gjm
f6d61f8d07
- checks.py：确定性检查（find_zero_length / find_duplicate_entities 传 window + 纯 Python 派生空文字、未闭合多段线）。问题带 source=deterministic，handle 来自 工具/数据本身，不依赖 LLM 回忆 - findings.py：解析 LLM 的 JSON 结论 + handle 交叉校验（引用未知 handle 时保留问题、 剥掉 handle、verified=False）+ findings 装配 - config.py：新增 DETERMINISTIC_CHECKS / VALIDATE_HANDLES / CHECK_UNCLOSED_POLYLINES 开关与 ZERO_LENGTH_TOLERANCE / DUP_TOLERANCE / DUP_GROUP_LIMIT 实机验证：find_zero_length / find_duplicate_entities 的 window 参数在基座上生效 （schema 未声明，C++ 侧 parseCommonQuery 实际支持）。
242 lines
9.2 KiB
Python
242 lines
9.2 KiB
Python
"""`dwg_review.findings` 单元测试：结构化解析 + handle 交叉校验 + 装配。"""
|
|
|
|
from dwg_review.findings import (
|
|
build_finding,
|
|
collect_known_handles,
|
|
extract_json_block,
|
|
flatten_issues,
|
|
normalize_issue,
|
|
parse_conclusion,
|
|
)
|
|
from tests.fakes import make_evidence
|
|
|
|
QUIET = lambda *a: None # noqa: E731
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# extract_json_block
|
|
# ---------------------------------------------------------------------------
|
|
def test_extract_bare_object():
|
|
assert extract_json_block('{"a": 1}') == '{"a": 1}'
|
|
|
|
|
|
def test_extract_bare_array():
|
|
assert extract_json_block('[{"a": 1}]') == '[{"a": 1}]'
|
|
|
|
|
|
def test_extract_fenced_object():
|
|
assert extract_json_block('```json\n{"a": 1}\n```') == '{"a": 1}'
|
|
|
|
|
|
def test_extract_single_line_fence():
|
|
# 旧 extract_issues 的已知瑕疵（单行围栏剥离失败）在此不再复现
|
|
assert extract_json_block('```json{"a": 1}```') == '{"a": 1}'
|
|
|
|
|
|
def test_extract_from_surrounding_prose():
|
|
text = '好的，结论如下：\n{"summary": "ok", "issues": []}\n以上。'
|
|
assert extract_json_block(text) == '{"summary": "ok", "issues": []}'
|
|
|
|
|
|
def test_extract_handles_braces_inside_strings():
|
|
text = 'prefix {"message": "包含 } 和 { 的文字", "n": 1} suffix'
|
|
assert extract_json_block(text) == '{"message": "包含 } 和 { 的文字", "n": 1}'
|
|
|
|
|
|
def test_extract_returns_none_for_garbage():
|
|
assert extract_json_block("未发现明显问题") is None
|
|
assert extract_json_block("") is None
|
|
assert extract_json_block(None) is None
|
|
assert extract_json_block("{ not json") is None
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# parse_conclusion
|
|
# ---------------------------------------------------------------------------
|
|
def test_parse_object_with_issues():
|
|
text = '{"summary": "整体尚可", "issues": [{"category": "几何", "message": "x"}]}'
|
|
out = parse_conclusion(text, log=QUIET)
|
|
assert out["summary"] == "整体尚可"
|
|
assert out["issues"] == [{"category": "几何", "message": "x"}]
|
|
assert out["raw"] == text
|
|
|
|
|
|
def test_parse_object_without_issues_key():
|
|
out = parse_conclusion('{"summary": "无问题"}', log=QUIET)
|
|
assert out["summary"] == "无问题"
|
|
assert out["issues"] == []
|
|
|
|
|
|
def test_parse_bare_array_becomes_issues():
|
|
out = parse_conclusion('[{"message": "a"}, {"message": "b"}]', log=QUIET)
|
|
assert out["summary"] == ""
|
|
assert [i["message"] for i in out["issues"]] == ["a", "b"]
|
|
|
|
|
|
def test_parse_filters_non_dict_issues():
|
|
out = parse_conclusion('{"summary": "s", "issues": [{"message": "ok"}, "junk", 3]}', log=QUIET)
