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）。
208 lines
6.9 KiB
Python
208 lines
6.9 KiB
Python
"""结构化结论：解析 LLM 的 JSON 输出、交叉校验 handle、装配 findings。
|
||
|
||
设计要点：
|
||
- `review_frame` 的结论是**受约束的 JSON**（`{summary, issues[]}`），不再是自由文本，
|
||
因此不需要第二次 LLM 调用来「抽取」结构。
|
||
- 解析失败时降级为 `summary=原文, issues=[]`：信息不丢，只是不进批注链路。
|
||
- LLM 引用的 handle 若不在已采集证据中 → **保留问题、剥掉 handle**（verified=False），
|
||
既不会丢发现，也绝不会批注到不存在的实体。
|
||
"""
|
||
|
||
import json
|
||
import re
|
||
|
||
# evidence 中带 handle 的数据源（items[].handle）
|
||
_SOURCES = ("entities", "texts", "dimensions", "blocks", "polylines")
|
||
_SEVERITIES = ("high", "medium", "low")
|
||
_FENCE = re.compile(r"```(?:json)?\s*(.*?)```", re.S)
|
||
_MISS = object() # 解析失败的哨兵（区别于合法的 JSON null）
|
||
|
||
|
||
def _try_load(text):
|
||
try:
|
||
return json.loads(text)
|
||
except (json.JSONDecodeError, TypeError):
|
||
return _MISS
|
||
|
||
|
||
def _iter_items(envelope):
|
||
"""健壮迭代数据信封的 items。
|
||
|
||
`result_json` 在解析失败时会返回**原始字符串**，因此必须做 dict/list 守卫。
|
||
"""
|
||
if not isinstance(envelope, dict):
|
||
return []
|
||
items = envelope.get("items")
|
||
if not isinstance(items, list):
|
||
return []
|
||
return [i for i in items if isinstance(i, dict)]
|
||
|
||
|
||
def _outermost_json(text):
|
||
"""抓文本中第一个 `{`/`[` 起、括号配平的整段 JSON（正确处理字符串内的括号）。"""
|
||
start = None
|
||
for i, ch in enumerate(text):
|
||
if ch in "{[":
|
||
start, open_c = i, ch
|
||
break
|
||
if start is None:
|
||
return None
|
||
close_c = "}" if open_c == "{" else "]"
|
||
depth = 0
|
||
in_str = False
|
||
esc = False
|
||
for i in range(start, len(text)):
|
||
ch = text[i]
|
||
if in_str:
|
||
if esc:
|
||
esc = False
|
||
elif ch == "\\":
|
||
esc = True
|
||
elif ch == '"':
|
||
in_str = False
|
||
continue
|
||
if ch == '"':
|
||
in_str = True
|
||
elif ch == open_c:
|
||
depth += 1
|
||
elif ch == close_c:
|
||
depth -= 1
|
||
if depth == 0:
|
||
cand = text[start : i + 1]
|
||
return cand if _try_load(cand) is not _MISS else None
|
||
return None
|
||
|
||
|
||
def extract_json_block(text):
|
||
"""从可能含围栏/前后缀的文本中抽出可解析的 JSON 字符串；抽不到返回 None。"""
|
||
t = (text or "").strip()
|
||
if not t:
|
||
return None
|
||
if _try_load(t) is not _MISS: # 整体就是 JSON
|
||
return t
|
||
m = _FENCE.search(t)
|
||
if m:
|
||
inner = m.group(1).strip()
|
||
if _try_load(inner) is not _MISS:
|
||
return inner
|
||
t = inner
|
||
return _outermost_json(t)
|
||
|
||
|
||
def parse_conclusion(text, *, log=print):
|
||
"""把 LLM 结论解析为 {"summary": str, "issues": [dict], "raw": str}。
|
||
|
||
支持：`{summary, issues}` 对象、裸 issues 数组、围栏包裹、前后夹带解释文字。
|
||
解析不到结构化内容时降级为 summary=原文、issues=[]。
|
||
"""
|
||
block = extract_json_block(text)
|
||
if block is not None:
|
||
data = json.loads(block)
|
||
if isinstance(data, dict):
|
||
raw_issues = data.get("issues")
|
||
issues = (
|
||
[i for i in raw_issues if isinstance(i, dict)]
|
||
if isinstance(raw_issues, list)
|
||
else []
|
||
)
|
||
summary = data.get("summary")
|
||
return {
|
||
"summary": str(summary).strip() if summary is not None else "",
|
||
