AiDOPWarehouse/doc/_compare_s1_cover_struct.py

# -*- coding: utf-8 -*-
"""对比 S1 与本次修改文档的封面细节、图片数量与标题结构差异。"""
from __future__ import annotations

import zipfile
from pathlib import Path

from docx import Document

BASE = Path(r"C:\Users\skygu\OneDrive\Projects\AIDOP\项目\项目管理\产互联项目管理\交付文档\Release产互联")
MINE = BASE / "待确认"

S1 = [
    "S1产销协同业务需求描述-V0.4.docx",
    "S1产销协同模块蓝图设计方案-V2.2.docx",
    "S1产销协同模块详细设计说明书-V1.2.docx",
    "S1产销协同模块用户操作手册-V1.2.docx",
]
MINE_DOCS = [
    "系统集成业务需求描述-V0.5.docx",
    "系统集成模块蓝图设计方案-V0.5.docx",
    "系统集成模块详细设计说明书-V0.5.docx",
    "运营改善业务需求描述-V0.5.docx",
    "运营改善模块蓝图设计方案-V0.5.docx",
    "运营改善模块详细设计说明书-V0.5.docx",
    "九宫格智慧运营看板模块详细设计说明书-V0.1.docx",
]


def img_count(path: Path) -> int:
    with zipfile.ZipFile(path) as z:
        return len([n for n in z.namelist() if n.startswith("word/media/")])


def headings_of(d: Document):
    out = []
    for p in d.paragraphs:
        s = p.style.name
        if s.startswith(("Heading", "标题")) and p.text.strip():
            out.append(f"[{s}] {p.text.strip()}")
    return out


def cover_info(d: Document, n=12):
    out = []
    for p in d.paragraphs[:n]:
        if p.text.strip():
            f = None
            for r in p.runs:
                if r.text.strip():
                    f = r.font
                    break
            sz = f.size.pt if f and f.size else None
            out.append(f"  ({f.name if f else '-'}/{sz}/b={f.bold if f else '-'}) {p.text.strip()}")
    return out


def dump(path: Path, show_heads: bool = True, head_limit: int = 100):
    d = Document(str(path))
    print(f"\n{'='*66}\n{path.name}  imgs={img_count(path)}  tables={len(d.tables)}")
    print("-- 封面段落 --")
    print("\n".join(cover_info(d)))
    if d.tables:
        t = d.tables[0]
        print(f"-- 首表 {len(t.rows)}行 --")
        for r in t.rows[:3]:
            print("  | " + " | ".join(c.text.strip().replace("\n", "/") for c in r.cells))
    if show_heads:
        hs = headings_of(d)
        print(f"-- 标题 {len(hs)} 个 --")
        print("\n".join("  " + h for h in hs[:head_limit]))


def main():
    print("########## S1 基线 ##########")
    for name in S1:
        dump(BASE / name, show_heads=False)
    print("\n\n########## 本次修改的文档 ##########")
    for name in MINE_DOCS:
        dump(MINE / name, show_heads=True)


if __name__ == "__main__":
    main()