602703c47c
- evals/gold：1,887 个标注单元（AI 标注、逐条裁定，未经人工复核），规范见 GUIDELINES.md - prepare / run_all / score / gold：导出文字层、批量抽取、打分、标注定位 - docs/architecture/extract-eval.md：修复前后的结果（三项目标全部达标）和剩余问题 - decisions.md 记 M1（只用 Flash）和 Q1–Q4；架构 §13 SK13；AGENTS.md 进度 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
59 lines
2.2 KiB
Python
59 lines
2.2 KiB
Python
"""准备标注集评测的输入：S01–S10 转成规范化 PDF，导出带句子编号的全文（给人工标注用）。
|
||
|
||
用法（在 server/ 下）：
|
||
../.venv/bin/python ../evals/prepare.py [S01 S02 ...]
|
||
输出 evals/out/docs/<ID>/：normalized.pdf、sentences.txt（每行 `[p12s3] 句子`，带格式标记和〔上级：…〕）。
|
||
规范化 PDF 生成一次后复用，抽取评测（run_extract.py）也用它作输入，标注和评测看到的是同一份文字层。
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import asyncio
|
||
import pathlib
|
||
import sys
|
||
|
||
from bid_doctor.checklist import extract
|
||
from bid_doctor.document import formats
|
||
from bid_doctor.document.pipeline import convert, structure, text_layer
|
||
|
||
ROOT = pathlib.Path(__file__).resolve().parent
|
||
SAMPLES = ROOT.parent / "samples" / "tenders"
|
||
OUT = ROOT / "out" / "docs"
|
||
|
||
|
||
async def prepare(doc_id: str) -> None:
|
||
out = OUT / doc_id
|
||
out.mkdir(parents=True, exist_ok=True)
|
||
pdf_path = out / "normalized.pdf"
|
||
if not pdf_path.exists():
|
||
src = next(p for p in (SAMPLES / doc_id).iterdir() if p.suffix in (".doc", ".docx", ".pdf"))
|
||
raw = src.read_bytes()
|
||
fmt = formats.detect(raw, src.name).format
|
||
pdf_path.write_bytes(raw if fmt == "pdf" else await convert.to_pdf(raw, fmt))
|
||
pages = text_layer.extract("D", pdf_path.read_bytes())
|
||
body = text_layer.body_sentences(pages)
|
||
parents = structure.parents(body)
|
||
notes = extract.marking_notes(body)
|
||
lines = [f"# {doc_id}：{len(pages)} 页，正文句子 {len(body)}", "## 标注规则说明（规则识别）"]
|
||
lines += [f"- [p{n.sentence.page_no}s{n.sentence.seq}] {n.sentence.text}" for n in notes] or ["（无）"]
|
||
page = 0
|
||
for s in body:
|
||
if s.page_no != page:
|
||
page = s.page_no
|
||
lines.append(f"\n=== 第 {page} 页")
|
||
line = f"[p{s.page_no}s{s.seq}] {s.marked}"
|
||
if p := parents.get(s.key):
|
||
line += f"〔上级：{p.text[:40]}〕"
|
||
lines.append(line)
|
||
(out / "sentences.txt").write_text("\n".join(lines) + "\n")
|
||
print(doc_id, len(pages), "页", len(body), "句")
|
||
|
||
|
||
async def main() -> None:
|
||
ids = sys.argv[1:] or [f"S{i:02d}" for i in range(1, 11)]
|
||
for doc_id in ids:
|
||
await prepare(doc_id)
|
||
|
||
|
||
asyncio.run(main())
|