"issues": issues,
|
||
"raw": text,
|
||
}
|
||
if isinstance(data, list):
|
||
return {
|
||
"summary": "",
|
||
"issues": [i for i in data if isinstance(i, dict)],
|
||
"raw": text,
|
||
}
|
||
log("[结论解析] 非结构化输出，降级为纯文本 summary")
|
||
return {"summary": (text or "").strip(), "issues": [], "raw": text}
|
||
|
||
|
||
def collect_known_handles(evidence, extra_handles=None):
|
||
"""汇总证据里出现过的全部 handle（统一大写），外加 extra_handles。"""
|
||
known = set()
|
||
for key in _SOURCES:
|
||
for item in _iter_items((evidence or {}).get(key)):
|
||
handle = item.get("handle")
|
||
if handle:
|
||
known.add(str(handle).upper())
|
||
for handle in extra_handles or ():
|
||
if handle:
|
||
known.add(str(handle).upper())
|
||
return known
|
||
|
||
|
||
def normalize_issue(issue, *, frame_index, source, known_handles, validate_handles):
|
||
"""补 frame/source/verified 并做 handle 交叉校验，返回统一 issue 结构。"""
|
||
issue = issue if isinstance(issue, dict) else {}
|
||
handle = issue.get("handle")
|
||
handle = str(handle) if handle else None
|
||
verified = True
|
||
# 确定性问题的 handle 来自工具/数据本身，恒可信；只校验 LLM 的引用
|
||
if source != "deterministic" and handle and validate_handles:
|
||
if handle.upper() not in known_handles:
|
||
verified, handle = False, None
|
||
|
||
severity = issue.get("severity")
|
||
if severity not in _SEVERITIES:
|
||
severity = "low"
|
||
|
||
out = {
|
||
"frame": frame_index,
|
||
"category": str(issue.get("category") or "图面整体"),
|
||
"severity": severity,
|
||
"message": str(issue.get("message") or "").strip(),
|
||
"handle": handle,
|
||
"source": source,
|
||
"verified": verified,
|
||
}
|
||
handles = issue.get("handles")
|
||
if isinstance(handles, list) and handles:
|
||
out["handles"] = [str(h) for h in handles if h]
|
||
return out
|
||
|
||
|
||
def build_finding(evidence, conclusion, checks_issues=None, *,
|
||
validate_handles=True, log=print):
|
||
"""把确定性检查与 LLM 结论合并、校验后装配成一个 findings 元素。"""
|
||
evidence = evidence or {}
|
||
index = evidence.get("index")
|
||
checks = checks_issues or []
|
||
known = collect_known_handles(
|
||
evidence, extra_handles=[i.get("handle") for i in checks]
|
||
)
|
||
|
||
det = [
|
||
normalize_issue(i, frame_index=index, source="deterministic",
|
||
known_handles=known, validate_handles=validate_handles)
|
||
for i in checks
|
||
]
|
||
llm = [
|
||
normalize_issue(i, frame_index=index, source="llm",
|
||
known_handles=known, validate_handles=validate_handles)
|
||
for i in (conclusion or {}).get("issues", [])
|
||
]
|
||
issues = det + llm
|
||
return {
|
||
"frame": index,
|
||
"sheet": (evidence.get("frame") or {}).get("sheet_size"),
|
||
"summary": (conclusion or {}).get("summary", ""),
|
||
"issues": issues,
|
||
"counts": {
|
||
"deterministic": len(det),
|
||
"llm": len(llm),
|
||
"unverified": sum(1 for i in issues if not i["verified"]),
|
||
},
|
||
}
|
||
|
||
|
||
def flatten_issues(findings):
|
||
"""拍平所有图框的 issues，供 annotator / save_report 使用。"""
|
||
out = []
|
||
for finding in findings or []:
|
||
out.extend(finding.get("issues") or [])
|
||
return out
|