AiDOPWarehouse/doc/_gen_acceptance_plan_docx.py

# -*- coding: utf-8 -*-
"""从《项目交付验收方案.md》生成 Word 文档。"""

from __future__ import annotations

import re
from pathlib import Path

from docx import Document
from docx.enum.text import WD_ALIGN_PARAGRAPH, WD_LINE_SPACING
from docx.oxml.ns import qn
from docx.shared import Cm, Pt

BASE = Path(__file__).resolve().parent
SRC = BASE / "项目交付验收方案.md"
OUT = BASE / "项目交付验收方案.docx"


def set_run_font(run, name_cn="宋体", name_en="Times New Roman", size=12, bold=False):
    run.font.name = name_en
    run._element.rPr.rFonts.set(qn("w:eastAsia"), name_cn)
    run.font.size = Pt(size)
    run.bold = bold


def style_normal(doc: Document):
    style = doc.styles["Normal"]
    style.font.name = "Times New Roman"
    style.font.size = Pt(12)
    style._element.rPr.rFonts.set(qn("w:eastAsia"), "宋体")
    pf = style.paragraph_format
    pf.line_spacing_rule = WD_LINE_SPACING.ONE_POINT_FIVE
    pf.space_after = Pt(6)


def add_title(doc: Document, text: str):
    p = doc.add_paragraph()
    p.alignment = WD_ALIGN_PARAGRAPH.CENTER
    p.paragraph_format.space_after = Pt(12)
    run = p.add_run(text)
    set_run_font(run, "黑体", "SimHei", 18, True)


def add_h1(doc: Document, text: str):
    p = doc.add_paragraph()
    p.paragraph_format.space_before = Pt(14)
    p.paragraph_format.space_after = Pt(8)
    run = p.add_run(text)
    set_run_font(run, "黑体", "SimHei", 14, True)


def add_h2(doc: Document, text: str):
    p = doc.add_paragraph()
    p.paragraph_format.space_before = Pt(10)
    p.paragraph_format.space_after = Pt(6)
    run = p.add_run(text)
    set_run_font(run, "黑体", "SimHei", 12, True)


def add_rich_paragraph(doc: Document, text: str, *, indent=True, left_indent_cm=0.0):
    p = doc.add_paragraph()
    if left_indent_cm:
        p.paragraph_format.left_indent = Cm(left_indent_cm)
        p.paragraph_format.first_line_indent = Pt(0)
    else:
        p.paragraph_format.first_line_indent = Pt(24) if indent else Pt(0)
    p.paragraph_format.space_after = Pt(6)
    parts = re.split(r"(\*\*.*?\*\*|`[^`]+`)", text)
    for part in parts:
        if not part:
            continue
        if part.startswith("**") and part.endswith("**"):
            run = p.add_run(part[2:-2])
            set_run_font(run, "宋体", "Times New Roman", 12, True)
        elif part.startswith("`") and part.endswith("`"):
            run = p.add_run(part[1:-1])
            set_run_font(run, "宋体", "Consolas", 10.5)
        else:
            run = p.add_run(part)
            set_run_font(run, "宋体", "Times New Roman", 12)


def add_table(doc: Document, headers: list[str], rows: list[list[str]], font_size=9.0):
    table = doc.add_table(rows=1 + len(rows), cols=len(headers))
    table.style = "Table Grid"
    table.autofit = True

    for i, h in enumerate(headers):
        cell = table.rows[0].cells[i]
        cell.text = ""
        p = cell.paragraphs[0]
        p.alignment = WD_ALIGN_PARAGRAPH.CENTER
        run = p.add_run(h)
        set_run_font(run, "宋体", "Times New Roman", font_size, True)
        tcPr = cell._tc.get_or_add_tcPr()
        shd = tcPr.makeelement(
            qn("w:shd"),
            {
                qn("w:val"): "clear",
                qn("w:color"): "auto",
                qn("w:fill"): "D9E2F3",
            },
        )
        tcPr.append(shd)

    for r_idx, row in enumerate(rows):
        for c_idx, val in enumerate(row):
            cell = table.rows[r_idx + 1].cells[c_idx]
            cell.text = ""
            p = cell.paragraphs[0]
            # strip inline code markers in table cells for readability
            text = re.sub(r"`([^`]+)`", r"\1", str(val))
            run = p.add_run(text)
            set_run_font(run, "宋体", "Times New Roman", font_size)

    doc.add_paragraph()


def parse_table_block(lines: list[str], start: int) -> tuple[list[str], list[list[str]], int]:
    header = [c.strip() for c in lines[start].strip().strip("|").split("|")]
    i = start + 1
    if i < len(lines) and re.match(r"^\|?\s*:?-{3,}", lines[i].strip()):
        i += 1
    rows: list[list[str]] = []
    while i < len(lines) and lines[i].strip().startswith("|"):
        row = [c.strip() for c in lines[i].strip().strip("|").split("|")]
        rows.append(row)
        i += 1
    return header, rows, i


def build_docx(md_text: str) -> Document:
    doc = Document()
    sec = doc.sections[0]
    sec.page_width = Cm(21.0)
    sec.page_height = Cm(29.7)
    sec.top_margin = Cm(2.54)
    sec.bottom_margin = Cm(2.54)
    sec.left_margin = Cm(2.5)
    sec.right_margin = Cm(2.5)
    style_normal(doc)

    lines = md_text.replace("\r\n", "\n").split("\n")
    i = 0
    while i < len(lines):
        line = lines[i].rstrip()
        stripped = line.strip()

        if not stripped:
            i += 1
            continue
        if stripped == "---":
            i += 1
            continue

        if stripped.startswith("# "):
            add_title(doc, stripped[2:].strip())
            i += 1
            continue

        if stripped.startswith("## "):
            add_h1(doc, stripped[3:].strip())
            i += 1
            continue

        if stripped.startswith("### "):
            add_h2(doc, stripped[4:].strip())
            i += 1
            continue

        if stripped.startswith("|"):
            headers, rows, i = parse_table_block(lines, i)
            font = 8.5 if len(headers) >= 6 else 10.5
            add_table(doc, headers, rows, font_size=font)
            continue

        m = re.match(r"^(\d+)\.\s+(.*)$", stripped)
        if m:
            add_rich_paragraph(doc, f"{m.group(1)}. {m.group(2)}", indent=False, left_indent_cm=0.5)
            i += 1
            continue

        add_rich_paragraph(doc, stripped, indent=True)
        i += 1

    return doc


def main():
    md = SRC.read_text(encoding="utf-8")
    doc = build_docx(md)
    doc.save(OUT)
    print(f"OK: {OUT}")


if __name__ == "__main__":
    main()