performance-test/docs/md_to_docx.py

#!/usr/bin/env python3
"""将操作说明 Markdown 转为 docx（供交付文档使用）。"""

import re
import sys
from pathlib import Path

from docx import Document
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
from docx.oxml.ns import qn
from docx.shared import Pt


def set_doc_font(doc):
    style = doc.styles["Normal"]
    style.font.name = "宋体"
    style.font.size = Pt(11)
    style._element.rPr.rFonts.set(qn("w:eastAsia"), "宋体")


def add_rich_text(paragraph, text):
    pattern = re.compile(r"(\*\*[^*]+\*\*)")
    parts = pattern.split(text)
    for part in parts:
        if not part:
            continue
        if part.startswith("**") and part.endswith("**"):
            run = paragraph.add_run(part[2:-2])
            run.bold = True
        else:
            paragraph.add_run(part)


def parse_table_row(line):
    line = line.strip()
    if not line.startswith("|"):
        return None
    cells = [c.strip() for c in line.strip("|").split("|")]
    return cells


def is_separator_row(cells):
    return all(re.fullmatch(r":?-+:?", c.replace(" ", "")) for c in cells if c != "")


def md_to_docx(md_path, docx_path):
    lines = Path(md_path).read_text(encoding="utf-8").splitlines()
    doc = Document()
    set_doc_font(doc)

    i = 0
    while i < len(lines):
        line = lines[i]
        stripped = line.strip()

        if not stripped:
            i += 1
            continue

        if stripped == "---":
            doc.add_paragraph("")
            i += 1
            continue

        if stripped.startswith("#"):
            level = len(stripped) - len(stripped.lstrip("#"))
            title = stripped[level:].strip()
            style = "Title" if level == 1 else f"Heading {min(level, 4)}"
            p = doc.add_paragraph(style=style)
            add_rich_text(p, title)
            i += 1
            continue

        if stripped.startswith("```"):
            lang = stripped[3:].strip()
            i += 1
            code_lines = []
            while i < len(lines) and not lines[i].strip().startswith("```"):
                code_lines.append(lines[i])
                i += 1
            if i < len(lines):
                i += 1
            p = doc.add_paragraph()
            run = p.add_run("\n".join(code_lines))
            run.font.name = "Consolas"
            run._element.rPr.rFonts.set(qn("w:eastAsia"), "宋体")
            run.font.size = Pt(9)
            doc.add_paragraph("")
            continue

        if stripped.startswith("|"):
            table_lines = []
            while i < len(lines) and lines[i].strip().startswith("|"):
                row = parse_table_row(lines[i])
                if row is not None:
                    table_lines.append(row)
                i += 1

            data_rows = []
            for row in table_lines:
                if is_separator_row(row):
                    continue
                data_rows.append(row)

            if not data_rows:
                continue

            cols = max(len(r) for r in data_rows)
            table = doc.add_table(rows=len(data_rows), cols=cols)
            table.style = "Table Grid"
            for r_idx, row in enumerate(data_rows):
                for c_idx in range(cols):
                    cell_text = row[c_idx] if c_idx < len(row) else ""
                    cell = table.rows[r_idx].cells[c_idx]
                    cell.text = ""
                    p = cell.paragraphs[0]
                    add_rich_text(p, cell_text)
            doc.add_paragraph("")
            continue

        if stripped.startswith(">"):
            p = doc.add_paragraph(style="Intense Quote")
            add_rich_text(p, stripped.lstrip("> ").strip())
            i += 1
            continue

        if stripped.startswith("- "):
            p = doc.add_paragraph(style="List Bullet")
            add_rich_text(p, stripped[2:].strip())
            i += 1
            continue

        p = doc.add_paragraph()
        add_rich_text(p, stripped)
        i += 1

    for section in doc.sections:
        section.top_margin = Pt(72)
        section.bottom_margin = Pt(72)
        section.left_margin = Pt(90)
        section.right_margin = Pt(90)

    doc.save(docx_path)
    print(f"Generated: {docx_path}")


def main():
    base = Path(__file__).parent
    pairs = [
        ("OPERATION_MANUAL_HEALTH.md", "OPERATION_MANUAL_HEALTH.docx"),
        ("OPERATION_MANUAL_ANOMALY.md", "OPERATION_MANUAL_ANOMALY.docx"),
        ("OPERATION_MANUAL_ANOMALY.md", "异常检测及风资源-操作说明.docx"),
        ("OPERATION_MANUAL_LEDGER.md", "OPERATION_MANUAL_LEDGER.docx"),
        ("OPERATION_MANUAL_LEDGER.md", "台账管理-操作说明.docx"),
        ("DEPLOY_FRONTEND.md", "DEPLOY_FRONTEND.docx"),
        ("DESIGN_SPEC_HEALTH.md", "健康评估系统设计说明.docx"),
        ("DESIGN_SPEC_ANOMALY_WRW.md", "异常检测及风资源尾流系统设计说明.docx"),
    ]
    for md_name, docx_name in pairs:
        md_to_docx(base / md_name, base / docx_name)


if __name__ == "__main__":
    main()