mescloud/_apk_work/md_to_docx.py

# -*- coding: utf-8 -*-
"""Convert 9.19 markdown manuals to Word."""
import os, re
from docx import Document
from docx.shared import Pt, Cm, RGBColor
from docx.oxml.ns import qn
from docx.enum.text import WD_ALIGN_PARAGRAPH
from docx.enum.table import WD_TABLE_ALIGNMENT

SRC = r"D:\产线\大洋\大洋操作手册汇总9.19"
FONT = "微软雅黑"

def set_run_font(run, size=11, bold=False, color=None):
    run.bold = bold
    run.font.size = Pt(size)
    run.font.name = FONT
    r = run._element
    rPr = r.get_or_add_rPr()
    rFonts = rPr.find(qn("w:rFonts"))
    if rFonts is None:
        from lxml import etree
        rFonts = rPr.makeelement(qn("w:rFonts"), {})
        rPr.append(rFonts)
    rFonts.set(qn("w:eastAsia"), FONT)
    rFonts.set(qn("w:ascii"), FONT)
    rFonts.set(qn("w:hAnsi"), FONT)
    if color:
        run.font.color.rgb = RGBColor(*color)

def add_runs(p, text, size=11, bold=False):
    # split **bold**
    parts = re.split(r"(\*\*[^*]+\*\*)", text)
    for part in parts:
        if part.startswith("**") and part.endswith("**"):
            run = p.add_run(part[2:-2])
            set_run_font(run, size=size, bold=True)
        else:
            run = p.add_run(part)
            set_run_font(run, size=size, bold=bold)

def parse_table(lines, i):
    rows = []
    while i < len(lines) and lines[i].startswith("|"):
        raw = [c.strip() for c in lines[i].strip().strip("|").split("|")]
        if not re.match(r"^:?-+:?$", raw[0].replace(" ", "")):
            rows.append(raw)
        i += 1
    return rows, i

def convert(md_path, docx_path):
    text = open(md_path, encoding="utf-8").read()
    lines = text.splitlines()
    doc = Document()
    section = doc.sections[0]
    section.top_margin = Cm(2)
    section.bottom_margin = Cm(2)
    section.left_margin = Cm(2.2)
    section.right_margin = Cm(2.2)
    style = doc.styles["Normal"]
    style.font.name = FONT
    style.font.size = Pt(11)
    style.element.rPr.rFonts.set(qn("w:eastAsia"), FONT)

    i = 0
    while i < len(lines):
        line = lines[i].rstrip()
        if not line:
            i += 1
            continue
        if line.startswith("# "):
            p = doc.add_heading("", level=0)
            p.clear()
            run = p.add_run(line[2:].strip())
            set_run_font(run, size=18, bold=True, color=(0x1F, 0x4E, 0x79))
            i += 1
            continue
        if line.startswith("## "):
            p = doc.add_heading("", level=1)
            p.clear()
            run = p.add_run(line[3:].strip())
            set_run_font(run, size=16, bold=True, color=(0x2E, 0x75, 0xB6))
            i += 1
            continue
        if line.startswith("### "):
            p = doc.add_heading("", level=2)
            p.clear()
            run = p.add_run(line[4:].strip())
            set_run_font(run, size=14, bold=True, color=(0x2E, 0x75, 0xB6))
            i += 1
            continue
        if line.startswith("#### "):
            p = doc.add_heading("", level=3)
            p.clear()
            run = p.add_run(line[5:].strip())
            set_run_font(run, size=12, bold=True)
            i += 1
            continue
        if line.startswith("---"):
            i += 1
            continue
        if line.startswith("|"):
            rows, i = parse_table(lines, i)
            if rows:
                cols = max(len(r) for r in rows)
                table = doc.add_table(rows=len(rows), cols=cols)
                table.style = "Table Grid"
                table.alignment = WD_TABLE_ALIGNMENT.CENTER
                for r_idx, row in enumerate(rows):
                    for c_idx in range(cols):
                        cell = table.cell(r_idx, c_idx)
                        cell.text = ""
                        p = cell.paragraphs[0]
                        val = row[c_idx] if c_idx < len(row) else ""
                        add_runs(p, val, size=10, bold=(r_idx == 0))
            continue
        if line.startswith("- "):
            p = doc.add_paragraph(style="List Bullet")
            p.clear()
            add_runs(p, line[2:].strip())
            i += 1
            continue
        if re.match(r"^\d+\.\s", line):
            p = doc.add_paragraph(style="List Number")
            p.clear()
            add_runs(p, re.sub(r"^\d+\.\s", "", line))
            i += 1
            continue
        p = doc.add_paragraph()
        add_runs(p, line)
        i += 1

    doc.save(docx_path)
    print("saved", os.path.basename(docx_path))

def main():
    files = [f for f in os.listdir(SRC) if f.endswith(".md")]
    files.sort()
    for f in files:
        md = os.path.join(SRC, f)
        docx = os.path.join(SRC, os.path.splitext(f)[0] + ".docx")
        convert(md, docx)

if __name__ == "__main__":
    main()