|
|
assert out["issues"] == [{"message": "ok"}]
|
|
|
|
|
|
def test_parse_degrades_prose_to_summary():
|
|
logs = []
|
|
out = parse_conclusion("未发现明显问题。", log=logs.append)
|
|
assert out["summary"] == "未发现明显问题。"
|
|
assert out["issues"] == []
|
|
assert any("降级" in line for line in logs)
|
|
|
|
|
|
def test_parse_degrades_empty_text():
|
|
out = parse_conclusion("", log=QUIET)
|
|
assert out["summary"] == "" and out["issues"] == []
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# collect_known_handles
|
|
# ---------------------------------------------------------------------------
|
|
def test_collect_known_handles_from_all_sources():
|
|
ev = make_evidence(
|
|
entities={"total": 1, "items": [{"handle": "AA"}]},
|
|
texts={"total": 1, "items": [{"handle": "BB"}]},
|
|
dimensions={"total": 1, "items": [{"handle": "CC"}]},
|
|
blocks={"total": 1, "items": [{"handle": "DD"}]},
|
|
polylines={"total": 1, "items": [{"handle": "EE"}]},
|
|
)
|
|
assert collect_known_handles(ev) == {"AA", "BB", "CC", "DD", "EE"}
|
|
|
|
|
|
def test_collect_known_handles_uppercases():
|
|
ev = make_evidence(entities={"items": [{"handle": "2f3a"}]})
|
|
assert collect_known_handles(ev) == {"2F3A"}
|
|
|
|
|
|
def test_collect_known_handles_includes_extra():
|
|
ev = make_evidence()
|
|
assert collect_known_handles(ev, extra_handles=["Ff", None, ""]) == {"FF"}
|
|
|
|
|
|
def test_collect_known_handles_tolerates_non_dict_envelope():
|
|
# result_json 解析失败会返回原始字符串
|
|
assert collect_known_handles({"entities": "oops", "texts": None}) == set()
|
|
|
|
|
|
def test_collect_known_handles_skips_items_without_handle():
|
|
ev = make_evidence(entities={"items": [{"type": "LINE"}, {"handle": ""}]})
|
|
assert collect_known_handles(ev) == set()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# normalize_issue
|
|
# ---------------------------------------------------------------------------
|
|
def test_normalize_llm_issue_with_known_handle_is_verified():
|
|
out = normalize_issue(
|
|
{"category": "文字", "severity": "high", "message": "重叠", "handle": "2f3a"},
|
|
frame_index=1, source="llm", known_handles={"2F3A"}, validate_handles=True,
|
|
)
|
|
assert out["handle"] == "2f3a" # 保留原样（大小写归一仅用于比对）
|
|
assert out["verified"] is True
|
|
assert out["source"] == "llm"
|
|
assert out["frame"] == 1
|
|
|
|
|
|
def test_normalize_llm_issue_with_unknown_handle_strips_it():
|
|
out = normalize_issue(
|
|
{"message": "疑似问题", "handle": "DEAD"},
|
|
frame_index=2, source="llm", known_handles={"2F3A"}, validate_handles=True,
|
|
)
|
|
assert out["handle"] is None
|
|
assert out["verified"] is False
|
|
assert out["message"] == "疑似问题" # 问题保留
|
|
|
|
|
|
def test_normalize_deterministic_never_stripped():
|
|
out = normalize_issue(
|
|
{"message": "零长度", "handle": "ZZZZ"},
|
|
frame_index=1, source="deterministic", known_handles=set(), validate_handles=True,
|
|
)
|
|
assert out["handle"] == "ZZZZ" and out["verified"] is True
|
|
|
|
|
|
def test_normalize_validation_disabled_keeps_handle():
|
|
out = normalize_issue(
|
|
{"message": "x", "handle": "DEAD"},
|
|
frame_index=1, source="llm", known_handles=set(), validate_handles=False,
