Undefined-bot 2.1.0__py3-none-any.whl

Undefined/skills/agents/file_analysis_agent/tools/extract_archive/handler.py

@@ -0,0 +1,190 @@
+from pathlib import Path
+from typing import Any, Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    file_path: str = args.get("file_path", "")
+    action: str = args.get("action", "list")
+    extract_path: str | None = args.get("extract_path")
+
+    path = Path(file_path)
+
+    if not path.exists():
+        return f"错误：文件不存在 {file_path}"
+
+    if not path.is_file():
+        return f"错误：{file_path} 不是文件"
+
+    suffix = path.suffix.lower()
+
+    try:
+        if suffix == ".zip":
+            return await _extract_zip(path, action, extract_path)
+        elif suffix in [".tar", ".gz", ".bz2", ".xz"]:
+            return await _extract_tar(path, action, extract_path)
+        elif suffix == ".7z":
+            return await _extract_7z(path, action, extract_path)
+        elif suffix == ".rar":
+            return await _extract_rar(path, action, extract_path)
+        else:
+            return f"不支持的压缩格式: {suffix}"
+
+    except Exception as e:
+        logger.exception(f"解析压缩包失败: {e}")
+        return f"解析压缩包失败: {e}"
+
+
+async def _extract_zip(path: Path, action: str, extract_path: str | None) -> str:
+    import zipfile
+
+    with zipfile.ZipFile(path, "r") as zip_ref:
+        file_list = zip_ref.namelist()
+        total_size = sum(info.file_size for info in zip_ref.infolist())
+
+    info: list[str] = []
+    info.append(f"文件大小：{path.stat().st_size} 字节")
+    info.append(f"压缩包内文件数：{len(file_list)}")
+    info.append(f"解压后总大小：{total_size} 字节")
+
+    if action == "list":
+        info.append("\n文件列表（前 100 个）：")
+        for i, name in enumerate(file_list[:100], 1):
+            info.append(f"  {i}. {name}")
+        if len(file_list) > 100:
+            info.append(f"  ... (共 {len(file_list)} 个文件)")
+        return "\n".join(info)
+
+    else:
+        if extract_path:
+            target_dir = Path(extract_path)
+        else:
+            target_dir = path.parent / f"extracted_{path.stem}"
+            target_dir.mkdir(exist_ok=True)
+
+        with zipfile.ZipFile(path, "r") as zip_ref:
+            zip_ref.extractall(target_dir)
+
+        info.append(f"\n已解压到：{target_dir}")
+        info.append(f"解压文件数：{len(file_list)}")
+        info.append("\n文件列表（前 50 个）：")
+        for i, name in enumerate(file_list[:50], 1):
+            info.append(f"  {i}. {name}")
+        if len(file_list) > 50:
+            info.append(f"  ... (共 {len(file_list)} 个文件)")
+
+        return "\n".join(info)
+
+
+async def _extract_tar(path: Path, action: str, extract_path: str | None) -> str:
+    import tarfile
+
+    with tarfile.open(path, "r:*") as tar_ref:
+        members = tar_ref.getmembers()
+        file_list = [m.name for m in members]
+        total_size = sum(m.size for m in members)
+
+    info: list[str] = []
+    info.append(f"文件大小：{path.stat().st_size} 字节")
+    info.append(f"压缩包内文件数：{len(file_list)}")
+    info.append(f"解压后总大小：{total_size} 字节")
+
+    if action == "list":
+        info.append("\n文件列表（前 100 个）：")
