape and triple extraction (Trafilatura, Newspaper4k, Readability) - Created unit, integration, and E2E test suite in tests/test_extract_article_contents.py (90/90 passing) - Updated specs/003-article-content-extractor and README.md with usage documentation and CLI contracts - Passed ruff linting/formatting and mypy type checking cleanly
1 line
7.0 KiB
JSON
1 line
7.0 KiB
JSON
{"nodes": [{"id": "$graphify-root$_tests_test_benchmark_24_py", "label": "test_benchmark_24.py", "file_type": "code", "source_file": "tests/test_benchmark_24.py", "source_location": "L1"}, {"id": "fixture", "label": "fixture", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "$graphify-root$/tests/test_benchmark_24.py"}, {"id": "$graphify-root$_tests_test_benchmark_24_classifier", "label": "classifier()", "file_type": "code", "source_file": "tests/test_benchmark_24.py", "source_location": "L23", "_callable": true}, {"id": "parametrize", "label": "parametrize", "file_type": "code", "source_file": "", "source_location": "", "origin_file": "$graphify-root$/tests/test_benchmark_24.py"}, {"id": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "label": "test_benchmark_case()", "file_type": "code", "source_file": "tests/test_benchmark_24.py", "source_location": "L28", "_callable": true}, {"id": "$graphify-root$_tests_test_benchmark_24_rationale_1", "label": "Controlled 24-case benchmark suite for Multilingual NLP Entity Inherence\u2026", "file_type": "rationale", "source_file": "tests/test_benchmark_24.py", "source_location": "L1"}], "edges": [{"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "json", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L7", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "pathlib", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L8", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "pytest", "relation": "imports", "context": "import", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L10", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "src_classifier", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L12", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "src_models", "relation": "imports_from", "context": "import", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L13", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_classifier", "target": "fixture", "relation": "references", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L22", "weight": 1.0, "context": "decorator"}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "$graphify-root$_tests_test_benchmark_24_classifier", "relation": "contains", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L23", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "target": "parametrize", "relation": "references", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L27", "weight": 1.0, "context": "decorator"}, {"source": "$graphify-root$_tests_test_benchmark_24_py", "target": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "relation": "contains", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L28", "weight": 1.0}, {"source": "$graphify-root$_tests_test_benchmark_24_rationale_1", "target": "$graphify-root$_tests_test_benchmark_24_py", "relation": "rationale_for", "confidence": "EXTRACTED", "source_file": "tests/test_benchmark_24.py", "source_location": "L1", "weight": 1.0}], "raw_calls": [{"caller_nid": "$graphify-root$_tests_test_benchmark_24_classifier", "callee": "InherenceClassifier", "is_member_call": false, "source_file": "tests/test_benchmark_24.py", "source_location": "L24", "receiver": null}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "is_file", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L34", "receiver": "ecp_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "is_file", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L35", "receiver": "content_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "is_file", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L36", "receiver": "expected_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "from_json_str", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L38", "receiver": "ECPSnapshot"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "read_text", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L38", "receiver": "ecp_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "read_text", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L39", "receiver": "content_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "loads", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L40", "receiver": "json"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "read_text", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L40", "receiver": "expected_file"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "classify", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L42", "receiver": "classifier"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "upper", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L46", "receiver": "lang"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "upper", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L51", "receiver": "lang"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "upper", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L56", "receiver": "lang"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "get", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L60", "receiver": "expected"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "upper", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L62", "receiver": "lang"}, {"caller_nid": "$graphify-root$_tests_test_benchmark_24_test_benchmark_case", "callee": "upper", "is_member_call": true, "source_file": "tests/test_benchmark_24.py", "source_location": "L68", "receiver": "lang"}]} |