|
|
)
|
|
assert out["handle"] == "DEAD" and out["verified"] is True
|
|
|
|
|
|
def test_normalize_llm_issue_without_handle_is_verified():
|
|
out = normalize_issue({"message": "整体偏空"}, frame_index=1, source="llm",
|
|
known_handles=set(), validate_handles=True)
|
|
assert out["handle"] is None and out["verified"] is True
|
|
|
|
|
|
def test_normalize_falls_back_on_invalid_severity_and_category():
|
|
out = normalize_issue({"severity": "critical", "message": "x"},
|
|
frame_index=1, source="llm", known_handles=set(),
|
|
validate_handles=True)
|
|
assert out["severity"] == "low"
|
|
assert out["category"] == "图面整体"
|
|
|
|
|
|
def test_normalize_preserves_handles_list():
|
|
out = normalize_issue({"message": "重复组", "handle": "A", "handles": ["A", "B"]},
|
|
frame_index=1, source="deterministic", known_handles=set(),
|
|
validate_handles=True)
|
|
assert out["handles"] == ["A", "B"]
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# build_finding
|
|
# ---------------------------------------------------------------------------
|
|
def test_build_finding_merges_deterministic_then_llm():
|
|
ev = make_evidence(index=3, entities={"items": [{"handle": "AA"}]})
|
|
checks = [{"category": "几何", "severity": "medium", "message": "零长度", "handle": "ZZ"}]
|
|
conclusion = {
|
|
"summary": "有 2 处问题",
|
|
"issues": [
|
|
{"category": "文字", "severity": "high", "message": "重叠", "handle": "AA"},
|
|
{"category": "几何", "severity": "low", "message": "臆测", "handle": "NOPE"},
|
|
],
|
|
}
|
|
finding = build_finding(ev, conclusion, checks, validate_handles=True, log=QUIET)
|
|
assert finding["frame"] == 3
|
|
assert finding["sheet"] == "A1"
|
|
assert finding["summary"] == "有 2 处问题"
|
|
assert [i["source"] for i in finding["issues"]] == ["deterministic", "llm", "llm"]
|
|
assert finding["counts"] == {"deterministic": 1, "llm": 2, "unverified": 1}
|
|
# 被剥掉 handle 的那条仍在
|
|
assert finding["issues"][2]["verified"] is False
|
|
|
|
|
|
def test_build_finding_deterministic_handle_counts_as_known():
|
|
# 确定性检查命中的 handle 应进入已知集合，供同框 LLM 引用
|
|
ev = make_evidence(entities={"items": []})
|
|
checks = [{"message": "零长度", "handle": "ZZ"}]
|
|
conclusion = {"summary": "", "issues": [{"message": "同一条", "handle": "zz"}]}
|
|
finding = build_finding(ev, conclusion, checks, validate_handles=True, log=QUIET)
|
|
assert finding["issues"][1]["verified"] is True
|
|
|
|
|
|
def test_build_finding_without_checks_or_conclusion():
|
|
finding = build_finding(make_evidence(), {}, None, log=QUIET)
|
|
assert finding["issues"] == []
|
|
assert finding["counts"] == {"deterministic": 0, "llm": 0, "unverified": 0}
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# flatten_issues
|
|
# ---------------------------------------------------------------------------
|
|
def test_flatten_issues_concatenates():
|
|
findings = [
|
|
{"issues": [{"message": "a"}, {"message": "b"}]},
|
|
{"issues": [{"message": "c"}]},
|
|
{},
|
|
]
|
|
assert [i["message"] for i in flatten_issues(findings)] == ["a", "b", "c"]
|
|
|
|
|
|
def test_flatten_issues_empty():
|
|
assert flatten_issues([]) == []
|
|
assert flatten_issues(None) == []
|