+        for i, name in enumerate(file_list[:100], 1):
+            info.append(f"  {i}. {name}")
+        if len(file_list) > 100:
+            info.append(f"  ... (共 {len(file_list)} 个文件)")
+        return "\n".join(info)
+
+    else:
+        if extract_path:
+            target_dir = Path(extract_path)
+        else:
+            target_dir = path.parent / f"extracted_{path.stem}"
+            target_dir.mkdir(exist_ok=True)
+
+        with tarfile.open(path, "r:*") as tar_ref:
+            tar_ref.extractall(target_dir)
+
+        info.append(f"\n已解压到：{target_dir}")
+        info.append(f"解压文件数：{len(file_list)}")
+
+        return "\n".join(info)
+
+
+async def _extract_7z(path: Path, action: str, extract_path: str | None) -> str:
+    import py7zr
+
+    with py7zr.SevenZipFile(path, "r") as archive:
+        file_list: list[str] = []
+        total_size = 0
+        for file_info in archive.files:
+            file_list.append(file_info.filename)
+            total_size += file_info.uncompressed
+
+    info: list[str] = []
+    info.append(f"文件大小：{path.stat().st_size} 字节")
+    info.append(f"压缩包内文件数：{len(file_list)}")
+    info.append(f"解压后总大小：{total_size} 字节")
+
+    if action == "list":
+        info.append("\n文件列表（前 100 个）：")
+        for i, name in enumerate(file_list[:100], 1):
+            info.append(f"  {i}. {name}")
+        if len(file_list) > 100:
+            info.append(f"  ... (共 {len(file_list)} 个文件)")
+        return "\n".join(info)
+
+    else:
+        if extract_path:
+            target_dir = Path(extract_path)
+        else:
+            target_dir = path.parent / f"extracted_{path.stem}"
+            target_dir.mkdir(exist_ok=True)
+
+        with py7zr.SevenZipFile(path, "r") as archive:
+            archive.extractall(target_dir)
+
+        info.append(f"\n已解压到：{target_dir}")
+        info.append(f"解压文件数：{len(file_list)}")
+
+        return "\n".join(info)
+
+
+async def _extract_rar(path: Path, action: str, extract_path: str | None) -> str:
+    import rarfile
+
+    with rarfile.RarFile(path, "r") as rar_ref:
+        file_list = rar_ref.namelist()
+        total_size = sum(info.file_size for info in rar_ref.infolist())
+
+    info: list[str] = []
+    info.append(f"文件大小：{path.stat().st_size} 字节")
+    info.append(f"压缩包内文件数：{len(file_list)}")
+    info.append(f"解压后总大小：{total_size} 字节")
+
+    if action == "list":
+        info.append("\n文件列表（前 100 个）：")
+        for i, name in enumerate(file_list[:100], 1):
+            info.append(f"  {i}. {name}")
+        if len(file_list) > 100:
+            info.append(f"  ... (共 {len(file_list)} 个文件)")
+        return "\n".join(info)
+
+    else:
+        if extract_path:
+            target_dir = Path(extract_path)
+        else:
+            target_dir = path.parent / f"extracted_{path.stem}"
+            target_dir.mkdir(exist_ok=True)
+
+        with rarfile.RarFile(path, "r") as rar_ref:
+            rar_ref.extractall(target_dir)
+
+        info.append(f"\n已解压到：{target_dir}")
+        info.append(f"解压文件数：{len(file_list)}")
+
+        return "\n".join(info)

