AiDOPWarehouse/doc/_bid_check_final.py

# -*- coding: utf-8 -*-
"""合并成册后的自检：目录条目、页码连续性、并入完整性、占位项清单。"""
import io
import os
import re
import sys

import fitz

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")

HERE = os.path.dirname(os.path.abspath(__file__))
PDF = os.path.join(HERE, "_bid_preview",
                   "响应文件（完整版）-2026年河南产互联制造业数据智能运营平台研发项目.pdf")

d = fitz.open(PDF)
pages = [d[i].get_text() for i in range(d.page_count)]
print(f"总页数 {d.page_count}")

# ---------------- 目录：条目、层级、页码
toc_pages = [i for i, t in enumerate(pages[:8]) if "目    录" in t or "目 录" in t]
toc_txt = "".join(pages[i] for i in range(toc_pages[0], toc_pages[0] + 4)) \
    if toc_pages else ""
ENTRY = re.compile(r"^(.*?)\s\.{3,}\s*(\d+)\s*$", re.M)
entries = ENTRY.findall(toc_txt)
print(f"目录页 P{toc_pages[0] + 1} 起，抓到条目 {len(entries)} 条")
bad = [e for e in entries if re.search(r"(四、\s*四、|（三）\s*（三）)", e[0])]
print("  重复编号：", bad or "无")
nums = [int(n) for _, n in entries]
print("  页码是否单调不减：", all(b >= a for a, b in zip(nums, nums[1:])))
print("  目录首条 / 末条：", entries[0][0].strip()[:30] if entries else "-",
      "/", entries[-1][0].strip()[:30] if entries else "-")

# ---------------- 页脚页码连续性：每页末尾的独立数字
foot = []
for i, t in enumerate(pages):
    m = re.match(r"\s*(\d+)\s", t)          # 页码在页面文本流最前（页脚被前置）
    foot.append(int(m.group(1)) if m else None)
miss = [i + 1 for i, v in enumerate(foot) if v is None]
jump = [(i + 1, foot[i], foot[i + 1]) for i in range(len(foot) - 1)
        if foot[i] is not None and foot[i + 1] is not None
        and foot[i + 1] != foot[i] + 1]
print(f"\n页脚页码：缺失 {len(miss)} 页 {miss[:8]}　断号 {len(jump)} 处 {jump[:6]}")

# ---------------- 并入完整性：各部分标志性文字
MARKS = {
    "增值税专票承诺书": "关于能够提供增值税专用发票的承诺书",
    "不组联合体承诺书": "关于不组成联合体及中选后不转包的承诺书",
    "资格及信用承诺书": "关于资格条件及信用状况的承诺书",
    "软著一览表": "计算机软件著作权登记证书一览表",
    "项目团队表": "项目团队岗位职责与人员配备表",
    "4 项目需求理解": "4、项目需求理解及综合分析",
    "5 系统功能展示": "5、系统功能展示",
    "6 系统建设方案": "6、系统建设方案",
    "7 智能诊断": "7、智能诊断与分析方案",
    "8 UAT 测试": "8、UAT 测试与质量保障",
    "9 质量与工期": "9、质量与工期保障",
    "10 应急支撑": "10、应急支撑方案",
    "11 售后服务": "11、售后服务方案",
    "12 项目培训": "12、项目培训方案",
}
print("\n并入完整性：")
for label, key in MARKS.items():
    hit = next((i + 1 for i, t in enumerate(pages)
                if key.replace(" ", "") in t.replace(" ", "").replace("\n", "")),
               None)
    print(f"  {'○' if hit else '×'} {label:<18} {('P' + str(hit)) if hit else '未找到'}")

# ---------------- 残留占位与标记
print("\n残留检查：")
for tok, name in (("@@MERGE", "合并标记"), ("【待填", "待填占位"),
                  ("【待补", "待补占位")):
    hits = [i + 1 for i, t in enumerate(pages) if tok in t]
    print(f"  {name}：{len(hits)} 页 {hits[:12]}")