""" skills/docx_skill.py - DOCX Word 文档生成/编辑技能 =============================================== 基于 python-docx 生成和编辑 Word 文档，融入 MiniMax DOCX Skill 设计理念。 支持标题、段落、列表、表格、图片、页眉页脚、样式等。 """ from __future__ import annotations import json import os import time from pathlib import Path from typing import Any, Dict, List, Optional from aiskills.base import Skill, SkillParameter, SkillResult class DOCXCreateSkill(Skill): """生成 Word 文档""" name = "docx_create" description = ( "生成 Word (DOCX) 文档。支持多级标题、段落、列表、表格、图片等。" "content 为 JSON 数组，每项: {type, text/items/headers/rows/path...}。" "type 可选: h1/h2/h3/body/bullet/numbered/table/image/pagebreak/spacer。" ) category = "doc" dangerous = True parameters = [ SkillParameter("content", "string", "内容块 JSON 数组。示例: [{\"type\":\"h1\",\"text\":\"报告\"},{\"type\":\"body\",\"text\":\"正文\"}]", required=True), SkillParameter("output_path", "string", "输出 DOCX 文件路径", required=True), SkillParameter("title", "string", "文档标题", required=False, default=""), SkillParameter("author", "string", "作者", required=False, default=""), SkillParameter("font", "string", "中文字体", required=False, default="SimHei"), ] async def execute(self, content: str = "", output_path: str = "", title: str = "", author: str = "", font: str = "SimHei", **kwargs) -> SkillResult: try: from docx import Document from docx.shared import Inches, Cm, Pt, Emu, RGBColor from docx.enum.text import WD_ALIGN_PARAGRAPH from docx.enum.table import WD_TABLE_ALIGNMENT except ImportError: return SkillResult(success=False, error="python-docx 未安装: pip install python-docx") try: if isinstance(content, str): content = content.strip() try: blocks = json.loads(content) except json.JSONDecodeError: decoder = json.JSONDecoder() blocks, _ = decoder.raw_decode(content) else: blocks = content if not isinstance(blocks, list): blocks = [{"type": "body", "text": str(blocks)}] except (json.JSONDecodeError, ValueError) as e: return SkillResult(success=False, error=f"content JSON 解析失败: {e}") try: if not output_path.strip(): default_dir = Path.home() / ".myagent" / "data" / "workspace" / "userfiles" default_dir.mkdir(parents=True, exist_ok=True) out = default_dir / f"doc_{int(time.time())}.docx" else: out = Path(output_path).expanduser().resolve() out.parent.mkdir(parents=True, exist_ok=True) doc = Document() if title: doc.core_properties.title = title if author: doc.core_properties.author = author style = doc.styles["Normal"] rpr = style.font rpr.name = font rpr.size = Pt(11) for level, size in [("Heading 1", 22), ("Heading 2", 16), ("Heading 3", 13)]: if level in doc.styles: hs = doc.styles[level] hs.font.name = font hs.font.size = Pt(size) hs.font.color.rgb = RGBColor(0x1a, 0x36, 0x5d) for block in blocks: if not isinstance(block, dict): continue bt = block.get("type", "body") if bt in ("h1", "h2", "h3"): heading_map = {"h1": 0, "h2": 1, "h3": 2} doc.add_heading(block.get("text", ""), level=heading_map[bt] + 1) elif bt == "body": p = doc.add_paragraph(block.get("text", "")) p.paragraph_format.first_line_indent = Cm(0.74) p.paragraph_format.line_spacing = 1.5 elif bt == "bullet": for item in block.get("items", []): doc.add_paragraph(item, style="List Bullet") elif bt == "numbered": for item in block.get("items", []): doc.add_paragraph(item, style="List Number") elif bt == "table": headers = block.get("headers", []) rows = block.get("rows", []) if headers: table = doc.add_table(rows=1 + len(rows), cols=len(headers)) table.style = "Light Grid Accent 1" table.alignment = WD_TABLE_ALIGNMENT.CENTER for j, h in enumerate(headers): cell = table.rows[0].cells[j] cell.text = str(h) for run in cell.paragraphs[0].runs: run.bold = True for i, row in enumerate(rows): for j, val in enumerate(row): if j < len(table.columns): table.rows[i + 1].cells[j].text = str(val) elif bt == "image": img_path = block.get("path", "") img_w = block.get("width", 0) if img_path and os.path.isfile(img_path): try: if img_w > 0: doc.add_picture(img_path, width=Emu(int(img_w))) else: doc.add_picture(img_path, width=Inches(5.5)) except Exception as e: doc.add_paragraph(f"[图片加载失败: {e}]") elif bt == "pagebreak": doc.add_page_break() elif bt == "spacer": doc.add_paragraph("") doc.save(str(out)) return SkillResult( success=True, message=f"Word 文档已生成: {out}", files=[str(out)], data={"path": str(out), "blocks": len(blocks)}, ) except Exception as e: return SkillResult(success=False, error=f"DOCX 生成失败: {e}") class DOCXReadSkill(Skill): """读取 Word 文档内容""" name = "docx_read" description = "读取 Word (DOCX) 文件，提取文本内容。支持提取表格数据。" category = "doc" parameters = [ SkillParameter("path", "string", "DOCX 文件路径", required=True), SkillParameter("max_chars", "integer", "最大字符数", required=False, default=50000), ] async def execute(self, path: str = "", max_chars: int = 50000, **kwargs) -> SkillResult: try: from docx import Document except ImportError: return SkillResult(success=False, error="python-docx 未安装: pip install python-docx") fp = Path(path).expanduser().resolve() if not fp.exists(): return SkillResult(success=False, error=f"文件不存在: {path}") try: doc = Document(str(fp)) parts = [] for para in doc.paragraphs: style_name = para.style.name if para.style else "" prefix = "" if "Heading" in style_name: level = style_name.replace("Heading", "").strip() prefix = f"[{'#' * int(level) if level.isdigit() else '#'}] " elif "Bullet" in style_name: prefix = " * " elif "Number" in style_name or "List" in style_name: prefix = " - " text = para.text.strip() if text: parts.append(f"{prefix}{text}") for i, table in enumerate(doc.tables): rows = [] for row in table.rows: cells = [cell.text.strip() for cell in row.cells] rows.append(" | ".join(cells)) if rows: parts.append(f"\n[表格 {i+1}]") parts.append(rows[0]) if len(rows) > 1: parts.append("-" * len(rows[0])) parts.extend(rows[1:]) full = "\n".join(parts) if len(full) > max_chars: full = full[:max_chars] + f"\n\n... (截断，共 {len(full)} 字符)" return SkillResult( success=True, message=f"已读取 Word 文档: {fp.name}", data={"path": str(fp), "paragraphs": len(doc.paragraphs), "tables": len(doc.tables)}, output=full, ) except Exception as e: return SkillResult(success=False, error=f"DOCX 读取失败: {e}")