Undefined/skills/agents/file_analysis_agent/tools/extract_docx/config.json

@@ -0,0 +1,17 @@
+{
+    "type": "function",
+    "function": {
+        "name": "extract_docx",
+        "description": "提取 Microsoft Word 文档 (.docx) 的文本内容和基本元数据。",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "file_path": {
+                    "type": "string",
+                    "description": "本地 Word 文档路径"
+                }
+            },
+            "required": ["file_path"]
+        }
+    }
+}

Undefined/skills/agents/file_analysis_agent/tools/extract_docx/handler.py

@@ -0,0 +1,78 @@
+from docx import Document
+from pathlib import Path
+from typing import Any, Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    file_path: str = args.get("file_path", "")
+
+    path = Path(file_path)
+
+    if not path.exists():
+        return f"错误：文件不存在 {file_path}"
+
+    if not path.is_file():
+        return f"错误：{file_path} 不是文件"
+
+    try:
+        doc = Document(str(path))
+
+        info: list[str] = []
+        info.append(f"文件大小：{path.stat().st_size} 字节")
+
+        core_props = doc.core_properties
+        if core_props:
+            info.append("\n文档属性：")
+            if core_props.title:
+                info.append(f"  标题: {core_props.title}")
+            if core_props.author:
+                info.append(f"  作者: {core_props.author}")
+            if core_props.last_modified_by:
+                info.append(f"  最后修改者: {core_props.last_modified_by}")
+            if core_props.created:
+                info.append(f"  创建时间: {core_props.created}")
+            if core_props.modified:
+                info.append(f"  修改时间: {core_props.modified}")
+            if core_props.comments:
+                info.append(f"  备注: {core_props.comments}")
+
+        paragraphs = list(doc.paragraphs)
+        tables = doc.tables
+
+        info.append(f"\n段落数：{len(paragraphs)}")
+        info.append(f"表格数：{len(tables)}")
+
+        text_content = ""
+        for para in paragraphs:
+            text = para.text.strip()
+            if text:
+                text_content += text + "\n"
+
+        if not text_content.strip():
+            text_content = "(文档未检测到文本内容)"
+
+        info.append(f"\n文本内容预览（前 5000 字符）：\n{text_content[:5000]}")
+        if len(text_content) > 5000:
+            info.append(f"\n... (共 {len(text_content)} 字符)")
+
+        if tables:
+            info.append("\n表格内容：")
+            for i, table in enumerate(tables[:3], 1):
+                info.append(f"\n表格 {i}:")
+                for row in table.rows[:5]:
+                    cells = [cell.text.strip() for cell in row.cells]
+                    row_text = " | ".join(cells)
+                    info.append(f"  {row_text}")
+                if len(table.rows) > 5:
+                    info.append(f"  ... (共 {len(table.rows)} 行)")
+            if len(tables) > 3:
+                info.append(f"\n... (还有 {len(tables) - 3} 个表格)")
+
+        return "\n".join(info)
+
+    except Exception as e:
+        logger.exception(f"解析 Word 文档失败: {e}")
+        return f"解析 Word 文档失败: {e}"

Undefined/skills/agents/file_analysis_agent/tools/extract_pdf/config.json

@@ -0,0 +1,21 @@
+{
+    "type": "function",
+    "function": {
+        "name": "extract_pdf",
+        "description": "提取 PDF 文档的文本内容和元数据。使用 PyMuPDF (fitz) 解析，支持获取页数、作者、标题等信息。",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "file_path": {
+                    "type": "string",
+                    "description": "本地 PDF 文件路径"
+                },
+                "extract_images": {
+                    "type": "boolean",
+                    "description": "是否提取图片（会返回图片数量和位置信息），默认为 false"
+                }
+            },
+            "required": ["file_path"]
+        }
+    }
+}

Undefined/skills/agents/file_analysis_agent/tools/extract_pdf/handler.py

@@ -0,0 +1,67 @@
+import fitz
+from pathlib import Path
+from typing import Any, Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    file_path: str = args.get("file_path", "")
+    extract_images: bool = args.get("extract_images", False)
+
+    path = Path(file_path)
+
+    if not path.exists():
+        return f"错误：文件不存在 {file_path}"
+
+    if not path.is_file():
+        return f"错误：{file_path} 不是文件"
+
+    try:
+        doc = fitz.open(str(path))
+        page_count = len(doc)
+
+        info: list[str] = []
+        info.append(f"文件大小：{path.stat().st_size} 字节")
+        info.append(f"页数：{page_count}")
+
+        metadata = doc.metadata
+        if metadata:
+            info.append("\n文档元数据：")
+            for key, value in metadata.items():
+                if value:
+                    info.append(f"  {key}: {value}")
+
+        text_content = ""
+        image_count = 0
+
+        for page_num in range(page_count):
+            page = doc.load_page(page_num)
+            text_raw = page.get_text()
+            text = str(text_raw) if text_raw else ""
+            text_content += f"\n--- 第 {page_num + 1} 页 ---\n"
+            text_content += text
+
+            if extract_images:
+                images = page.get_images()
+                for _ in images:
+                    image_count += 1
+
+        if extract_images:
+            info.append(f"\n图片数量：{image_count}")
+
+        if not text_content.strip():
+            text_content = "(文档未检测到文本内容，可能是扫描版 PDF 或图片)"
+
+        info.append(f"\n文本内容预览（前 5000 字符）：\n{text_content[:5000]}")
+        if len(text_content) > 5000:
+            info.append(f"\n... (共 {len(text_content)} 字符)")
+
+        doc.close()
+
+        return "\n".join(info)
+
+    except Exception as e:
+        logger.exception(f"解析 PDF 失败: {e}")
+        return f"解析 PDF 失败: {e}"

