#!/usr/bin/env python3 """Сборка DOCX из простого Markdown.""" from __future__ import annotations import argparse import re import sys from pathlib import Path from docx import Document from docx.shared import Pt INLINE = re.compile(r"(\*\*.+?\*\*|\*[^*]+?\*|`[^`]+?`)") TABLE_SEPARATOR = re.compile(r"^\s*\|?\s*:?-{3,}:?\s*(\|\s*:?-{3,}:?\s*)+\|?\s*$") def add_inline(paragraph, text: str) -> None: position = 0 for match in INLINE.finditer(text): if match.start() > position: paragraph.add_run(text[position : match.start()]) token = match.group(0) if token.startswith("**"): run = paragraph.add_run(token[2:-2]) run.bold = True elif token.startswith("`"): run = paragraph.add_run(token[1:-1]) run.font.name = "Courier New" run.font.size = Pt(10) else: run = paragraph.add_run(token[1:-1]) run.italic = True position = match.end() if position < len(text): paragraph.add_run(text[position:]) def split_row(line: str) -> list[str]: return [cell.strip() for cell in line.strip().strip("|").split("|")] def main() -> int: parser = argparse.ArgumentParser(description="Собрать DOCX из Markdown") parser.add_argument("input", type=Path, help="Исходный Markdown") parser.add_argument("-o", "--output", type=Path, help="Итоговый DOCX") parser.add_argument("--outdir", type=Path, default=Path("word"), help="Папка результатов") parser.add_argument("--force", action="store_true", help="Перезаписать результат") args = parser.parse_args() path = args.input.expanduser() if not path.is_file(): print(f"Файл не найден: {path}", file=sys.stderr) return 2 if path.suffix.lower() not in {".md", ".markdown"}: print("Поддерживаются файлы .md и .markdown", file=sys.stderr) return 2 target = args.output.expanduser() if args.output else args.outdir.expanduser() / f"{path.stem}.docx" if target.suffix.lower() != ".docx": print("Итоговый файл должен иметь расширение .docx", file=sys.stderr) return 2 if target.exists() and not args.force: print(f"Файл уже существует: {target}. Добавьте --force.", file=sys.stderr) return 2 lines = path.read_text(encoding="utf-8").splitlines() document = Document() index = 0 while index < len(lines): line = lines[index] stripped = line.strip() if stripped.startswith("```"): code: list[str] = [] index += 1 while index < len(lines) and not lines[index].strip().startswith("```"): code.append(lines[index]) index += 1 index += 1 paragraph = document.add_paragraph(style="No Spacing") run = paragraph.add_run("\n".join(code)) run.font.name = "Courier New" run.font.size = Pt(10) continue if not stripped: index += 1 continue heading = re.match(r"^(#{1,6})\s+(.*)$", line) if heading: document.add_heading(heading.group(2).strip(), level=len(heading.group(1))) index += 1 continue if stripped in {"---", "***", "___"}: index += 1 continue if ( "|" in line and index + 1 < len(lines) and TABLE_SEPARATOR.match(lines[index + 1]) ): header = split_row(line) index += 2 rows: list[list[str]] = [] while index < len(lines) and "|" in lines[index] and lines[index].strip(): rows.append(split_row(lines[index])) index += 1 table = document.add_table(rows=1, cols=len(header)) table.style = "Table Grid" for column, value in enumerate(header): table.rows[0].cells[column].text = value for row in rows: cells = table.add_row().cells for column in range(min(len(row), len(cells))): cells[column].text = row[column] continue if stripped.startswith(">"): paragraph = document.add_paragraph(style="Quote") add_inline(paragraph, stripped.lstrip(">").strip()) index += 1 continue bullet = re.match(r"^\s*[-*+]\s+(.*)$", line) if bullet: paragraph = document.add_paragraph(style="List Bullet") add_inline(paragraph, bullet.group(1)) index += 1 continue numbered = re.match(r"^\s*\d+\.\s+(.*)$", line) if numbered: paragraph = document.add_paragraph(style="List Number") add_inline(paragraph, numbered.group(1)) index += 1 continue paragraph = document.add_paragraph() add_inline(paragraph, stripped) index += 1 target.parent.mkdir(parents=True, exist_ok=True) document.save(str(target)) print(f"Готово: {target}") return 0 if __name__ == "__main__": raise SystemExit(main())