207 lines
6.9 KiB
Python
207 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
|