Undefined/skills/agents/file_analysis_agent/tools/extract_pptx/config.json

@@ -0,0 +1,17 @@
+{
+    "type": "function",
+    "function": {
+        "name": "extract_pptx",
+        "description": "提取 Microsoft PowerPoint 演示文稿 (.pptx) 的文本内容，包括幻灯片文本和基本结构。",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "file_path": {
+                    "type": "string",
+                    "description": "本地 PowerPoint 文件路径"
+                }
+            },
+            "required": ["file_path"]
+        }
+    }
+}

Undefined/skills/agents/file_analysis_agent/tools/extract_pptx/handler.py

@@ -0,0 +1,73 @@
+from pptx import Presentation
+from pathlib import Path
+from typing import Any, Dict
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    file_path: str = args.get("file_path", "")
+
+    path = Path(file_path)
+
+    if not path.exists():
+        return f"错误：文件不存在 {file_path}"
+
+    if not path.is_file():
+        return f"错误：{file_path} 不是文件"
+
+    try:
+        prs = Presentation(str(path))
+
+        info: list[str] = []
+        info.append(f"文件大小：{path.stat().st_size} 字节")
+
+        slide_count = len(prs.slides)
+        info.append(f"幻灯片数量：{slide_count}")
+
+        if prs.core_properties.title:
+            info.append(f"标题: {prs.core_properties.title}")
+        if prs.core_properties.author:
+            info.append(f"作者: {prs.core_properties.author}")
+        if prs.core_properties.last_modified_by:
+            info.append(f"最后修改者: {prs.core_properties.last_modified_by}")
+
+        text_content = ""
+
+        for slide_num, slide in enumerate(prs.slides, 1):
+            slide_text = f"\n--- 幻灯片 {slide_num} ---\n"
+
+            title = ""
+            if slide.shapes.title:
+                title = slide.shapes.title.text.strip()
+                if title:
+                    slide_text += f"标题: {title}\n"
+
+            content_count = 0
+            for shape in slide.shapes:
+                if shape != slide.shapes.title:
+                    shape_text = getattr(shape, "text", None)
+                    if shape_text:
+                        text = shape_text.strip()
+                        if text and len(text) > 0:
+                            content_count += 1
+                            slide_text += f"{text}\n"
+
+            if not title and content_count == 0:
+                slide_text += "(空白幻灯片)"
+
+            text_content += slide_text
+
+        if not text_content.strip():
+            text_content = "(演示文稿未检测到文本内容)"
+
+        info.append(f"\n内容预览（前 5000 字符）：\n{text_content[:5000]}")
+        if len(text_content) > 5000:
+            info.append(f"\n... (共 {len(text_content)} 字符)")
+
+        return "\n".join(info)
+
+    except Exception as e:
+        logger.exception(f"解析 PowerPoint 失败: {e}")
+        return f"解析 PowerPoint 失败: {e}"

Undefined/skills/agents/file_analysis_agent/tools/extract_xlsx/config.json

@@ -0,0 +1,17 @@
+{
+    "type": "function",
+    "function": {
+        "name": "extract_xlsx",
+        "description": "提取 Microsoft Excel 工作簿 (.xlsx, .xls, .csv) 的表格数据，包括工作表列表和内容预览。",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "file_path": {
+                    "type": "string",
+                    "description": "本地 Excel 或 CSV 文件路径"
+                }
+            },
+            "required": ["file_path"]
+        }
+    }
+}

Undefined/skills/agents/file_analysis_agent/tools/extract_xlsx/handler.py

@@ -0,0 +1,101 @@
+from pathlib import Path
+from typing import Any, Dict
+import logging
+import csv
+
+logger = logging.getLogger(__name__)
+
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    file_path: str = args.get("file_path", "")
+
+    path = Path(file_path)
+
+    if not path.exists():
+        return f"错误：文件不存在 {file_path}"
+
+    if not path.is_file():
+        return f"错误：{file_path} 不是文件"
+
+    try:
+        info: list[str] = []
+        info.append(f"文件大小：{path.stat().st_size} 字节")
+
+        if path.suffix.lower() == ".csv":
+            return await _extract_csv(path, info)
+        else:
+            return await _extract_excel(path, info)
+
+    except Exception as e:
+        logger.exception(f"解析 Excel/CSV 失败: {e}")
+        return f"解析 Excel/CSV 失败: {e}"
+
+
+async def _extract_csv(path: Path, info: list[str]) -> str:
+    try:
+        with open(path, "r", encoding="utf-8-sig") as f:
+            reader = csv.reader(f)
+            rows = list(reader)
+
+        if not rows:
+            return "CSV 文件为空"
+
+        info.append("工作表：CSV (单个)")
+        info.append(f"总行数：{len(rows)}")
+        if rows:
+            info.append(f"列数：{len(rows[0])}")
+
+        preview = []
+        preview.append("\n--- 前 20 行预览 ---\n")
+        for i, row in enumerate(rows[:20], 1):
+            preview.append(f"行 {i}: {' | '.join(row)}")
+        if len(rows) > 20:
+            preview.append(f"\n... (共 {len(rows)} 行)")
+
+        return "\n".join(info) + "\n" + "\n".join(preview)
+
+    except Exception as e:
+        return f"解析 CSV 失败: {e}"
+
+
+async def _extract_excel(path: Path, info: list[str]) -> str:
+    try:
+        from openpyxl import load_workbook
+
+        wb = load_workbook(str(path), read_only=True, data_only=True)
+
+        sheet_names = wb.sheetnames
+        info.append(f"工作表数量：{len(sheet_names)}")
+        info.append(f"工作表列表：{', '.join(sheet_names)}")
+
+        all_content = []
+
+        for sheet_name in sheet_names[:5]:
+            ws = wb[sheet_name]
+            rows = list(ws.iter_rows(max_row=100, values_only=True))
+
+            if not rows:
+                continue
+
+            max_cols = max(len(row) for row in rows if row)
+            info.append(f"\n工作表 '{sheet_name}':")
+            info.append(f"  行数（前 100 行）: {len(rows)}")
+            info.append(f"  列数: {max_cols}")
+
+            preview = []
+            preview.append(f"  --- {sheet_name} 前 15 行预览 ---\n")
+            for i, row in enumerate(rows[:15], 1):
+                row_values = [str(cell) if cell is not None else "" for cell in row]
+                preview.append(f"    行 {i}: {' | '.join(row_values)}")
+            if len(rows) > 15:
+                preview.append(f"    ... (共 {len(rows)} 行)")
+            all_content.append("\n".join(preview))
+
+        if len(sheet_names) > 5:
+            info.append(f"\n... (还有 {len(sheet_names) - 5} 个工作表)")
+
+        return "\n".join(info) + "\n" + "\n".join(all_content)
+
+    except Exception as e:
+        logger.exception(f"解析 Excel 失败: {e}")
+        return f"解析 Excel 失败: {e}"

Undefined/skills/agents/file_analysis_agent/tools/get_current_time/config.json

@@ -0,0 +1,12 @@
+{
+    "type": "function",
+    "function": {
+        "name": "get_current_time",
+        "description": "获取当前系统时间。",
+        "parameters": {
+            "type": "object",
+            "properties": {},
+            "required": []
+        }
+    }
+}

Undefined/skills/agents/file_analysis_agent/tools/get_current_time/handler.py

@@ -0,0 +1,5 @@
+from typing import Any, Dict
+from datetime import datetime
+
+async def execute(args: Dict[str, Any], context: Dict[str, Any]) -> str:
+    return datetime.now().strftime("%Y-%m-%d %H:%M:%S")

Undefined/skills/agents/file_analysis_agent/tools/read_text_file/config.json

@@ -0,0 +1,21 @@
+{
+    "type": "function",
+    "function": {
+        "name": "read_text_file",
+        "description": "读取文本文件内容，自动检测文件编码。支持 txt, md, log, rst, json, yaml, xml, html, css, js, py 等纯文本格式。大文件可限制读取行数。",
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "file_path": {
+                    "type": "string",
+                    "description": "本地文件路径"
+                },
+                "max_lines": {
+                    "type": "number",
+                    "description": "最大读取行数，默认读取全部"
+                }
+            },
+            "required": ["file_path"]
+        }
+    }
+}